CN116911960A - Electronic commerce data recommendation method based on big data - Google Patents

Electronic commerce data recommendation method based on big data Download PDF

Info

Publication number
CN116911960A
CN116911960A CN202311174648.6A CN202311174648A CN116911960A CN 116911960 A CN116911960 A CN 116911960A CN 202311174648 A CN202311174648 A CN 202311174648A CN 116911960 A CN116911960 A CN 116911960A
Authority
CN
China
Prior art keywords
group
commodity
data
target
order data
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
Application number
CN202311174648.6A
Other languages
Chinese (zh)
Other versions
CN116911960B (en
Inventor
刘辉
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.)
Guichang Group Co ltd
Original Assignee
Guichang Group Co ltd
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 Guichang Group Co ltd filed Critical Guichang Group Co ltd
Priority to CN202311174648.6A priority Critical patent/CN116911960B/en
Publication of CN116911960A publication Critical patent/CN116911960A/en
Application granted granted Critical
Publication of CN116911960B publication Critical patent/CN116911960B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/06—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
    • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/35—Clustering; Classification
    • 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
    • G06F16/9537—Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
    • 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

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

Abstract

The invention relates to the field of data processing, in particular to an electronic commerce data recommendation method based on big data, which comprises the following steps: collecting user purchase data; obtaining a target group credibility parameter according to the frequency of the target group data in all the group data; obtaining the credibility parameter of the target label according to the frequency of the target label in the target group and the time sequence of the target label; obtaining the credibility parameter of the target commodity according to the credibility parameter of the target group and the credibility parameter of the target label; obtaining the recommendation degree of the target group according to the credibility parameters of the commodities purchased at the moment and the commodities identical to the target group; and calculating the recommendation degrees of all groups according to the recommendation degrees of the target groups, selecting a group with the largest recommendation degree as an optimal group, and recommending the optimal group to a user. According to the invention, the data processing mode is used for recommending the optimal group by analyzing the corresponding recommendation degrees of different groups.

