CN114691744A - Method for mining micro map user association rule under constraint of propagation force - Google Patents
Method for mining micro map user association rule under constraint of propagation force Download PDFInfo
- Publication number
- CN114691744A CN114691744A CN202011586403.0A CN202011586403A CN114691744A CN 114691744 A CN114691744 A CN 114691744A CN 202011586403 A CN202011586403 A CN 202011586403A CN 114691744 A CN114691744 A CN 114691744A
- Authority
- CN
- China
- Prior art keywords
- propagation
- index
- mining
- propagation force
- micro
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—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
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/29—Geographical information databases
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Remote Sensing (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Probability & Statistics with Applications (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a method for mining a user association rule of a micro map under the constraint of a propagation force, which comprises the following steps: firstly, analyzing influence factors of the propagation force of the micro map, constructing a micro map propagation force evaluation system, and quantifying the propagation force index of the micro map by using a weighted average method; then, a behavior association rule method under the constraint of the propagation force is provided by combining a classical association rule FP-growth algorithm. A simple data structure of a propagation power index pattern tree is constructed by adopting a method of constructing a frequent pattern tree (FP-tree) in an FP-growth algorithm, and association rules can be directly mined while association information in data is reserved; and finally, combining the propagation index with the support degree-confidence degree, setting a proper threshold value, and mining the user behavior association combination with strong propagation. The method aims at the propagation characteristics of the micro map in the self-media era, takes the propagation force index as the measurement standard of the association rule mining, screens out the association rule which can better express the habits of mass media, and has better mining effect on the user behavior habits combined by strong propagation force.
Description
Technical Field
The invention relates to the technical field of data analysis and data association rule mining, in particular to a method for mining a user association rule of a micro map under the constraint of a transmission force.
Background
The progress of map civilization is promoted from the media age, and maps can be gradually drawn by experts from the past to be drawn by the general public. The wide spread of information and the demand of people for map civilization make the 'micro map' suitable for delivery, and the micro map has real-time participation of mass users in the manufacturing process, only needs to meet the user demand in the content, and is distributed and spread in real time by means of self media. Meanwhile, a real-time communication platform for drawing by oneself or several people in cooperation is provided for the user on the mobile terminal of the mobile phone, so that the map becomes a communication tool. The point-to-point transmission mode in the self-media enables the micro map to have a wide crowd basis, but also enables the micro map user behavior data to be increased, and the user behavior rules stored in the micro map are mined out from the massive user behavior data, so that the social network structure and the map information transmission rule are disclosed, and the method has great practical significance.
At present, user behavior association rule mining usually mines user behavior rules by counting occurrence frequency of things by people, and finds potential association characteristics in cross behaviors. In the association rule method research, the earliest proposed association rule is Apriori algorithm based on classical association rule of frequent item set, which adopts a layer-by-layer recursion method to obtain the frequent item set, and generates an association rule in the form of a → B through the frequent item set. Many scholars optimize based on Apriori algorithm, but because the method adopts a calculation method of recursion layer by layer, a large number of candidate sets can be generated in the calculation process, and meanwhile, the setting of minimum support degree causes that rare information cannot be analyzed, and inherent defects in the methods cannot be overcome. Then, an excavating method FP-growth for finding Frequent item sets without generating candidate sets appears, which directly extracts Frequent item sets from a structure Tree by constructing a Frequent Pattern Tree (FP-Tree). The whole process only needs to scan the data twice, and the data structure is compressed, so that the efficiency of the FP-growth algorithm is greatly improved compared with that of the Apriori algorithm.
In addition to optimizing the performance of the method, there are also many studies on the mining quality of association rules. For example: on the basis of FP-growth, a brand-new term constraint association rule discovery algorithm FPC is provided, and a high-frequency term set meeting constraint conditions is finally obtained by constructing a high-frequency mode tree FP-tree and a constraint tree C-tree. A constrained concept lattice building algorithm DFTFH for depth-first traversal of FP-tree generates candidate concept lattice nodes by traversing FP-tree, constructs constrained concept lattices according to constraint conditions, effectively reduces redundant information and filters uninteresting rules. These are all aimed at improving mining quality, designing relevant constraint conditions and mining interesting association rules.
Therefore, how to provide a map user association rule mining method suitable for the age of media, and ensure the performance advantages of the method and the mining effect of the method is a problem that needs to be solved by those skilled in the art.
Disclosure of Invention
In view of the above, the invention designs a mining method of the micro map user behavior association rule under the constraint condition of "propagation power" by taking the improvement of the mining quality of the association rule as an entry point and considering factors such as the information recognition degree and the information propagation degree of the micro map based on the self-media propagation theory. The propagation power index and the FP-growth algorithm are combined, the performance advantages of the FP-growth algorithm in a high-density database are inherited, and meanwhile, the propagation power index is used as a constraint rule, so that the user behavior habits and association rules with the propagation performance are mined out under the condition of meeting the requirements of wide propagation and easy propagation, and data support is provided for the realization of the recommendation algorithm.
In order to achieve the purpose, the invention adopts the following technical scheme:
step 1: constructing a transmission power index;
step 2: carrying out propagation power index constraint on user information;
step 3: screening data items with strong transmission capacity;
step 4: constructing a propagation force index pattern tree;
step 5: digging a propagation power index pattern tree;
step 6: useful association rules are extracted.
Compared with the prior art, the method for mining the micro map user association rule under the constraint of the propagation force is provided. Through the analysis of the propagation characteristics of the micro map, a micro map propagation force evaluation system is constructed, and the propagation force index is used as a constraint condition for association rule mining. And a mode tree is constructed by combining a mode tree construction method in a classical mining method, and association rule mining is carried out on the micro map user. The method has the capability of mining hidden user behavior combination with strong transmission capacity; and reasonable minimum propagation index and minimum support degree are set, and on the premise of ensuring the operation efficiency of the algorithm, association rules with strong constraint and high propagation index can be obtained.
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, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
FIG. 1 is a flow chart of an association rule mining method under propagation force constraints provided by the present invention;
FIG. 2 is a system diagram for evaluating the transmission of a micro map according to the present invention;
FIG. 3 is a sample data graph of the present invention;
FIG. 4 is a diagram of a process for constructing a "propagation force index pattern tree" according to the present invention;
FIG. 5 is a process diagram for mining the "A" term in the propagation index pattern tree according to the present invention;
FIG. 6 is a diagram of data and mining results generated by the mining process 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 the attached figure 1, the embodiment of the invention discloses a method for mining the user association rule of a micro map under the constraint of a propagation force, which comprises the following steps:
step 1: a transmission power index is constructed. Counting the propagation force influence parameters (reading number, use number, collection number and praise number) of the micro map made by the user, setting different weights for different propagation force influence factors by counting the habits of the user and analyzing the propagation range, and constructing a propagation force index by adopting a weighted average method.
Step 2: and carrying out propagation force index constraint on the user information. Establishing a corresponding data structure < user information, propagation power index > between the user information and the propagation power index, scanning a database, merging the propagation power indexes of the same item, and rearranging each data item according to a descending order.
Step 3: and screening the data items with strong transmission capacity. And setting a minimum support threshold according to the actual propagation range, calculating a minimum propagation force index (Min-CCI), deleting a data item set with a small propagation force index, and finally reserving the data item set meeting the propagation force requirement because the items do not play any role in the whole mining.
Step 4: a "propagation force index pattern tree" is constructed. And (3) carrying out secondary scanning on the screened database, wherein the process is the same as the process of constructing the frequent pattern tree, and the data information is scanned to obtain a concise data structure, namely the propagation power index pattern tree, according to a certain data arrangement method.
Step 5: a "propagation force index pattern tree" is mined. And (3) finding out the condition mode base of each item by adopting a bottom-up iteration mode on the constructed mode tree, constructing the condition mode tree, and finally excavating the mode combination with strong propagation force.
Step 6: useful association rules are extracted. Calculating the confidence of each association rule, setting the minimum confidence, deleting the rules with low confidence, filtering useless rules and keeping the association rules with high confidence.
The methods involved in the present invention are further described below.
In Step 1, the invention adopts the definition of the transmission power 'efficiency theory' and uses the 'transmission effect' to construct a micro map transmission power evaluation system. Specifically, from the actual start of the micro map, a transmission force evaluation system is constructed through the information transmission degree and the information recognition degree, the transmission force is described in the aspects of transmission scale, transmission depth, personal recognition and social recognition, the transmission effect of the micro map is evaluated by adopting four influence factors of reading number, use number, collection number and praise number according to the transmission function of the micro map, and the final expression form of sharing number is returned to the four factors, so that the evaluation is not involved. The system for propagation evaluation of the micro-maps is shown in fig. 2.
According to the constructed micro map transmission Capacity evaluation system, the transmission function of the micro map is combined, and the specific influence factors are quantitatively measured and calculated by using a transmission Capacity Index (CCI). According to different influences of the indexes on the propagation of the micro map, different weights are given to the evaluation indexes, and the propagation index is quantified and calculated by adopting a weighted average algorithm. The concrete formula is as follows:
in the formula, xiIs the ith influence factor, fiIs the weight occupied by the corresponding ith influence factor. Herein, the micro map transmission power influence factor is a Reading Number (RN), a Use Number (UN), a collection number (FN), and a Like Number (LN). The corresponding weights are respectively fRN、fUN、fFN、fLNThen the single item propagation force index of the micro map can be written as:
in Step 2, a data structure of < user information, single-term propagation force index > is created using the dictionary structure. And merging the same user information, and performing superposition processing on the corresponding single propagation power indexes.
In Step 3, when setting a threshold for multi-sample data, combining news knowledge, adopting two-parameter constraint for a minimum propagation index (Min-CCI), and specifically, setting the threshold more effectively by estimating a support degree and a single-term propagation index, that is, formula 3:
Min_CCI＝N*Min_sup*Min_ICCI (3)
in Step 4, the propagation power index of each item is used as attribute data of each item, and a frequent pattern tree is constructed by using an FP-growth algorithm, so that a propagation power index pattern tree is constructed. Referring to the data in fig. 3 as sample data, first, the items are sorted after being statistically stacked, the minimum propagation index is set to 24, and the items that do not satisfy the condition are filtered. The transaction items are then ordered, and each transaction item is mapped to a branch of the pattern tree in turn, building a propagation power index pattern tree, see fig. 4.
In Step 5, a "propagation force index pattern tree" is mined. First, find the frequent item set with "A" as suffix, then "D", "C", "B", "E" in sequence. It can be found that three branches including "A" construct a conditional pattern base of { (EBCD:10), (ECD:11), (C:8) }, and a conditional pattern tree is constructed using the conditional pattern base, see FIG. 5. The data generated by the mining process is shown in fig. 6, and the mode combination with strong propagation force can be mined according to the conditional mode tree.
In Step 6, the association rule is extracted using the confidence correlation definition.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (5)
1. The method for mining the user association rule of the micro map under the constraint of the propagation force is characterized by comprising the following steps:
s1: establishing a transmission index, counting transmission influence parameters (reading number, use number, collection number and praise number) of a micro map made by a user, setting different weights for different transmission influence factors by counting user habits and analyzing a transmission range, and establishing the transmission index by adopting a weighted average method;
s2: carrying out propagation power index constraint on user information, establishing a corresponding data structure < user information, propagation power index > between the user information and the propagation power index, scanning a database, merging the propagation power indexes of the same item, and rearranging each data item according to a descending order;
s3: screening data items with strong transmission capacity, setting a minimum support threshold according to an actual transmission range, calculating a minimum transmission capacity index (Min-CCI), deleting a data item set with a small transmission capacity index, and finally reserving the data item set meeting the transmission capacity requirement as the items do not play any role in the whole mining;
s4: constructing a propagation power index pattern tree, carrying out secondary scanning on the screened database, wherein the process of constructing the frequent pattern tree is the same as that of constructing the frequent pattern tree, and obtaining a simple data structure, namely the propagation power index pattern tree, by scanning data information according to a certain data arrangement method;
s5: digging a 'propagation force index mode tree', adopting a bottom-up iteration mode for the constructed mode tree, finding out a condition mode base of each item, constructing the condition mode tree, and finally digging out a mode combination with strong propagation force;
s6: extracting useful association rules, calculating the confidence of each association rule, setting the minimum confidence, deleting the rules with low confidence, filtering useless rules and keeping the association rules with high confidence.
2. The mining method of the micro-map user association rule under the propagation force constraint according to claim 1, wherein in step S1, the propagation force index is quantified by constructing a micro-map propagation force evaluation system, combining the propagation function of the micro-map itself, and performing quantitative measurement and calculation by using specific influence factors, and the propagation force index is quantified and calculated by using a weighted average method.
3. The method for mining the user association rule of the micro map under the propagation force constraint according to the claim 1 or 2, wherein in the step S2, a data structure of < user information, propagation force index > is established by using a dictionary structure.
4. The method for mining the user association rules of the micro-maps under the propagation force constraints as claimed in claims 1, 2 and 3, wherein in step S3, when setting the threshold for the multi-sample data, the minimum propagation force index (Min-CCI) is subjected to a two-parameter constraint in combination with news knowledge, and the threshold is set more effectively by estimating the support and the single propagation force index.
5. The method for mining the micro-map user association rules under propagation force constraints as claimed in claims 1, 2, 3 and 4, wherein in steps S4 to S6, a "propagation force index pattern tree" is constructed for association rule mining and filtering with confidence.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011586403.0A CN114691744A (en) | 2020-12-29 | 2020-12-29 | Method for mining micro map user association rule under constraint of propagation force |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011586403.0A CN114691744A (en) | 2020-12-29 | 2020-12-29 | Method for mining micro map user association rule under constraint of propagation force |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114691744A true CN114691744A (en) | 2022-07-01 |
Family
ID=82129356
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011586403.0A Pending CN114691744A (en) | 2020-12-29 | 2020-12-29 | Method for mining micro map user association rule under constraint of propagation force |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114691744A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115588062A (en) * | 2022-10-18 | 2023-01-10 | 兰州交通大学 | Method for constructing direction system of micro map |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105808766A (en) * | 2016-03-21 | 2016-07-27 | 西南科技大学 | Multilevel association rule mining method based on transaction item constraint expansion |
| US20180107695A1 (en) * | 2016-10-19 | 2018-04-19 | Futurewei Technologies, Inc. | Distributed fp-growth with node table for large-scale association rule mining |
| CN111177533A (en) * | 2019-12-05 | 2020-05-19 | 哈勃智远(北京)科技有限公司 | Method and equipment for generating converged media influence analysis report |
-
2020
- 2020-12-29 CN CN202011586403.0A patent/CN114691744A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105808766A (en) * | 2016-03-21 | 2016-07-27 | 西南科技大学 | Multilevel association rule mining method based on transaction item constraint expansion |
| US20180107695A1 (en) * | 2016-10-19 | 2018-04-19 | Futurewei Technologies, Inc. | Distributed fp-growth with node table for large-scale association rule mining |
| CN111177533A (en) * | 2019-12-05 | 2020-05-19 | 哈勃智远(北京)科技有限公司 | Method and equipment for generating converged media influence analysis report |
Non-Patent Citations (1)
| Title |
|---|
| 张剑 等: "多维情景下的微地图用户分析", 《测绘科学》, vol. 45, no. 7, pages 148 - 153 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115588062A (en) * | 2022-10-18 | 2023-01-10 | 兰州交通大学 | Method for constructing direction system of micro map |
| CN115588062B (en) * | 2022-10-18 | 2023-09-22 | 兰州交通大学 | Construction method of micro map direction system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP5092165B2 (en) | Data construction method and system | |
| CN108304867A (en) | Information popularity prediction technique towards social networks and system | |
| CN109189917B (en) | City functional zone division method and system integrating landscape and social characteristics | |
| CN103927398A (en) | Microblog hype group discovering method based on maximum frequent item set mining | |
| Hill et al. | Building an effective representation for dynamic networks | |
| Gong et al. | Novel heuristic density-based method for community detection in networks | |
| CN112330047A (en) | Credit card repayment probability prediction method based on user behavior characteristics | |
| CN116127190B (en) | Digital earth resource recommendation system and method | |
| CN110598129A (en) | Cross-social network user identity recognition method based on two-stage information entropy | |
| CN108647729A (en) | A kind of user's portrait acquisition methods | |
| Tran et al. | Radflow: A recurrent, aggregated, and decomposable model for networks of time series | |
| Sudharson et al. | A Survey on ATTACK–A nti T errorism T echnique for A DHOC Using C lustering and K nowledge Extraction | |
| CN114691744A (en) | Method for mining micro map user association rule under constraint of propagation force | |
| Wang et al. | [Retracted] Overlapping Community Detection Based on Node Importance and Adjacency Information | |
| CN112380267B (en) | Community discovery method based on privacy graph | |
| CN115712511A (en) | Web service classification method based on bilinear graph neural network | |
| CN115330056A (en) | Topic network influence user prediction method based on deep propagation and breadth propagation | |
| CN112052549B (en) | Method for selecting roads in small mesh gathering area | |
| Mozhaiev et al. | Development of an Information Model for the Personality’s Social Portrait Formation Using OSINT Technology | |
| CN109614491B (en) | Further mining method based on mining result of data quality detection rule | |
| Ninoria et al. | A survey on high utility itemsets mining | |
| Fu | Dimensionality optimization by heuristic greedy learning vs. genetic algorithms in knowledge discovery and data mining | |
| CN111209513B (en) | Network user classification method based on graph link analysis | |
| CN117614845B (en) | Communication information processing method and device based on big data analysis | |
| Yu et al. | Public-private-core maintenance in public-private-graphs |
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 |