CN114757742A - Intelligent recommendation method and system for E-commerce platform products - Google Patents

Intelligent recommendation method and system for E-commerce platform products Download PDF

Info

Publication number
CN114757742A
CN114757742A CN202210440924.8A CN202210440924A CN114757742A CN 114757742 A CN114757742 A CN 114757742A CN 202210440924 A CN202210440924 A CN 202210440924A CN 114757742 A CN114757742 A CN 114757742A
Authority
CN
China
Prior art keywords
user
products
commerce platform
recommendation
product
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
Application number
CN202210440924.8A
Other languages
Chinese (zh)
Inventor
王超
罗伟
饶海笛
邵童
刘志宏
邹能锋
焦俊
辜丽川
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Anhui Agricultural University AHAU
Original Assignee
Anhui Agricultural University AHAU
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Anhui Agricultural University AHAU filed Critical Anhui Agricultural University AHAU
Priority to CN202210440924.8A priority Critical patent/CN114757742A/en
Publication of CN114757742A publication Critical patent/CN114757742A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/06—Buying, selling or leasing transactions
    • G06Q30/0601—Electronic shopping [e-shopping]
    • G06Q30/0631—Item recommendations
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/953—Querying, e.g. by the use of web search engines
    • G06F16/9535—Search customisation based on user profiles and personalisation

Landscapes

  • Engineering & Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • Business, Economics & Management (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Accounting & Taxation (AREA)
  • Finance (AREA)
  • Physics & Mathematics (AREA)
  • Economics (AREA)
  • General Business, Economics & Management (AREA)
  • Strategic Management (AREA)
  • Marketing (AREA)
  • Development Economics (AREA)
  • Data Mining & Analysis (AREA)
  • General Engineering & Computer Science (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention belongs to the field of E-commerce product recommendation, and particularly relates to an intelligent E-commerce platform product recommendation method and system, which comprise the following steps: s1: the method comprises the following steps of collecting product information sold by the conventional E-commerce platform, and classifying different products into different categories to realize the induction of similar products; s2: collecting age information of users who purchase different commodities so as to distinguish product categories which people of different age groups like to purchase; s3: the method comprises the steps of collecting information of commodity user evaluation sold by the traditional E-commerce platform, preferentially recommending products with better evaluation, and taking off the shelves of commodities with poor evaluation; by the intelligent recommendation method, products of a user can be automatically recommended according to people of different age groups, and the user can also be searched on the platform and preferentially recommended, so that the user is prevented from purchasing improper products, browsing time of the products purchased by the user is saved, and experience of using an e-commerce platform is improved.