Description

Electronic commerce data recommendation method based on big data
Technical Field
The invention relates to the technical field of data processing, in particular to an electronic commerce data recommendation method based on big data.
Background
Electronic commerce data recommendations are very important to the e-commerce field. The method can improve user experience, increase sales and profits, optimize commodity management and supply chains, and realize personalized marketing and accurate advertisement delivery. The electronic commerce data recommendation can provide personalized recommended goods and services for the user according to the information such as historical purchase records, browsing behaviors and the like of the user. The personalized recommendation can greatly improve the shopping experience of the user and increase the satisfaction and loyalty of the user. By fully utilizing the advantages of electronic commerce data recommendation, the electronic commerce platform can stand out from the competitive market, and better performance and development can be achieved.
The existing electronic commerce data recommendation is to recommend products to users according to association rules of articles, and products in corresponding high-frequency groups are recommended to users when the users purchase the articles by utilizing the commonly-occurring grouping frequency of the articles. However, the association rule algorithm mainly recommends based on historical data, and cannot capture interest changes of the user in real time, which means that when the interest of the user changes, the association rule algorithm may not be capable of timely adjusting recommendation results.
According to the invention, the goods are recommended to the user by analyzing the goods attribute labels, the weight is added to the labels according to the occurrence frequency and the time sequence of the goods purchased by the user, the higher the occurrence frequency of the labels is, the greater the time sequence is, the more the goods containing the labels are liked by the user, and the time sequence weight is added to respond to the interest change of the user to a certain extent. And the e-commerce data recommendation can be more accurate by combining the associated recommendation according to the weight of the tag.
Disclosure of Invention
The invention provides an electronic commerce data recommendation method based on big data, which aims to solve the existing problems.
The electronic commerce data recommendation method based on big data adopts the following technical scheme:
one embodiment of the invention provides an electronic commerce data recommendation method based on big data, which comprises the following steps:
collecting all groups of order data purchased by a user;
marking any group of order data as a target group, marking any commodity of the target group as a target commodity, and marking any label of any commodity of the target group as a target label;
obtaining a target group credibility parameter according to the frequency of the target group data in all the group data;
obtaining the credibility parameter of the target label according to the frequency of the target label in the target group and the time sequence of the target label;
obtaining the credibility parameter of the target commodity according to the credibility parameter of the target group and the credibility parameter of the target label;
according to the commodity types added into the shopping cart at the moment and the commodity types in the target group, the commodity types are the same, the commodity types are marked as a set Q, and the commodity number in the set Q is marked as C;
obtaining the recommendation degree of the target group according to the set Q, the corresponding credibility parameter and the commodity number C;
and calculating the recommendation degrees of all groups according to the recommendation degrees of the target groups, and recommending the target groups to the user according to the recommendation degrees of all groups.
Further, the collecting all the group order data purchased by the user comprises the following specific steps:
and recording commodity data purchased by the user every week before the current moment as one group of order data, and acquiring all groups of order data of one week before the current moment.
Further, the specific obtaining steps of the target group credibility parameter are as follows:
and obtaining the credibility parameter of the target group according to the ratio between the times of the target group in all the purchase order data and the times of all the purchase order data.
Further, the specific acquisition steps of the time sequence of the target tag are as follows:
counting the ratio of the number of continuous occurrences of the mth label in the ith group of order data in the collection X to the number of occurrences of the mth label in the ith group of order data in the collection X, and recording the ratio as the time sequence of the mth label in the ith group of order data, wherein the collection，/>Representing the nth set of order data.
Further, the specific obtaining steps of the credibility parameter of the target label are as follows:
the credibility parameter formula of the target label is as follows:
in the method, in the process of the invention,representing the frequency of occurrence of the mth tag in the ith set of order data,representing the timing of the mth tag in the ith set of order data, +.>The credibility parameter representing the mth tag in the ith group.
Further, the specific obtaining steps of the credibility parameter of the target commodity are as follows:
the formula of the credibility parameter of the target commodity is as follows:
