CN112100483A - Association rule recommendation method fusing user interest weight - Google Patents
Association rule recommendation method fusing user interest weight Download PDFInfo
- Publication number
- CN112100483A CN112100483A CN202010788400.9A CN202010788400A CN112100483A CN 112100483 A CN112100483 A CN 112100483A CN 202010788400 A CN202010788400 A CN 202010788400A CN 112100483 A CN112100483 A CN 112100483A
- Authority
- CN
- China
- Prior art keywords
- user
- customized
- tree
- content
- item
- 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 26
- 238000005065 mining Methods 0.000 claims abstract description 18
- 239000011159 matrix material Substances 0.000 claims abstract description 8
- 238000007781 pre-processing Methods 0.000 claims description 3
- 238000007418 data mining Methods 0.000 abstract description 2
- 238000002474 experimental method Methods 0.000 description 4
- 238000009412 basement excavation Methods 0.000 description 2
- 230000007423 decrease Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000052 comparative effect Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Images
Classifications
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2465—Query processing support for facilitating data mining operations in structured databases
-
- 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
- G06F16/901—Indexing; Data structures therefor; Storage structures
- G06F16/9027—Trees
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
Abstract
The invention discloses an association rule recommendation method fusing user interest weights, which is implemented according to the following steps: step 1, constructing a scoring matrix of a user and a customized project; step 2, calculating the interest weight of the user on the customized content; step 3, constructing a UIFP-tree according to the user customized content interest weight; and 4, mining the frequent pattern of the UIFP-tree to obtain a frequent item combination, and recommending the frequent item combination to the user. According to the invention, through fusing the user interest weight, the obtained customized content rule more retains the preference of the user, a large number of meaningless rules are filtered, the data mining efficiency is improved, and the finally obtained strong association rule has practical application value.
Description
Technical Field
The invention belongs to the technical field of customized content association rule recommendation, and relates to an association rule recommendation method fusing user interest weights.
Background
In recent years, association rule mining algorithms are widely applied to the field of recommendation, and by analyzing data, association between the data is found, and recommendation is realized by using association rules. The clothing customized content recommendation is based on a clothing style, and a customized content combination with a specific rule is mined and recommended to a user according to related order information of a certain clothing style. The traditional FP-growth association rule algorithm only uses the minimum support degree as a filtering and screening standard of an item set in a transaction database, in the recommendation process, the support degree and the confidence degree are two thresholds which are frequently applied in the traditional association rule algorithm, but sometimes strong association rules with high support degree and high confidence degree have no practical application value, particularly in the field of e-commerce, a preference rule obtained according to user subjective scoring is more valuable, and the preference is easily filtered by using the traditional FP-growth association rule algorithm.
Disclosure of Invention
The invention aims to provide an association rule recommendation method fusing user interest weights, and solves the problems that in the prior art, the association rule recommendation efficiency is low, and the recommendation result is inaccurate.
The technical scheme adopted by the invention is that an association rule recommendation method fusing user interest weights is implemented according to the following steps:
and 4, mining the frequent pattern of the UIFP-tree to obtain a frequent item combination, and recommending the frequent item combination to the user.
The invention is also characterized in that:
the step 1 is implemented according to the following steps:
step 1.1, if the set system item has K items, the customized content is indicated as content, and the customized combination is indicated as item ═ content1,content2,......,contentk}；
Step 1.2, n user customized combinations and m users are set, and the user customized combinations are expressed as I ═ item1,item2,......,itemnUser is expressed as U ═ user }1,user2,......,userm}；
And 1.3, building a rating matrix of the user and the customized project according to the historical rating of the user on the customized project.
Step 1.3 specifically includes preprocessing the commonly used 5-star user scores, setting all the scores from 0 to 3 as 0, representing that the current customized combination is not favored, setting all the scores from 4 to 5 as 1, representing that the current customized combination is favored, and expressing the score matrixes of the users and the customized items as follows:
wherein ,Ri,j(i is more than or equal to 1 and less than or equal to m, j is more than or equal to 1 and less than or equal to n) represents the useriCombining items for customizationjThe score of (1).
wherein ,
represents the number of users having a rating value of 1 for the customized content, | U | represents the total number of users.
step 3.1, scanning a transaction database D, and solving a frequent item set F which meets the minimum support degree count min _ sup in the database D;
step 3.2, solving all the weights W meeting the user customized content interestingness in the set FiMin _ u or moreoptionA set W of (A);
3.3, sorting the set W in a descending order according to the support degree, recording the result as a table L, creating a UIFP-tree root node, recording the UIFP-tree root node as root, and recording the root node as NULL;
and 3.4, inserting a node under the root node to obtain the UIFP-tree.