Description

Intelligent recommendation method and system for E-commerce platform products
Technical Field
The invention relates to the field of e-commerce product recommendation, in particular to an intelligent recommendation method and system for e-commerce platform products.
Background
The E-commerce platform means that a user can browse commodities through a mobile phone APP, and the user directly purchases the commodities on the mobile phone after selecting a satisfactory product.
With the continuous development of life, more and more merchants are located on the e-commerce platform, so that more and more commodities on the e-commerce platform are provided, and further, a user needs to browse a large number of suitable products when buying the products, and cannot quickly find satisfactory commodities.
Disclosure of Invention
The invention provides an intelligent recommendation method and system for E-commerce platform products, aiming at making up for the defects of the prior art and solving the problems that a user needs to browse a large number of products when needing to buy proper products and cannot quickly find satisfactory products.
The technical scheme adopted by the invention for solving the technical problems is as follows: the invention relates to an intelligent recommendation method for E-commerce platform products, which comprises the following steps:
s1: the method comprises the following steps of collecting product information sold by the conventional E-commerce platform, and classifying different products into different categories to realize the induction of similar products;
s2: collecting age information of users who purchase different commodities so as to distinguish product categories which people of different age groups like to purchase;
s3: the method comprises the steps of collecting information of commodity user evaluation sold by the traditional E-commerce platform, preferentially recommending products with better evaluation, and taking off the shelves of commodities with poor evaluation;
s4: establishing a search bar on an e-commerce platform, and collecting historical behavior data through historical search of a user;
s5: and establishing a recommendation column on the e-commerce platform, wherein the recommendation column screens data in historical behavior data based on an improved recommendation algorithm for recommendation, and preferentially recommends products of a proper user age.
By the intelligent recommendation method, products which are interested by the user can be preferentially recommended to the user on the platform according to historical search according to people of different age groups, products which are suitable for the user can be automatically recommended, the user can be prevented from purchasing unsuitable products, browsing time of the products purchased by the user is saved, and experience of using an e-commerce platform is improved.
Preferably, the improved recommendation algorithm in S5 mainly adds a time decay factor in the process of calculating the similarity, wherein the time decay function refers to an ibbingos forgetting curve;
applying the rule contained in the Ebinghaos forgetting curve to a recommendation algorithm, wherein the prediction influence of the historical behavior data with longer time on the current interest of the user is lower, and when the historical behavior data are recommended to the user, articles with historical behaviors are endowed with different influence weights according to time factors.
Preferably, for the collected historical behavior data, time factors in the historical behavior data of the user are extracted in the data collection and processing process, the behavior data to be predicted is divided according to time nodes, and then the time interval of the occurrence of the user behavior is calculated according to the time nodes.
Preferably, the function expression of the time attenuation factor in the recommendation algorithm is determined by fitting an Ebbinriches curve in the recommendation algorithm; the user interest is attenuated along with the increase of time, the attenuation trend conforms to the Eibongos forgetting curve rule, the speed is high before the speed is low, and the attenuation function expression after fitting is shown as a formula (1):
Figure BDA0003613960010000021
wherein t is0Representing the current time node, tvjRepresenting user to item class vjThe time unit of the behavior timestamp is hour, and represents the time difference from the historical behavior of the user to the current time;
in the formula (1), when the fixed parameter alpha value is selected to be 1, and the parameter beta values are 0.01, 0.02 and 0.05, the larger the value is, the faster the interest attenuation speed is.
Preferably, the time attenuation weight of the user behavior is calculated according to the formula (1), and then the weight formula is merged into the calculation of the similarity score of the non-interactive object according to the historical behavior data of the user, so that the formula (2) is obtained:
p(u，i)＝∑j∈N(u)∩S(i，k)wijrujf(t0-tvj) (2)
where N (u) represents the set of items that the user has interacted with, S (i, k) is the set of k items that are most similar to item i, wijRepresenting the similarity of two articles, rujRepresents the interaction score of user u on item j, f (t)0-tvj) Is a newly added time attenuation factor.
Preferably, in the process of collecting information of products sold by the previous e-commerce platform in S1, four-quarter information collection may be performed on products within the last year to distinguish between products purchased by users in different quarters, and by collecting information of products in different quarters, products that users need to purchase in different time periods may be better distinguished.
Preferably, when the similar products in S1 are summarized, the products may be sorted in descending order and also sorted in ascending order according to the prices of the similar products, and the price requirements of different users on the products may be met by sorting the prices of the products in descending order or in ascending order.
Preferably, in S2, information leakage should be prevented when the age of the user who purchases different commodities is collected, and meanwhile, commodities of a suitable user are automatically popped up on the platform according to users of different age groups, so that privacy leakage can be avoided by protecting the information.
Preferably, in S3, when collecting information about good scores and bad scores, the ratio of good scores to bad scores is higher than ninety-nine and is preferentially recommended for one, and the experience of the user using the e-commerce platform can be improved by preferentially recommending good products.
Preferably, the search bar in S4 may be preferentially selected by category before use, and a search is performed in the search bar to facilitate a user to accurately find a suitable commodity, so that the range of products may be reduced by performing a category search on the products, and a suitable product may be better recommended to the customer.
An intelligent recommendation system for E-commerce platform products, which is suitable for the intelligent recommendation method for E-commerce platform products, the intelligent recommendation system comprises a recommendation module, a standby module, a search recommendation module, an information analysis module, a product information acquisition module, an age information acquisition module and an evaluation information acquisition module, the information analysis module is used for analyzing information collected by the product information collection module, the age information collection module and the evaluation information collection module, then the appropriate product is recommended to the user through the recommendation module, the user can also search for the product through the recommendation module and reduce the range of the recommended product and then recommend the product, the age information collection module is used for collecting the age of a person who buys the product, the product information collection module is used for collecting information of the person who buys the product in the past year, and the evaluation information collection module is used for collecting good comment and bad comment of the product.
Preferably, the standby module is used for storing data obtained by the information analysis module, so that data loss in the information analysis module caused by failure of the intelligent recommendation system is avoided.
The invention has the advantages that:
1. by the intelligent recommendation method, the products which are interested by the user can be preferentially recommended to the user according to history searching on the platform according to people of different age groups, the products which are suitable for the user are automatically recommended, the user is prevented from purchasing unsuitable products, the browsing time of the products purchased by the user is saved, and the experience of using the e-commerce platform is improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without inventive exercise.
FIG. 1 is a flow chart of an intelligent method recommendation of the present invention;
FIG. 2 is a flowchart of a recommendation algorithm incorporating time decay factors according to the present invention;
FIG. 3 is a graph of Ebinghaos fitting forgetting in the present invention;
FIG. 4 is a graph of the effect of different values of the parameter β on the decay function in accordance with the present invention;
FIG. 5 is a graph of the effect on the decay function when the parameter α takes different values in the present invention;
FIG. 6 is a diagram of an intelligent recommendation system profile of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, an intelligent recommendation method for e-commerce platform products includes the following steps:
s1: the method comprises the following steps of collecting product information sold by the conventional E-commerce platform, and classifying different products into different categories to realize the induction of similar products;
in the process of information acquisition of products sold by an e-commerce platform in the past, four-quarter information acquisition can be carried out on the products within the last year so as to distinguish the products purchased by users in different quarters;
when similar products are summarized, the products can be arranged in a descending order and in an ascending order according to the prices of the similar products, and the price requirements of different users on the products can be met by arranging the prices of the products in the descending order or the ascending order;
s2: collecting age information of users who purchase different commodities so as to distinguish what products people in different age groups like to purchase;
information leakage is prevented when the ages of users purchasing different commodities are collected, meanwhile, commodities suitable for the users are automatically popped up on a platform according to the users of different ages, and the condition of privacy leakage can be avoided by protecting the information;
s3: the method comprises the following steps of collecting information of commodity user evaluation sold by the traditional e-commerce platform, preferentially recommending products with better evaluation scores, and taking off the shelves of commodities with poor evaluation scores;
when the good comment and the bad comment are subjected to information acquisition, the good comment and the bad comment are preferentially recommended in a ratio higher than ninety-nine to one, and the experience of a user using an electric commerce platform can be improved by preferentially recommending good products;
s4: establishing a search bar on an e-commerce platform, and collecting historical behavior data through historical search of a user;
the search bar can be preferentially selected in a classified manner before being used, the search is carried out in the classified bar so that a user can find out a proper commodity accurately, and the product range can be reduced by carrying out classified search on the product so as to better recommend the proper product to a customer;
s5: and establishing a recommendation column on the e-commerce platform, wherein the recommendation column screens data in historical behavior data based on an improved recommendation algorithm for recommendation, and preferentially recommends products of a proper user age.
Considering that the interest of the user changes dynamically, a time attenuation factor is added into the recommendation algorithm to adjust the influence of the user behaviors in different periods on the interest of the user at the current time. The improvement of the recommended algorithm mainly adds a time attenuation factor in the process of calculating the similarity, wherein a time attenuation function mainly refers to an Ebingos forgetting curve.
The Ebinghaos forgetting curve reveals the memory rule of the human brain for information, and when the information is memorized, forgetting of the information by people is started. The forgetting degree changes along with the advancing of time, the forgetting degree is maximum at the initial stage of memory, and the attenuation of the forgetting rate gradually becomes slower as the memory time is longer. As shown in Table 1, the degree of memory of people for information at different time nodes is given.
TABLE 1 Ebinghaos time interval and memory
Figure BDA0003613960010000061
Figure BDA0003613960010000071
According to the memory data in the table 1, a fitted Ebingos forgetting curve graph is drawn, as shown in FIG. 3, revealing the forgetting rule of human beings.
The rules contained in the forgetting curve are applied to a recommendation algorithm, and the prediction influence of the historical behaviors with longer time on the current interest of the user is lower, so that when the recommendation is carried out on the user, the articles with the historical behaviors are endowed with different influence weights according to time factors, the articles with the interactive behaviors in the short term of the user are more concerned, and the obtained user interest is more in line with the dynamic transfer rule of the user interest in practical application.