in the method, in the process of the invention,credibility parameter indicating i-th group order data,/->Credibility parameter indicating the mth label of the mth commodity of the ith group of order data,/item>Represents the number of category of the v-th commodity label in the i-th group order data,and the credibility parameter of the v commodity in the ith group of order data is represented.
Further, the specific acquisition steps of the commodity added into the shopping cart at the moment are as follows:
the merchandise added to the shopping cart at this point represents merchandise that has not been paid for by the order.
Further, the specific acquisition steps of the set Q are as follows:
the commodity type of the shopping cart added by the user at the moment is recorded asWherein, the method comprises the steps of, wherein,g represents the g-th commodity in the order data of the c-th group, and g represents all commodity numbers in the order data of the c-th group; the category of the item in the ith group order data among the items purchased by the user in the previous week is marked +.>Wherein->Representing a v-th commodity in the i-th group order data, v representing all commodity numbers in the i-th group order data; counting the type of goods added to the shopping cart at the moment>Merchandise category +.>The same commodity is recorded as a set Q.
Further, the recommendation degree of the target group is obtained according to the set Q, the corresponding credibility parameter and the commodity number C, and the method comprises the following specific steps:
the formula of the recommended degree of the target group is:
in the method, in the process of the invention,credibility parameter indicating the v-th commodity in the i-th group order data, +.>Indicating that the commodity purchased at this time has the same commodity category number as the target group, and +.>The degree of recommendation that the i-th set of order data is recommended to the user after the items of shopping cart are added at this time is abbreviated as the degree of recommendation of the i-th set of order data.
Further, the recommendation is performed to the user according to the recommendation degree of all groups, and the method comprises the following specific steps:
and selecting a group of order data with the largest recommendation degree to recommend to the user.
The technical scheme of the invention has the beneficial effects that: the conventional electronic commerce data recommending method is used for recommending products to a user according to the association rule of the articles, but the method can only recommend the purchased article types to the user based on the history record, but cannot respond to the article preference of the user, and the association rule does not consider the time sequence and cannot push proper article information to the user based on the current article preference of the user. According to the method, the similarity degree of the commodity labels is compared, the associated recommendation method is combined, and then the labels are added with frequency weights, so that commodity recommendation is more accordant with user preference, and time sequence weights are added, so that the change situation of the user preference can be responded to a certain degree, and electronic commerce data recommendation is more accurate.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flowchart illustrating steps of a big data based electronic commerce data recommendation method according to the present invention.
Detailed Description
In order to further describe the technical means and effects adopted by the invention to achieve the preset aim, the following detailed description is given below of the specific implementation, structure, characteristics and effects of the electronic commerce data recommendation method based on big data according to the invention with reference to the attached drawings and the preferred embodiment. In the following description, different "one embodiment" or "another embodiment" means that the embodiments are not necessarily the same. Furthermore, the particular features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The following specifically describes a specific scheme of the electronic commerce data recommendation method based on big data provided by the invention with reference to the accompanying drawings.
Referring to fig. 1, a flowchart illustrating steps of a big data-based electronic commerce data recommendation method according to an embodiment of the present invention is shown, the method includes the following steps:
step S001: user purchase data and merchandise information data are collected.
It should be noted that, the user purchase record refers to a record of a user's purchase behavior on the e-commerce platform. By analyzing the user's purchase records, the user's interests, preferences, and consumption habits can be understood. This information is important for personalized recommendations. The recommendation method based on the user purchase record can recommend similar or related commodities to the user according to the historical purchase behavior of the user. Therefore, the purchasing satisfaction of the user can be improved, and the purchasing frequency and the purchasing amount of the user are increased. The commodity attribute tags are keywords or tags that describe and classify commodities. By labeling the merchandise, the attributes and features of the merchandise may be better understood and organized. The commodity attribute tags can help the electronic commerce platform to classify and recommend commodities. The recommendation method based on the commodity attribute tags can recommend commodities with similar attribute tags to users according to interests and preferences of the users. This may improve the user's purchase intent and purchase experience.
