A mining method and system for privacy preserving periodic utility item sets

Abstract

The application discloses a mining method and system for privacy protection periodic high utility item set, relates to the cross field of data mining and privacy protection, mainly relates to the field of privacy protection utility mining, and comprises a selection stage and a hiding stage of a sensitive periodic high utility item set, wherein in the selection stage, the periodic high utility item set is mined and the sensitive item set is acquired; the hiding stage comprises a preprocessing stage and an official hiding stage; in the preprocessing stage, a sensitive item set list and a sensitive item list are constructed as a list structure of the sensitive periodic high utility item set and are stored in a database; in the official hiding stage, the sensitive transactions and the sensitive items in the database are selected and processed, so that the sensitive periodic high utility item set cannot be mined in the database. The application can ensure that sensitive information is not leaked when the user shares data, and can ensure that the hidden database does not affect the user's analysis on the data.

Description

TECHNICAL FIELD

[0001] The present application relates to the cross field of data mining and privacy protection, and particularly to the field of privacy protection utility mining, and more particularly to a mining method and system for privacy protection periodic high utility item set. BACKGROUND

[0002] With the rapid development of the Internet, people have generated a large amount of data in the network. Although a large amount of data is generated, most of the data is not valuable. Therefore, how to find valuable information from a large amount of data is crucial. The generation of data mining technology effectively solves this problem, which can mine meaningful knowledge from a large amount of data. High utility pattern mining, as a branch of data mining, can mine information with high value from a large amount of data. However, the results of high utility mining may have high value in the short term, and they may not have high value over time. For example: some goods take advantage of the curiosity of customers, and have high sales in the short term, but have low sales in the long term. The periodic high utility item set mining method can effectively mine the item set with high utility in the database in the long term.

[0003] Although data mining technology can find useful information from a large amount of data, some criminals can also mine some sensitive information from the database. In order to solve the problem of privacy leakage, the existing privacy protection utility mining method only considers the utility value of the item set when hiding the sensitive item set, and does not consider the period of the item set. Therefore, if the existing privacy protection utility mining algorithm is used to solve the problem of privacy protection periodic high utility item set mining, artificial cost (AC) will be generated, which will interfere with the user's decision. SUMMARY

[0004] In order to solve the problem that the existing technology does not consider the period information of the item set, and thus cannot be effectively used to solve the problem of privacy protection periodic high utility item set mining, the purpose of the present application is to provide a mining technology for privacy protection periodic high utility item set, which aims to solve the problem of privacy protection in the process of periodic high utility item set mining.

[0005] In order to achieve the above technical purpose, the present application provides a mining method for privacy protection periodic high utility item set, comprising a sensitive periodic high utility item set selection stage and a hiding stage, wherein,

[0006] In the selection stage, the periodic high utility item set is mined and the sensitive item set is obtained;

[0007] The hiding stage includes a preprocessing stage and an official hiding stage;

[0008] In the preprocessing stage, a list of sensitive item sets and a list of sensitive items are constructed as a list structure of sensitive periodic high utility item sets and stored in the database.

[0009] In the formal hiding stage, sensitive transactions and sensitive items in the database are selected and processed so that sensitive periodic high utility item sets cannot be mined in the database.

[0010] Preferably, in the selection stage, all periodic high utility item sets meeting the conditions are mined using the PHM algorithm, and sensitive item sets are selected from the periodic high utility item sets using a random algorithm.

[0011] Preferably, in the preprocessing stage, the list of sensitive item sets is a five-tuple structure, represented as: [SIS, SU, <tid:utility>SIS = {S | S is a sensitive periodic utility item set, and S has a utility value SU > LP,sup], wherein SIS represents S, S is a sensitive periodic utility item set; SU represents the utility value of S; <tid:utility>The transaction identifier of the transaction containing S and the utility value in the transaction; LP represents the maximum period of S; sup represents the support of S, and the average period of the item set is calculated by sup, which is used to determine whether an item set meets the periodicity constraint.

[0012] Preferably, in the preprocessing stage, the sensitive item list is a five-tuple, and its structure is: [tid, si, iu, cnt, mp], wherein, tid represents the transaction identifier of the transaction containing S; si represents the sensitive item in S; iu represents the utility value of the sensitive item in S; cnt represents the number of the sensitive item in S; and mp represents the maximum period of the sensitive item.

[0013] Preferably, in the formal hiding stage, when the sensitive transaction is processed, the transaction is selected to be processed preferentially, so that the utility value of the sensitive periodic high-utility item set is maximum.

[0014] Preferably, in the formal hiding stage, when the sensitive item is processed, the item with the maximum maximum period and the minimum maximum period is selected to be processed preferentially according to the maximum period of the sensitive item.

[0015] Preferably, in the formal hiding stage, the sensitive item in the sensitive transaction is deleted or the number of the sensitive item in the sensitive transaction is modified, so that the utility or the period of the sensitive item set does not meet the threshold constraint, thereby achieving the hiding effect.

[0016] Preferably, in the preprocessing stage, based on the constructed sensitive item set list and the sensitive item list, the sensitive item set is sorted in descending order according to the number of items contained in the sensitive item set, so as to form the list structure of the ordered sensitive periodic high-utility item set.

[0017] Preferably, when the sensitive item set is sorted in descending order, the minimum support threshold is calculated, and the minimum support threshold is applied to the formal hiding stage to complete the hiding of the sensitive periodic high-utility item set, wherein the minimum support threshold minSup = |D| / maxAvg-1, wherein |D| is the size of the database D, and maxAvg represents the maximum average period threshold.

[0018] The application further discloses a mining system for privacy protection periodic utility, which is used for realizing the mining method for the privacy protection periodic high-utility item set.

[0019] The mining module is used for mining the periodic high-utility item set and obtaining the sensitive item set.

[0020] The hidden module is used for storing the list structure of the sensitive periodic high utility item set in the database by constructing the sensitive item set list and the sensitive item list; and selecting and processing the sensitive transaction and the sensitive item in the database, so that the sensitive periodic high utility item set cannot be mined in the database.

[0021] The present application discloses the following technical effects:

[0022] 1. The present application can ensure that the user does not leak sensitive information when sharing data;

[0023] 2. The present application can ensure that the hidden database does not affect the user's analysis of the data;

[0024] 3. The present application provides a secure mining analysis method for periodic high utility item sets. BRIEF DESCRIPTION OF DRAWINGS

[0025] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments. Obviously, the drawings described in the following are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0026] Figure 1 is the model diagram described in the present application;

[0027] Figure 2 is the workflow diagram described in the present application;

[0028] Figure 3 is the algorithm pseudo code described in the present application. DETAILED DESCRIPTION

[0029] In order to make the purpose, technical scheme and advantages of the embodiments of the present application more clear, the technical scheme in the embodiments of the present application will be clearly and completely described below in combination with the drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, not all. The components of the embodiments of the present application described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the claimed present application, but only represents selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0030] As Figure 1 As shown, the present application provides a mining technique for privacy protection of periodic high utility item sets, which includes two parts of a selection stage and a hiding stage of sensitive periodic high utility item sets, and specifically includes the following contents:

[0031] The selection stage includes a mining stage of periodic high utility item sets and a discovery stage of sensitive periodic high utility item sets; in the mining stage of periodic high utility item sets, all periodic high utility item sets meeting the conditions are mined using an existing PHM algorithm; in the discovery stage of sensitive periodic high utility item sets, a specified number of sensitive item sets are randomly selected from the mined periodic high utility item sets using a random algorithm.

[0032] The hiding stage includes a preprocessing stage of sensitive periodic high utility item sets and an official hiding stage.

[0033] The preprocessing stage constructs a list structure of sensitive periodic high utility item sets and sorts the sensitive periodic high utility item sets, wherein a hiding algorithm is used to modify the original database to obtain a cleaned database; in the cleaned database, sensitive periodic high utility item sets cannot be mined, and at this time, the data owner can safely share the data.