The method determines the function expression of the time attenuation factor in the recommendation algorithm by fitting an Ebbinriches curve. Along with the increase of time, the interest of a user is attenuated, the attenuation trend conforms to the Eobinghaos forgetting curve rule, the speed is high before the speed is low, and the expression of the attenuation function after fitting is shown as a formula (1):
Figure BDA0003613960010000072
wherein t is0Representing the current time node, tvjRepresenting user to item class vjThe time unit of the behavior time stamp of (1) is hour, and represents the time difference from the historical behavior of the user to the current time.
In the formula (1), values of parameters β and α are different, and attenuation degrees and speeds of time attenuation functions are correspondingly different, and in fig. 4, when the value of the fixed parameter α is 1, and values of the parameter β are 0.01, 0.02 and 0.05, decreasing rates of corresponding function curves are different, and the larger the value is, the faster the interest attenuation speed is.
In fig. 5, the fixed parameter β is 0.02, the parameter α is 0.5, 0.7, and 1, respectively, and when the decreasing rate of the curve is very low, the reached attenuation degrees are different, and the larger the value is, the larger the final attenuation degree is. In the same time interval, for example 1000h, when α is 1, interest decays to 4.8%; when α is 0.7, interest decays to 28.4%; when α is 0.5, interest decays to 61.3%.
Based on the above analysis of the parameters β and α, it can be known that the selection of the parameter values depends on the sensitivity of the model and the experimental data to time, and the values of the parameter values in the experiment of the present invention are respectively selected to be 0.02 and 0.7, and the specific time decay function is shown in formula (1).
The invention designs an algorithm flow for integrating time attenuation factors, particularly an algorithm flow for integrating time attenuation factors, wherein the influence of recent behaviors of a user on future interest preference of the user is deeper, so that the influence of time attenuation on a final recommendation result is considered, the time attenuation factors are integrated into a recommendation algorithm, and influence deviation of historical item scores of the user on future possibly interested items is corrected.
The invention takes a graph embedding model as a recall algorithm, calculates an item set which is possibly interested by a user by utilizing item similarity, integrates a time attenuation factor in the process, and has the specific operations of: firstly, extracting time factors in user behavior data in the data collection and processing process, dividing behavior data to be predicted according to time nodes, calculating time intervals of user behaviors according to the time nodes, calculating time attenuation weight of the user behaviors according to a formula (1), and then integrating a weight formula when calculating similarity score of non-interactive articles according to historical user behavior data to obtain a formula (2):
p(u，i)＝∑j∈N(u)∩S(i，k)wij rujf(t0-tvj) (2)
where N (u) represents the set of items that the user has interacted with, S (i, k) is the set of k items most similar to item i, wijRepresenting the similarity of two articles, rujRepresents the interaction score of user u on item j, f (t)0-tvj) A specific recommended flow for fusing the time attenuation factors for the newly added time attenuation factors is shown in fig. 2.
By the intelligent recommendation method, products which are interested by the user can be preferentially recommended to the user on the platform according to history searching according to people of different age groups, products which are suitable for the user are automatically recommended, the user is prevented from purchasing unsuitable products, browsing time of the products purchased by the user is saved, and experience of using an e-commerce platform is improved.
Please refer to fig. 6, which illustrates an intelligent recommendation system for e-commerce platform products, the intelligent recommendation system is suitable for the above-mentioned intelligent recommendation method for e-commerce platform products, and the intelligent recommendation system includes a recommendation module, a standby module, a search recommendation module, an information analysis module, a product information collection module, an age information collection module, and an evaluation information collection module, the information analysis module is used to analyze the information collected by the product information collection module, the age information collection module, and the evaluation information collection module, and then the recommendation module is used to recommend a user after the appropriate product is recommended by the user after the product is searched by the search recommendation module to reduce the recommended product range, the age information collection module is used to collect the age of the person who buys the product, the product information collection module is used to collect the information of the person who buys the product in the past year, the evaluation information acquisition module is used for acquiring good evaluation and poor evaluation of the product;
after the recommending module screens out the product types which are interesting to the user by adopting a recommending algorithm, selecting proper products according to the age information collecting module from the product types and recommending the proper products to the user, and preferentially recommending the proper products according to the good product rating by the evaluating information collecting module;
the search recommending module selects proper products according to the product types searched by the client and recommends the products to the user according to the age information collecting module, and the proper products are recommended preferentially according to the product goodness of evaluation information collecting module.
The standby module is used for storing data obtained by the information analysis module, and data loss in the information analysis module caused by failure of the intelligent recommendation system is avoided.
In the description herein, references to the description of "one embodiment," "an example," "a specific example" or the like are intended to 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 do not 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.
The foregoing shows and describes the general principles, essential features, and advantages of the invention. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, which are given by way of illustration of the principles of the present invention, but that various changes and modifications may be made without departing from the spirit and scope of the invention, and such changes and modifications are within the scope of the invention as claimed.