Specifically, all purchase data of a week before the current time of the user and commodity data and commodity label data of each purchase are collected.
Since the user purchases a commodity, the commodity purchased at this time is usually found in a commodity purchased at a previous time, and the commodities purchased at two times may be identical, analysis is performed based on these characteristics. All commodities purchased in each order are recorded as a group of order data, the group of order data comprises a plurality of commodity data, each commodity data comprises a plurality of label data, wherein each group of data comprises a plurality of commodities, and one commodity comprises a plurality of labels.
Step S002: and obtaining each group of credibility parameters according to each purchase data.
The credibility parameter of each group of order data can be obtained according to the occurrence times of different order data in the order data purchased in a week before the current moment.
Specifically, acquiring the commodity purchasing behavior in a week before the current moment of the user to generate all group order data to obtain a setWherein->Represents the nth group order data, n represents the number of all groups. According to the ratio of the number of times of occurrence of each group of order data in the collection X to all order data in the collection X, recording the ratio as a credibility parameter of each group of order data, using +.>And (3) representing.
Step S003: and associating and recommending the new commodity purchased by the user with the commodity according to the frequency and time sequence of the commodity attribute labels in each group and the credibility parameters of each group.
It should be noted that, in the traditional electronic commerce data recommending method, products are recommended to users according to association rules of the products, association degrees of the products are determined according to occurrence frequency of the common purchasing commodity groups of the users, an association degree threshold is selected, the association groups are screened, and finally the corresponding association groups are selected according to the commodities purchased by the users and the commodities in the group are recommended, but the method can only recommend the purchased commodity types to the users based on historical records, but cannot respond to the commodity preferences of the users, and the association rules do not consider time sequences and cannot push proper commodity information to the users based on the current commodity preferences of the users. The embodiment obtains the reliability parameters of the groups according to the occurrence times of different groups, and then obtains the reliability parameters of each commodity for different groups by combining the reliability parameters of the groups with the occurrence frequency and time sequence of each commodity attribute label in the groups. The selection recommendation meets the preference of the user for certain commodities according to the commodity attributes, and the time sequence of the commodity labels is considered, so that the current commodity preference of the user can be reflected well. And selecting proper groups according to the credibility parameters of the commodities (possibly one commodity or a plurality of commodities) selected by the user, and finally recommending the commodity with the highest similarity according to the similarity degree of each commodity attribute label in the groups and the commodity attribute label selected by the user, so that the electronic commerce data recommendation can be more accurate. According to the frequency combination time sequence of the commodity labels and the credibility parameter of each grouping, a proper group is allocated to each user, commodity attributes are analyzed according to the commodity labels, more accurate commodity recommendation can be achieved for the user, time sequence weights are added to the commodity attribute labels, the larger the time sequence is, the closer the commodity corresponding to the label is to the recent purchasing trend of the user, so that the larger the time sequence weights of the commodity attribute labels are, the more the occurrence times of certain labels contained in the same group of commodities are, and the larger the probability that the commodity containing the label is liked by the user is.
(1) And obtaining the credibility parameter of each commodity label in the group according to the duty ratio and the total time sequence of the occurrence frequency of the commodity label in each group in the group.
It should be noted that, the more the number of times of the labels in the group is, the greater the probability that the goods containing the labels are liked by the user is, the greater the time sequence weight is, and the closer the goods corresponding to the labels are to the recent purchasing trend of the user. Wherein, a plurality of labels are contained in one commodity, and different commodities have the same label.
In particular, forIn (i) th group order data>Statistics of->The frequency of occurrence of each tag in (a) is denoted as +.>Wherein->Represents the frequency of occurrence of the mth tag in the ith set of order data, and m represents the number of all tags in the ith set of order data.
