Data processing method and device

Abstract

The invention discloses a data processing method and device. Determining a transaction item set comprising at least one first transaction item by scanning a target database; scanning the target database again to determine a to-be-used triple and a first utility list corresponding to every two first transaction items; according to the first utility list corresponding to each triad to be used, dividing the first quantization item set corresponding to the at least one triad to be used to obtain at least one quantization item set; and adjusting the at least one quantization item set based on the at least one triad to be used, a first utility list corresponding to the triad to be used and the transaction item set to obtain a target quantization item set, and determining item selection reference information based on the target quantization item set. According to the invention, the accuracy of the determined target quantization item set is improved, so that the item selection reference information corresponding to the target quantization item set can meet the actual demand of a user.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a data processing method and apparatus. Background Technology

[0002] To meet the diverse project selection needs of users, users who already own trading projects typically recommend projects to those with specific needs. Therefore, identifying the optimal users who own trading projects and the optimal trading projects themselves is crucial for users with specific needs.

[0003] Currently, users primarily select trading projects based on recommendations from those who already hold them. However, different users have varying experiences, and the utility of different projects differs significantly. Existing technology, which relies solely on subjective user selection to determine suitable projects and holders, cannot guarantee that the selected projects will meet the actual needs of the users. Summary of the Invention

[0004] This invention provides a data processing method and apparatus that improves the accuracy of the determined target quantified itemset set, so that the item selection reference information corresponding to the target quantified itemset set can meet the actual needs of users.

[0005] According to one aspect of the present invention, a data processing method is provided, the method comprising:

[0006] Scan the target database to determine a set of transaction items that includes at least one first transaction item, wherein the first transaction item is an original transaction item in the target database that meets a first preset condition;

[0007] Scan the target database again to determine the triplet to be used corresponding to each pair of first transaction items and the first utility list corresponding to the triplet to be used; wherein, the first utility list includes at least one utility information associated with the triplet to be used, the utility information is used to characterize the return attribute information of the first quantitative itemset corresponding to the triplet to be used, and the first quantitative itemset is the set of items corresponding to the two first transaction items in the triplet to be used.

[0008] Based on the first utility list corresponding to each triplet to be used, the first quantized itemset corresponding to at least one triplet to be used is partitioned to obtain at least one quantized itemset set.

[0009] At least one quantitative itemset set is adjusted based on at least one triplet to be used, a first utility list corresponding to the triplet to be used, and a set of transaction items to obtain a target quantitative itemset set, and the item selection reference information is determined based on the target quantitative itemset set.

[0010] According to another aspect of the present invention, a data processing apparatus is provided, the apparatus comprising:

[0011] The project set determination module is used to scan the target database and determine a set of transaction projects that includes at least one first transaction project, wherein the first transaction project is an original transaction project in the target database that meets a first preset condition;

[0012] The utility list determination module is used to scan the target database again to determine the triplet to be used corresponding to each pair of first transaction items and the first utility list corresponding to the triplet to be used; wherein, the first utility list includes at least one utility information associated with the triplet to be used, the utility information is used to characterize the return attribute information of the first quantitative itemset corresponding to the triplet to be used, and the first quantitative itemset is the set of items corresponding to the two first transaction items in the triplet to be used;

[0013] The itemset set determination module is used to partition the first quantized itemset corresponding to at least one triplet to be used based on the first utility list corresponding to each triplet to be used, so as to obtain at least one quantized itemset set.

[0014] The reference information determination module is used to adjust at least one quantitative itemset set based on at least one triplet to be used, a first utility list corresponding to the triplet to be used, and a set of transaction items to obtain a target quantitative itemset set, so as to determine the item selection reference information based on the target quantitative itemset set.

[0015] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0016] At least one processor; and

[0017] A memory that is communicatively connected to at least one processor; wherein,

[0018] The memory stores a computer program that can be executed by at least one processor, such that the at least one processor is able to perform the data processing method of any embodiment of the present invention.

[0019] According to another aspect of the present invention, a computer-readable storage medium is provided that stores computer instructions for causing a processor to execute and implement the data processing method of any embodiment of the present invention.

[0020] According to another aspect of the present invention, a computer program product is provided, comprising a computer program, characterized in that the computer program, when executed by a processor, implements a data processing method as described in any embodiment of the present invention.

[0021] The technical solution of this invention involves scanning a target database to determine a set of transaction items including at least one first transaction item. The target database is then scanned again to determine the triplet to be used corresponding to every two first transaction items and the first utility list corresponding to each triplet. Based on the first utility list, the combination of quantitative itemsets to which the first quantitative itemset corresponding to the triplet to be used belongs is determined. This achieves the partitioning of at least one first quantitative itemset, providing data support for the subsequent determination of the target quantitative itemset set. Based on at least one triplet to be used, the first utility list corresponding to the triplet to be used, and the transaction item set, the at least one quantitative itemset set is adjusted. Based on the adjusted at least one quantitative itemset set, the target quantitative itemset set is determined, and item selection reference information is determined based on the first transaction items in the target quantitative itemset set. This invention solves the problem in the prior art that it is difficult to guarantee that the selected items meet the actual needs of the user. By using a first utility list and the triplet to be used, a set of highly effective quantitative itemsets, namely the target quantitative itemsets, is determined. The target quantitative itemsets are then used to determine the reference information for item selection, which improves the accuracy of the determined target quantitative itemsets and ensures that the reference information for item selection corresponding to the target quantitative itemsets can meet the user's actual needs.

[0022] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0023] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0024] Figure 1 This is a flowchart of a data processing method provided in an embodiment of the present invention;

[0025] Figure 2 This is an example diagram of a quantitative transaction data table provided in an embodiment of the present invention;

[0026] Figure 3 This is an example diagram of the external utility table provided in an embodiment of the present invention;

[0027] Figure 4 This is a flowchart of a data processing method provided in an embodiment of the present invention;

[0028] Figure 5This is a flowchart illustrating the recursive pruning and quantized itemset expansion processes provided in this embodiment of the invention.

[0029] Figure 6 This is a schematic diagram of the structure of a data processing device provided in an embodiment of the present invention;

[0030] Figure 7 This is a schematic diagram of the structure of an electronic device that implements the data processing method of the present invention. Detailed Implementation

[0031] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0032] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0033] Example 1

[0034] Figure 1 This is a flowchart of a data processing method provided in Embodiment 1 of the present invention. This embodiment is applicable to situations where a set of highly efficient target quantification itemsets is determined to provide accurate and reliable reference information for item selection to users. This method can be executed by a data processing device, which can be implemented in hardware and / or software and can be configured in electronic devices such as mobile phones, computers, or servers. Figure 1 As shown, the method includes:

[0035] S110. Scan the target database to determine a set of transaction items that includes at least one first transaction item, wherein the first transaction item is an original transaction item in the target database that meets the first preset condition.

[0036] The target database can be a database containing transaction information associated with a pre-defined trading system. The pre-defined trading system can be a predetermined trading system that requires analysis to determine the target quantitative itemset. The target database can contain multiple trading transactions, each containing at least one original trading item. Each trading transaction corresponds to transaction information, including transaction details related to the transaction. Optionally, the transaction information may include: a transaction identifier, a transaction name, a transaction initiation time, and at least one original trading item included in the transaction. Each original trading item corresponds to item information, which may include: the item identifier, percentage information, number of items, and transaction return attributes of the original trading item within its respective trading transaction. The transaction return attributes can be used to characterize the return obtained from investing in the original trading item.

[0037] The first transaction item can be any original transaction item in the target database that meets the first preset condition. The first preset condition can be a condition that needs to be met based on the proportion information or number of items in the project information and the transaction return attribute. The transaction item set contains all first transaction items in the target database that meet the first preset condition.

[0038] Specifically, a target database containing transaction information associated with a preset transaction system is obtained. The target database is scanned to determine whether each original transaction item under each transaction in the target database meets a first preset condition. If an original transaction item meets the first preset condition, it is determined as a first transaction item. All first transaction items in the target database are then identified as a transaction item set.

[0039] In this embodiment of the invention, the method for determining a set of transaction items including at least one first transaction item may be as follows: obtaining a target database associated with a transaction; scanning the target database to determine multiple transaction transactions in the target database and transaction information corresponding to each transaction transaction, wherein the transaction information includes: a transaction identifier, at least one original transaction item under each transaction transaction, and project information corresponding to each original transaction item, the project information including: a project identifier, external utility, and internal utility, the internal utility representing the proportion or number of original transaction items in the transaction to which the original transaction item belongs, and the external utility representing the transaction return attribute corresponding to the original transaction item; obtaining a first weighted utility corresponding to each original transaction item based on the external utility, internal utility, and weighted utility determination function of each original transaction item; determining the original transaction item as a first transaction item if the first weighted utility of the original transaction item exceeds a first preset utility threshold; and determining a set of transaction items based on at least one first transaction item.