Claims (10)

1. An intelligent recommendation method for E-commerce platform products is characterized by comprising the following steps: the intelligent recommendation method comprises the following steps:
s1: the method comprises the following steps of collecting product information sold by the traditional e-commerce platform, dividing different products into different categories, and summarizing the same products;
s2: collecting age information of users who purchase different commodities so as to distinguish product categories which people of different age groups like to purchase;
s3: the method comprises the following steps of collecting information of commodity user evaluation sold by the traditional E-commerce platform, preferentially recommending products with better evaluation, and taking off the shelves of commodities with poor evaluation;
s4: establishing a search bar on an e-commerce platform, and collecting historical behavior data through historical search of a user;
s5: and establishing a recommendation column on the e-commerce platform, wherein the recommendation column screens data in historical behavior data based on an improved recommendation algorithm for recommendation, and preferentially recommends products of a proper user age.
2. The intelligent recommendation method for e-commerce platform products according to claim 1, wherein: the improved recommendation algorithm in the S5 mainly adds a time attenuation factor in the process of calculating the similarity, wherein a time attenuation function refers to an Einghaos forgetting curve;
applying the rules contained in the Ebinghaos forgetting curve to a recommendation algorithm, wherein the prediction influence of the historical behavior data with longer time on the current interest of the user is lower, and when the recommendation is carried out on the user, articles with historical behaviors are endowed with different influence weights according to time factors.
3. The intelligent recommendation method for e-commerce platform products according to claim 2, characterized in that: for the collected historical behavior data, time factors in the historical behavior data of the user are extracted in the data collecting and processing process, the behavior data to be predicted is divided according to time nodes, and the time interval of the occurrence of the user behavior is calculated according to the time nodes.
4. The intelligent recommendation method for E-commerce platform products according to claim 3, wherein: determining the function expression of a time attenuation factor in the recommendation algorithm by fitting an Ebbinriches curve in the recommendation algorithm; the user interest is attenuated along with the increase of time, the attenuation trend conforms to the Eibongos forgetting curve rule, the speed is high before the speed is low, and the attenuation function expression after fitting is shown as a formula (1):
Figure FDA0003613959000000021
wherein t is0Representing the current time node, tvjRepresenting user to item class vjThe behavior timestamp of (1) represents the time difference from the user historical behavior to the current time, wherein the time unit is hour;
the values of parameters beta and alpha in the formula are different, and the attenuation degree and the speed of the time attenuation function are correspondingly different.
5. The intelligent recommendation method for E-commerce platform products according to claim 4, wherein: calculating the time attenuation weight of the user behavior according to the formula (1), and then integrating the weight formula when calculating the similarity score of the non-interactive articles according to the historical behavior data of the user to obtain a formula (2):
p(u，i)＝∑j∈N(u)∩S(i，k)wijrujf(t0-tvj) (2)
where N (u) represents the set of items that the user has interacted with, S (i, k) is the set of k items that are most similar to item i, wijRepresenting the similarity of two articles, rujRepresents the interaction score of user u on item j, f (t)0-tvj) Is a newly added time attenuation factor.
6. The intelligent recommendation method for e-commerce platform products according to claim 1, wherein: in the process of collecting information of products sold by the previous e-commerce platform in S1, four seasons of information collection are performed on products in the last year, so as to distinguish the products purchased by users in different seasons.
7. The intelligent recommendation method for e-commerce platform products according to claim 1, characterized in that: when the similar products in the S1 are summarized, the products are arranged in a descending order and can also be arranged in an ascending order according to the prices of the similar products.
8. The intelligent recommendation method for e-commerce platform products according to claim 1, wherein: in the step S3, when the information collection is performed on the good scores and the bad scores, the ratio of the good scores to the bad scores is more than ninety-nine to one, and the preferential recommendation is performed.
9. The intelligent recommendation method for e-commerce platform products according to claim 1, wherein: the search bar in S4 is preferably selected by category before use, and a search is performed in the category bar to facilitate the user to find a suitable commodity accurately.
10. The utility model provides an intelligent recommendation system of electricity merchant platform product which characterized in that: the intelligent recommendation system applies the intelligent recommendation method of any one of the preceding claims 1-9, the intelligent recommendation system comprises a recommendation module, a standby module, a search recommendation module, an information analysis module, a product information acquisition module, an age information acquisition module and an evaluation information acquisition module, the information analysis module is used for analyzing the information collected by the product information collection module, the age information collection module and the evaluation information collection module, then the recommendation module recommends a proper product to the user, the user can also search for the product through the recommendation module and reduce the range of the recommended product and then recommend the product, the age information collection module is used for collecting the age of a person purchasing the product, the product information collection module is used for collecting the information of the person purchasing the product in the past year, and the evaluation information collection module is used for collecting the good comment and the bad comment of the product.
CN202210440924.8A 2022-04-25 2022-04-25 Intelligent recommendation method and system for E-commerce platform products Pending CN114757742A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210440924.8A CN114757742A (en) 2022-04-25 2022-04-25 Intelligent recommendation method and system for E-commerce platform products

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210440924.8A CN114757742A (en) 2022-04-25 2022-04-25 Intelligent recommendation method and system for E-commerce platform products

Publications (1)

Publication Number Publication Date
CN114757742A true CN114757742A (en) 2022-07-15

Family

ID=82332678

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210440924.8A Pending CN114757742A (en) 2022-04-25 2022-04-25 Intelligent recommendation method and system for E-commerce platform products

Country Status (1)

Country Link
CN (1) CN114757742A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117522528A (en) * 2024-01-04 2024-02-06 厦门智数联科技有限公司 Internet data detection and analysis method and system
CN117892011A (en) * 2024-03-14 2024-04-16 众星北斗(北京)科技发展有限公司 Intelligent information pushing method and system based on big data

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117522528A (en) * 2024-01-04 2024-02-06 厦门智数联科技有限公司 Internet data detection and analysis method and system
CN117522528B (en) * 2024-01-04 2024-03-12 厦门智数联科技有限公司 Internet data detection and analysis method and system
CN117892011A (en) * 2024-03-14 2024-04-16 众星北斗(北京)科技发展有限公司 Intelligent information pushing method and system based on big data
CN117892011B (en) * 2024-03-14 2024-05-17 众星北斗(北京)科技发展有限公司 Intelligent information pushing method and system based on big data

Similar Documents

Publication Publication Date Title
CN108629665B (en) Personalized commodity recommendation method and system
CN106503258B (en) Accurate searching method in website
US8510298B2 (en) Method for relevancy ranking of products in online shopping
US8762226B2 (en) Item discovery tools and methods for shopping in an electronic commerce environment
CN114757742A (en) Intelligent recommendation method and system for E-commerce platform products
CN107633430A (en) A kind of Method of Commodity Recommendation based on community of colony
CN107862566A (en) A kind of Method of Commodity Recommendation and system
CN106600372A (en) Commodity recommending method and system based on user behaviors
CN108153792B (en) Data processing method and related device
CN107169849A (en) Shopping information method for pushing, system and storage medium
CN112102037A (en) Live E-commerce platform commodity content intelligent pushing management system based on big data
CN109446402B (en) Searching method and device
CN105931082B (en) Commodity category keyword extraction method and device
CN111738805B (en) Behavior log-based search recommendation model generation method, device and storage medium
CN107679898A (en) A kind of Method of Commodity Recommendation and device
CN110619559B (en) Method for accurately recommending commodities in electronic commerce based on big data information
CN105630836A (en) Searching result sorting method and apparatus
CN116757794A (en) Big data-based product recommendation method in wine selling applet
CN109886778A (en) The recommended method and system of the tie-in sale product of air ticket
CN113689259A (en) Commodity personalized recommendation method and system based on user behaviors
CN107133811A (en) The recognition methods of targeted customer a kind of and device
Tahir et al. E-commerce platform based on Machine Learning Recommendation System
CN113095904A (en) Recommendation system based on user demands
CN113077320A (en) Business opportunity recommendation method based on user behavior acquisition and analysis
CN112561596A (en) Commodity recommendation method and device

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