It should be further noted that, because the larger the time, the closer the time of the scale surface of the article where the tag is located is to the current time, and the more representative the purchasing trend of the user, it is necessary to add a weight to each time t according to the time size and perform time weighting averaging. In the time series analysis of each of the merchandise tags, when one tag is longer in continuous length in the purchasing time series, it is indicated that it is stronger in time series. And weighting and averaging the labels according to the duty ratio of each time of the labels, wherein the larger the time (the closer to the current time), the more the corresponding commodities purchased by the user at the time accords with the purchasing preference change trend of the user, and the obtained time sequence is more accurate.
Specifically, continuing to analyze the mth label in the ith group of order data as an example, counting the ratio of the number of times the mth label in the ith group of order data continuously appears in the collection X to the number of times the mth label in the ith group of order data appears in the collection X, recording as the time sequence of the mth label in the ith group of order data, usingRepresenting, m represents the number of all tags in the ith set of order data.
According to the frequency of occurrence of the mth label in the ith order dataAnd the timing of the mth tag in the ith group order data +.>And obtaining the credibility parameter of the mth label in the ith group of order data.
The calculation formula is as follows:
in the method, in the process of the invention,representing the frequency of occurrence of the mth tag in the ith set of order data,representing the timing of the mth tag in the ith set of order data, +.>The credibility parameter representing the mth tag in the ith group.
So far, the credibility parameter of each label is obtained.
(2) And obtaining the credibility parameters of each commodity according to the credibility parameters of the labels in the groups and the credibility parameters of each group.
It should be noted that, according to the reliability parameters of the labels in the group, the reliability of the commodities can be obtained by combining the commodities in the group, and in order to conveniently compare the reliability of the same commodities in different groups, the reliability of the commodities needs to be combined with the grouping reliability parameters of the corresponding groups to obtain the reliability parameters of each commodity.
Specifically, the category of the commodity existing in the ith group order data is recorded asWherein->The v commodity in the i-th order data is represented, and v represents the number of all commodities in the i-th order data.
Taking the commodity thereinThe tag species present is->Wherein->The j-th label of the v-th commodity in the i-th group is represented, and k represents the number of all labels in the v-th commodity in the i-th group. The confidence parameters for each commodity are:
in the method, in the process of the invention,credibility parameter indicating i-th group order data,/->Credibility parameter indicating the mth label of the mth commodity of the ith group of order data,/item>Represents the number of category of the v-th commodity label in the i-th group order data,and the credibility parameter of the v commodity in the ith group of order data is represented.
(3) And carrying out relevance grouping according to the credibility parameter of the commodity.
It should be noted that, when comparing the credibility of the commodities in different groups, there may be some groups in which the user does not purchase the commodities currently, but the credibility of other commodities purchased by the user is higher, so that the group is also higher for the user, and when comparing the average value of the grouped credibility of each product purchased by the user at the current time in different groups, if the commodity purchased currently does not exist in the groups, the credibility parameter of the commodity is 0, but the calculation of the average value is counted.
Specifically, the type of merchandise that the user added to the shopping cart at the moment is recorded asWherein->Representing the g-th item in the order data of group c. The category of the item in the ith group order data among the items purchased by the user in the previous week is marked +.>Wherein->Representing the v-th item in the i-th set of order data. Counting the type of goods added to the shopping cart at the moment>Merchandise category +.>The same commodity is recorded as a set Q, and the commodity number in the set Q is recorded as C.
And obtaining a recommendation degree of the commodity of the target group after the purchased commodity is obtained according to the credibility selection parameter of the same commodity in the ith group of order data.
The formula of the recommended degree is:
in the method, in the process of the invention,credibility parameter indicating the v-th commodity in the i-th group order data in set Q,/and>indicating that the merchandise purchased at this time in the set Q has the same number of merchandise as the target group, ++>The degree of recommendation that the i-th group of order data in the set Q is recommended to the user after the items of the shopping cart are added at this time is abbreviated as the degree of recommendation of the i-th group of order data.
So far, the recommended degree of each group of order data is obtained.
Step S004: and recommending the commodity according to the recommendation degree in the group.
At this time, after the user selects the commodity to the shopping cart, the platform recommends the commodity of the group of order data with the largest recommendation degree to the user according to the recommendation degree of the obtained group of order data.
This embodiment is completed.
The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, alternatives, and improvements that fall within the spirit and scope of the invention.

Claims (10)

1. The electronic commerce data recommendation method based on big data is characterized by comprising the following steps of:
collecting all groups of order data purchased by a user;
marking any group of order data as a target group, marking any commodity of the target group as a target commodity, and marking any label of any commodity of the target group as a target label;
obtaining a target group credibility parameter according to the frequency of the target group data in all the group data;
obtaining the credibility parameter of the target label according to the frequency of the target label in the target group and the time sequence of the target label;
obtaining the credibility parameter of the target commodity according to the credibility parameter of the target group and the credibility parameter of the target label;
according to the commodity types added into the shopping cart at the moment and the commodity types in the target group, the commodity types are the same, the commodity types are marked as a set Q, and the commodity number in the set Q is marked as C;
obtaining the recommendation degree of the target group according to the set Q, the corresponding credibility parameter and the commodity number C;
and calculating the recommendation degrees of all groups according to the recommendation degrees of the target groups, and recommending the target groups to the user according to the recommendation degrees of all groups.
2. The method for recommending electronic commerce data based on big data as claimed in claim 1, wherein the collecting all sets of order data purchased by the user comprises the following specific steps:
and recording commodity data purchased by the user every week before the current moment as one group of order data, and acquiring all groups of order data of one week before the current moment.
3. The electronic commerce data recommendation method based on big data as claimed in claim 1, wherein the specific obtaining steps of the target group credibility parameter are as follows:
and obtaining the credibility parameter of the target group according to the ratio between the times of the target group in all the purchase order data and the times of all the purchase order data.
4. The electronic commerce data recommendation method based on big data as claimed in claim 1, wherein the specific acquisition step of the time sequence of the target tag is as follows:
counting the ratio of the number of continuous occurrences of the mth label in the ith group of order data in the collection X to the number of occurrences of the mth label in the ith group of order data in the collection X, and recording the ratio as the time sequence of the mth label in the ith group of order data, wherein the collection，/>Representing the nth set of order data.
5. The electronic commerce data recommendation method based on big data as claimed in claim 1, wherein the specific obtaining steps of the credibility parameter of the target tag are as follows:
the credibility parameter formula of the target label is as follows:
in the method, in the process of the invention,representing the frequency of occurrence of the mth tag in the ith set of order data, etc.>Representing the timing of the mth tag in the ith set of order data, +.>The credibility parameter representing the mth tag in the ith group.
6. The electronic commerce data recommendation method based on big data as claimed in claim 1, wherein the specific obtaining steps of the credibility parameter of the target commodity are as follows:
the formula of the credibility parameter of the target commodity is as follows:
in the method, in the process of the invention,credibility parameter indicating i-th group order data,/->Representing the v-th quotient in the i-th group order dataCredibility parameter of item m tag, < ->Represents the number of category of the v-th commodity label in the i-th group order data,and the credibility parameter of the v commodity in the ith group of order data is represented.
7. The electronic commerce data recommendation method based on big data according to claim 1, wherein the specific acquisition steps of the commodity added to the shopping cart at the moment are as follows:
the merchandise added to the shopping cart at this point represents merchandise that has not been paid for by the order.
8. The method for recommending electronic commerce data based on big data as claimed in claim 1, wherein the specific acquiring step of the set Q is as follows:
the commodity type of the shopping cart added by the user at the moment is recorded asWherein->G represents the g-th commodity in the order data of the c-th group, and g represents all commodity numbers in the order data of the c-th group; the category of the item in the ith group order data among the items purchased by the user in the previous week is marked +.>Wherein->Representing a v-th commodity in the i-th group order data, v representing all commodity numbers in the i-th group order data; counting the type of goods added to the shopping cart at the moment>Merchandise category +.>The same commodity is recorded as a set Q.
9. The method for recommending e-commerce data based on big data as claimed in claim 1, wherein the recommendation degree of the target group is obtained according to the set Q and the corresponding credibility parameter and the commodity number C, comprising the following specific steps:
the formula of the recommended degree of the target group is:
in the method, in the process of the invention,credibility parameter indicating the v-th commodity in the i-th group order data, +.>Indicating that the commodity purchased at this time has the same commodity category number as the target group, and +.>The degree of recommendation that the i-th set of order data is recommended to the user after the items of shopping cart are added at this time is abbreviated as the degree of recommendation of the i-th set of order data.
10. The method for recommending e-commerce data based on big data as claimed in claim 1, wherein said recommending to the user according to the recommended degree of all groups comprises the specific steps of:
and selecting a group of order data with the largest recommendation degree to recommend to the user.
CN202311174648.6A 2023-09-12 2023-09-12 Electronic commerce data recommendation method based on big data Active CN116911960B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202311174648.6A CN116911960B (en) 2023-09-12 2023-09-12 Electronic commerce data recommendation method based on big data

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202311174648.6A CN116911960B (en) 2023-09-12 2023-09-12 Electronic commerce data recommendation method based on big data

Publications (2)

Publication Number Publication Date
CN116911960A true CN116911960A (en) 2023-10-20
CN116911960B CN116911960B (en) 2023-11-17

Family

ID=88363381

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202311174648.6A Active CN116911960B (en) 2023-09-12 2023-09-12 Electronic commerce data recommendation method based on big data

Country Status (1)

Country Link
CN (1) CN116911960B (en)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108665333A (en) * 2017-03-31 2018-10-16 北京京东尚科信息技术有限公司 Method of Commodity Recommendation, device, electronic equipment and storage medium
US20180374141A1 (en) * 2017-06-27 2018-12-27 Alibaba Group Holding Limited Information pushing method and system
CN109214893A (en) * 2018-08-31 2019-01-15 深圳春沐源控股有限公司 Method of Commodity Recommendation, recommender system and computer installation
CN113283960A (en) * 2021-05-18 2021-08-20 武汉畅来电子商务有限公司 Vertical e-commerce platform commodity intelligent recommendation method based on big data analysis and cloud computing and cloud service platform
CN115878903A (en) * 2023-02-21 2023-03-31 万链指数(青岛)信息科技有限公司 Intelligent information recommendation method based on big data

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108665333A (en) * 2017-03-31 2018-10-16 北京京东尚科信息技术有限公司 Method of Commodity Recommendation, device, electronic equipment and storage medium
US20180374141A1 (en) * 2017-06-27 2018-12-27 Alibaba Group Holding Limited Information pushing method and system
CN109214893A (en) * 2018-08-31 2019-01-15 深圳春沐源控股有限公司 Method of Commodity Recommendation, recommender system and computer installation
CN113283960A (en) * 2021-05-18 2021-08-20 武汉畅来电子商务有限公司 Vertical e-commerce platform commodity intelligent recommendation method based on big data analysis and cloud computing and cloud service platform
CN115878903A (en) * 2023-02-21 2023-03-31 万链指数(青岛)信息科技有限公司 Intelligent information recommendation method based on big data

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
肖晓丽;周锡玲;: "基于用户相似度和信任度的药品推荐算法", 计算机工程与应用, no. 08 *

Also Published As

Publication number Publication date
CN116911960B (en) 2023-11-17

Similar Documents

Publication Publication Date Title
CN104679771B (en) A kind of individuation data searching method and device
US8027865B2 (en) System and method for providing E-commerce consumer-based behavioral target marketing reports
CN104866474B (en) Individuation data searching method and device
Sivapalan et al. Recommender systems in e-commerce
CN107590675B (en) User shopping behavior identification method based on big data, storage device and mobile terminal
CN111709812A (en) E-commerce platform commodity recommendation method and system based on user dynamic classification
US20070294149A1 (en) Catalog based price search
CN112435067A (en) Intelligent advertisement putting method and system for cross-e-commerce platform and social platform
CN105630836A (en) Searching result sorting method and apparatus
CN115878903B (en) Information intelligent recommendation method based on big data
CN115496566B (en) Regional specialty recommendation method and system based on big data
CN106919995A (en) A kind of method and device for judging user group&#39;s loss orientation
CN116431931A (en) Real-time incremental data statistical analysis method
Zheng et al. A scalable purchase intention prediction system using extreme gradient boosting machines with browsing content entropy
CN117455632B (en) Big data-based E-commerce option analysis management platform
CN117474631A (en) Recommendation algorithm for data mining and emotion analysis based on e-commerce platform comments
CN116911960B (en) Electronic commerce data recommendation method based on big data
Zuo Prediction of consumer purchase behaviour using Bayesian network: an operational improvement and new results based on RFID data
CN115330476A (en) Cross-border retail imported commodity intelligent recommendation system based on big data
CN110020136B (en) Object recommendation method and related equipment
Malik et al. Applying data mining for clustering shoppers based on store loyalty
CN117035947B (en) Agricultural product data analysis method and cloud platform based on big data processing
Tabak Kizgin et al. Random Forest Based Hybrid Approaches to Analysis of Retail Stores
CN117635237A (en) Advertisement management system based on SaaS information flow and cross-platform crowd data
Ajayi et al. Made-to-Order: Targeted Marketing in Fast-Food Using Collaborative Filtering

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