[0034] The list structure of sensitive periodic high utility item sets is to construct a sensitive item set list (SISL) and a sensitive item list (SIL) for each sensitive item set, wherein the SISL structure is a five-tuple, expressed as: [SIS, SU, <tid:utility>, LP, sup]. Given a set of sensitive periodic utility items S, SISrepresents S; SUdenotes the utility value of S; <tid:utility>The transaction identifier representing the transaction in which S appears and the utility value in the transaction; LP represents the maximum period of S; sup represents the support of S, and the average period of the item set can be calculated by sup, which is used to determine whether an item set meets the periodicity constraint. The SIL structure is also a five-tuple, and its structure is: [tid, si, iu, cnt, mp]. Wherein, tid represents the transaction identifier of the transaction containing S; si represents the sensitive item in S; iu represents the utility value of the sensitive item in S; cnt represents the number of sensitive items in S; and mp represents the maximum period of the sensitive item.

[0035] Using these data structures can save the information of the sensitive item set in the database, thereby avoiding multiple scans of the database;

[0036] The sorting of the sensitive period high-utility item set is the processing order of each sensitive item set in the hiding algorithm, and the application preferentially selects the sensitive period high-utility item set containing the most items for processing, and the appropriate processing order can speed up the execution of the algorithm.

[0037] The formal hiding phase includes the selection of sensitive transactions, the selection of sensitive items and the processing of sensitive items:

[0038] The selection of sensitive transactions is the processing order of all transactions containing the sensitive item set, and different sensitive transaction selection strategies will affect the performance of the algorithm, and the application preferentially selects the transaction with the maximum utility value of the sensitive period high-utility item set for processing;

[0039] The selection of sensitive items is the processing order of the sensitive items in the sensitive item set in the selected sensitive transaction, which is used to determine which sensitive item is preferentially processed, and the application adopts different selection strategies according to the maximum period of the sensitive item: the items with the maximum maximum period and the minimum maximum period are preferentially selected for processing, respectively;

[0040] The processing of the sensitive item is to delete the sensitive item in the sensitive transaction or modify the number of the sensitive item in the sensitive transaction, so that the utility or period of the sensitive item set does not meet the threshold constraint, thereby achieving the hiding effect.

[0041] As shown in Figure 2 The mining method provided by the application specifically comprises the following steps:

[0042] Step 1: using a periodic high-utility item set mining algorithm to mine all high-utility item sets meeting the periodicity constraint;

[0043] Step 2: selecting the sensitive item set to be hidden from the mined periodic high-utility item set;

[0044] Step 3: using a privacy-preserving periodic high-utility item set mining algorithm to hide the selected sensitive item set.

[0045] Specifically, in step 1, select the set of sensitive periodic high-efficiency items that you want to hide;

[0046] Step 1.1: Use the existing PHM algorithm to mine all periodic high-utility itemsets that meet the conditions. Assume that the minimum utility threshold is α, the maximum periodicity threshold is maxPer, the maximum average periodicity threshold is maxAvg, the minimum periodicity threshold is minPer, and the minimum average periodicity threshold is minAvg. This threshold setting will be used in the following parts of this invention.

[0047] Step 1.2: Use a random algorithm to randomly select a specified number of sensitive periodic efficient itemsets (SPIs) from the periodic efficient itemset mined above;

[0048] In step 2, the preprocessing of SPIs involves recording the information of SPIs in the database, thereby avoiding multiple database scans.

[0049] Step 2.1: Efficiently use itemsets (sp) for each sensitive period k Construct its SISL and SIL structures;

[0050] Step 2.2: According to sp k The number of items contained in the SPIs, sorted in descending order;

[0051] Step 2.3: Calculate the minimum support threshold minSup = |D| / maxAvg-1 based on maxAvg, where |D| is the size of the database D.

[0052] In step 3, the SPIs are officially hidden;

[0053] Step 3.1: According to sp k SISL, obtain sp k The utility value of SISL (sp k ).SU、sp k Support for SISL (sp k The maximum period of sup and spk is SISL(sp k ).LP, thereby calculating the utility value du(sp) of the modifications needed to hide spk. k ) = SISL(sp k ).SU-α, current support ds(sp k ) = SISL(sp k ).sup, currently the maximum period dp(sp k ) = SISL(sp k ).LP.

[0054] Step 3.2: Determine du(sp) k )≥0, dp(sp) k )≤maxPer and ds(sp k Does ≥ minSup simultaneously hold true? If so, it means that sp k It's still a periodic, high-efficiency itemset; we need to go back to step 3.3 to hide the sp. k If not, then it means sp k If the item set is not periodic and efficient, hiding is successful; proceed to step 3.9.

[0055] Step 3.3: Select the option that makes sp k The transaction with the highest utility value is designated as the victim transaction T. vic T vic =max{u(sp k ,T d ),T d ∈SISL.[tid:utility]};

[0056] Step 3.4: If victim transaction T is selected vic In the middle makes sp k The project with the longest cycle as the victim project I vic I vic =max{mp(i k ,T vic ), 1≤k≤|sp k |,i k ∈SIL(sp k ,T vic If the strategy adopted is to select the victim transaction T vic In the middle makes sp k The project with the shortest maximum cycle is the victim project I. vic I vic =min{mp(i k ,T vic ), 1≤k≤|sp k |,i k ∈SIL(sp k ,T vic )};

[0057] Step 3.5: According to sp k SIL, determine I vic Is the utility value greater than du(sp)? k If yes, proceed to step 3.6; otherwise, proceed to step 3.7.

[0058] Step 3.6: Modify Victim Project I vic The quantity, calculate the I that needs to be subtracted. vic the number dq of sp k is divided by I vic 's external utility value eu(I vic ) is rounded up. SIL(I vic , T vic ).cnt- = dq, SIL(I vic , T vic ).iu- = dq x eu(I vic ), where sp k has not satisfied the minimum utility threshold, so sp k is deleted from SPIs. Then, jump to step 3.8.

[0059] Step 3.7: delete I vic from T vic , recalculate the utility value SISL(sp k ).su- = u(I k , T vic ), the support SISL(sp vic ).sup- and the maximum period SISL(sp k ).LP of sp k in SISL. Then, jump to step 3.8.

[0060] Step 3.8: update SPIs, SISL and SIL, and jump to step 3.2.

[0061] Step 3.9: update the database.

[0062] As shown in Figure 3 , the mining method provided by the present application has the algorithm pseudo code as follows:

[0063] The algorithm can clean the original database and successfully and effectively hide the sensitive period high utility item set. The algorithm can be divided into two parts: a sensitive period high utility item set preprocessing stage and a hiding stage. In the preprocessing stage, SISL and SIL structures are used to accelerate the execution time of the algorithm and improve its efficiency.

[0064] The first stage is the preprocessing of SPIs (Lines 1-5). First, construct the SISL and SIL structures of each sensitive item set in SPIs (Line 2). Then, sort the sensitive item sets in descending order according to the number of items contained in the sensitive item sets (Line 4). In the algorithm, longer sensitive item sets are processed first. According to maxAvg, calculate the minimum support threshold minSup (Line 5).

[0065] The second phase is the hiding operation of SPIs (Lines 6-28). The algorithm processes each element sp k in SPIs iteratively until all the sensitive itemsets are hidden. For each sensitive itemset sp k , its SISL and SIL structures are obtained (Line 7). According to the SISL of this itemset, its threshold information, du(sp k ), ds(sp k ), dp(sp k ) are calculated (Lines 8-10). du(sp k ) represents the difference between the utility of sp k and α. ds(sp k ) represents the support of sp k . dp(sp k ) represents the maximum period of sp k . According to the SISL of sp k , the transaction that makes the utility value of sp k maximum is selected as the victim transaction to be modified first (Line 12). Then, according to the SIL of sp k , the item in sp k with the maximum maxPer or the minimum maxPer is selected as the victim item (Line 13). According to the utility of the victim item in the victim transaction, the decision is made whether to delete the item or modify the number of the item (Lines 14-27). If the utility of the victim item in the victim transaction is not greater than du(sp k ), the victim item is deleted from the victim transaction, and SPIs, SISL and SIL are updated (Lines 14-19). Otherwise, the number of the victim item in the victim transaction is reduced (Line 22). Then, sp k can be removed from SPIs because it has been hidden (Line 24). Next, SPIs, SISL and SIL are updated (Line 25). When all the SPIs are hidden, the algorithm terminates.

[0066] In summary, the present application proposes two novel data structures: Sensitive Itemset List (SISL) and Sensitive Item List (SIL); and the present application adopts a sensitive item selection strategy that selects the victim item according to the period of the sensitive item. Compared with the existing technology, the present application can ensure that the user does not leak sensitive information when sharing data; and the present application can ensure that the hidden database does not affect the user's analysis of the data.

[0067] The computer program instructions can also be loaded onto a computer, other programmable data processing apparatus, or other processing device to cause a series of operational steps to be performed on the computer, other programmable apparatus or other processing device to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide processes for implementing the functions specified in the flowchart block or blocks. Figure 1 one or more of the blocks Figure 1 one or more of the blocks

[0068] In the description of the present application, it is to be understood that the terms "first", "second", "third" and the like, merely identify features belonging to distinct categories, and do not imply or suggest a relative importance or an implied

[0069] Obviously, numerous modifications and variations of the present application are possible in light of the above teachings. It is therefore to be understood that within the scope of the apparatuses and systems of the present application may vary.< / tid:utility> < / tid:utility> < / tid:utility> < / tid:utility>

Claims

1. A mining method for privacy preserving periodic utility itemsets, characterized in that, The method comprises: a selection stage and a hiding stage of sensitive periodic high utility item sets, wherein, in the selection stage, periodic high utility item sets are mined and sensitive item sets are obtained; in the selection stage, the PHM algorithm mines all periodic high utility item sets meeting the conditions and selects sensitive item sets from the periodic high utility item sets using a random algorithm; the hiding stage comprises a preprocessing stage and an official hiding stage; in the preprocessing stage, a sensitive item set list and a sensitive item list are constructed as a list structure of sensitive periodic high utility item sets and are stored in a database; in the preprocessing stage, the sensitive item set list is a five-tuple structure and is expressed as: [SIS, SU, <tid:utility>, LP, sup], wherein SIS represents S, S is a sensitive periodic high utility item set; SU represents the utility value of S; <tid:utility> represents the transaction identifier of a transaction containing S and the utility value in the transaction; LP represents the maximum period of S; and sup represents the support of S, which is used to calculate the average period of an item set and is used to judge whether an item set meets the periodic constraint; in the preprocessing stage, the sensitive item list is a five-tuple structure and is expressed as: [tid, si, iu, cnt, mp], wherein tid represents the transaction identifier of a transaction containing S; si represents a sensitive item in S; iu represents the utility value of the sensitive item in S; cnt represents the number of the sensitive item in S; and mp represents the maximum period of the sensitive item; in the preprocessing stage, based on the constructed sensitive item set list and sensitive item list, the sensitive item sets are sorted in descending order according to the number of items contained in the sensitive item sets to form an ordered list structure of sensitive periodic high utility item sets; in the descending order sorting of the sensitive item sets, a minimum support threshold is calculated, and the minimum support threshold is applied to the official hiding stage to complete the hiding of the sensitive periodic high utility item sets, wherein the minimum support threshold minSup = |D| / maxAvg-1, wherein |D| is the size of the database D, and maxAvg represents the maximum average period threshold; in the official hiding stage, the sensitive transactions and sensitive items in the database are selected and processed so that the sensitive periodic high utility item sets cannot be mined in the database.

2. The method according to claim 1, wherein: in the official hiding stage, when the sensitive transactions are processed, the transactions that make the utility value of the sensitive periodic high utility item sets maximum are selected for priority processing.

3. The method according to claim 2, wherein: in the official hiding stage, when the sensitive items are processed, the items with the maximum maximum period and the minimum maximum period are selected for priority processing according to the maximum period of the sensitive items.

4. The method according to claim 3, wherein: In the formal hiding phase, the sensitive items in the sensitive transactions are deleted or the number of the sensitive items in the sensitive transactions is modified, so that the utility or the period of the sensitive item set does not satisfy the threshold constraint, and the hiding effect is achieved.

5. A system for privacy preserving periodic utility item set mining for implementing the method of privacy preserving periodic utility item set mining as claimed in claim 1, characterized by, The method comprises the following steps: a mining module is used to mine the periodic high-utility item set and obtain the sensitive item set; a hiding module is used to construct the sensitive item set list and the sensitive item list as the list structure of the sensitive periodic high-utility item set, and store them in the database; meanwhile, the sensitive transactions and the sensitive items in the database are selected and processed, so that the sensitive periodic high-utility item set cannot be mined in the database.

Images