Step 3.4 is specifically implemented according to the following steps:
step 3.4.1, satisfy min _ u in each transactionoptionIs ordered in the order in L, and the ordered list is denoted as [ P | P]Where P is the first element and P is the table of the remaining elements;
step 3.4.2, invoke an Insert _ tree ([ P | P ], T).
step 4.1, obtaining a conditional mode base, starting from a leaf node of the UIFP-tree, obtaining a prefix path of each node from bottom to top, and replacing the support degree count with the support degree count of the current node;
step 4.2, constructing a conditional FP tree by using a conditional mode base, recursively calling a tree structure, deleting nodes smaller than the minimum support degree, and directly listing all combinations, namely frequent item combinations, if the tree structure of a single path is finally presented; if the tree structure of the non-single path is finally presented, the tree structure is continuously called until the tree structure of the single path is formed;
and 4.3, repeating the step 4.1 and the step 4.2 until the tree only contains one element, namely the frequent item combination finally recommended to the user.
The invention has the beneficial effects that: compared with the traditional FP-growth algorithm, the method disclosed by the invention has the advantages that the user interest weight is fused, more user preferences are kept in the obtained clothing customization content rules, a large number of meaningless rules are filtered, the data mining efficiency is improved, and the finally obtained strong association rules have actual application values
Drawings
FIG. 1 is a tree diagram of frequent patterns filtered by the minimum support and the user interest weight in the association rule recommendation method with the user interest weight fused according to the present invention;
FIG. 2 is a graph showing the comparison experiment result of the algorithm running time of the UIFP-growth algorithm and the existing FP-growth algorithm under different minimum support degrees;
FIG. 3 is a comparison graph of the number of excavation results of the UIFP-growth algorithm adopted by the present invention and the existing FP-growth algorithm under different minimum support degrees;
FIG. 4 is a diagram comparing the running time of the UIFP-growth algorithm adopted by the present invention with the existing FP-growth algorithm under different transaction numbers.
Detailed Description
The present invention will be described in detail below with reference to the accompanying drawings and specific embodiments.
The invention relates to an association rule recommendation method fusing user interest weights, which is implemented according to the following steps:
step 1.1, all the customizable contents of a certain clothing style have k items, and the customizable contents comprise: the customized content is expressed as content, and the customized combination is expressed as item ═ content { (content)1,content2,......,contentk}；
Step 1.2, assuming that a certain clothing style has n user-customized combinations and m users, the user-customized combination is expressed as I ═ item ═ m1,item2,......,itemnUser is expressed as U ═ user }1,user2,......,userm}；
Step 1.3, building a rating matrix of the user and the customized project according to the historical rating of the user on the customized project; preprocessing the commonly used 5-star user scores, setting all the scores of 0-3 as 0 to represent that the current customized combination is disliked, setting all the scores of 4-5 as 1 to represent that the current customized combination is liked, and expressing the score matrixes of the users and the customized items as follows:
wherein ,Ri,j(i is more than or equal to 1 and less than or equal to m, j is more than or equal to 1 and less than or equal to n) represents the useriCombining items for customizationjScoring of (4);
TABLE 1 user-customized content interest Scoring
The customized content option weight is set to find out items which can better describe the user interest, and the customized content interest weight is as follows:
wherein ,
the number of users with the rating value of 1 of the customized content is represented, and the total number of the users is represented by U |; the higher W indicates that the user is more interested in the content, and the lower W indicates that the user is less interested in the content, particularly
When all users have selected the itemThe content, namely the interestingness of the content to all users is not different;
step 3.1, scanning a transaction database D, and solving a frequent item set F which meets the minimum support degree count min _ sup in the database D;
step 3.2, solving all the weights W meeting the user customized content interestingness in the set FiMin _ u or moreoptionA set W of (A);
3.3, sorting the set W in a descending order according to the support degree, recording the result as a table L, creating a UIFP-tree root node, recording the UIFP-tree root node as root, and recording the root node as NULL;
