CN117011019B - Bank architecture self-adaptive analysis management system and method based on big data - Google Patents
Bank architecture self-adaptive analysis management system and method based on big data Download PDFInfo
- Publication number
- CN117011019B CN117011019B CN202311265271.5A CN202311265271A CN117011019B CN 117011019 B CN117011019 B CN 117011019B CN 202311265271 A CN202311265271 A CN 202311265271A CN 117011019 B CN117011019 B CN 117011019B
- Authority
- CN
- China
- Prior art keywords
- user
- service recommendation
- information
- user information
- duty ratio
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 40
- 238000004458 analytical method Methods 0.000 title claims abstract description 37
- 239000013598 vector Substances 0.000 claims description 24
- 230000008859 change Effects 0.000 claims description 18
- 238000007726 management method Methods 0.000 claims description 13
- 230000003044 adaptive effect Effects 0.000 claims description 7
- 230000004927 fusion Effects 0.000 claims description 6
- 238000012795 verification Methods 0.000 claims description 5
- 230000007246 mechanism Effects 0.000 claims description 4
- 230000000694 effects Effects 0.000 abstract description 4
- 230000008901 benefit Effects 0.000 description 10
- 230000009471 action Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000012937 correction Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000013475 authorization Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 150000001875 compounds Chemical class 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- PCHJSUWPFVWCPO-UHFFFAOYSA-N gold Chemical compound [Au] PCHJSUWPFVWCPO-UHFFFAOYSA-N 0.000 description 1
- 239000010931 gold Substances 0.000 description 1
- 229910052737 gold Inorganic materials 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000012954 risk control Methods 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
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
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/02—Banking, e.g. interest calculation or account maintenance
-
- 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
- G06F16/283—Multi-dimensional databases or data warehouses, e.g. MOLAP or ROLAP
-
- 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
- G06F16/285—Clustering or classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/60—Protecting data
- G06F21/602—Providing cryptographic facilities or services
-
- 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
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Databases & Information Systems (AREA)
- Development Economics (AREA)
- Strategic Management (AREA)
- General Engineering & Computer Science (AREA)
- Economics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Life Sciences & Earth Sciences (AREA)
- Entrepreneurship & Innovation (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Technology Law (AREA)
- Game Theory and Decision Science (AREA)
- Health & Medical Sciences (AREA)
- Bioethics (AREA)
- General Health & Medical Sciences (AREA)
- Computer Hardware Design (AREA)
- Computer Security & Cryptography (AREA)
- Software Systems (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a bank architecture self-adaptive analysis management system and method based on big data, relating to the technical field of bank architecture, wherein the system comprises: the system comprises a data warehouse, an analysis module, a mobile terminal and a safety module, wherein the output end of the data warehouse is connected with the input end of the analysis module and is used for storing information of a user; the analysis module is connected with the mobile terminal, and user experience is improved based on information of a user; the output end of the mobile terminal is connected with the input end of the data warehouse and is used for interacting with a user and providing personalized services; the safety module is connected with the mobile terminal and is used for protecting the identity information and fund safety of a user; according to the invention, the personalized service recommendation suitable for the specific user is determined through the historical big data, and the personalized service recommendation is optimized by utilizing the subsequent information of the specific user, so that the effect of personalized service recommendation is improved, and the effect of improving user experience is achieved.
Description
Technical Field
The invention relates to the technical field of bank architecture, in particular to a bank architecture self-adaptive analysis management system and method based on big data.
Background
The bank architecture refers to the overall architecture data of the bank in the aspects of business, organization, data, application, data and the like, the design and optimization of the bank architecture need to consider various factors such as business requirements, compliance requirements, technical development trends and the like, and a reasonable bank architecture can help the bank to achieve the goals of business growth, risk control, innovation competition and the like and provide good user experience and service quality; in a business architecture of a bank, different business fields related to the bank are defined, so that the requirements of customers on different businesses are met, and the experience of the users is improved; improving user experience can bring many advantages to banks, including improving customer loyalty, increasing bank competitiveness, improving bank brand image, etc.; however, the initiative of the banking architecture is insufficient, and the customer is usually not easy to acquire the service information required by the customer in response to the requirement of the customer passively; how to automatically provide user information of customer demands for different customers becomes a problem to be solved.
Disclosure of Invention
The invention aims to provide a bank architecture self-adaptive analysis management system and method based on big data, so as to solve the problems in the background technology.
A big data based bank architecture adaptive analysis management system, comprising: the system comprises a data warehouse, an analysis module, a mobile terminal and a security module; the output end of the data warehouse is connected with the input end of the analysis module, and is used for storing information of a user and sending the information of the user to the analysis module; the analysis module is connected with the mobile terminal and automatically adjusts the working state of the mobile terminal based on the information of the user so as to improve the user experience; the output end of the mobile terminal is connected with the input end of the data warehouse and is used for acquiring information of authorized users, sending the user information to the data warehouse and the analysis module, interacting with the users and providing services; the security module is connected with the mobile terminal and is used for storing account information of a user and carrying out identity verification on the mobile terminal so as to protect identity information and fund security of the user.
Specifically, the mobile terminal further comprises a mobile application program, a user is allowed to perform banking operation through the mobile terminal, and personalized service recommendation is provided for the user according to the analysis result of the analysis module, so that user experience is improved; the mobile application is also used to collect information generated when the mobile application is used by an authorized user.
Specifically, the analysis module analyzes the user information stored in the data warehouse, determines the general service recommendation and the special service recommendation, and obtains the duty ratio of various service information most suitable for the user after fusion so as to provide personalized service recommendation.
Specifically, the mobile application program circularly displays various service information on the mobile application program according to the duty ratio of the various service information most suitable for the user, and provides a window for actively switching the service information for the user so as to improve the user experience.
A bank architecture self-adaptive analysis management method based on big data specifically comprises the following steps:
s5-1, integrating different mobile terminals, and synchronizing information of a user on the different mobile terminals by adopting a unified account and identity authentication mechanism on the different mobile terminals so as to realize that the user can enjoy the same service on the different mobile terminals; the mobile terminal comprises a smart phone, a tablet, a computer and other devices;
s5-2, analyzing information of the user, and determining requirements of the user so as to improve user experience; the mobile application program on the mobile terminal explains the acquired information to the user for improving the use experience of the user, and acquires the information generated when the user uses the mobile application program through the authorization of the user;
s5-3, based on the analysis result of the user demand in the step S5-2, personalized service recommendation is carried out, and a service information interface required by the user is provided on the mobile terminal;
s5-4, perfecting a security architecture, adopting an account of a user as a security verification mechanism, and carrying out encryption protection on user information.