[0040] Transaction information is used to characterize the attributes of a transaction. Transaction information includes: a transaction identifier, at least one original transaction item under each transaction, and item information corresponding to each original transaction item. The transaction identifier can be a string used to uniquely identify the transaction. Typically, the transaction identifier can be numbers or letters. For each transaction, it can have one or more original transaction items. Each original transaction item corresponds to item information. Item information includes an item identifier, external utility, and internal utility. The item identifier is a string used to uniquely identify the original transaction item. Optionally, the item identifier can be represented by letters or numbers. Internal utility characterizes the proportion or number of items in the original transaction, while external utility characterizes the transaction return attribute corresponding to the original transaction item. The transaction return attribute can be understood as the return obtained from investing in or choosing the original transaction item. It should be noted that since external utility represents the transaction return attribute corresponding to the original transaction item, external utility can be positive or negative.

[0041] The weighted utility function can be a function used to determine the weighted utility of an original transaction item or quantified itemset. Here, the weighted utility is used to determine the first weighted utility corresponding to the original transaction item. The first weighted utility can be understood as the Reality Transaction-weighted utility (RTWU) corresponding to the original transaction item. The first preset utility threshold can be a pre-set standard value corresponding to the first weighted utility. Optionally, if the first weighted utility corresponding to the original transaction item exceeds the first preset utility threshold, it is determined that the original transaction item meets the first preset condition, and the original transaction item is designated as the first transaction item; if the first weighted utility corresponding to the original transaction item does not exceed the first preset utility threshold, it is determined that the original transaction item does not meet the first preset condition, and the original transaction item is not designated as the first transaction item. The transaction item set can be a set containing at least one first transaction item in the target database.

[0042] Specifically, the target database associated with the transaction is acquired and scanned to obtain multiple transaction transactions and their corresponding transaction information. Based on the external and internal utilities of each original transaction item within each transaction transaction, a weighted utility determination function is used to first determine the actual transaction utility of all original transaction items within the transaction transaction to which each original transaction item belongs. Then, based on the sum of the actual transaction utilities of at least one transaction containing the same original transaction item, a first weighted utility corresponding to that original transaction item is obtained. When the first weighted utility exceeds a first preset utility threshold, the original transaction item is determined as the first transaction item. This process of determining whether an original transaction item is the first transaction item is repeated until all original transaction items in the target database have been determined. Based on the determined at least one first transaction item, a transaction item set is obtained.

[0043] Optionally, the first weighted utility can be determined by the following weighted utility determination function.

[0044]

[0045] Where RTWU(X) represents the first weighted utility corresponding to the original transaction item X, and RTU(T) r ) represents a transaction T that contains the original transaction item X. r The actual transaction utility used to characterize transaction T r The sum of positive externalities in all transactions. OOC(X) represents the set of all transactions that contain the original transaction X.

[0046]

[0047] Where u(x,T) r ) represents a transaction T that contains the original transaction item X. r Each original transaction item x = (i c ,q) in transaction T r The utility of [the transaction]. For example, transaction T r The original transaction item x = (i c ,q) in transaction T r The utility in T is internal utility * external utility, denoted as u(x,T) r That is, u(x,T) r )=p(i c )×q(i c ,T r ), where q(i c ,T r ) represents the original transaction item i c In transaction T rThe percentage information or number of items (internal utility) in q(i) c ,T r ) represents the original transaction item i c The transaction return attribute (external utility). p(x) > 0 indicates that the original transaction item x = (i c The external utility of q is positive.

[0048] Using the aforementioned weighted utility determination function, the first weighted utility corresponding to each original transaction item can be determined. When the first weighted utility is higher than a first preset utility threshold, the original transaction item is designated as the first transaction item, thus obtaining the transaction item set P*. Optionally, the first transaction items can be sorted in descending order according to their first weighted utility, and the sorted first transaction items can be stored in the transaction item set P*.

[0049] Optionally, after scanning the database, to facilitate the determination of the transaction item set, the transaction transactions and corresponding transaction information obtained from scanning the target database can be divided into an external utility table and an internal utility table according to the external and internal utilities of the original transaction items in the transaction transactions. The internal utility table, also known as the quantitative transaction data table, has each row representing a transaction. The data before the comma represents the item identifier of the original transaction item in the transaction, and the data after the comma represents the proportion or number of original transaction items corresponding to that item identifier in the transaction. For example, taking internal utility as the proportion information, the quantitative transaction data table can be found in [reference needed]. Figure 2 , Figure 2 There are ten rows of data, that is, ten transaction transactions. Taking the first row as an example, "1, 10" means that the number of original transaction items with item identifier 1 in the first transaction is 10% of the total number of all transaction items in the first transaction.

[0050] In the external utility table, the item identifier and external utility of each original transaction item are separated by a comma. That is, the data before the comma represents the item identifier corresponding to the original transaction item within the transaction, and the data after the comma represents the external utility of the original transaction item corresponding to that item identifier within its respective transaction. For example, ... Figure 3 As shown, in Figure 3 The text represents information about the external utilities corresponding to the 10 original transaction items under a transaction.

[0051] Optionally, a mapping table can be established between the project name and project identifier of the original transaction project in the transaction information obtained from scanning the target database.

[0052] It should be noted that after constructing the external utility table and the internal utility table, when calculating the first weighted utility, the external utility corresponding to each original transaction item can be retrieved from the external utility table, and the internal utility corresponding to each original transaction item can be retrieved from the internal utility table, so as to calculate the first weighted utility based on the retrieved internal and external utilities of each original transaction item.

[0053] Optionally, if the first weighted utility RTWU(X) corresponding to the original transaction item is less than the second preset utility threshold θ q Wherein, the second preset utility threshold θ q It is the ratio data determined based on the first preset utility threshold θ and the preset parameter qrc, that is, θ q If the first weighted utility is less than θ / qrc, then both the original transaction and its superset are inefficient. Therefore, original transaction items with a first weighted utility less than the second preset utility threshold can be removed. It should be noted that the superset containing the original transaction can be a set including the original transaction and at least one other original transaction.

[0054] S120. Scan the target database again to determine the triplet to be used for every two first transaction items and the first utility list corresponding to the triplet to be used.

[0055] The first utility list includes at least one utility information associated with the triple to be used. The utility information is used to characterize the return attribute information of the first quantitative itemset corresponding to the triple to be used. The first quantitative itemset is the set of items corresponding to the two first transaction items in the triple to be used.

[0056] The triplets to be used include the item identifiers of every two first transaction items and the actual transaction-weighted utility (RTWU) of the first quantitative itemset corresponding to those two first transaction items. It should be noted that the actual transaction-weighted utility of the first quantitative itemset can be calculated using the weighted utility determination function described above, the difference being that X represents the first quantitative itemset.

[0057] Optionally, the triple to be used can be represented as (m,n,t), where m and n represent the item identifiers of the first transaction items that simultaneously exist in the target database, and t is the actual transaction-weighted utility (RTWU) of the first quantized itemset {m,n}. It should be noted that at least one triple to be used can be obtained based on the triples to be used corresponding to every two first transaction items in the target database. A TQCS structure is constructed based on at least one triple to be used. That is, the TQCS structure contains all triples to be used, and only contains all first quantized itemsets 2-QI that simultaneously exist in the target database. sReal-Transaction Weighted Utility (RTWU).

[0058] The first utility list includes at least one utility information corresponding to the triplet to be used. One first utility list can be determined for each triplet to be used. The utility information is used to characterize the reward attribute information of the first quantified itemset corresponding to the triplet to be used. For example, the utility information may include: actual utility, residual utility, actual total utility, and residual total utility, etc.

[0059] Specifically, the target database is scanned again to determine the first quantitative itemset corresponding to every two first transaction items, as well as the actual transaction-weighted utility of the first quantitative itemset. Based on the item identifiers of every two first transaction items and the actual transaction-weighted utility of the first quantitative itemset of every two first transaction items, the triples to be used are determined. Based on the external and internal utilities of each first transaction item in the target database, at least one utility information corresponding to the first quantitative itemset formed by every two first transaction items is determined. Based on the at least one utility information corresponding to the first quantitative itemset, the first utility list of the corresponding triples to be used is determined.

[0060] In this embodiment of the invention, the method for determining the first utility list may be as follows: scan the target database again to determine the first quantitative itemset corresponding to every two first transaction items and the second weighted utility corresponding to the first quantitative itemset; based on the first quantitative itemset and the second weighted utility, determine the triplet to be used corresponding to every two first transaction items; determine the transaction identifier of each transaction to which the first quantitative itemset belongs, and determine the actual utility and residual utility corresponding to the first quantitative itemset in each transaction to which it belongs based on the actual utility determination function and the residual utility determination function, respectively; determine the actual total utility based on at least one actual utility, and determine the residual total utility based on at least one residual utility; and determine the first utility list based on the transaction identifier, actual utility, residual utility, actual total utility, residual total utility, and the second weighted utility.

[0061] The second weighted utility can be understood as the actual transaction weighted utility of the first quantified itemset. The actual utility determination function can be used to determine the actual utility of the first quantified itemset in each associated transaction. Actual utility can be understood as the sum of the product of the internal and external utilities of the first first transaction item in the first quantified itemset within its associated transaction and the product of the internal and external utilities of the second first transaction item within the same associated transaction. For example, in a certain transaction, if the external utility of the first transaction item m is 10% and its internal utility is 20%, and the external utility of the second transaction item is -20% and its internal utility is 20%, then the actual utility of the first quantified itemset in that transaction is 10% * 20% + (-20%) * 20%.

[0062] The residual utility determination function can be used to determine the residual utility in the transaction to which the first quantitative itemset belongs. Residual utility can be understood as the sum of the positive external utilities of the remaining transaction items excluding the first quantitative itemset in the transaction to which the first quantitative itemset belongs.

[0063] Optionally, the residual utility determination function can be expressed as:

[0064]

[0065] Among them, RRU(X,T) r ) represents the first quantized itemset X in transaction T. r The residual utility in T, where X represents the first quantized itemset, and T r This indicates the transaction to which the first set of quantified items belongs. x i This indicates the transaction T to which the first quantified itemset X belongs. r The remaining transaction items excluding the first quantitative item set, T r / X represents transaction T r The set of remaining transaction items excluding the first quantitative item set, p(x) i >0) indicates that the remaining transaction item x has a positive externality. i u(x) i ,T r ) represents the remaining transaction item x i In the transaction T r The utility in the remaining transaction items is x. i The product of internal utility and external utility.

[0066] Since multiple transactions may contain the first quantified itemset, meaning that the first quantified itemset has both actual utility and residual utility in each transaction, the total actual utility can be obtained by summing at least one actual utility corresponding to the first quantified itemset. The total residual utility can be obtained by summing at least one residual utility corresponding to the first quantified itemset.

[0067] Specifically, the target database is scanned again to determine the first quantized itemset corresponding to every two first transaction items and the second weighted utility corresponding to the first quantized itemset. Based on the item identifier and second weighted utility corresponding to the two first transaction items in the first quantized itemset, the triplet to be used corresponding to the first quantized itemset is determined. The transaction identifier of at least one transaction to which the first quantized itemset belongs is determined. The actual utility of the first quantized itemset in each transaction to which it belongs is determined based on the actual utility determination function. The actual total utility is determined based on at least one actual utility. The residual utility of the first quantized itemset in each transaction to which it belongs is determined based on the residual utility determination function. The residual total utility is determined based on at least one residual utility. A first utility list is determined based on the transaction identifier of at least one transaction to which the first quantized itemset belongs, at least one actual utility, at least one residual utility, actual total utility, residual total utility, and the second weighted utility corresponding to the first quantized itemset. Optionally, the residual total utility SumRRU can be understood as the sum of the residual utilities of at least one transaction to which the first quantized itemset X belongs in the target database.

[0068]

[0069] Where SumRRU represents the total residual utility, T r RRU(X,T) represents the set of transactions containing the first quantized itemset, and OCC(X) represents the set of transactions containing the first quantized itemset. r ) represents the first quantized itemset X in transaction T. r The residual utility in.

[0070] Optionally, the first utility list RUL (RUL) of the first quantized itemset X can consist of |OCC(X)| tuples, each tuple containing the first quantized itemset X in its respective transaction T. r The utility information is in the form of (Tid, EU, RRU). Here, Tid represents the transaction T to which the first quantized itemset belongs. r The transaction identifier, EU(X,T) r ) represents the transaction T to which the first quantitative itemset X belongs. r The actual utility, RRU(X,T) r ) represents the first quantized itemset X in transaction T. r The residual utility in T. It should be noted that T r ∈OCC(X), where OCC(X) represents the set of transactions containing the first quantized itemset.

[0071] In addition to the list of tuples, the first utility list also includes the actual total utility SumEU, the remaining total utility SumRRU, and the second weighted utility RTWU(X) corresponding to the first quantized itemset.

[0072] S130. Based on the first utility list corresponding to each triplet to be used, the first quantized itemset corresponding to at least one triplet to be used is partitioned to obtain at least one quantized itemset set.

[0073] The set of at least one quantified itemsets includes: a first set of quantified itemsets for utility, a set of candidate quantified itemsets for utility, and a set of second quantified itemsets for utility. The first set of quantified itemsets for utility may be a set of quantified itemsets whose utility information satisfies a first utility condition. The set of candidate quantified itemsets for utility may be a set of quantified itemsets whose utility information satisfies a second utility condition. The second set of quantified itemsets for utility may be a set of quantified itemsets whose utility information satisfies a third utility condition.

[0074] Specifically, based on the utility information of the first utility list of each triplet to be used, the first quantized itemset of each triplet to be used is partitioned to determine the set of quantized itemsets to which each first quantized itemset belongs.

[0075] In this embodiment of the invention, the method for partitioning at least one first quantized itemset may be as follows: for at least one triplet to be used, if the actual total utility in the first utility list of the triplet to be used exceeds a first preset utility threshold, then the first quantized itemset corresponding to the triplet to be used is determined to belong to the first utility quantized itemset set; if the sum of the actual total utility in the first utility list of the triplet to be used and the remaining total utility exceeds the first preset utility threshold, then the first quantized itemset corresponding to the triplet to be used is determined to belong to the candidate quantized itemset set; if the actual total utility in the first utility list of the triplet to be used exceeds a second preset utility threshold but does not exceed the first preset utility threshold, then the first quantized itemset corresponding to the triplet to be used is determined to belong to the second utility quantized itemset set.

[0076] The second preset utility threshold is a ratio determined based on the first preset utility threshold and preset parameters. The preset parameters can be pre-set values.

[0077] Specifically, for at least one triplet to be used, based on the utility information in the first utility list of each triplet to be used, if the actual total utility corresponding to the current triplet to be used exceeds a first preset utility threshold, it is determined that the utility information of the current triplet to be used satisfies the first utility condition, and the first quantized itemset corresponding to the current triplet to be used belongs to the first utility quantized itemset set. If the sum of the actual total utility and the remaining total utility of the current triplet to be used exceeds the first preset utility threshold, it is determined that the utility information of the current triplet to be used satisfies the second utility condition, and the first quantized itemset corresponding to the current triplet to be used belongs to the candidate quantized itemset set. If the actual total utility of the current triplet to be used exceeds the second preset utility threshold but does not exceed the first preset utility threshold, it is determined that the utility information of the current triplet to be used satisfies the third utility condition, and the first quantized itemset corresponding to the current triplet to be used belongs to the second utility quantized itemset set.

[0078] Optionally, in conjunction with the above, let θ represent the first preset utility threshold (0≤θ≤σ, where σ can be the total utility corresponding to all original transaction items in the target database), and let θ represent the first preset utility threshold. q θ represents the second preset utility threshold. q =θ / qrc, where RUL(X) denotes the first utility list using triples corresponding to the first quantized itemset X. The first utility quantized itemset set can be a set of high utility quantized itemsets, and the second utility quantized itemset set can be a set of weak utility quantized itemsets.

[0079] If the actual total utility RUL(X).SumEU ≥ θ in the first utility list of the triplets to be used, then the first quantized itemset X belongs to the high-utility quantized itemset, and the first quantized itemset X is stored in the first utility quantized itemset set H; if the sum of the actual total utility and the remaining total utility RUL(x).SumEU + RUL(x).SumRRU ≥ θ in the first utility list of the triplets to be used, then the first quantized itemset X belongs to the candidate quantized itemset, and the first quantized itemset X is stored in the candidate quantized itemset set E; if the actual total utility θ in the first utility list of the triplets to be used... q If ≤RUL(X).SumEU<θ, then the first quantized itemset X belongs to the weak utility quantized itemset, and the first quantized itemset X is stored in the second utility quantized itemset set C.

[0080] It should be noted that the first quantitative itemset in the candidate quantitative itemset set E can be connected with the first transaction item in the transaction item set q* to generate a superset of the first quantitative itemset. That is, the superset includes the two first transaction items of the first quantitative itemset and at least one first transaction item in the transaction item set q*, so as to obtain a high-efficiency quantitative itemset through the superset determined by the connection operation.

[0081] It should be noted that for at least one first quantized itemset in the second utility quantized itemset set C, a high utility quantized itemset can be obtained by merging first quantized itemsets with the same item identifier.

[0082] S140. Based on at least one triplet to be used, a first utility list corresponding to the triplet to be used, and a set of transaction items, adjust at least one quantitative itemset set to obtain a target quantitative itemset set, and determine item selection reference information based on the target quantitative itemset set.

[0083] The target quantitative itemset set can be a set that includes at least one target quantitative itemset. A target quantitative itemset can be the quantitative itemset with the highest actual total utility exceeding a first preset threshold. Since there may be two or more quantitative itemsets with the same actual total utility, and this actual total utility is higher than that of other quantitative itemsets, there can be at least one target quantitative itemset. The target quantitative itemset includes at least one target trading project. The project selection reference information can provide users with information on selectable trading projects and users holding selectable trading projects. Users who need to select trading projects can be those users who require such selection.

[0084] Specifically, by using at least one triplet to be used, a first utility list corresponding to the triplet to be used, and a set of transaction items, the first utility quantified itemset set, the candidate quantified itemset set, and the second utility quantified itemset set are merged and / or pruned and / or recursively expanded to obtain a target quantified itemset set, and based on the target quantified itemset set, reference information for item selection is determined.

[0085] In this embodiment of the invention, the specific method for determining the project selection reference information based on the target quantified itemset set may be as follows: based on at least one target quantified itemset in the target quantified itemset set, determine at least one target transaction to which each target quantified itemset belongs; determine the user holding at least one target transaction as the target user; and generate project selection reference information based on the target user and at least one target transaction.

[0086] The target transaction can be any transaction to which the target quantitative itemset belongs. The target user can be any user holding the target transaction.

[0087] Specifically, for at least one target quantitative itemset in the target quantitative itemset set, at least one target transaction to which each target quantitative itemset belongs is identified. Users holding at least one target transaction to which a target quantitative itemset belongs are identified as target users. Based on the target users and at least one target transaction, project selection reference information is generated so that users can select suitable transaction projects according to the project selection reference information.

[0088] For example, if there is only one target quantified itemset in the target quantified itemset set, and that target quantified itemset is {(284,8),(301,5),(299,7),(797,9),(48,6),(478,4)}, the actual total utility of this target quantified itemset is 38.1%. Taking (284,8) as an example, it represents a target transaction item with item identifier 284 and external utility of 8%. Based on the six target transaction items in the above target quantified itemset set, and comparing them with the transaction information in the target database, it is found that target transaction A and target transaction B have the configuration of the above target transaction items. Furthermore, target transaction A and target transaction B are both the same target user. Then, item selection reference information is generated based on this target user, target transaction A, and target transaction B.

[0089] The technical solution of this embodiment involves scanning a target database to determine a set of transaction items including at least one first transaction item. The target database is then scanned again to determine the triplets to be used corresponding to every two first transaction items and the first utility list corresponding to each triplet. Based on the first utility list, the combination of quantitative itemsets to which the first quantitative itemset corresponding to the triplet belongs is determined. This achieves the partitioning of at least one first quantitative itemset, providing data support for the subsequent determination of the target quantitative itemset set. Based on at least one triplet to be used, the first utility list corresponding to the triplet, and the transaction item set, the at least one quantitative itemset set is adjusted. Based on the adjusted at least one quantitative itemset set, the target quantitative itemset set is determined, and the first transaction items in the target quantitative itemset set are used to determine item selection reference information. This invention solves the problem in the prior art that it is difficult to guarantee that the selected items meet the actual needs of the user. By using a first utility list and the triplet to be used, a set of highly effective quantitative itemsets, namely the target quantitative itemsets, is determined. The target quantitative itemsets are then used to determine the reference information for item selection, which improves the accuracy of the determined target quantitative itemsets and ensures that the reference information for item selection corresponding to the target quantitative itemsets can meet the user's actual needs.

[0090] Example 2

[0091] Figure 4This is a flowchart of a data processing method provided in Embodiment 2 of the present invention. This embodiment refines the step of "adjusting at least one quantitative itemset set based on at least one triplet to be used, a first utility list corresponding to the triplet to be used, and a set of transaction items to obtain a target quantitative itemset set" based on the above embodiment. Specific implementation details can be found in the technical solution of this embodiment. Technical terms that are the same as or corresponding to those in the above embodiments will not be repeated here. Figure 4 As shown, the method includes:

[0092] S210. Scan the target database to determine a set of transaction items that includes at least one first transaction item, wherein the first transaction item is an original transaction item in the target database that meets a first preset condition.

[0093] S220. Scan the target database again to determine the triplet to be used for every two first transaction items and the first utility list corresponding to the triplet to be used.

[0094] The first utility list includes at least one utility information associated with the triple to be used. The utility information is used to characterize the return attribute information of the first quantitative itemset corresponding to the triple to be used. The first quantitative itemset is the set of items corresponding to the two first transaction items in the triple to be used.

[0095] S230. Based on the first utility list corresponding to each triplet to be used, the first quantized itemset corresponding to at least one triplet to be used is partitioned to obtain at least one quantized itemset set.

[0096] Among them, at least one set of quantified itemsets includes: a first set of utility quantified itemsets, a set of candidate quantified itemsets, and a set of second utility quantified itemsets.

[0097] S240. Perform a merging operation on at least one first quantized itemset of the second utility quantized itemset set to obtain a range quantized itemset set.

[0098] The range quantization itemset set includes at least one merged quantization itemset.

[0099] Specifically, since the first transaction items of the first quantitative itemsets that can be merged in the second quantitative itemset set have the same item identifier, the first quantitative itemsets with the same item identifier in the second quantitative itemset set can be sorted. Then, according to the sorting order, each first quantitative itemset is merged with other quantitative itemsets in turn until all first quantitative itemsets with the same item identifier in the second utility quantitative itemset set have been processed. At least one merged quantitative itemset is evaluated to determine whether the merged quantitative itemset is a high-utility quantitative itemset. If so, the range quantitative itemset set is determined based on at least one merged quantitative itemset.

[0100] Optionally, the method for determining whether the merged quantified itemset is a high-utility quantified itemset may be: determining the actual total utility corresponding to the merged quantified itemset; if the actual total utility exceeds a first preset utility threshold, then the merged quantified itemset is determined to be a high-utility quantified itemset.

[0101] In this embodiment of the invention, the method for merging at least one first quantitative itemset in the second utility quantitative itemset set may be as follows: For at least one first quantitative itemset in the second utility quantitative itemset set, based on the item identifier corresponding to the first transaction item in each first quantitative itemset set, determine at least one quantitative itemset to be merged corresponding to each first quantitative itemset set; perform itemset merging processing on each first quantitative itemset set and the corresponding at least one quantitative itemset to be merged to obtain the second quantitative itemset set; wherein, the internal utility of the first transaction item in the second quantitative itemset set is determined based on the internal utility of the same first transaction item in the first quantitative itemset set and at least one quantitative itemset to be merged, and the external utility corresponding to each first transaction item in the second quantitative itemset set is the utility range corresponding to the external utility of the same first transaction item in the first quantitative itemset set and at least one quantitative itemset to be merged; and determine a range quantitative itemset set based on at least one second quantitative itemset set.

[0102] The quantitative itemset to be merged can be any other first quantitative itemset in the second utility quantitative itemset set that shares the same item identifier as the two first transaction items in the current first quantitative itemset. The second quantitative itemset can be the merged quantitative itemset. The internal utility of the first transaction item in the second quantitative itemset is the sum of the internal utility of the same first transaction item in the first quantitative itemset and the internal utility of the same first transaction item in at least one quantitative itemset to be merged.

[0103] For example, taking the number of items as the internal utility, let's consider a first quantitative itemset A and a quantitative itemset B to be merged. If the first quantitative itemset A includes first transaction item a and first transaction item b, and first transaction item a has one item in its respective transaction with an external utility of 20%, and the quantitative itemset B to be merged includes first transaction item a and first transaction item b, and first transaction item a has one item in another transaction with an external utility of 40%, then by performing a merge on the first quantitative itemset A and the quantitative itemset B, taking first transaction item a as an example, the resulting second quantitative itemset will have an internal utility of 3 and an external utility ranging from 20% to 40%. It should be noted that the determination of the internal and external utility of first transaction item b is similar and will not be elaborated here.

[0104] Specifically, for at least one first quantitative itemset in the second utility quantitative itemset set, based on the item identifiers corresponding to the two first transaction items in each first quantitative itemset set, at least one quantitative itemset to be merged that matches the two item identifiers of each first quantitative itemset set is determined. Each first quantitative itemset is sequentially merged with the corresponding at least one quantitative itemset to be merged to obtain the merged quantitative itemset, i.e., the second quantitative itemset. If the actual total utility of the second quantitative itemset is determined to be higher than a first preset utility threshold, a range quantitative itemset set is determined based on at least one second quantitative itemset whose actual total utility is higher than the first preset utility threshold.

[0105] S250. Update the first utility list based on the first utility quantification itemset set, the candidate quantification itemset set, and the range quantification itemset set.

[0106] Specifically, since the range quantitative itemset set contains the merged quantitative itemset (second quantitative itemset), at least one utility information corresponding to the second quantitative itemset can be determined based on the external and internal utility of each first transaction item in the second quantitative itemset set. Based on the at least one utility information corresponding to the second quantitative itemset set, the first utility list is updated to obtain the updated first utility list. Based on the updated first utility list, the quantitative itemsets in the first utility quantitative itemset set, the candidate quantitative itemset set, and the range quantitative itemset set are pruned or removed.

[0107] S260. Based on the updated first utility list, at least one triplet to be used, and the transaction item set, recursively prune and expand the first utility quantized itemset set, the candidate quantized itemset set, and the range quantized itemset set to obtain the target quantized itemset set after the first transaction item in the transaction item set has been processed.

[0108] The quantitative itemset expansion process, also known as itemset expansion, involves adding a first transaction item to the quantitative itemsets in the first utility quantitative itemset set, the candidate quantitative itemset set, and the range quantitative itemset set, based on the first transaction item in the transaction item set. It's important to note that after the quantitative itemset expansion process, there are both pre-expansion and post-expansion quantitative itemsets. For example, by expanding the first quantitative itemset in the first utility quantitative itemset set (containing first transaction items a and b) using the first transaction item c from the transaction item set, we can obtain a quantitative itemset containing first transaction items a, b, and c, and a quantitative itemset containing only first transaction items a and b.

[0109] Specifically, based on the first quantized itemsets in the first utility quantized itemset set, the first quantized itemsets in the candidate quantized itemset set, and the second quantized itemsets in the range quantized itemset set, a total set of quantized itemsets containing all first quantized itemsets and all second quantized itemsets is obtained. Using the updated first utility list and at least one triplet to be used, the quantized itemsets in the total set of quantized itemsets are pruned to obtain a pruned total set of quantized itemsets.

[0110] Based on the first transaction item in the transaction item set, the quantitative itemsets in the pruned quantitative itemset set are expanded to obtain at least one expanded quantitative itemset. Each expanded quantitative itemset is then stored in a first utility quantitative itemset set, a candidate quantitative itemset set, or a second quantitative itemset set, based on its actual total utility and remaining total utility. The second quantitative itemset set containing the expanded quantitative itemsets is then processed to update the candidate quantitative itemset set. Based on the first utility quantitative itemset set, the candidate quantitative itemset set, and the updated range quantitative itemset set, the first utility list is updated, resulting in an updated total quantitative itemset set. The quantitative itemsets in the updated total quantitative itemset set are then pruned, and the above quantitative itemset expansion, range quantitative itemset set update, first utility list update, and quantitative itemset pruning processes are repeated until the first transaction item in the transaction item set is processed, resulting in the target quantitative itemset set.

[0111] In this embodiment of the invention, the recursive pruning and quantized itemset expansion processing of the first utility quantized itemset set, the candidate quantized itemset set, and the range quantized itemset set can be performed as follows: The updated first utility list is used as the second utility list; the first quantized itemsets in the first utility quantized itemset set, the first quantized itemsets in the candidate quantized itemset set, and the second quantized itemsets in the range quantized itemset set are used as the third quantized itemsets; based on the updated first utility list and the triplets to be used, the third quantized itemsets that do not meet the second preset condition are removed to obtain at least one pruned third quantized itemset; for at least one pruned third quantized itemset, each pruned third quantized itemset is expanded based on the first transaction item in the transaction item set to obtain... At least one fourth quantized itemset; based on at least one fourth quantized itemset, update the first utility quantized itemset set, the candidate quantized itemset set, and the range quantized itemset set, and update the second utility list; based on the updated second utility list and the triplet to be used, remove fourth quantized itemsets that do not meet the second preset condition to obtain at least one pruned fourth quantized itemset; based on at least one pruned third quantized itemset and at least one pruned fourth quantized itemset, repeat the processes of itemset expansion, itemset set update, utility list update, and quantized itemset pruning, so that after all the first transaction items in the transaction item set have been processed, the target quantized itemset set is obtained based on the updated first utility quantized itemset set.

[0112] Specifically, the first quantized itemset in the first utility quantized itemset set, the first quantized itemset in the candidate quantized itemset set, and the second quantized itemset in the range quantized itemset set are taken as the third quantized itemset. Based on this, at least one third quantized itemset can be obtained, namely the total set of quantized itemsets mentioned above. The second preset condition can be a pre-set condition that the third quantized itemset needs to satisfy. The pruned third quantized itemset is the third quantized itemset that satisfies the second preset condition.

[0113] It should be noted that pruning at least one third quantitative itemset results in a pruned third quantitative itemset that satisfies the second preset condition. That is, the pruned third quantitative itemset is identical to the original third quantitative itemset. In other words, pruning only removes third quantitative itemsets that do not meet the second preset condition. Specifically, the number of itemsets in the pruned third quantitative itemset is less than or equal to the number of itemsets in the original third quantitative itemset, while the number of first transaction items in the third quantitative itemset remains unchanged. For example, if there are three third quantitative itemsets, pruning these three itemsets will result in either two or one third quantitative itemset.

[0114] The fourth quantitative itemset can be a quantitative itemset obtained by expanding the pruned third quantitative itemset. For example, if the third quantitative itemset (the pruned third quantitative itemset) that satisfies the second preset condition contains first transaction items a and b, expanding the third quantitative itemset that satisfies the second preset condition will result in a fourth quantitative itemset that can include the first transaction items a and b, as well as a newly added first transaction item c, where the first transaction item c is the first transaction item in the transaction item set. The pruned fourth quantitative itemset is thus the fourth quantitative itemset that satisfies the second preset condition.

[0115] Specifically, the updated first utility list is used as the second utility list, and the first quantized itemsets in the first utility quantized itemset set, the first quantized itemsets in the candidate quantized itemset set, and the second quantized itemsets in the range quantized itemset set are used as the third quantized itemsets, thus obtaining a total set of quantized itemsets that includes at least one third quantized itemset. Based on at least one utility information from the second utility list and the triplet to be used, at least one third quantized itemset in the total set of quantized itemsets is subjected to itemset removal processing to obtain a pruned total set of quantized itemsets, and the third quantized itemsets in the pruned total set of quantized itemsets are used as the pruned third quantized itemsets.

[0116] Based on the first transaction item in the transaction item set, each pruned third quantitative itemset is expanded to obtain at least one fourth quantitative itemset. Since the quantitative itemset expansion process has been performed, the first utility quantitative itemset set, the candidate quantitative itemset set, and the range quantitative itemset set are updated based on at least one fourth quantitative itemset, as is the second utility list.

[0117] Based on the updated second utility list and the triplet to be used, the fourth quantized itemsets that do not meet the second preset condition are removed to obtain at least one pruned fourth quantized itemset. Based on at least one pruned third quantized itemset and at least one pruned fourth quantized itemset, the process of itemset expansion, itemset set update, utility list update, and quantized itemset pruning is repeated. After all the first transaction items in the transaction item set have been processed, the target quantized itemset set with the highest actual total utility is determined based on the updated first utility quantized itemset set.

[0118] For example, in conjunction with the above, see Figure 5 , Figure 5 Example flowchart for recursive pruning and quantized itemset expansion.

[0119] After partitioning the first quantized itemsets corresponding to at least one triplet to be used, a first utility quantized itemset set H, a candidate quantized itemset set E, and a second utility quantized itemset set C are obtained. At least one first quantized itemset in the second utility quantized itemset set C is merged to obtain a range quantized itemset set HR. The first utility list RUL is then updated based on the first utility quantized itemset set H, the candidate quantized itemset set E, and the range quantized itemset set HR.

[0120] The updated first utility list RUL is used as the second utility list RUL. The first quantized itemset in the first utility quantized itemset set H, the first quantized itemset E in the candidate quantized itemset set, and the second quantized itemset in the range quantized itemset set HR are used as the third quantized itemset, resulting in a total quantized itemset set Qls containing at least one third quantized itemset. The total quantized itemset set Qls is then pruned using the second utility list RUL and at least one unused triple in the TQCS structure, resulting in a pruned total quantized itemset set Qls.

[0121] Based on the first transaction item in the transaction item set P*, the pruned third quantitative itemset in the pruned quantitative itemset set Qls is expanded to obtain at least one fourth quantitative itemset. Based on the utility information corresponding to each fourth quantitative itemset, the fourth quantitative itemset is stored in the first utility quantitative itemset set H, the candidate quantitative itemset set E, and the second utility quantitative itemset set C. A merging operation is then performed on the quantitative itemsets in the second utility quantitative itemset set C to update the first utility quantitative itemset set H, the candidate quantitative itemset set E, and the range quantitative itemset set HR, as well as to update the second utility list RUL.

[0122] Based on at least one unused triplet in the updated second utility list RUL and TQCS structure, fourth quantized itemsets that do not meet the second preset condition are removed, resulting in a pruned Qls. The processes of duplicate itemset expansion, itemset set update, utility list update, and quantized itemset pruning continue until all first transaction items in the transaction item set P* have been processed. Finally, based on the updated first utility quantized itemset set, the target quantized itemset set with the highest actual total utility is determined.

[0123] Optionally, the method for removing third quantitative itemsets that do not meet the second preset condition to obtain at least one pruned third quantitative itemset can be as follows: For at least one third quantitative itemset, if the first transaction item in the triplet to be used corresponding to the third quantitative itemset is inconsistent with the preset quantitative item, or if the weighted utility corresponding to the third quantitative itemset in the updated first utility list does not exceed the second preset utility threshold, then the third quantitative itemset is determined to not meet the second preset condition; the third quantitative itemset that does not meet the second preset condition is removed to obtain at least one pruned third quantitative itemset.

[0124] Among them, the preset quantification items can be set according to actual needs, and the quantification items can be precisely quantified. The weighted utility of the third quantification itemset can be the weighted utility of the actual transactions corresponding to the third quantification itemset.

[0125] Specifically, for at least one third quantitative itemset, if the first transaction item in the triplet to be used corresponding to the third quantitative itemset is inconsistent with the preset quantitative item, or if the weighted utility corresponding to the third quantitative itemset in the updated first utility list does not exceed the second preset utility threshold, it is determined that the third quantitative itemset does not meet the second preset condition. Then, the third quantitative itemset that does not meet the second preset condition is removed to obtain at least one pruned third quantitative itemset.

[0126] Optionally, two precise quantization items x and y can be defined. If the triplet to be used in the third quantization itemset is (m,n,t), where m and n represent the item identifiers of the two first transaction items in the third quantization itemset, and t is the weighted utility (RTWU) of the third quantization itemset, then the triplet to be used (m,n,t) does not satisfy m = x, n = y, t ≥ θ. q If the third quantized itemset is not a high-efficiency quantized itemset and does not meet the second preset condition, then the third quantized itemset that does not meet the second preset condition will be removed.

[0127] S270. Based on the target quantification itemset set, determine the reference information for project selection.

[0128] The technical solution of this embodiment involves scanning a target database to determine a set of transaction items including at least one first transaction item. The target database is then scanned again to determine the triplet to be used corresponding to every two first transaction items and the first utility list corresponding to the triplet to be used. Based on the first utility list, the combination of quantitative itemsets to which the first quantitative itemset corresponding to the triplet to be used belongs is determined. This achieves the partitioning of at least one first quantitative itemset, providing data support for the subsequent determination of the target quantitative itemset set. At least one first quantitative itemset in the second utility quantitative itemset set is merged to obtain a range quantitative itemset set. Based on the first utility quantitative itemset set, the candidate quantitative itemset set, and the range quantitative itemset set, the first utility list is updated. Based on the updated first utility list, at least one triplet to be used, and the transaction item set, recursive pruning and quantitative itemset expansion are performed on the first utility quantitative itemset set, the candidate quantitative itemset set, and the range quantitative itemset set. After processing the first transaction items in the transaction item set, the target quantitative itemset set is obtained, and the item selection reference information is determined based on the first transaction items in the target quantitative itemset set. By employing efficient quantitative itemset mining techniques to consider the impact of negative externalities on transactions, the utility list is updated, further reducing the search space. Through data mining and analysis of the target database, reference information for item selection is determined, solving the problem in existing technologies that it is difficult to guarantee that the selected items meet the actual needs of users. By using the first utility list and the triples to be used, a set of highly efficient quantitative itemsets, i.e., the target quantitative itemset set, is determined. Reference information for item selection is then determined using the target quantitative itemset set, improving the accuracy of the determined target quantitative itemset set and ensuring that the reference information for item selection corresponding to the target quantitative itemset set can meet the actual needs of users.

[0129] Example 3

[0130] Figure 6 This is a schematic diagram of the structure of a data processing device provided in Embodiment 3 of the present invention. Figure 6 As shown, the device includes: an item set determination module 310, a utility list determination module 320, an itemset set determination module 330, and a reference information determination module 340.

[0131] The project set determination module 310 is used to scan the target database and determine a set of transaction projects including at least one first transaction project, wherein the first transaction project is an original transaction project in the target database that meets a first preset condition; the utility list determination module 320 is used to scan the target database again and determine the triplet to be used corresponding to every two first transaction projects and the first utility list corresponding to the triplet to be used; wherein the first utility list includes at least one utility information associated with the triplet to be used, and the utility information is used to characterize the return attribute information of the first quantitative itemset corresponding to the triplet to be used, the first quantitative... An itemset is the set of items corresponding to the two first transaction items in the triplet to be used. The itemset set determination module 330 is used to partition the first quantitative itemset corresponding to at least one triplet to be used based on the first utility list corresponding to each triplet to be used, to obtain at least one quantitative itemset set. The reference information determination module 340 is used to adjust the at least one quantitative itemset set based on at least one triplet to be used, the first utility list corresponding to the triplet to be used, and the transaction item set, to obtain a target quantitative itemset set, so as to determine the item selection reference information based on the target quantitative itemset set.

[0132] The technical solution of this embodiment involves scanning a target database to determine a set of transaction items including at least one first transaction item. The target database is then scanned again to determine the triplets to be used corresponding to every two first transaction items and the first utility list corresponding to each triplet. Based on the first utility list, the combination of quantitative itemsets to which the first quantitative itemset corresponding to the triplet belongs is determined. This achieves the partitioning of at least one first quantitative itemset, providing data support for the subsequent determination of the target quantitative itemset set. Based on at least one triplet to be used, the first utility list corresponding to the triplet, and the transaction item set, the at least one quantitative itemset set is adjusted. Based on the adjusted at least one quantitative itemset set, the target quantitative itemset set is determined, and the first transaction items in the target quantitative itemset set are used to determine item selection reference information. This invention solves the problem in the prior art that it is difficult to guarantee that the selected items meet the actual needs of the user. By using a first utility list and the triplet to be used, a set of highly effective quantitative itemsets, namely the target quantitative itemsets, is determined. The target quantitative itemsets are then used to determine the reference information for item selection, which improves the accuracy of the determined target quantitative itemsets and ensures that the reference information for item selection corresponding to the target quantitative itemsets can meet the user's actual needs.

[0133] Based on the above embodiments, optionally, a project set determination module is used to obtain a target database associated with the transaction; scan the target database to determine multiple transaction transactions in the target database and transaction information corresponding to each transaction transaction, wherein the transaction information includes: a transaction identifier, at least one original transaction item under each transaction transaction, and project information corresponding to each original transaction item, the project information includes: a project identifier, external utility, and internal utility, the internal utility characterizing the proportion information or number of items of the original transaction item in its respective transaction transaction, and the external utility characterizing the transaction return attribute corresponding to the original transaction item; based on the external utility, internal utility, and weighted utility determination function of each original transaction item, a first weighted utility corresponding to each original transaction item is obtained; if the first weighted utility of the original transaction item exceeds a first preset utility threshold, the original transaction item is determined as a first transaction item; based on at least one first transaction item, a transaction project set is determined.

[0134] Optionally, the utility list determination module is used to rescan the target database to determine the first quantitative itemset corresponding to every two first transaction items and the second weighted utility corresponding to the first quantitative itemset; based on the first quantitative itemset and the second weighted utility, determine the triplet to be used corresponding to every two first transaction items; determine the transaction identifier of each transaction to which the first quantitative itemset belongs, and determine the actual utility and residual utility corresponding to the first quantitative itemset in each transaction to which it belongs based on the actual utility determination function and the residual utility determination function, respectively; determine the actual total utility based on at least one actual utility, and determine the residual total utility based on at least one residual utility; and determine the first utility list based on the transaction identifier, actual utility, residual utility, actual total utility, residual total utility, and second weighted utility.

[0135] Optionally, at least one set of quantified itemsets includes: a first set of quantified itemsets, a set of candidate quantified itemsets, and a set of second quantified itemsets. The itemset determination module is used to determine, for at least one triplet to be used, if the actual total utility in the first utility list of the triplet to be used exceeds a first preset utility threshold, that the first quantified itemset corresponding to the triplet to be used belongs to the first set of quantified itemsets; if the sum of the actual total utility and the remaining total utility in the first utility list of the triplet to be used exceeds the first preset utility threshold, that the first quantified itemset corresponding to the triplet to be used belongs to the set of candidate quantified itemsets; if the actual total utility in the first utility list of the triplet to be used exceeds a second preset utility threshold but does not exceed the first preset utility threshold, that the first quantified itemset corresponding to the triplet to be used belongs to the set of second quantified itemsets; wherein, the second preset utility threshold is a ratio data determined based on the first preset utility threshold and preset parameters.

[0136] Optionally, at least one set of quantized itemsets includes: a first set of utility quantized itemsets, a set of candidate quantized itemsets, and a set of second utility quantized itemsets. The reference information determination module includes: a target quantized itemset determination submodule, which includes: a range quantized itemset determination unit, used to merge at least one first quantized itemset from the second set of utility quantized itemsets to obtain a range quantized itemset set; a first utility list update unit, used to update a first utility list based on the first set of utility quantized itemsets, the set of candidate quantized itemsets, and the range quantized itemset set; and a target quantized itemset determination unit, used to perform recursive pruning and quantized itemset expansion processing on the first set of utility quantized itemsets, the set of candidate quantized itemsets, and the range quantized itemset set based on the updated first utility list, at least one triplet to be used, and a set of transaction items, so as to obtain the target quantized itemset set after the first transaction item in the set of transaction items has been processed.

[0137] Optionally, the range quantified itemset set determination unit is used to, for at least one first quantified itemset in the second utility quantified itemset set, determine at least one quantified itemset to be merged corresponding to each first quantified itemset based on the item identifier corresponding to the first transaction item in each first quantified itemset set; perform itemset aggregation and processing on each first quantified itemset and the corresponding at least one quantified itemset to be merged to obtain the second quantified itemset; wherein, the internal utility of the first transaction item in the second quantified itemset set is determined based on the internal utility of the same first transaction item in the first quantified itemset set and at least one quantified itemset to be merged, and the external utility corresponding to each first transaction item in the second quantified itemset set is the utility range corresponding to the external utility of the same first transaction item in the first quantified itemset set and at least one quantified itemset to be merged; and determine the range quantified itemset set based on at least one second quantified itemset set.

[0138] Optionally, the target quantized itemset set determination unit includes: a third quantized itemset determination subunit, used to use the updated first utility list as the second utility list, and the first quantized itemset in the first utility quantized itemset set, the first quantized itemset in the candidate quantized itemset set, and the second quantized itemset in the range quantized itemset set as the third quantized itemset; a third quantized itemset pruning subunit, used to remove third quantized itemsets that do not meet the second preset condition based on the updated first utility list and the triplet to be used, to obtain at least one pruned third quantized itemset; a fourth quantized itemset determination subunit, used to perform itemset expansion processing on each pruned third quantized itemset based on the first transaction item in the transaction item set, to obtain at least one fourth quantized itemset; and an itemset set updating subunit. The system is used to update the first utility quantized itemset set, the candidate quantized itemset set, and the range quantized itemset set based on at least one fourth quantized itemset, and to update the second utility list; the fourth quantized itemset pruning subunit is used to remove fourth quantized itemsets that do not meet the second preset condition based on the updated second utility list and the triplet to be used, so as to obtain at least one pruned fourth quantized itemset; the target quantized itemset set determination subunit is used to repeat the process of itemset expansion, itemset set update, utility list update, and quantized itemset pruning based on at least one pruned third quantized itemset and at least one pruned fourth quantized itemset, so as to obtain the target quantized itemset set based on the updated first utility quantized itemset set after all the first transaction items in the transaction item set have been processed.

[0139] Optionally, the third quantitative itemset pruning subunit is used to determine that the third quantitative itemset does not meet the second preset condition if, for at least one third quantitative itemset, the first transaction item in the triplet to be used corresponding to the third quantitative itemset is inconsistent with the preset quantitative item, or the weighted utility corresponding to the third quantitative itemset in the updated first utility list does not exceed the second preset utility threshold; and to remove the third quantitative itemset that does not meet the second preset condition to obtain at least one pruned third quantitative itemset.

[0140] Optionally, the reference information determination module includes: a project selection reference information determination submodule, which is used to determine at least one target transaction to which each target quantified item set belongs based on at least one target quantified item set in the target quantified item set set; determine users holding at least one target transaction as target users; and generate project selection reference information based on target users and at least one target transaction.

[0141] The data processing apparatus provided in the embodiments of the present invention can execute the data processing method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of executing the method.

[0142] Example 4

[0143] Figure 7 This is a schematic diagram of the structure of an electronic device provided in Embodiment 4 of the present invention. The electronic device 10 is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smartphones, wearable devices (such as helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0144] like Figure 7 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 may also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0145] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0146] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as data processing methods.

[0147] In some embodiments, the data processing method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or mounted on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the data processing method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the data processing method by any other suitable means (e.g., by means of firmware).

[0148] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), system-on-a-chip (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0149] Computer programs for implementing the data processing methods of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The computer programs can be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0150] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication unit 19, or installed from storage unit 18, or installed from ROM 12. When the computer program is executed by processor 11, it performs the functions defined in the methods of the embodiments of the present invention.

[0151] Example 5

[0152] Embodiment 5 of the present invention also provides a computer-readable storage medium storing computer instructions for causing a processor to execute a data processing method, the method comprising:

[0153] Scan the target database to identify a set of transaction items including at least one first transaction item, wherein the first transaction item is an original transaction item in the target database that meets a first preset condition; scan the target database again to identify the triplet to be used corresponding to every two first transaction items and the first utility list corresponding to the triplet to be used; wherein the first utility list includes at least one utility information associated with the triplet to be used, the utility information being used to characterize the return attribute information of the first quantitative itemset corresponding to the triplet to be used, and the first quantitative itemset is the set of items corresponding to the two first transaction items in the triplet to be used; based on the first utility list corresponding to each triplet to be used, the first quantitative itemset corresponding to at least one triplet to be used is partitioned to obtain at least one quantitative itemset set; based on at least one triplet to be used, the first utility list corresponding to the triplet to be used, and the transaction item set, the at least one quantitative itemset set is adjusted to obtain a target quantitative itemset set, and based on the target quantitative itemset set, project selection reference information is determined.

[0154] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0155] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0156] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0157] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0158] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0159] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A data processing method, characterized in that, include: Scan the target database to determine a set of transaction items that includes at least one first transaction item, wherein the first transaction item is an original transaction item in the target database that meets a first preset condition; The target database is scanned again to determine the triplet to be used corresponding to each pair of first transaction items and the first utility list corresponding to the triplet to be used; wherein, the first utility list includes at least one utility information associated with the triplet to be used, the utility information being used to characterize the return attribute information of the first quantitative itemset corresponding to the triplet to be used, and the first quantitative itemset being the set of items corresponding to the two first transaction items in the triplet to be used; Based on the first utility list corresponding to each triplet to be used, the first quantized itemset corresponding to at least one triplet to be used is partitioned to obtain at least one quantized itemset set. The at least one quantitative itemset set is adjusted based on at least one triplet to be used, a first utility list corresponding to the triplet to be used, and the transaction item set to obtain a target quantitative itemset set, so as to determine the item selection reference information based on the target quantitative itemset set.

2. The method according to claim 1, characterized in that, The scanning of the target database determines a set of transaction items that includes at least one first transaction item, including: Retrieve the target database associated with the transaction; The target database is scanned to identify multiple transaction transactions and corresponding transaction information for each transaction. The transaction information includes: a transaction identifier, at least one original transaction item under each transaction, and item information corresponding to each original transaction item. The item information includes: an item identifier, external utility, and internal utility. The internal utility represents the proportion or number of items of the original transaction item in its respective transaction, and the external utility represents the transaction return attribute corresponding to the original transaction item. Based on the external utility, internal utility, and weighted utility determination function of each original transaction item, the first weighted utility corresponding to each original transaction item is obtained; If the first weighted utility of the original transaction item exceeds a first preset utility threshold, the original transaction item is determined to be the first transaction item. Based on at least one of the first transaction items, a set of transaction items is determined.

3. The method according to claim 1, characterized in that, The step of rescanning the target database to determine the triplets to be used for every two first transaction items and the first utility list corresponding to the triplets to be used includes: Scan the target database again to determine the first quantitative itemset corresponding to every two first transaction items and the second weighted utility corresponding to the first quantitative itemset; Based on the first quantitative itemset and the second weighted utility, determine the triplet to be used for every two first transaction items; Determine the transaction identifier of each transaction to which the first quantized itemset belongs, and determine the actual utility and residual utility of the first quantized itemset in each transaction based on the actual utility determination function and the residual utility determination function, respectively. The actual total utility is determined based on at least one of the actual utilities, and the residual total utility is determined based on at least one of the residual utilities; A first utility list is determined based on the transaction identifier, the actual utility, the remaining utility, the actual total utility, the remaining total utility, and the second weighted utility.

4. The method according to claim 1, characterized in that, The at least one set of quantified itemsets includes: a first set of utility quantified itemsets, a set of candidate quantified itemsets, and a second set of utility quantified itemsets. The step of partitioning the first set of quantified itemsets corresponding to at least one triplet to be used, based on the first utility list corresponding to each triplet to be used, to obtain at least one set of quantified itemsets includes: For at least one of the triplets to be used, if the actual total utility in the first utility list of the triplets to be used exceeds a first preset utility threshold, then it is determined that the first quantized itemset corresponding to the triplets to be used belongs to the first utility quantized itemset set. If the sum of the actual total utility and the remaining total utility in the first utility list of the triplet to be used exceeds the first preset utility threshold, then it is determined that the first quantized itemset corresponding to the triplet to be used belongs to the candidate quantized itemset set. If the actual total utility in the first utility list of the triplet to be used exceeds the second preset utility threshold but does not exceed the first preset utility threshold, then the first quantized itemset corresponding to the triplet to be used is determined to belong to the second utility quantized itemset set; wherein, the second preset utility threshold is a ratio data determined based on the first preset utility threshold and preset parameters.

5. The method according to claim 1, characterized in that, The at least one set of quantitative itemsets includes: a first set of utility quantitative itemsets, a set of candidate quantitative itemsets, and a second set of utility quantitative itemsets. The adjustment process based on at least one triplet to be used, the first utility list corresponding to the triplet to be used, and the set of transaction items to obtain the target set of quantitative itemsets includes: Merge at least one first quantized itemset from the second utility quantized itemset set to obtain a range quantized itemset set; Update the first utility list based on the first utility quantification itemset set, the candidate quantification itemset set, and the range quantification itemset set; Based on the updated first utility list, at least one of the triples to be used, and the set of transaction items, recursively prune and expand the first utility quantized itemset set, the candidate quantized itemset set, and the range quantized itemset set to obtain the target quantized itemset set after the first transaction item in the set of transaction items has been processed.

6. The method according to claim 5, characterized in that, The step of merging at least one first quantized itemset from the second utility quantized itemset set to obtain a range quantized itemset set includes: For at least one first quantitative itemset in the second utility quantitative itemset set, at least one quantitative itemset to be merged is determined based on the item identifier corresponding to the first transaction item in each first quantitative itemset set; Each first quantitative item set and its corresponding at least one quantitative item set to be merged are combined to obtain a second quantitative item set; wherein, the internal utility of the first transaction item in the second quantitative item set is determined based on the internal utility of the same first transaction item in the first quantitative item set and at least one quantitative item set to be merged, and the external utility corresponding to each first transaction item in the second quantitative item set is the utility range corresponding to the external utility of the same first transaction item in the first quantitative item set and at least one quantitative item set to be merged; A range quantization itemset set is determined based on at least one of the second quantization itemsets.

7. The method according to claim 5, characterized in that, The process involves recursively pruning and expanding the first utility itemset set, the candidate itemset set, and the range itemset set based on the updated first utility list, at least one of the three triplets to be used, and the transaction item set. After processing the first transaction item in the transaction item set, a target itemset set is obtained, including: The updated first utility list is used as the second utility list, and the first quantized itemset in the first utility quantized itemset set, the first quantized itemset in the candidate quantized itemset set, and the second quantized itemset in the range quantized itemset set are used as the third quantized itemset. Based on the updated first utility list and the triplet to be used, the third quantized itemsets that do not meet the second preset condition are removed to obtain at least one pruned third quantized itemset. For the at least one pruned third quantitative itemset, each pruned third quantitative itemset is expanded according to the first transaction item in the transaction item set to obtain at least one fourth quantitative itemset. Based on the at least one fourth quantization itemset, the first utility quantization itemset set, the candidate quantization itemset set, and the range quantization itemset set are updated, and the second utility list is updated. Based on the updated second utility list and the triplet to be used, the fourth quantized itemsets that do not meet the second preset condition are removed to obtain at least one pruned fourth quantized itemset; Based on the at least one pruned third quantized itemset and the at least one pruned fourth quantized itemset, the processes of itemset expansion, itemset set update, utility list update, and quantized itemset pruning are repeated until the first transaction item in the transaction item set has been processed. Based on the updated first utility quantized itemset set, the target quantized itemset set is obtained.

8. The method according to claim 7, characterized in that, The step of removing third quantized itemsets that do not meet the second preset condition based on the updated first utility list and the triplet to be used, to obtain at least one pruned third quantized itemset, includes: For at least one of the third quantitative itemsets, if the first transaction item in the triplet to be used corresponding to the third quantitative itemset is inconsistent with the preset quantitative item, or if the weighted utility corresponding to the third quantitative itemset in the updated first utility list does not exceed the second preset utility threshold, then the third quantitative itemset is determined not to meet the second preset condition. Remove the third quantized itemsets that do not meet the second preset condition to obtain at least one pruned third quantized itemset.

9. The method according to claim 1, characterized in that, The process of determining project selection reference information based on the target quantified itemset set includes: Based on at least one target quantization item set in the target quantization item set set, determine at least one target transaction to which each target quantization item set belongs; Users holding at least one target transaction are identified as target users, and project selection reference information is generated based on the target users and the at least one target transaction.

10. A data processing apparatus, characterized in that, include: The project set determination module is used to scan the target database and determine a transaction project set that includes at least one first transaction project, wherein the first transaction project is an original transaction project in the target database that meets a first preset condition; The utility list determination module is used to scan the target database again to determine the triplet to be used corresponding to each pair of first transaction items and the first utility list corresponding to the triplet to be used; wherein, the first utility list includes at least one utility information associated with the triplet to be used, the utility information being used to characterize the return attribute information of the first quantitative itemset corresponding to the triplet to be used, and the first quantitative itemset being the set of items corresponding to the two first transaction items in the triplet to be used; The itemset set determination module is used to partition the first quantized itemset corresponding to at least one triplet to be used based on the first utility list corresponding to each triplet to be used, so as to obtain at least one quantized itemset set. The reference information determination module is used to adjust the at least one quantitative itemset set based on at least one triplet to be used, a first utility list corresponding to the triplet to be used, and the transaction item set to obtain a target quantitative itemset set, so as to determine the item selection reference information based on the target quantitative itemset set.

Images