step 3.4, inserting nodes under the root node to obtain a UIFP-tree; the method is implemented according to the following steps:
step 3.4.1, satisfy min _ u in each transactionoptionIs ordered in the order in L, and the ordered list is denoted as [ P | P]Where P is the first element and P is the table of the remaining elements;
step 3.4.2, call Insert _ tree ([ P | P ], T);
the Insert _ tree comprises the following specific steps:
1) if T has a child N such that the N. item name is p. item name, then the count of N is incremented by 1;
2) otherwise, creating a new node N, setting the count of the new node N to 1, and linking to the parent node T of the new node N;
3) linking the nodes of N to nodes having the same item name through a node chain structure;
4) if P is not empty, recursively invoke an Insert _ Tree ([ Q | Q ], N), where Q is one element in P and Q is a table of remaining elements;
step 4.1, obtaining a conditional mode base, starting from a leaf node of the UIFP-tree, obtaining a prefix path of each node from bottom to top, and replacing the support degree count with the support degree count of the current node;
step 4.2, constructing a conditional FP tree by using a conditional mode base, recursively calling a tree structure, deleting nodes smaller than the minimum support degree, and directly listing all combinations, namely frequent item combinations, if the tree structure of a single path is finally presented; if the tree structure of the non-single path is finally presented, the tree structure is continuously called until the tree structure of the single path is formed;
and 4.3, repeating the step 4.1 and the step 4.2 until the tree only contains one element, namely the frequent item combination finally recommended to the user.
Examples
Taking suit customization as an example, the application of the method in the recommendation of the clothing customized content is analyzed in detail, and according to the research on the customized content of a certain style of suit, the name and parameters of the customized content are shown in table 2:
table 2 customized content for western style clothes
According to the research on the customized content of the suit with a certain style, part of experimental data are extracted for specific analysis, and a data set is shown in table 3:
TABLE 3 data set
Assuming that the minimum support count is min _ sup-3, min _ u option1/3, parameterize the data in the dataset and scan the database once, and the results are shown in table 4:
TABLE 4 transaction database D and filtered sorted items
The process of mining frequent items of the transaction database D is as follows:
(1) deriving a frequent item set;
for the 1 st scan of the database, derive the frequent 1-term set F ═ L1:5, N1:5, E1:3, F1:3, D1: 3;
(2) finding all item sets satisfying the minimum customized content interestingness weight;
solving for set F where all customized content interest weights are greater than min _ uoptionAnd performing descending sorting according to the support degree to obtain a sorted set L. Then the interestingness weights for each of F are F ═ L1:3/7, N1:4/7, E1:3/7, F1:3/7, D1:2/7]Since the interestingness weight of D1 is below the threshold min _ uoptionThus, when D1 is clipped, L ═ L1:5, N1:5, E1:3, F1:3]The set of frequent items in each transaction that meet the minimum interestingness weight is shown in table 5:
TABLE 5 frequent item set satisfying minimum interestingness weight
(1) Constructing a UIFP-tree;
creating a root node of the tree, which is marked as root and has a value of "NULL", scanning the transaction database D again, creating a branch for each transaction, and for the first transaction "T1: L1, N1, E1, F1" in the transaction database, for the first branch of the tree < (L1:1), (N1:1), (E1:1), (F1:1) >, for the second transaction, since it is identical to the first transaction, each node count is increased by 1, for the third transaction, since its frequent entry table < L1> shares the existing branch path < L1, N1, E1, F1> prefix path < L1>, the node < L1> in the prefix path is increased by 1, if there is a new node, only creating a new link later, and so on, resulting in a frequent pattern tree as shown in fig. 2, (2) mining-owp;
according to the FP-growth algorithm, the UIFP-tree shown in FIG. 2 is mined as follows: firstly, searching the item head table according to the bottom-up sequence, finding the last item F1 in the item head table, and finding two branches where the item F1 is located according to the node chain of F1: < L1:3, N1:2, E1:2, F1:2> and < L1:3, E1:1, F1:1>, it can be seen that prefix paths of F1 are < L1, E1, N1:2> and < L1, E1:1>, which constitute the conditional pattern base of F1, for such a sub-database, a conditional frequent pattern tree is established, the conditional frequent pattern tree of F1 contains only nodes < L1, E1> and does not contain node < N1>, because the number of supported nodes of N1 is less than the minimum number of supported 3, so node N1 is filtered out, the resulting set of frequent items is { (F1:3), (L1, F1:3), (E1, F1:3), (L1, E1, F1:3), and so on the result table is as shown in the mining of frequent pattern pairs.
TABLE 6 UIFP-growth mining results
The experimental data of the invention come from a background database of a negara garment customization mall, all user customization combinations under a certain suit style are derived from the background database, and 2000 pieces of customization information are used as a test data set; the hardware environment for the experiment was: windows10, memory 8G, CPUi7-8550, the software environment is: python version 3.6.3, PyCharm integration environment; in order to verify the effectiveness of the UIFP-growth algorithm, the invention compares the UIFP-growth algorithm with the following three aspects:
1) the comparison experiment results of the algorithm running time under different minimum support degrees are shown in FIG. 2;
it can be seen from fig. 2 that, under different minimum support degrees, the UIFP-growth algorithm is shorter than the FP-growth algorithm in running time, the mining efficiency is higher, the FP-growth algorithm running time gradually decreases with the increase of the minimum support degree, and the UIFP-growth algorithm running time is dependent on the minimum support degree and a given user-customized content interest weight threshold value min _ uoptionGradually decreases when the minimum support and min _ uoptionWhen it is greater than 0.3, calculateThe run time of the method does not change significantly, so when the minimum support and min _ uoptionWhen the value is 0.3, the mining result efficiency is higher, and the result is more meaningful;
2) the comparative experiment of the quantity of excavation results under different minimum support degrees is shown in FIG. 3;
it can be seen from fig. 3 that the number of mining results of the UIFP-growth algorithm under the same minimum support degree is smaller than that of the FP-growth algorithm, the number of mining results by using the FP-growth algorithm is gradually reduced with the increase of the minimum support degree, and the UIFP-growth algorithm is associated with the given minimum support degree and the user customized content interest weight min _ uoptionThe mining result is gradually reduced, and the mining result is less than the FP-growth algorithm under different minimum support degrees, because the UIFP-growth algorithm filters the interest degree weight on the basis of the minimum support degree in the mining process, certain meaningless rules are reduced, and the mining result is more meaningful;
3) in the case that the minimum support and the customized content interest weight are both 0.3, the UIFP-growth algorithm and the FP-growth algorithm run time pairs under different transaction numbers, as shown in fig. 4;
it can be seen from fig. 4 that the running time of the UIFP-growth algorithm is lower than that of the FP-growth algorithm when mining is performed in the same number of transactions, and as the number of database transactions increases, the running times of the FP-growth algorithm and the UIFP-growth algorithm both increase, but the growth speed of the UIFP-growth algorithm is slower, so that the UIFP-growth algorithm has shorter mining time and better performance than the FP-growth algorithm.
Claims (7)
1. A recommendation method for association rules fusing user interest weights is characterized by being implemented according to the following steps:
step 1, constructing a scoring matrix of a user and a customized project;
step 2, calculating the interest weight of the user on the customized content;
step 3, constructing a UIFP-tree according to the user customized content interest weight;
and 4, mining the frequent pattern of the UIFP-tree to obtain a frequent item combination, and recommending the frequent item combination to the user.
2. The association rule recommendation method fusing user interest weights according to claim 1, wherein the step 1 is implemented specifically according to the following steps:
step 1.1, if the set system item has K items, the customized content is indicated as content, and the customized combination is indicated as item ═ content1,content2,......,contentk}；
Step 1.2, n user customized combinations and m users are set, and the user customized combinations are expressed as I ═ item1,item2,......,itemnUser is expressed as U ═ user }1,user2,......,userm}；
And 1.3, building a rating matrix of the user and the customized project according to the historical rating of the user on the customized project.
3. The association rule recommendation method fusing user interest weights according to claim 2, wherein the step 1.3 specifically comprises preprocessing a commonly used 5-star user score, setting all scores 0-3 as 0, representing that the current customized combination is not favored, setting all scores 4-5 as 1, representing that the current customized combination is favored, and expressing a score matrix of the user and the customized item as:
wherein ,Ri,j(i is more than or equal to 1 and less than or equal to m, j is more than or equal to 1 and less than or equal to n) represents the useriCombining items for customizationjThe score of (1).
4. The method as claimed in claim 1, wherein the step 2 is specifically configured to set the content to include n choices, the content ═ option [ [ option ] ], and the method is further characterized in that1,option2,......,optionnIf user }, ifiCombining items for customized contentjIs scored as 1, then itemjThe option corresponding to each customized content score in the customized content score is 1, and the customized content interest weight is as follows:
wherein ,
represents the number of users having a rating value of 1 for the customized content, | U | represents the total number of users.
5. The association rule recommendation method fusing user interest weights according to claim 1, wherein the step 3 is implemented specifically according to the following steps:
step 3.1, scanning a transaction database D, and solving a frequent item set F which meets the minimum support degree count min _ sup in the database D;
step 3.2, solving all the weights W meeting the user customized content interestingness in the set FiMin _ u or moreoptionA set W of (A);
3.3, sorting the set W in a descending order according to the support degree, recording the result as a table L, creating FP-tree root nodes, recording the FP-tree root nodes as roots, and recording the root nodes as NULL;
and 3.4, inserting a node under the root node to obtain the UIFP-tree.
6. The association rule recommendation method fusing user interest weights according to claim 5, wherein the step 3.4 is implemented according to the following steps:
step 3.4.1, satisfy min _ u in each transactionoptionIs ordered in the order in L, and the ordered list is denoted as [ P | P]Where P is the first element and P is the table of the remaining elements;
step 3.4.2, invoke an Insert _ tree ([ P | P ], T).
7. The association rule recommendation method fusing user interest weights according to claim 1, wherein the step 4 is implemented specifically according to the following steps:
step 4.1, obtaining a conditional mode base, starting from a leaf node of the UIFP-tree, obtaining a prefix path of each node from bottom to top, and replacing the support degree count with the support degree count of the current node;
step 4.2, constructing a conditional FP tree by using a conditional mode base, recursively calling a tree structure, deleting nodes smaller than the minimum support degree, and directly listing all combinations, namely frequent item combinations, if the tree structure of a single path is finally presented; if the tree structure of the non-single path is finally presented, the tree structure is continuously called until the tree structure of the single path is formed;
and 4.3, repeating the step 4.1 and the step 4.2 until the tree only contains one element, namely the frequent item combination finally recommended to the user.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010788400.9A CN112100483B (en) | 2020-08-07 | 2020-08-07 | Association rule recommendation method fusing user interest weights |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010788400.9A CN112100483B (en) | 2020-08-07 | 2020-08-07 | Association rule recommendation method fusing user interest weights |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112100483A true CN112100483A (en) | 2020-12-18 |
| CN112100483B CN112100483B (en) | 2023-09-19 |
Family
ID=73752755
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010788400.9A Active CN112100483B (en) | 2020-08-07 | 2020-08-07 | Association rule recommendation method fusing user interest weights |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112100483B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116611769A (en) * | 2023-07-19 | 2023-08-18 | 杭州吉客云网络技术有限公司 | Order aggregation method, order aggregation device, computer equipment and storage medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160358211A1 (en) * | 2015-06-04 | 2016-12-08 | Sap Se | Personalized recommendation system for coupon deals |
| WO2018010591A1 (en) * | 2016-07-12 | 2018-01-18 | 腾讯科技（深圳）有限公司 | Information push method and apparatus, server, and storage medium |
| CN109299313A (en) * | 2018-08-03 | 2019-02-01 | 昆明理工大学 | A kind of song recommendations method based on FP-growth |
| CN109871479A (en) * | 2019-01-08 | 2019-06-11 | 西北大学 | A kind of collaborative filtering method based on user items class and the reliability that scores |
| CN109977309A (en) * | 2019-03-21 | 2019-07-05 | 杭州电子科技大学 | Combination point of interest querying method based on multiple key and user preference |
| CN110825977A (en) * | 2019-10-10 | 2020-02-21 | 平安科技（深圳）有限公司 | Data recommendation method and related equipment |
| CN110851718A (en) * | 2019-11-11 | 2020-02-28 | 重庆邮电大学 | Movie recommendation method based on long-time memory network and user comments |
| CN111428127A (en) * | 2020-01-21 | 2020-07-17 | 江西财经大学 | Personalized event recommendation method and system integrating topic matching and two-way preference |
-
2020
- 2020-08-07 CN CN202010788400.9A patent/CN112100483B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160358211A1 (en) * | 2015-06-04 | 2016-12-08 | Sap Se | Personalized recommendation system for coupon deals |
| WO2018010591A1 (en) * | 2016-07-12 | 2018-01-18 | 腾讯科技（深圳）有限公司 | Information push method and apparatus, server, and storage medium |
| CN109299313A (en) * | 2018-08-03 | 2019-02-01 | 昆明理工大学 | A kind of song recommendations method based on FP-growth |
| CN109871479A (en) * | 2019-01-08 | 2019-06-11 | 西北大学 | A kind of collaborative filtering method based on user items class and the reliability that scores |
| CN109977309A (en) * | 2019-03-21 | 2019-07-05 | 杭州电子科技大学 | Combination point of interest querying method based on multiple key and user preference |
| CN110825977A (en) * | 2019-10-10 | 2020-02-21 | 平安科技（深圳）有限公司 | Data recommendation method and related equipment |
| CN110851718A (en) * | 2019-11-11 | 2020-02-28 | 重庆邮电大学 | Movie recommendation method based on long-time memory network and user comments |
| CN111428127A (en) * | 2020-01-21 | 2020-07-17 | 江西财经大学 | Personalized event recommendation method and system integrating topic matching and two-way preference |
Non-Patent Citations (3)
| Title |
|---|
| HUAXIN ZHANG 等: "Integrating Spectral-CF and FP-Growth for Recommendation", 《EBIMCS \'19: PROCEEDINGS OF THE 2019 2ND INTERNATIONAL CONFERENCE ON E-BUSINESS, INFORMATION MANAGEMENT AND COMPUTER SCIENCE》, pages 1 - 7 * |
| 李昌兵 等: "基于兴趣度的Web访问用户关联规则挖掘", 《计算机工程与设计》, pages 852 - 856 * |
| 申晋祥 等: "基于项目关联的Slope One协同过滤算法研究", 《计算机与数字工程 》, pages 1856 - 1860 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116611769A (en) * | 2023-07-19 | 2023-08-18 | 杭州吉客云网络技术有限公司 | Order aggregation method, order aggregation device, computer equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112100483B (en) | 2023-09-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP4429236B2 (en) | Classification rule creation support method | |
| US7610284B2 (en) | Compressed prefix trees and estDec+ method for finding frequent itemsets over data streams | |
| CN108132927B (en) | Keyword extraction method for combining graph structure and node association | |
| CN104199822B (en) | It is a kind of to identify the method and system for searching for corresponding demand classification | |
| US20020078044A1 (en) | System for automatically classifying documents by category learning using a genetic algorithm and a term cluster and method thereof | |
| CN106570128A (en) | Mining algorithm based on association rule analysis | |
| CN112749281B (en) | Restful type Web service clustering method fusing service cooperation relationship | |
| CN101551806A (en) | Personalized website navigation method and system | |
| CN105487663A (en) | Intelligent robot oriented intention identification method and system | |
| CN108898479A (en) | The construction method and device of Credit Evaluation Model | |
| Chang et al. | A novel incremental data mining algorithm based on fp-growth for big data | |
| US20160170993A1 (en) | System and method for ranking news feeds | |
| CN110516704A (en) | A kind of MLKNN multi-tag classification method based on correlation rule | |
| CN112100483B (en) | Association rule recommendation method fusing user interest weights | |
| KR101516329B1 (en) | System and method for recommending group in social network environments | |
| CN110019646B (en) | Method and device for establishing index | |
| Kyung-Yong et al. | Prediction of user preference in recommendation system using associative user clustering and Bayesian estimated value | |
| CN113076481B (en) | Document recommendation system and method based on maturity technology | |
| CN108615182A (en) | A kind of method and system that product intelligent is recommended | |
| Sinthuja et al. | Comparative Analysis of Association Rule Mining Algorithms in Mining Frequent Patterns. | |
| CN114327607A (en) | Automatic generation method of BS code | |
| CN111310066B (en) | Friend recommendation method and system based on topic model and association rule algorithm | |
| Vijayarani et al. | Frequent Items Mining on Data Streams using Matrix and Scan Reduced Indexing Algorithms | |
| CN106168982A (en) | Data retrieval method for particular topic | |
| CN106294652A (en) | Web page information search method |
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 |