Specifically, in step S5-3, personalized service recommendation is performed, and the method further includes the following steps:
s7-1, respectively extracting main characteristics x of the user information from the user information and the rest of the user information stored in the data warehouse 1 Slave features x 2 ，x 3 ，…，x n Main features x of remaining user information stored in data warehouse 1 Λ (i) Slave features x 2 Λ (i)，x 3 Λ (i)，…，x n Λ (i) Wherein n-1 is the number of slave features; the value range of i is [1, qu 1]]Positive integer between, qu1 is the main feature x of the rest of the user information stored in the data warehouse 1 Λ (i) Slave features x 2 Λ (i)，x 3 Λ (i)，…，x n Λ (i) Formed characteristic data points [ x 1 Λ (i),x 2 Λ (i)，x 3 Λ (i)，…，x n Λ (i)]Is the number of (3); main feature x 1 Is the input of the method, the subordinate feature x 2 ，x 3 ，…，x n Is the output of the method, when the slave feature x 2 ，x 3 ，…，x n For multiple occurrences, for optimizing the convergence of generic and specific service recommendations, the subordinate features x 2 ，x 3 ，…，x n When first appearing, the compound has no special effect;
s7-2, extracting main feature x 1 Λ (i) Is located in interval x 1 -Δ,x 1 +Δ]Feature data points [ x ] of the remaining user information stored in the data warehouse in 1 Λ (i),x 2 Λ (i)，x 3 Λ (i)，…，x n Λ (i)]The method comprises the steps of carrying out a first treatment on the surface of the 2 delta is the interval length; main feature x 1 Λ (i) And x 1 Is discrete data, which may not be identical, and therefore requires the determination of a principal feature x 1 The interval in which the rate of change of the slave features is small;
s7-3, calculating all characteristic data points [ x ] 1 Λ (i),x 2 Λ (i)，x 3 Λ (i)，…，x n Λ (i)]Dissimilarity dis, dis= v [ (x) with user information feature data points 2 -x 2 Λ (i)) 2 +…+(x n -x n Λ (i)) 2 ]/|x 1 -x 1 Λ (i) I (I); slave feature x 2 ，x 3 ，…，x n Is the output that the method needs to obtain, and therefore the dissimilarity dis and the data point [ x ] 2 ，x 3 ，…，x n ]And [ x ] 2 Λ (i)，x 3 Λ (i)，…，x n Λ (i)]The Euclidean distance between the two features becomes positive correlation, and the smaller the Euclidean distance is, the subordinate feature [ x 2 ，x 3 ，…，x n ]And [ x ] 2 Λ (i)，x 3 Λ (i)，…，x n Λ (i)]The closer the match, the higher the match, and vice versa; i x 1 -x 1 Λ (i) I is the correction coefficient of Euclidean distance, and I x 1 -x 1 Λ (i) I is inversely related to dissimilarity dis, |x 1 -x 1 Λ (i) The larger the I, the larger the matching degree, the smaller the dissimilarity dis, since the distance x is the same Euclidean distance 1 The characteristic data points of the far rest of the user information reach a distance x 1 The same Euclidean distance of the characteristic data points of the near rest user information, which illustrates the distance x 1 The matching degree of the far characteristic data point and the user information characteristic data point is higher, and vice versa; i x 1 -x 1 Λ (i) When the I is used as the correction coefficient of the Euclidean distance, calculating by adopting normalized data;
s7-4, determining a special service recommendation by adopting the characteristic data points with dissimilarity dis smaller than a threshold dis0 in the step S7-3, and determining a general service recommendation by adopting all the characteristic data points in the step S7-3.
Specifically, in step S5-3, personalized service recommendation is performed, and the method further includes the following steps:
s10-1, acquiring that main features are located in interval [ x ] 1 -Δ,x 1 +Δ]The duty ratio of the various services of the other users stored in the data warehouse in the system, and the average value p of the duty ratio of the various services of the other users is calculated 1 ，p 2 ，…，p m As a general service recommendation, the interval [ x ] is calculated 1 -Δ,x 1 +Δ]The average value q of the duty ratios of various services of users with dissimilarity dis smaller than a threshold dis0 1 ，q 2 ，…，q m Recorded as a first duty ratio, used as a special service recommendation, and the average value of dissimilarity dis under the first duty ratio is calculated and recorded as mu<dis 1 >Wherein m is the number of service types;
s10-2, fusing general service recommendation and special service recommendation to obtain the duty ratio r of various services recommended by personalized service 1 ，r 2 ，…，r m ，r b =Up b +Vq b The method comprises the steps of carrying out a first treatment on the surface of the Wherein b has a value of [1, m]The positive integer between U and V are the connection weights of the general service recommendation and the special service recommendation, and the initial value is set by itself;
s10-3, when the main feature of the user information is represented by x 1 Becomes x 1 At ' time, at this time Δ becomes Δ ', Δ ' =x 1 ' x R2, R2 is the main feature change rate, and the main feature is obtained and located in the interval [ x ] 1 ’-Δ’,x 1 ’+Δ’]The duty ratio of the various services of the other users stored in the data warehouse in the system is calculated again as the average value of the duty ratio of the various services of the other users and recorded as p 1 1 ，p 2 1 ，…，p m 1 As a generic service recommendation;
for interval [ x ] in step S10-1 1 -Δ,x 1 +Δ]User information whose dissimilarity is smaller than the threshold dis0,
if in section [ x ] 1 ’-Δ’,x 1 ’+Δ’]If the user information exists, the user in the interval x is acquired 1 ’-Δ’,x 1 ’+Δ’]Average q of the duty ratios of various services 1 1 ，q 2 1 ，…，q m 1 The second duty ratio is recorded as a special service recommendation, and the average value of dissimilarity under the second duty ratio is calculated and recorded as mu<dis 2 >Adjusting the connection weights U and V to obtainTo U (U) 1 And V 1 ，V 1 =V×[1+(μ<dis 1 >-μ<dis 2 >)/μ<dis 2 >]，U 1 =1-V 1 The method comprises the steps of carrying out a first treatment on the surface of the Fusing special service recommendation and general service recommendation to obtain the duty ratio r of various services of personalized service recommendation 1 1 ，r 2 1 ，…，r m 1 ，r b 1 =U 1 p b 1 +V 1 q b 1 The method comprises the steps of carrying out a first treatment on the surface of the Various services are presented on the mobile terminal according to the duty ratio of the services;
if in section [ x ] 1 ’-Δ’,x 1 ’+Δ’]If the user information does not exist, acquiring the interval [ x ] 1 ’-Δ’,x 1 ’+Δ’]Average value q of duty ratio of various services of user with dissimilarity smaller than threshold value dis0 1 2 ，q 2 2 ，…，q m 2 The second duty ratio is recorded as a special service recommendation, and the average value of dissimilarity under the second duty ratio is calculated and recorded as mu<dis 3 >Adjusting the connection weights U and V to obtain U 2 And V 2 ，V 2 =V×[1+(μ<dis 1 >-μ<dis 3 >)/μ<dis 3 >]，U 2 =1-V 2 The method comprises the steps of carrying out a first treatment on the surface of the Fusing special service recommendation and general service recommendation to obtain the duty ratio r of various services of personalized service recommendation 1 2 ，r 2 2 ，…，r m 2 ，r b 2 =U 2 p b 1 +V 2 q b 2 The method comprises the steps of carrying out a first treatment on the surface of the Various services are presented on the mobile terminal according to the duty ratio of the services;
the average value of the dissimilarity is used for measuring the matching degree between the special service recommendation and the user, when the average value of the dissimilarity is reduced, the matching degree between the special service recommendation and the user is described to be increased, the connection weight of the special service recommendation is also increased, and vice versa; for interval [ x ] in step S10-1 1 -Δ,x 1 +Δ]User information whose dissimilarity is smaller than threshold dis0 in section [ x ] 1 ’-Δ’,x 1 ’+Δ’]The presence of user information in the data warehouse, i.e. indicating the possible presence thereofThe requirements of the rest users are consistent with the requirements of the users at this time, and the requirements can be used as references for providing personalized services; for interval [ x ] in step S10-1 1 -Δ,x 1 +Δ]User information whose dissimilarity is smaller than threshold dis0 in section [ x ] 1 ’-Δ’,x 1 ’+Δ’]If the user information does not exist, the requirements of other users in the data warehouse are not completely consistent with the requirements of the user, and only the interval x can be used 1 ’-Δ’,x 1 ’+Δ’]And (5) carrying out personalized service recommendation on the rest user data with dissimilarity smaller than the threshold value dis 0.
Specifically, in step S5-3, personalized service recommendations are provided for the user, comprising the following analysis steps:
s6-1, acquiring user information and information of other users stored in a data warehouse;
s6-2, analyzing the correlation between the user information and the rest of user information stored in the data warehouse, and determining the general service recommendation and the special service recommendation of the user; the universal service recommendation has universality, is suitable for most users, has specificity, is suitable for certain fixed types of users, and is used for meeting the requirements of the users;
s6-3, fusing the general service recommendation and the special service recommendation, and providing personalized service recommendation for the user;
s6-4, when the user information changes, adjusting the fusion mode of the general service recommendation and the special service recommendation; when the user information changes, the data about the user is increased at the moment, the correlation between the general service recommendation and the special service recommendation and the user can be analyzed according to the increased data, and the fusion mode is optimized to better describe the user requirements;
s6-5, analyzing the correlation between the user information and the rest of user information stored in the data warehouse again, determining new general service recommendation and special service recommendation, and fusing the new general service recommendation and special service recommendation in an adjusted fusion mode to provide personalized service recommendation for the user.
Specifically, in step S7-2, the interval [ x ] 1 -Δ,x 1 +Δ]The determination is made by:
s8-1, characteristic data points [ x ] of the remaining user information stored in the data warehouse 1 Λ (i),x 2 Λ (i)，x 3 Λ (i)，…，x n Λ (i)]By main feature x 1 Λ (j) For the target, calculating the subordinate feature x when the main features are the same 2 Λ (i)，x 3 Λ (i)，…，x n Λ (i) Mean. Mu.of (A)<x 2 (j)>，μ<x 3 (j)>，…，μ<x n (j)>Obtaining a mean value vector [ x ] 1 Λ (j),μ<x 2 (j)>，μ<x 3 (j)>，…，μ<x n (j)>]The method comprises the steps of carrying out a first treatment on the surface of the Wherein j is a subset of i, and q 2 is the number of qu2, and qu2 is the main feature x with different information of other users stored in the data warehouse 1 Λ (i) Is equal to or less than qu1 in terms of qu 2;
s8-2, according to main feature x 1 Λ (j) Sequential pair average value vector from small to large [ x ] 1 Λ (j),μ<x 2 (j)>，μ<x 3 (j)>，…，μ<x n (j)>]Arranging;
s8-3, calculating the sum R1 of all the absolute values of the subordinate feature change rates of the previous average value vector and the subsequent average value vector from the second average value vector to obtain a relation vector [ R2, R1] of the subordinate feature change rate and the main feature change rate R2;
s8-4, arranging vectors [ R2, R1] in the order of from small to large of R1, and finding out a corresponding main characteristic change rate R2 when R1 is greater than or equal to a threshold L, wherein the threshold L is set by itself;
s8-5, determining interval [ x ] 1 -Δ,x 1 +Δ]，Δ=x 1 X R2; obtain interval [ x ] 1 -x 1 ×R2,x 1 +x 1 ×R2]。
Specifically, in step S7-4, the threshold dis0 is determined by:
s9-1, acquisition interval [ x ] 1 -Δ,x 1 +Δ]Is stored in a data warehouseFeature data point [ x ] of the remaining user information of (a) 1 Λ (i),x 2 Λ (i)，x 3 Λ (i)，…，x n Λ (i)]And characteristic data point of user information [ x 1 ,x 2 ，x 3 ，…，x n ]；
S9-2, replacing Euclidean distance with dissimilarity dis, and classifying the data points in the step S9-1 in an unsupervised classification mode; the threshold dis0 is used to determine a specific service recommendation, i.e. to find a feature data point x with a high degree of matching with the user 1 Λ (i),x 2 Λ (i)，x 3 Λ (i)，…，x n Λ (i)]Therefore, the data points in the step S9-1 are classified by adopting an unsupervised classification mode, and characteristic data points [ x ] with high similarity to the data points in the step S9-1 are found 1 Λ (i),x 2 Λ (i)，x 3 Λ (i)，…，x n Λ (i)]；
S9-3, calculating characteristic data points [ x ] of the user information according to the classification result 1 ,x 2 ，x 3 ，…，x n ]Remaining feature data points [ x ] in the belonging classification cluster 1 Λ (k),x 2 Λ (k)，x 3 Λ (k)，…，x n Λ (k)]Feature data point [ x ] to user information 1 ,x 2 ，x 3 ，…，x n ]Selecting the maximum dissimilarity dis as a threshold dis0; where k is a subset of the range of values of i.
Compared with the prior art, the invention has the following beneficial effects: the general service recommendation and the special service recommendation suitable for the specific user are determined through the historical big data, the general service recommendation and the special service recommendation are fused to obtain the personalized service recommendation, meanwhile, the fusion mode is optimized by utilizing the follow-up information of the specific user, the effect of the personalized service recommendation is improved, and the user experience is improved.
Drawings
The accompanying drawings are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate the invention and together with the embodiments of the invention, serve to explain the invention. In the drawings:
fig. 1 is a schematic structural diagram of a bank architecture adaptive analysis management system based on big data.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
In the embodiment of the invention, a bank architecture self-adaptive analysis management method based on big data specifically comprises the following steps:
s5-1, integrating different mobile terminals together to realize that users can enjoy the same service on different mobile terminals; the mobile terminal comprises a smart phone, a tablet, a computer and other devices;
s5-2, analyzing information of the user, and providing personalized service recommendation for the user so as to improve user experience;
acquiring user information and information of other users stored in a data warehouse, and extracting main characteristics x of the user information 1 Slave feature x 2 、x 3 、x 4 、x 5 And x 6 Wherein the main feature x 1 The subordinate feature x is the sum of funds of the user 2 、x 3 、x 4 、x 5 And x 6 The main characteristics x of the rest user information stored in the data warehouse are extracted for the share of cash, the warranty type financial product, the fixed benefit type financial product, the floating benefit type financial product and the lever benefit type financial product in the user fund synthesis 1 Λ (i) Slave features x 2 Λ (i)，x 3 Λ (i)，…，x 6 Λ (i) The method comprises the steps of carrying out a first treatment on the surface of the Wherein i has a value in the range of [1, qu 1]]A positive integer therebetween;
next, the remaining user information stored in the data warehouse is used as main characteristic x 1 Λ (i) For the target, calculate the main feature x 1 Λ (i) Identical slave features x 2 Λ (i)，x 3 Λ (i)，…，x 6 Λ (i) Mean. Mu.of (A)<x 2 (j)>，μ<x 3 (j)>，…，μ<x 6 (j)>The method comprises the steps of carrying out a first treatment on the surface of the Wherein j is a subset of i, and q 2 is the number of qu2, and qu2 is the main feature x with different information of other users stored in the data warehouse 1 Λ (i) Is equal to or less than qu1 in terms of qu 2; obtaining a mean value vector [ x ] 1 Λ (j),μ<x 2 (j)>，μ<x 3 (j)>，…，μ<x 6 (j)>]The method comprises the steps of carrying out a first treatment on the surface of the For the following 5 remaining user information feature vectors: [500000,0.25,0.3,0.2,0.15,0.1]，[500000,0.25,0.28,0.21,0.16,0.1]，[510000, 0.25,0.25,0.2,0.18,0.12]，[520000,0.25,0.25,0.2,0.17,0.13]，[530000,0.25,0.24,0.2,0.17,0.14]After calculating the mean value, 4 mean value vectors are obtained [500000,0.25,0.29,0.205,0.155,0.1 ]]，[510000,0.25,0.25,0.2,0.18,0.12]，[520000,0.25,0.25,0.2,0.17,0.13]，[530000,0.25,0.24,0.2,0.17,0.14]；
According to main feature x 1 Λ (j) Sequential pair average value vector from small to large [ x ] 1 Λ (j),μ<x 2 (j)>，μ<x 3 (j)>，…，μ<x 6 (j)]>Arranging; starting from the second mean vector, calculating the sum R1 of the absolute values of all the subordinate feature change rates of the previous mean vector and the subsequent mean vector to obtain a relation vector of the subordinate feature change rate and the main feature change rate R2, and for [500000,0.25,0.29,0.205,0.155,0.1 ]]，[510000,0.25,0.25,0.2,0.18,0.12]Two mean vectors, r2= (510000-500000)/500000=0.02, r1= |0.25-0.25|/0.25+|0.25-0.29|/0.29+|0.2-0.205|/0.205+|0.18-0.155|/0.155+| 0.12-0.1|/0.1= 0.5236. Vector [ R2, R1] is aligned in order of decreasing R1]Arranging, when R1 is greater than or equal to a threshold L, finding out a corresponding main characteristic change rate R2, and when the threshold L is set to 0.5236, setting the main characteristic change rate R2 to be 0.02;
determining a user information main feature x according to the main feature change rate R2 1 Is defined in the following ranges: [0.98x 1 0.102x 1 ]The method comprises the steps of carrying out a first treatment on the surface of the When the main characteristic x of the user information 1 100000 the interval is [98000,102000 ]]Extracting main feature x 1 Λ (i) Located in interval [98000,102000 ]]Feature data points [ x ] of the remaining user information stored in the data warehouse in 1 Λ (i),x 2 Λ (i)，x 3 Λ (i)，…，x 6 Λ (i)]The method comprises the steps of carrying out a first treatment on the surface of the Calculating the average value p of the duty ratios of various services of other users 1 ，p 2 ，p 3 ，p 4 And p 5 P as a generic service recommendation 1 =∑x 2 Λ (i)/qu，…，p 5 =∑x 6 Λ (i) Wherein qu is interval [98000,102000 ]]Feature data points [ x ] of the remaining user information stored in the data warehouse in 1 Λ (i),x 2 Λ (i)，x 3 Λ (i)，…，x 6 Λ (i)]Is the number of (3);
calculate all characteristic data points [ x ] 1 Λ (i),x 2 Λ (i)，x 3 Λ (i)，…，x 6 Λ (i)]Dissimilarity dis, dis= v [ (x) with user information feature data points 2 -x 2 Λ (i)) 2 +…+(x 6 -x 6 Λ (i)) 2 ]/|x 1 -x 1 Λ (i)|；|x 1 -x 1 Λ (i) The I is normalized data, and the calculation formula is I x 1 -x 1 Λ (i)|=(|x 1 -x 1 Λ (i)| 0 -Δx min )/(Δx max -Δx min ) The method comprises the steps of carrying out a first treatment on the surface of the In |x 1 -x 1 Λ (i)| 0 Is the data before normalization; subtracting the main characteristic data stored in any two different data warehouses and taking an absolute value, wherein the minimum value is deltax min The maximum value is Deltax max ；
The Euclidean distance is replaced by dissimilarity dis, and the interval [98000,102000 ] is subjected to DBSCAN algorithm]Data warehouse in (a)Characteristic data points [ x ] of the remaining user information stored in the library 1 Λ (i),x 2 Λ (i)，x 3 Λ (i)，…，x 6 Λ (i)]Clustering to determine characteristic data points [100000, x ] of user information 2 ,x 3 ,x 4 ,x 5 ,x 6 ]Cluster to which it belongs, and will [100000, x 2 ,x 3 ,x 4 ,x 5 ,x 6 ]Characteristic data points [ x ] of the remaining user information in the belonging cluster 1 Λ (i),x 2 Λ (i)，x 3 Λ (i)，…，x 6 Λ (i)]The maximum value of dissimilarity dis with the user information characteristic data points is used as a threshold value dis0;
average q of duty ratio of various services extracting feature data points of rest user information with dissimilarity dis smaller than threshold dis0 1 ，q 2 ，q 3 ，q 4 And q 5 Calculation method and p 1 ，p 2 ，p 3 ，p 4 And p 5 Concordance, serving as a special service recommendation, and calculating the average mu of dissimilarity dis<dis 1 >；
Fusing special service recommendation and general service recommendation to obtain personalized service recommendation, setting initial values of connection weights U and V to be 0.5 and r 1 =0.5p 1 +0.5q 1 ，…，r 5 =0.5p 5 +0.5q 5 ，r 1 ，r 2 ，r 3 ，r 4 And r 5 Representing the share of the gold, the warranty type financial product, the fixed benefit type financial product, the floating benefit type financial product and the lever benefit type financial product respectively, when r 1 When the content is more than or equal to 0.5, the possibility of purchasing the financial product by the user is low, and the information of the financial product is not displayed on the mobile application program; when r is 1 When the content is less than 0.5, the information of the warranty type financial product, the fixed benefit type financial product, the floating benefit type financial product and the lever benefit type financial product is circularly displayed on the mobile application program, and the proportion of the display time is r 2 :r 3 :r 4 :r 5 Simultaneously, an active switching window is set, and a user is given an independent selection principleRights to property product information;
when the main characteristic of the user information is changed from 100000 to 200000, the total amount of funds of the user is changed, and the connection weights U and V are adjusted to obtain the main characteristic x possibly along with the change of the share of various financial products of the user 1 Λ (i) Located in interval [196000,204000 ]]The average value p of the ratios of the various services of the other users is calculated again according to the ratios of the various services of the other users stored in the data warehouse 1 1 ，p 2 1 ，p 3 1 ，p 4 1 And p 5 1 As a generic service recommendation;
interval of [98000,102000 ]]If the user information whose dissimilarity dis is smaller than the threshold dis0 is in the section [196000,204000 ]]At least 1 of the user information is present, the user is acquired in the interval [196000,204000 ]]Average q of the duty ratios of various services 1 1 ，q 2 1 ，q 3 1 ，q 4 1 And q 5 1 As a special service recommendation, the mean μ of dissimilarity dis is calculated<dis 2 >Adjusting the connection weights U and V to obtain U 1 And V 1 ，V 1 =0.5×[1+(μ<dis 1 >-μ<dis 2 >)/μ<dis 2 >]，U 1 =1-V 1 The method comprises the steps of carrying out a first treatment on the surface of the Fusing special service recommendation and general service recommendation to obtain the duty ratio r of various services of personalized service recommendation 1 1 ，r 2 1 ，r 3 1 ，r 4 1 And r 5 1 ，r 1 1 =U 1 p 1 1 +V 1 q 1 1 ，…，r 5 1 =U 1 p 5 1 +V 1 q 5 1 The method comprises the steps of carrying out a first treatment on the surface of the Various services are presented on the mobile terminal according to the duty ratio of the services
Interval of [98000,102000 ]]If the user information with dissimilarity smaller than the threshold dis0 is in the section [196000,204000 ]]If the user information does not exist, the section is acquired [196000,204000 ]]Dissimilarity dis of less than a thresholdAverage q of duty ratio of various services of user with value dis0 1 2 ，q 2 2 ，q 3 2 ，q 4 2 And q 5 2 As a special service recommendation, the mean mu of dissimilarity is calculated<dis 3 >Adjusting the connection weights U and V to obtain U 2 And V 2 ，V 2 =0.5×[1+(μ<dis 1 >-μ<dis 3 >)/μ<dis 3 >]，U 2 =1-V 2 The method comprises the steps of carrying out a first treatment on the surface of the Fusing special service recommendation and general service recommendation to obtain the duty ratio r of various services of personalized service recommendation 1 2 ，r 2 2 ，r 3 2 ，r 4 2 And r 5 2 ，r 1 1 =U 2 p 1 1 +V 2 q 1 2 ，…，r 5 1 =U 2 p 5 1 +V 2 q 5 2 The method comprises the steps of carrying out a first treatment on the surface of the And various services are presented on the mobile terminal according to the service duty ratio.
It is noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
Finally, it should be noted that: the foregoing description is only a preferred embodiment of the present invention, and the present invention is not limited thereto, but it is to be understood that modifications and equivalents of some of the technical features described in the foregoing embodiments may be made by those skilled in the art, although the present invention has been described in detail with reference to the foregoing embodiments. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (7)
1. The bank architecture self-adaptive analysis management method based on big data is characterized by comprising the following steps of:
s5-1, integrating different mobile terminals, and synchronizing information of a user on the different mobile terminals by adopting a unified account and identity verification mechanism on the different mobile terminals;
s5-2, analyzing information of the user and determining requirements of the user;
s5-3, based on the analysis result of the user demand in the step S5-2, personalized service recommendation is carried out, and a service information interface required by the user is provided on the mobile terminal;
s5-4, perfecting a security architecture, adopting an account of a user as a security verification mechanism, and carrying out encryption protection on user information;
in step S5-3, the personalized service recommendation further includes the following steps:
s7-1, respectively extracting main characteristics x of the user information from the user information and the rest of the user information stored in the data warehouse 1 Slave features x 2 ，x 3 ，…，x n Main features x of remaining user information stored in data warehouse 1 Λ (i) Slave features x 2 Λ (i)，x 3 Λ (i)，…，x n Λ (i) Wherein n-1 is the number of subordinate features; the value range of i is [1, qu 1]]Positive integer between, qu1 is the main feature x of the rest of the user information stored in the data warehouse 1 Λ (i) Slave features x 2 Λ (i)，x 3 Λ (i)，…，x n Λ (i) Formed characteristic data points [ x 1 Λ (i),x 2 Λ (i)，x 3 Λ (i)，…，x n Λ (i)]Is the number of (3);
s7-2, extracting main feature x 1 Λ (i) Is located in interval x 1 -Δ,x 1 +Δ]Is stored in a data warehouseFeature data point [ x ] of the remaining user information of (a) 1 Λ (i),x 2 Λ (i)，x 3 Λ (i)，…，x n Λ (i)]The method comprises the steps of carrying out a first treatment on the surface of the 2 delta is the interval length;
s7-3, calculating all characteristic data points [ x ] 1 Λ (i),x 2 Λ (i)，x 3 Λ (i)，…，x n Λ (i)]Dissimilarity dis with the user information feature data points,
dis＝√[(x 2 -x 2 Λ (i)) 2 +…+(x n -x n Λ (i)) 2 ]/|x 1 -x 1 Λ (i)|；
s7-4, determining special service recommendation by adopting characteristic data points with dissimilarity smaller than a threshold value dis0 in the step S7-3, and determining general service recommendation by adopting all characteristic data points in the step S7-3;
in step S5-3, the personalized service recommendation further includes the following steps:
s10-1, acquiring that main features are located in interval [ x ] 1 -Δ,x 1 +Δ]The duty ratio of the various services of the other users stored in the data warehouse in the system, and the average value p of the duty ratio of the various services of the other users is calculated 1 ，p 2 ，…，p m As a general service recommendation, the interval [ x ] is calculated 1 -Δ,x 1 +Δ]Average q of the duty ratios of various services of users with dissimilarity smaller than threshold dis0 1 ，q 2 ，…，q m As a special service recommendation, the first duty ratio is recorded, and the average value of dissimilarity under the first duty ratio is calculated and recorded as mu<dis 1 >Wherein m is the number of service types;
s10-2, fusing general service recommendation and special service recommendation to obtain the duty ratio r of various services recommended by personalized service 1 ，r 2 ，…，r m ，r b ＝Up b +Vq b The method comprises the steps of carrying out a first treatment on the surface of the Wherein b has a value of [1, m]The positive integer between U and V are the initial connection weights of the general service recommendation and the special service recommendation, and the initial values are set by themselves;
S10-3，when the main characteristic of the user information is represented by x 1 Becomes x 1 ’ At this time, delta becomes delta ’ ，Δ ’ ＝x 1 ’ X R2, R2 is the change rate of the main feature, and the main feature is obtained and located in the interval [ x ] 1 ’ -Δ ’ ,x 1 ’ +Δ ’ ]The duty ratio of the various services of the other users stored in the data warehouse in the system is calculated again as the average value of the duty ratio of the various services of the other users and recorded as p 1 1 ，p 2 1 ，…，p m 1 As a generic service recommendation;
for interval [ x ] in step S10-1 1 -Δ,x 1 +Δ]User information whose dissimilarity is smaller than the threshold dis0,
if in section [ x ] 1 ’ -Δ ’ ,x 1 ’ +Δ ’ ]If the user information exists, the user in the interval x is acquired 1 ’ -Δ ’ ,x 1 ’ +Δ ’ ]Average q of the duty ratios of various services 1 1 ，q 2 1 ，…，q m 1 As a special service recommendation, the average value of dissimilarity under the second duty ratio is calculated and recorded as mu<dis 2 >Adjusting the connection weights U and V to obtain U 1 And V 1 ，V 1 ＝V×[1+(μ<dis 1 >-μ<dis 2 >)/μ<dis 2 >]，U 1 ＝1-V 1 The method comprises the steps of carrying out a first treatment on the surface of the Fusing special service recommendation and general service recommendation to obtain the duty ratio r of various services of personalized service recommendation 1 1 ，r 2 1 ，…，r m 1 ，r b 1 ＝U 1 p b 1 +V 1 q b 1 The method comprises the steps of carrying out a first treatment on the surface of the Various services are presented on the mobile terminal according to the duty ratio of the services;
if in section [ x ] 1 ’ -Δ ’ ,x 1 ’ +Δ ’ ]If the user information does not exist, acquiring the interval [ x ] 1 ’ -Δ ’ ,x 1 ’ +Δ ’ ]Average value q of duty ratio of various services of user with dissimilarity smaller than threshold value dis0 1 2 ，q 2 2 ，…，q m 2 As a special service recommendation, the average value of dissimilarity under the third duty ratio is calculated and recorded as mu<dis 3 >Adjusting the connection weights U and V to obtain U 2 And V 2 ，V 2 ＝V×[1+(μ<dis 1 >-μ<dis 3 >)/μ<dis 3 >]，U 2 ＝1-V 2 The method comprises the steps of carrying out a first treatment on the surface of the Fusing special service recommendation and general service recommendation to obtain the duty ratio r of various services of personalized service recommendation 1 2 ，r 2 2 ，…，r m 2 ，r b 2 ＝U 2 p b 1 +V 2 q b 2 The method comprises the steps of carrying out a first treatment on the surface of the And various services are presented on the mobile terminal according to the service duty ratio.
2. The method for adaptively analyzing and managing bank architecture based on big data according to claim 1, wherein the interval [ x ] 1 -Δ,x 1 +Δ]The determination is made by:
s8-1, characteristic data points [ x ] of the remaining user information stored in the data warehouse 1 Λ (i),x 2 Λ (i)，x 3 Λ (i)，…，x n Λ (i)]By main feature x 1 Λ (j) For the target, calculating the subordinate feature x when the main features are the same 2 Λ (i)，x 3 Λ (i)，…，x n Λ (i) Mean. Mu.of (A)<x 2 (j)>，μ<x 3 (j)>，…，μ<x n (j)>Obtaining a mean value vector [ x ] 1 Λ (j),μ<x 2 (j)>，μ<x 3 (j)>，…，μ<x n (j)>]The method comprises the steps of carrying out a first treatment on the surface of the Wherein j is a subset of i, and q 2 is the number of qu2, and qu2 is the main feature x with different information of other users stored in the data warehouse 1 Λ (i) Is equal to or less than qu1 in terms of qu 2;
s8-2 according to the main modeFeature x 1 Λ (j) Sequential pair average value vector from small to large [ x ] 1 Λ (j),μ<x 2 (j)>，μ<x 3 (j)>，…，μ<x n (j)>]Arranging;
s8-3, calculating the sum R1 of all the absolute values of the subordinate feature change rates of the previous average value vector and the subsequent average value vector from the second average value vector to obtain a relation vector [ R2, R1] of the subordinate feature change rate and the main feature change rate R2;
s8-4, arranging vectors [ R2, R1] in the order of from small to large of R1, and finding out a corresponding main characteristic change rate R2 when R1 is greater than or equal to a threshold L, wherein the threshold L is set by itself;
s8-5, determining interval [ x ] 1 -Δ,x 1 +Δ]，Δ＝x 1 X R2; obtain interval [ x ] 1 -x 1 ×R2,x 1 +x 1 ×R2]。
3. The method for adaptively analyzing and managing a bank architecture based on big data according to claim 2, wherein the threshold dis0 is determined by:
s9-1, acquisition interval [ x ] 1 -Δ,x 1 +Δ]Feature data points [ x ] of the remaining user information stored in the data warehouse in 1 Λ (i),x 2 Λ (i)，x 3 Λ (i)，…，x n Λ (i)]And characteristic data point of user information [ x 1 ,x 2 ，x 3 ，…，x n ]；
S9-2, replacing Euclidean distance with dissimilarity, and classifying the data points in the step S9-1 in an unsupervised classification mode;
s9-3, calculating characteristic data points [ x ] of the user information according to the classification result 1 ,x 2 ，x 3 ，…，x n ]Remaining feature data points [ x ] in the belonging classification cluster 1 Λ (k),x 2 Λ (k)，x 3 Λ (k)，…，x n Λ (k)]Feature data point [ x ] to user information 1 ,x 2 ，x 3 ，…，x n ]Selecting the maximum dissimilarity dis as a threshold dis0; where k is a subset of the range of values of i.
4. A big data based bank architecture adaptive analysis management system, using a big data based bank architecture adaptive analysis management method according to any of claims 1-3, comprising: the system comprises a data warehouse, an analysis module, a mobile terminal and a security module; the output end of the data warehouse is connected with the input end of the analysis module, and is used for storing information of a user and sending the information of the user to the analysis module; the analysis module is connected with the mobile terminal and automatically adjusts the working state of the mobile terminal based on the information of the user so as to improve the user experience; the output end of the mobile terminal is connected with the input end of the data warehouse and is used for acquiring information of authorized users, sending the user information to the data warehouse and the analysis module, interacting with the users and providing personalized services; the security module is connected with the mobile terminal and is used for storing account information of a user and carrying out identity verification on the mobile terminal so as to protect identity information and fund security of the user.
5. The adaptive analysis management system for bank architecture based on big data according to claim 4, wherein the mobile terminal further comprises a mobile application program, allowing a user to perform banking operation through the mobile terminal, and providing personalized service recommendation for the user according to the analysis result of the analysis module, so as to improve user experience; the mobile application is also used to gather information of authorized users.
6. The adaptive analysis management system for bank architecture based on big data according to claim 4, wherein the analysis module analyzes the user information stored in the data warehouse to determine a general service recommendation and a specific service recommendation, and obtains the duty ratio of each type of service information most suitable for the user after the fusion, so as to provide personalized service recommendation.
7. The adaptive analysis management system for a bank architecture based on big data according to claim 5, wherein the mobile application program circularly displays various service information on the mobile application program according to the duty ratio of the various service information most suitable for the user, and provides a window for actively switching the service information to the user, so as to improve the user experience.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311265271.5A CN117011019B (en) | 2023-09-28 | 2023-09-28 | Bank architecture self-adaptive analysis management system and method based on big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311265271.5A CN117011019B (en) | 2023-09-28 | 2023-09-28 | Bank architecture self-adaptive analysis management system and method based on big data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117011019A CN117011019A (en) | 2023-11-07 |
| CN117011019B true CN117011019B (en) | 2023-12-22 |
Family
ID=88569387
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311265271.5A Active CN117011019B (en) | 2023-09-28 | 2023-09-28 | Bank architecture self-adaptive analysis management system and method based on big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117011019B (en) |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6092049A (en) * | 1995-06-30 | 2000-07-18 | Microsoft Corporation | Method and apparatus for efficiently recommending items using automated collaborative filtering and feature-guided automated collaborative filtering |
| KR20160090509A (en) * | 2015-01-22 | 2016-08-01 | 주식회사 디케이아이테크놀로지 | Personalized Advertisement Service System Using Sensitiveness-Based User Characteristic Analysis |
| CN107329994A (en) * | 2017-06-08 | 2017-11-07 | 天津大学 | A kind of improvement collaborative filtering recommending method based on user characteristics |
| CN109447728A (en) * | 2018-09-07 | 2019-03-08 | 平安科技（深圳）有限公司 | Financial product recommended method, device, computer equipment and storage medium |
| CN109636538A (en) * | 2018-12-20 | 2019-04-16 | 成都知数科技有限公司 | Bank product recommended method, device and server |
| CN111079009A (en) * | 2019-12-11 | 2020-04-28 | 中国地质大学（武汉） | User interest detection method and system for government map service |
| CN111143681A (en) * | 2019-12-27 | 2020-05-12 | 中国银行股份有限公司 | Information recommendation device, method, equipment and system |
| CN111191117A (en) * | 2019-12-11 | 2020-05-22 | 中国地质大学（武汉） | Accurate user interest detection method and system for government map service |
| CN114048389A (en) * | 2022-01-11 | 2022-02-15 | 山东捷瑞数字科技股份有限公司 | Content recommendation method and system for engineering machinery industry |
| CN114707074A (en) * | 2022-06-06 | 2022-07-05 | 深圳尚米网络技术有限公司 | Content recommendation method, device and system |
| CN115062238A (en) * | 2022-06-27 | 2022-09-16 | 中国工商银行股份有限公司 | Product recommendation method and device, computer equipment and storage medium |
| CN115271931A (en) * | 2022-08-17 | 2022-11-01 | 平安科技（深圳）有限公司 | Credit card product recommendation method and device, electronic equipment and medium |
| KR102484545B1 (en) * | 2021-11-23 | 2023-01-04 | 주식회사 룩코 | Similarity tendency based user recommendation method |
| CN116629964A (en) * | 2023-05-22 | 2023-08-22 | 哈尔滨源芯智能科技发展有限公司 | Personalized recommendation system and method based on data analysis |
-
2023
- 2023-09-28 CN CN202311265271.5A patent/CN117011019B/en active Active
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6092049A (en) * | 1995-06-30 | 2000-07-18 | Microsoft Corporation | Method and apparatus for efficiently recommending items using automated collaborative filtering and feature-guided automated collaborative filtering |
| KR20160090509A (en) * | 2015-01-22 | 2016-08-01 | 주식회사 디케이아이테크놀로지 | Personalized Advertisement Service System Using Sensitiveness-Based User Characteristic Analysis |
| CN107329994A (en) * | 2017-06-08 | 2017-11-07 | 天津大学 | A kind of improvement collaborative filtering recommending method based on user characteristics |
| CN109447728A (en) * | 2018-09-07 | 2019-03-08 | 平安科技（深圳）有限公司 | Financial product recommended method, device, computer equipment and storage medium |
| CN109636538A (en) * | 2018-12-20 | 2019-04-16 | 成都知数科技有限公司 | Bank product recommended method, device and server |
| CN111191117A (en) * | 2019-12-11 | 2020-05-22 | 中国地质大学（武汉） | Accurate user interest detection method and system for government map service |
| CN111079009A (en) * | 2019-12-11 | 2020-04-28 | 中国地质大学（武汉） | User interest detection method and system for government map service |
| CN111143681A (en) * | 2019-12-27 | 2020-05-12 | 中国银行股份有限公司 | Information recommendation device, method, equipment and system |
| KR102484545B1 (en) * | 2021-11-23 | 2023-01-04 | 주식회사 룩코 | Similarity tendency based user recommendation method |
| CN114048389A (en) * | 2022-01-11 | 2022-02-15 | 山东捷瑞数字科技股份有限公司 | Content recommendation method and system for engineering machinery industry |
| CN114707074A (en) * | 2022-06-06 | 2022-07-05 | 深圳尚米网络技术有限公司 | Content recommendation method, device and system |
| CN115062238A (en) * | 2022-06-27 | 2022-09-16 | 中国工商银行股份有限公司 | Product recommendation method and device, computer equipment and storage medium |
| CN115271931A (en) * | 2022-08-17 | 2022-11-01 | 平安科技（深圳）有限公司 | Credit card product recommendation method and device, electronic equipment and medium |
| CN116629964A (en) * | 2023-05-22 | 2023-08-22 | 哈尔滨源芯智能科技发展有限公司 | Personalized recommendation system and method based on data analysis |
Non-Patent Citations (2)
| Title |
|---|
| 协同过滤推荐系统在银行产品个性化服务中的应用;陈燕;马兴敏;宿媛媛;;数字通信世界(第06期);155、197 * |
| 陈燕 ; 马兴敏 ; 宿媛媛 ; .协同过滤推荐系统在银行产品个性化服务中的应用.数字通信世界.2018,(第06期),155、197. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117011019A (en) | 2023-11-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20210097603A1 (en) | System and method for issuing a loan to a consumer determined to be creditworthy and with bad debt forecast | |
| US20210174439A1 (en) | System and method for issuing a loan to a consumer determined to be creditworthy and generating a behavioral profile of that consumer | |
| US11587101B2 (en) | Platform for detecting abnormal entities and activities using machine learning algorithms | |
| US8131615B2 (en) | Incremental factorization-based smoothing of sparse multi-dimensional risk tables | |
| US20190073714A1 (en) | System and method for issuing a loan to a consumer determined to be creditworthy onto a transaction card | |
| US9792653B2 (en) | Recommender engine for collections treatment selection | |
| CN112862298B (en) | Credit evaluation method for user portrait | |
| US20180101907A1 (en) | Methods and Systems for Cluster-Based Historical Data | |
| WO2021167858A1 (en) | Transaction card system having overdraft capability | |
| US20230325796A1 (en) | Methods for determining user experience (ux) effectiveness of atms | |
| US20170270496A1 (en) | Instant funds availablity risk assessment and real-time fraud alert system and method | |
| CN114186626A (en) | Abnormity detection method and device, electronic equipment and computer readable medium | |
| CN117011019B (en) | Bank architecture self-adaptive analysis management system and method based on big data | |
| CA3018229A1 (en) | Dynamic provisioning of data exchanges based on detected relationships within processed image data | |
| US11822576B2 (en) | Database management for digitally storing item information | |
| CN115689708A (en) | Screening method, risk assessment method, device, equipment and medium of training data | |
| CN110728243B (en) | Business management method, system, equipment and medium for right classification | |
| CN110738561A (en) | service management method, system, equipment and medium based on characteristic classification | |
| CN114510650B (en) | Heterogeneous social network wind control processing method and system | |
| CN110767224B (en) | Service management method, system, equipment and medium based on characteristic right level | |
| KR102502986B1 (en) | User terminal and method for providing ui for insurance policy transaction | |
| KR102374068B1 (en) | System for providing blockchain based facial recognition payment service | |
| Gao et al. | Potential User Prediction for Financial APP Based on Random Forest Model | |
| US20220237445A1 (en) | Systems and methods for anomaly detection | |
| KR20230049889A (en) | Method, devce and system for generating customized financial product recommendation information based on big data and artificial intelligence |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |