CN113177828A - Article recommendation method, device, equipment and storage medium - Google Patents

Article recommendation method, device, equipment and storage medium Download PDF

Info

Publication number
CN113177828A
CN113177828A CN202110563543.4A CN202110563543A CN113177828A CN 113177828 A CN113177828 A CN 113177828A CN 202110563543 A CN202110563543 A CN 202110563543A CN 113177828 A CN113177828 A CN 113177828A
Authority
CN
China
Prior art keywords
asset
asset class
item
combination
class
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202110563543.4A
Other languages
Chinese (zh)
Inventor
余德水
李保仓
胡赞华
韩亚辉
江鑫淇
方菲
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
China Construction Bank Corp
Original Assignee
China Construction Bank Corp
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by China Construction Bank Corp filed Critical China Construction Bank Corp
Priority to CN202110563543.4A priority Critical patent/CN113177828A/en
Publication of CN113177828A publication Critical patent/CN113177828A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/06—Buying, selling or leasing transactions
    • G06Q30/0601—Electronic shopping [e-shopping]
    • G06Q30/0631—Item recommendations
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/23—Updating
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/28—Databases characterised by their database models, e.g. relational or object models
    • G06F16/284—Relational databases

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • Physics & Mathematics (AREA)
  • Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Accounting & Taxation (AREA)
  • General Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Finance (AREA)
  • Development Economics (AREA)
  • Economics (AREA)
  • Marketing (AREA)
  • Strategic Management (AREA)
  • General Business, Economics & Management (AREA)
  • Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)

Abstract

The embodiment of the invention discloses an article recommendation method, a device, equipment and a storage medium, which relate to the field of automatic program design, and the method comprises the following steps: acquiring a preset asset class combination and generating an association relation table; wherein the incidence relation table comprises asset classes and incidence asset class combinations; determining an asset class combination data set according to an asset class combination of an asset application form within preset time; updating the association relation table according to the asset class combination data set based on a preset recommendation set algorithm; and recommending the asset class items related to the selected asset class to the user according to the current application form asset class combination of the user, the selected asset class in the current application form asset class combination and the association relation table. According to the technical scheme of the embodiment of the invention, the association relation table is updated through the asset type combination in the asset application form, so that more accurate and efficient article recommendation is provided for the user.

Description

Article recommendation method, device, equipment and storage medium
Technical Field
The embodiment of the invention relates to the technical field of automatic program design, in particular to an article recommendation method, device, equipment and storage medium.
Background
Under the scenes of commodity purchasing, asset management and the like, a user can place an order for an article or apply for the article.
In many cases, a user needs to purchase an article in a matching manner or simultaneously retrieve related assets, for example, when the user applies for retrieving a printer, the user generally needs to apply for printing paper simultaneously, and when the user applies for retrieving a notebook computer, the user generally needs to apply for retrieving a keyboard, a mouse and a display screen simultaneously. If the user is not familiar with the service and the like, the user does not need to initiate multiple applications to examine and approve the assets to obtain enough assets. In the prior art, in order to solve the above problems, the association relationship of the asset and the object is usually maintained manually.
However, manual maintenance has the following problems: under the condition that the types of articles are more, the maintenance workload is large, and the efficiency is not high. The article association relationship is easy to be overlooked, so that the association information of the article is incomplete. Under the condition that new receiving applications or shopping lists exist and new article types exist, the updating instantaneity of the article association relationship is not strong, and the article association relationship cannot be updated to the latest article association relationship in time.
Disclosure of Invention
The embodiment of the invention provides an article recommendation method, device, equipment and storage medium, which are used for providing accurate article recommendation for a user.
In a first aspect, an embodiment of the present invention provides an item recommendation method, including:
acquiring a preset asset class combination and generating an association relation table; wherein the incidence relation table comprises asset classes and incidence asset class combinations;
determining an asset class combination data set according to an asset class combination of an asset application form within preset time;
updating the association relation table according to the asset class combination data set based on a preset recommendation set algorithm;
and recommending the asset class items related to the selected asset class to the user according to the current application form asset class combination of the user, the selected asset class in the current application form asset class combination and the association relation table.
In a second aspect, an embodiment of the present invention further provides an article recommendation apparatus, including:
the incidence relation table generating module is used for acquiring a preset asset class combination and generating an incidence relation table; wherein the incidence relation table comprises asset classes and incidence asset class combinations;
the asset class combination data set determining module is used for determining an asset class combination data set according to an asset class combination of an asset application form in preset time;
the incidence relation table updating module is used for updating the incidence relation table according to the asset class combination data set based on a preset recommendation set algorithm;
and the article recommending module is used for recommending the asset class articles related to the selected asset class to the user according to the current application form asset class combination of the user, the selected asset class in the current application form asset class combination and the association relation table.
In a third aspect, an embodiment of the present invention further provides an item recommendation apparatus, where the item recommendation apparatus includes:
one or more processors;
a memory for storing one or more programs;
when executed by the one or more processors, cause the one or more processors to implement a method of item recommendation as provided in any embodiment of the invention.
In a fourth aspect, embodiments of the present invention also provide a storage medium containing computer-executable instructions, which when executed by a computer processor, are used to perform the item recommendation method provided in any of the embodiments of the present invention.
According to the embodiment of the invention, the association relation table is updated through the asset type combination in the asset application form, the articles associated with the asset application form are provided for the user, the problems of low efficiency caused by manually maintaining the association relation of the articles and inaccurate recommended article caused by untimely update of the association relation are solved, and the effect of providing more accurate and efficient article recommendation for the user is realized.
Drawings
FIG. 1 is a flow chart of a method for recommending items according to a first embodiment of the present invention;
FIG. 2 is a flowchart of an item recommendation method according to a second embodiment of the present invention;
fig. 3 is a flowchart of updating an association table in an item recommendation method according to a third embodiment of the present invention;
fig. 4 is a schematic structural diagram of an article recommendation device according to a fourth embodiment of the present invention;
fig. 5 is a schematic structural diagram of an article recommendation device in the fifth embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention. It should be further noted that, for the convenience of description, only some of the structures related to the present invention are shown in the drawings, not all of the structures.
Example one
Fig. 1 is a flowchart of an item recommendation method according to an embodiment of the present invention, where this embodiment is applicable to a situation where a user needs to recommend an associated item when ordering to purchase an order and applying for an asset item, and the method may be executed by an item recommendation apparatus, where the apparatus may be implemented by hardware and/or software, and may be generally integrated in a device, such as a server, an intelligent terminal, and the like, and the method specifically includes the following steps:
step 110, acquiring a preset asset class combination, and generating an association relation table;
wherein the incidence relation table comprises asset classes and incidence asset class combinations. The preset asset class grouping may be an asset class grouping manually input by a user, and the preset asset class grouping includes two parts of an asset class selected by the user and a corresponding associated asset class grouping. Therefore, in the association relation table, the asset class selected by the user is recorded, and the associated asset class combination corresponding to the asset class is recorded. The associated asset class group includes at least one asset class associated with the user selected asset class group.
Step 120, determining an asset class combination data set according to an asset class combination of the asset application form within preset time;
the preset time may be a default time period of the system or a time period set by a user. For example, weekly asset application slips are obtained. And extracting the asset class combination appearing in the asset application form, and recording the asset class combination as an asset class combination data set. Of course, this asset class portfolio data set may be continually updated with new asset application forms. The asset class combination data set can record the asset class combination in each asset application form which appears historically, and the asset class combination is subjected to duplication elimination, namely one asset class combination keeps one record, for the asset class combination which appears for a plurality of times, the corresponding support item needs to be recorded, namely the number of times of appearance of one asset class combination is taken as the support item of the asset class combination to be recorded in the asset class combination data set, and the asset class combination data set can record the asset class combination and the corresponding support item in a two-dimensional table form.
Step 130, updating the association relation table according to the asset class combination data set based on a preset recommendation set algorithm;
when the asset type combination data has new asset type combination and/or the existing asset type combination support items are increased. The profile categories and corresponding associated asset category groupings in the association table may be updated with the asset category grouping data set. The pre-set recommendation set algorithm may be an association rule mining algorithm, which uses the asset class combination data set as a database and finds the relationship of item sets in the database by using an iterative method of searching layer by layer to form a rule, for example, Apriori algorithm, which consists of connecting (class matrix operation) and pruning (removing unnecessary intermediate results). The concept of a set of terms in the algorithm is a set of terms. The set of K items is a set of K items.
Step 140, recommending the asset class article associated with the selected asset class to the user according to the current application form asset class combination of the user, the selected asset class in the current application form asset class combination and the association relation table.
When a user submits an asset request form, the asset request form is used as a current request form, and at least one asset type article is applied in the request form. Wherein one of the asset classes is selected by the user as a selected asset class. And searching the asset class matched with the selected asset class from the association relation table, then determining an associated asset class combination corresponding to the matched asset class, acquiring the current application form asset class combination, and determining the asset class article needing to be recommended to the user by comparing the data class in the current application form asset class combination with the asset class in the associated asset class.
Optionally, the recommending, according to the current application form asset class combination of the user, the selected asset class in the current application form asset class combination, and the association relationship table, an asset class item associated with the selected asset class to the user includes:
according to the selected asset type, inquiring the corresponding associated asset type combination in the association relation table;
comparing the associated asset class portfolio to the current application form asset class portfolio, recommending to a user the material class items that appear in the associated asset class portfolio and not appear in the current application form asset class portfolio.
According to the technical scheme, the association relation table is updated through the asset type combination in the asset application form, the articles associated with the asset application form are provided for the user, the problems that efficiency is low due to manual maintenance of article association relations, and article recommendation is inaccurate due to the fact that the association relations are not updated timely are solved, and the effect of providing more accurate and efficient article recommendation for the user is achieved.
Example two
Fig. 2 is a flowchart of an article recommendation method according to a second embodiment of the present invention, which is further detailed based on the foregoing technical solution in this embodiment, and specifically may be a detailed description of determining an asset class combination data set according to an asset class combination of an asset request form within a preset time, where the method specifically includes:
step 210, acquiring a preset asset class combination, and generating an association relation table;
step 220, extracting asset types from the asset request form within preset time, and acquiring asset type combinations in the asset request form;
step 230, generating the asset class combination data set according to the acquired asset class combination; wherein the asset class portfolio data set includes support items for each of the asset class portfolios.
Step 240, updating the association relation table according to the asset class combination data set based on a preset recommendation set algorithm;
and step 250, recommending the asset class article associated with the selected asset class to the user according to the current application form asset class combination of the user, the selected asset class in the current application form asset class combination and the association relation table.
Optionally, the item recommendation method further includes:
if a newly added asset application form is obtained, extracting an asset class combination in the newly added application form;
according to the asset class combination in the newly added application form, updating the asset class combination data set in the following mode:
when the asset class combination data set contains the asset class combination in the newly added application form, increasing the corresponding support items of the asset class combination in the asset class combination data set by corresponding quantity;
and when the asset type combination data set does not contain the asset type combination in the newly-added application form, newly adding a corresponding data type combination record in the asset type combination data set, and setting a corresponding support item.
If the asset class combination in the new application form already exists in the asset class combination dataset, the number of the support items of the corresponding asset class combination is only required to be increased, for example, for an asset class combination { a, B, C } already recorded in the asset class combination dataset, the support item is 2, and the asset class combination { a, B, C } also exists in the new application form and appears 2 times, then the asset class combination { a, B, C } in the asset class combination dataset becomes 2+ 2-4. If the asset type combination in the newly added application form does not exist in the asset type combination data set, the asset type combination needs to be added in the asset type combination data set, and according to the occurrence frequency of the asset type combination in the newly added application form, a support item of the asset type combination in the asset type combination data set is set, for example, the asset type combination { A, B, D } in the newly added application form is 3, the occurrence frequency is 3, the asset type combination { A, B, D } is not recorded in the asset type combination data set, a record { A, B, D } is newly added in the asset type combination data set, and the support item is set to be 3.
Optionally, after updating the asset class portfolio data set, the method further includes:
and deleting the asset class combinations with the number of items smaller than a first preset value in the asset class combination data set. Wherein the first preset value may be a default of the system or set by the user, for example, the first preset value is set to 1, which will filter out the asset class combinations of 1 item in the asset class combination data set. In a general asset application, only one specific asset is applied to be always the most, and the data source can be greatly reduced by filtering the asset application form. Classifying the asset class combination data set, and classifying the same combination into the same record; the records with the category number of 1 in the category set are filtered, in daily application, most application forms only pick up one article, the data has no direct relation to the analysis association relation, the data sources can be reduced by filtering, and the number of records which need to be compared when frequent item sets are calculated each time is reduced.
According to the technical scheme of the embodiment, the asset class combination data set is generated through the asset application form within the preset time, the asset class combination and the corresponding support items are recorded, the asset class combination data set can be updated after the asset application form is newly added, iteration is carried out along with the increase of data, and the recommended rule is more accurate.
EXAMPLE III
Fig. 3 is a flowchart of an article recommendation method provided in a third embodiment of the present invention, which is further detailed based on the above technical solution, and specifically may be a detailed description that updates the association table according to the asset class composition data set based on a preset recommendation set algorithm, as shown in fig. 3, updating the association table according to the asset class composition data set based on the preset recommendation set algorithm, and specifically may include:
step 301, recording each of the asset classes appearing in the asset class portfolio data set in a candidate item set;
wherein, each asset class appearing in the asset class composition data set is registered with a record in a candidate item set, and a support item num3 of each record is set, and an initial value of the support item is 0. For example, if four asset classes a, B, C, and D are present in the asset class composition dataset, a record is added to each asset class in a candidate item set, four records are added in total, and the support item of each record is set to 0. Each record in a candidate set is an asset class.
Step 302, determining a support item of each asset class in the candidate item according to the support item of the asset class combination in the asset class combination data set, and deleting the asset classes of which the support degree is less than a preset support degree and the support items are less than a second preset value in the candidate item;
and calculating the value of a support item of each record in one candidate item set, traversing the asset class combination data set one by one, wherein num3 is num3+ num2 when the value appears in the asset class combination data set, wherein num2 is the support item of the asset class combination in the asset class combination data set, and num3 is the support item of the asset class in one candidate item set. And directly deleting the data with the support degree smaller than the minimum support degree and the support items smaller than a second preset value (for example, the second preset value is 10) in one item of candidate item record, namely pruning the data.
Step 303, moving the asset class of the candidate item set into a frequent item set, and emptying the candidate item set;
step 304, recording two asset class combinations obtained by pairwise combination of the asset classes in the frequent item set in a two item candidate item set;
the asset class pairwise combination is a two-item asset class combination, that is, two asset classes are in the two-item asset class combination.
Step 305, determining a support item of each two-item asset class combination in the two-item candidate items according to the support items of the asset class combinations in the asset class combination data set, and deleting the two-item asset class combination of which the support degree is less than the preset support degree and the support item is less than the second preset value in the two-item candidate items;
wherein, the value of the support item of each record in the two-item candidate item set is calculated, the asset class combination data set is traversed item by item, and if the asset class combination in the record contains the two-item asset class combination in the two-item candidate item set, num3 is num3+ num2, wherein num2 is the support item of the asset class combination in the asset class combination data set, and num3 is the support item of the asset class in the two-item candidate item set. And directly deleting the data with the support degree smaller than the minimum support degree and the support items smaller than a second preset value (for example, the second preset value is 10) in the two-item candidate item record, namely pruning the data.
Step 306, updating the association relation table according to the two candidate item sets;
step 307, moving the two asset class combinations in the two candidate item sets into a two frequent item set, and emptying the two candidate item sets;
step 308, recording K asset class combinations obtained by pairwise combination of the first K-2 same K-1 asset class combinations in the K-1 frequent item set in the K candidate item set; wherein K is a positive integer greater than 2;
step 309, determining a support item of each K asset class portfolio in the K candidate items according to the support items of the asset class portfolio in the asset class portfolio data set, and deleting the K asset class portfolio of which the support degree is less than the preset support degree and the support item is less than the second preset value;
step 310, updating the association relation table according to the K item candidate item set;
step 311, moving the K asset class combinations in the K candidate item sets into K frequent item sets, and emptying the K candidate item sets;
and step 312, when the support items of the K asset class combinations in the K candidate items are all smaller than the second preset value or the K value is greater than a third preset value, stopping generating the next-level candidate item set.
And repeating the self connection of the K-1 frequent item sets to obtain corresponding K candidate item sets, and then performing data pruning, wherein the generation of the next-level candidate item set is stopped when all the support items of the K asset class combinations in the K candidate item sets are smaller than the second preset value (for example, the second preset value is 10, which indicates that no filtering set meeting the filtering condition exists) or the K value is larger than the third preset value (for example, the third preset value is 4, which can take the median of the asset class numbers of the asset class combinations of the asset class combination data sets).
Optionally, the association relationship table further includes an update coverage identifier of the asset class, where the update coverage identifier includes an overrideable identifier and an overrideable identifier; when the association table is generated, the update coverage identifier input by the user may be recorded in the association table, and a corresponding update coverage identifier may be added for each asset class in the association table. For example, 00 may be used to indicate that the record cannot be overwritten, i.e., the record cannot be overwritten when the association table is updated according to the H item candidate set; it may be denoted by 01 that the record may be overwritten when the association table is updated according to the H candidate set, where H is a positive integer greater than 1, that is, the association table is updated according to the two candidates and the candidate sets generated thereafter.
Updating the association table according to the H item candidate item, including:
comparing the asset class in the frequent item set with the asset class in the association relationship table, and removing the asset class of which the update coverage identifier is not covered in the frequent item set as a total asset class set;
sequentially selecting each asset class in the asset class total set, searching the H asset class combination containing the selected asset class in the H candidate item set, and taking the H asset class combination with the largest supported item as the selected H asset class combination; wherein H is a positive integer greater than 1;
determining the asset classes other than the selected asset class in the selected H asset class combination as the associated asset classes of the selected asset classes;
if the association relation table contains the selected asset type, updating the corresponding association asset type combination by using the corresponding association asset type;
if the selected asset type is not contained in the association relationship table, the selected asset type is newly added in the association relationship table, the corresponding association asset type is set as the corresponding association asset type combination, and the update coverage mark is set to be covered.
And setting the updating coverage mark of the corresponding record as 00 (which cannot be covered) for the fixed and unchangeable incidence relation among the asset class articles recorded in the incidence relation table, avoiding being covered by the result of the automatic analysis, and setting the other updating coverage mark as 01 (which can be covered). Finding an asset class total set of a frequent item set, matching asset classes in the association relation table, and removing the asset classes with the updated coverage marks of 00 in the association relation table from the asset class total set; then, traversing each asset class in the asset class total set to be sequentially used as a selected asset class, taking a record with the largest support item of the selected asset class in the H asset class combination in the H item candidate item set, and taking the record with the largest support item of the selected asset class as an associated asset class to update the record in the association relation table after the selected asset class is removed from the record. And if the selected asset type exists in the association relationship table, updating the association asset type combination into the association asset type of the selected asset type, if the selected asset type does not exist in the association relationship table, adding an asset type record, recording the association asset type of the selected asset type into the corresponding association asset type combination, and setting an update coverage identifier to be 01 (capable of being covered).
According to the technical scheme of the embodiment, manual maintenance and automatic analysis of the user are combined, and manual maintenance avoids the problems that the early-stage data volume is small, the automatic analysis result is inaccurate, and recommended related articles cannot be provided when an application is initiated; the automatic analysis solves the problems that the manual maintenance workload is large, the manual maintenance data cannot be updated in time, and the manual maintenance data is incomplete.
Generating a candidate C for each iteration of the Apriori algorithmKPost-delete frequent itemsets LK-1Record with CKUpdating the primary association table (k) with the result of (1)>1) Each time L is generatedjThen, delete Cj(j>0) (ii) a The purpose is to reduce the candidate set and to do so with CKThe priority of the K value is higher when the association relation table is updated. And directly deleting the data with the support degree smaller than the minimum support degree and the support items smaller than N (for example, N is 10) in the record. The purpose is to prevent that a certain set, although occurring a few times in the total sample of data sources for a certain period of time, is filtered out of sets that appear together with a large probability once they occur. Adding update override identification (status) field in the association relation table to define whether the record can be automatically overridden, and resolvingThe partially fixed combinatorial relationship is not covered by the results of the automated analysis with errors.
Example four
Fig. 4 is a schematic structural diagram of an article recommendation device according to a fourth embodiment of the present invention, and as shown in fig. 4, the article recommendation device may include: an association table generation module 410, an asset class portfolio data set determination module 420, an association table update module 430, and an item recommendation module 440, wherein,
an association table generating module 410, configured to obtain a preset asset class combination and generate an association table; wherein the incidence relation table comprises asset classes and incidence asset class combinations;
the asset class combination data set determining module 420 is configured to determine an asset class combination data set according to an asset class combination of the asset request form within a preset time;
an association table updating module 430, configured to update the association table according to the asset class combination data set based on a preset recommendation set algorithm;
and the item recommending module 440 is configured to recommend an asset type item associated with the selected asset type to the user according to the current application form asset type combination of the user, the selected asset type in the current application form asset type combination, and the association relationship table.
According to the technical scheme, the association relation table is updated through the asset type combination in the asset application form, the articles associated with the asset application form are provided for the user, the problems that efficiency is low due to manual maintenance of article association relations, and article recommendation is inaccurate due to the fact that the association relations are not updated timely are solved, and the effect of providing more accurate and efficient article recommendation for the user is achieved.
Optionally, the asset class portfolio dataset determination module includes:
the asset type combination acquiring unit is used for extracting asset types from the asset application form within preset time and acquiring asset type combinations in the asset application form;
the asset class combination data set generating unit is used for generating the asset class combination data set according to the acquired asset class combination; wherein the asset class portfolio data set includes support items for each of the asset class portfolios.
Optionally, the article recommending apparatus further includes:
the newly-added asset type combination extraction module is used for extracting an asset type combination in a newly-added application form if the newly-added asset application form is obtained;
and the asset class combination data set updating module is used for updating the asset class combination data set in the following mode according to the asset class combination in the newly added application form:
when the asset class combination data set contains the asset class combination in the newly added application form, increasing the corresponding support items of the asset class combination in the asset class combination data set by corresponding quantity;
and when the asset type combination data set does not contain the asset type combination in the newly-added application form, newly adding a corresponding data type combination record in the asset type combination data set, and setting a corresponding support item.
Optionally, the article recommending apparatus further includes:
and the asset class combination filtering module is used for deleting the asset class combinations with the item number smaller than a first preset value in the asset class combination data set after the asset class combination data set is updated.
Optionally, the association table updating module is specifically configured to:
recording each of the asset classes present in the asset class portfolio data set in a candidate set;
determining a support item of each asset class in the candidate item set according to the support item of the asset class combination in the asset class combination data set, and deleting the asset classes of which the support degree is less than a preset support degree and the support items are less than a second preset value in the candidate item set;
moving the asset class of the candidate item set into a frequent item set and emptying the candidate item set;
recording two asset class combinations obtained by combining the asset classes in the frequent item set in pairs in a two item candidate item set;
determining a support item of each two-item asset class combination in the two-item candidate items according to the support items of the asset class combinations in the asset class combination data set, and deleting the two-item asset class combination of which the support degree is less than the preset support degree and the support item is less than the second preset value in the two-item candidate items;
updating the incidence relation table according to the two candidate item sets;
moving the two-item asset class combination in the two-item candidate item set into a two-item frequent item set, and emptying the two-item candidate item set;
recording K asset class combinations obtained by pairwise combination of first K-2 identical K-1 asset class combinations in the K-1 frequent item set in the K candidate item set; wherein K is a positive integer greater than 2;
determining a support item of each K asset class combination in the K candidate items according to the support items of the asset class combinations in the asset class combination data set, and deleting the K asset class combinations with the support degrees smaller than the preset support degree and the support items smaller than the second preset value in the K candidate items;
updating the incidence relation table according to the K item candidate item set;
moving the K asset class combinations in the K candidate item sets into K frequent item sets, and emptying the K candidate item sets;
and when the support items of the K asset class combinations in the K candidate item sets are all smaller than the second preset value or the K value is larger than a third preset value, stopping generating the next-level candidate item set.
Optionally, the association relationship table further includes an update coverage identifier of the asset class, where the update coverage identifier includes an overrideable identifier and an overrideable identifier;
the association table updating module is specifically configured to:
updating the association table according to the H item candidate item, including:
comparing the asset class in the frequent item set with the asset class in the association relationship table, and removing the asset class of which the update coverage identifier is not covered in the frequent item set as a total asset class set;
sequentially selecting each asset class in the asset class total set, searching the H asset class combination containing the selected asset class in the H candidate item set, and taking the H asset class combination with the largest supported item as the selected H asset class combination; wherein H is a positive integer greater than 1;
determining the asset classes other than the selected asset class in the selected H asset class combination as the associated asset classes of the selected asset classes;
if the association relation table contains the selected asset type, updating the corresponding association asset type combination by using the corresponding association asset type;
if the selected asset type is not contained in the association relationship table, the selected asset type is newly added in the association relationship table, the corresponding association asset type is set as the corresponding association asset type combination, and the update coverage mark is set to be covered.
Optionally, the item recommendation module is specifically configured to:
according to the selected asset type, inquiring the corresponding associated asset type combination in the association relation table;
comparing the associated asset class portfolio to the current application form asset class portfolio, recommending to a user the material class items that appear in the associated asset class portfolio and not appear in the current application form asset class portfolio.
The article recommending device provided by the embodiment of the invention can execute the article recommending method provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the executing method.
EXAMPLE five
Fig. 5 is a schematic structural diagram of an item recommendation apparatus according to a fifth embodiment of the present invention, as shown in fig. 5, the item recommendation apparatus includes a processor 510, a memory 520, an input device 530, and an output device 540; the number of the processors 510 in the item recommendation device may be one or more, and one processor 510 is taken as an example in fig. 5; the processor 510, the memory 520, the input device 530 and the output device 540 in the item recommendation apparatus may be connected by a bus or other means, and fig. 5 illustrates an example of a connection by a bus.
The memory 520 may be used as a computer-readable storage medium for storing software programs, computer-executable programs, and modules, such as program instructions/modules corresponding to the item recommendation method in the embodiment of the present invention (for example, the association table generation module 410, the asset class combination data set determination module 420, the association table update module 430, and the item recommendation module 440 in the item recommendation apparatus). The processor 510 executes various functional applications and data processing of the item recommendation device by executing software programs, instructions and modules stored in the memory 520, thereby implementing the item recommendation method described above.
The memory 520 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application program required for at least one function; the storage data area may store data created according to the use of the terminal, and the like. Further, the memory 520 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid state storage device. In some examples, the memory 520 may further include memory located remotely from the processor 510, which may be connected to the item recommendation device via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The input means 530 may be used to receive input numeric or character information and generate key signal inputs related to user settings and function control of the item recommendation apparatus. The output device 540 may include a display device such as a display screen.
EXAMPLE six
An embodiment of the present invention further provides a storage medium containing computer-executable instructions, which when executed by a computer processor, perform a method for item recommendation, the method including:
acquiring a preset asset class combination and generating an association relation table; wherein the incidence relation table comprises asset classes and incidence asset class combinations;
determining an asset class combination data set according to an asset class combination of an asset application form within preset time;
updating the association relation table according to the asset class combination data set based on a preset recommendation set algorithm;
and recommending the asset class items related to the selected asset class to the user according to the current application form asset class combination of the user, the selected asset class in the current application form asset class combination and the association relation table.
Of course, the storage medium provided by the embodiment of the present invention contains computer-executable instructions, and the computer-executable instructions are not limited to the method operations described above, and may also perform related operations in the item recommendation method provided by any embodiment of the present invention.
From the above description of the embodiments, it is obvious for those skilled in the art that the present invention can be implemented by software and necessary general hardware, and certainly, can also be implemented by hardware, but the former is a better embodiment in many cases. Based on such understanding, the technical solutions of the present invention may be embodied in the form of a software product, which can be stored in a computer-readable storage medium, such as a floppy disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a FLASH Memory (FLASH), a hard disk or an optical disk of a computer, and includes several instructions for enabling a computer device (which may be a personal computer, a server, or a network device) to execute the methods according to the embodiments of the present invention.
It should be noted that, in the embodiment of the article recommendation device, the included units and modules are merely divided according to the functional logic, but are not limited to the above division as long as the corresponding functions can be implemented; in addition, specific names of the functional units are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present invention.
It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present invention and the technical principles employed. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in greater detail by the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the appended claims.

Claims (16)

1. An item recommendation method, comprising:
acquiring a preset asset class combination and generating an association relation table; wherein the incidence relation table comprises asset classes and incidence asset class combinations;
determining an asset class combination data set according to an asset class combination of an asset application form within preset time;
updating the association relation table according to the asset class combination data set based on a preset recommendation set algorithm;
and recommending the asset class items related to the selected asset class to the user according to the current application form asset class combination of the user, the selected asset class in the current application form asset class combination and the association relation table.
2. The method of claim 1, wherein the determining the asset class combination data set according to the asset class combination of the asset application form within the preset time comprises:
extracting asset types from the asset request form within preset time, and acquiring asset type combinations in the asset request form;
generating the asset class combination data set according to the acquired asset class combination; wherein the asset class portfolio data set includes support items for each of the asset class portfolios.
3. The method of claim 2, further comprising:
if a newly added asset application form is obtained, extracting an asset class combination in the newly added application form;
according to the asset class combination in the newly added application form, updating the asset class combination data set in the following mode:
when the asset class combination data set contains the asset class combination in the newly added application form, increasing the corresponding support items of the asset class combination in the asset class combination data set by corresponding quantity;
and when the asset type combination data set does not contain the asset type combination in the newly-added application form, newly adding a corresponding data type combination record in the asset type combination data set, and setting a corresponding support item.
4. The method of claim 3, further comprising, after updating the asset class portfolio dataset:
and deleting the asset class combinations with the number of items smaller than a first preset value in the asset class combination data set.
5. The method of claim 1, wherein updating the association table according to the asset class portfolio data set based on a preset recommendation set algorithm comprises:
recording each of the asset classes present in the asset class portfolio data set in a candidate set;
determining a support item of each asset class in the candidate item set according to the support item of the asset class combination in the asset class combination data set, and deleting the asset classes of which the support degree is less than a preset support degree and the support items are less than a second preset value in the candidate item set;
moving the asset class of the candidate item set into a frequent item set and emptying the candidate item set;
recording two asset class combinations obtained by combining the asset classes in the frequent item set in pairs in a two item candidate item set;
determining a support item of each two-item asset class combination in the two-item candidate items according to the support items of the asset class combinations in the asset class combination data set, and deleting the two-item asset class combination of which the support degree is less than the preset support degree and the support item is less than the second preset value in the two-item candidate items;
updating the incidence relation table according to the two candidate item sets;
moving the two-item asset class combination in the two-item candidate item set into a two-item frequent item set, and emptying the two-item candidate item set;
recording K asset class combinations obtained by pairwise combination of first K-2 identical K-1 asset class combinations in the K-1 frequent item set in the K candidate item set; wherein K is a positive integer greater than 2;
determining a support item of each K asset class combination in the K candidate items according to the support items of the asset class combinations in the asset class combination data set, and deleting the K asset class combinations with the support degrees smaller than the preset support degree and the support items smaller than the second preset value in the K candidate items;
updating the incidence relation table according to the K item candidate item set;
moving the K asset class combinations in the K candidate item sets into K frequent item sets, and emptying the K candidate item sets;
and when the support items of the K asset class combinations in the K candidate item sets are all smaller than the second preset value or the K value is larger than a third preset value, stopping generating the next-level candidate item set.
6. The method of claim 5, wherein the association table further comprises an update override identifier of the asset class, wherein the update override identifier comprises overrideable and non-overrideable;
updating the association table according to the H item candidate item, including:
comparing the asset class in the frequent item set with the asset class in the association relationship table, and removing the asset class of which the update coverage identifier is not covered in the frequent item set as a total asset class set;
sequentially selecting each asset class in the asset class total set, searching the H asset class combination containing the selected asset class in the H candidate item set, and taking the H asset class combination with the largest supported item as the selected H asset class combination; wherein H is a positive integer greater than 1;
determining the asset classes other than the selected asset class in the selected H asset class combination as the associated asset classes of the selected asset classes;
if the association relation table contains the selected asset type, updating the corresponding association asset type combination by using the corresponding association asset type;
if the selected asset type is not contained in the association relationship table, the selected asset type is newly added in the association relationship table, the corresponding association asset type is set as the corresponding association asset type combination, and the update coverage mark is set to be covered.
7. The method of claim 1, wherein recommending to the user an asset class item associated with the selected asset class based on the user's current application form asset class portfolio, the selected asset class in the current application form asset class portfolio, and the incidence relation table comprises:
according to the selected asset type, inquiring the corresponding associated asset type combination in the association relation table;
comparing the associated asset class portfolio to the current application form asset class portfolio, recommending to a user the material class items that appear in the associated asset class portfolio and not appear in the current application form asset class portfolio.
8. An item recommendation device, comprising:
the incidence relation table generating module is used for acquiring a preset asset class combination and generating an incidence relation table; wherein the incidence relation table comprises asset classes and incidence asset class combinations;
the asset class combination data set determining module is used for determining an asset class combination data set according to an asset class combination of an asset application form in preset time;
the incidence relation table updating module is used for updating the incidence relation table according to the asset class combination data set based on a preset recommendation set algorithm;
and the article recommending module is used for recommending the asset class articles related to the selected asset class to the user according to the current application form asset class combination of the user, the selected asset class in the current application form asset class combination and the association relation table.
9. The apparatus of claim 8, wherein the asset class portfolio dataset determination module comprises:
the asset type combination acquiring unit is used for extracting asset types from the asset application form within preset time and acquiring asset type combinations in the asset application form;
the asset class combination data set generating unit is used for generating the asset class combination data set according to the acquired asset class combination; wherein the asset class portfolio data set includes support items for each of the asset class portfolios.
10. The apparatus of claim 9, further comprising:
the newly-added asset type combination extraction module is used for extracting an asset type combination in a newly-added application form if the newly-added asset application form is obtained;
and the asset class combination data set updating module is used for updating the asset class combination data set in the following mode according to the asset class combination in the newly added application form:
when the asset class combination data set contains the asset class combination in the newly added application form, increasing the corresponding support items of the asset class combination in the asset class combination data set by corresponding quantity;
and when the asset type combination data set does not contain the asset type combination in the newly-added application form, newly adding a corresponding data type combination record in the asset type combination data set, and setting a corresponding support item.
11. The apparatus of claim 10, further comprising:
and the asset class combination filtering module is used for deleting the asset class combinations with the item number smaller than a first preset value in the asset class combination data set after the asset class combination data set is updated.
12. The apparatus according to claim 8, wherein the association table updating module is specifically configured to:
recording each of the asset classes present in the asset class portfolio data set in a candidate set;
determining a support item of each asset class in the candidate item set according to the support item of the asset class combination in the asset class combination data set, and deleting the asset classes of which the support degree is less than a preset support degree and the support items are less than a second preset value in the candidate item set;
moving the asset class of the candidate item set into a frequent item set and emptying the candidate item set;
recording two asset class combinations obtained by combining the asset classes in the frequent item set in pairs in a two item candidate item set;
determining a support item of each two-item asset class combination in the two-item candidate items according to the support items of the asset class combinations in the asset class combination data set, and deleting the two-item asset class combination of which the support degree is less than the preset support degree and the support item is less than the second preset value in the two-item candidate items;
updating the incidence relation table according to the two candidate item sets;
moving the two-item asset class combination in the two-item candidate item set into a two-item frequent item set, and emptying the two-item candidate item set;
recording K asset class combinations obtained by pairwise combination of first K-2 identical K-1 asset class combinations in the K-1 frequent item set in the K candidate item set; wherein K is a positive integer greater than 2;
determining a support item of each K asset class combination in the K candidate items according to the support items of the asset class combinations in the asset class combination data set, and deleting the K asset class combinations with the support degrees smaller than the preset support degree and the support items smaller than the second preset value in the K candidate items;
updating the incidence relation table according to the K item candidate item set;
moving the K asset class combinations in the K candidate item sets into K frequent item sets, and emptying the K candidate item sets;
and when the support items of the K asset class combinations in the K candidate item sets are all smaller than the second preset value or the K value is larger than a third preset value, stopping generating the next-level candidate item set.
13. The apparatus according to claim 12, wherein the association relationship table further comprises an update override identifier of the asset class, wherein the update override identifier comprises overrideable and non-overrideable;
the association table updating module is specifically configured to:
updating the association table according to the H item candidate item, including:
comparing the asset class in the frequent item set with the asset class in the association relationship table, and removing the asset class of which the update coverage identifier is not covered in the frequent item set as a total asset class set;
sequentially selecting each asset class in the asset class total set, searching the H asset class combination containing the selected asset class in the H candidate item set, and taking the H asset class combination with the largest supported item as the selected H asset class combination; wherein H is a positive integer greater than 1;
determining the asset classes other than the selected asset class in the selected H asset class combination as the associated asset classes of the selected asset classes;
if the association relation table contains the selected asset type, updating the corresponding association asset type combination by using the corresponding association asset type;
if the selected asset type is not contained in the association relationship table, the selected asset type is newly added in the association relationship table, the corresponding association asset type is set as the corresponding association asset type combination, and the update coverage mark is set to be covered.
14. The apparatus of claim 8, wherein the item recommendation module is specifically configured to:
according to the selected asset type, inquiring the corresponding associated asset type combination in the association relation table;
comparing the associated asset class portfolio to the current application form asset class portfolio, recommending to a user the material class items that appear in the associated asset class portfolio and not appear in the current application form asset class portfolio.
15. An item recommendation device, characterized in that the item recommendation device comprises:
one or more processors;
a memory for storing one or more programs;
when executed by the one or more processors, cause the one or more processors to implement the item recommendation method of any one of claims 1-7.
16. A storage medium containing computer-executable instructions for performing the item recommendation method of any one of claims 1-7 when executed by a computer processor.
CN202110563543.4A 2021-05-24 2021-05-24 Article recommendation method, device, equipment and storage medium Pending CN113177828A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110563543.4A CN113177828A (en) 2021-05-24 2021-05-24 Article recommendation method, device, equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110563543.4A CN113177828A (en) 2021-05-24 2021-05-24 Article recommendation method, device, equipment and storage medium

Publications (1)

Publication Number Publication Date
CN113177828A true CN113177828A (en) 2021-07-27

Family

ID=76929700

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110563543.4A Pending CN113177828A (en) 2021-05-24 2021-05-24 Article recommendation method, device, equipment and storage medium

Country Status (1)

Country Link
CN (1) CN113177828A (en)

Similar Documents

Publication Publication Date Title
US8103704B2 (en) Method for database consolidation and database separation
US20140351261A1 (en) Representing enterprise data in a knowledge graph
US9280551B2 (en) De-duplication deployment planning
US20160162507A1 (en) Automated data duplicate identification
CN111008253A (en) Data model generation method, data warehouse generation device and electronic equipment
WO2020259325A1 (en) Feature processing method applicable to machine learning, and device
CN112269805A (en) Data processing method, device, equipment and medium
US20210334292A1 (en) System and method for reconciliation of data in multiple systems using permutation matching
CN110990403A (en) Business data storage method, system, computer equipment and storage medium
US9158599B2 (en) Programming framework for applications
US10679230B2 (en) Associative memory-based project management system
KR20140058408A (en) Method, system and computer program to provide fares detection from rules attributes
US20040002983A1 (en) Method and system for detecting tables to be modified
JP6153331B2 (en) Project management system based on associative memory
CN113177828A (en) Article recommendation method, device, equipment and storage medium
US9852166B2 (en) Task handling in a multisystem environment
CN113434585B (en) Resource preservation method and equipment
CN113780950A (en) Data processing method, device, server and readable storage medium
US20070226085A1 (en) System and method for automated mapping of data in a multi-valued data structure
US10430775B1 (en) Validation and lookup techniques for rule-based data categorization
WO2020101478A1 (en) System and method for managing duplicate entities based on a relationship cardinality in production knowledge base repository
US20190079967A1 (en) Aggregation and deduplication engine
CN112131215A (en) Bottom-up database information acquisition method and device
US11551464B2 (en) Line based matching of documents
US20070214139A1 (en) System and method for mapping data in a multi-valued data structure

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination