CN113674066A - Recommendation method and system for mobile banking financing products - Google Patents
Recommendation method and system for mobile banking financing products Download PDFInfo
- Publication number
- CN113674066A CN113674066A CN202111039375.5A CN202111039375A CN113674066A CN 113674066 A CN113674066 A CN 113674066A CN 202111039375 A CN202111039375 A CN 202111039375A CN 113674066 A CN113674066 A CN 113674066A
- Authority
- CN
- China
- Prior art keywords
- product
- scoring matrix
- mobile phone
- matrix
- phone bank
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 52
- 239000011159 matrix material Substances 0.000 claims abstract description 206
- 238000012549 training Methods 0.000 claims abstract description 43
- 238000012545 processing Methods 0.000 claims description 24
- 238000000354 decomposition reaction Methods 0.000 claims description 20
- 238000010276 construction Methods 0.000 claims description 3
- 238000012163 sequencing technique Methods 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 8
- 238000012804 iterative process Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
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
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- 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
- G06Q20/00—Payment architectures, schemes or protocols
- G06Q20/08—Payment architectures
- G06Q20/10—Payment architectures specially adapted for electronic funds transfer [EFT] systems; specially adapted for home banking systems
- G06Q20/108—Remote banking, e.g. home banking
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Development Economics (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- General Business, Economics & Management (AREA)
- Mathematical Physics (AREA)
- Entrepreneurship & Innovation (AREA)
- Data Mining & Analysis (AREA)
- Educational Administration (AREA)
- Pure & Applied Mathematics (AREA)
- Marketing (AREA)
- Mathematical Optimization (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Computing Systems (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Algebra (AREA)
- Game Theory and Decision Science (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The invention discloses a recommendation method and a recommendation system for financial management products of a mobile phone bank, which can be applied to the field of big data. Acquiring the operation times of operating various mobile banking financial products by a user; constructing a first product scoring matrix according to the operation times corresponding to each mobile phone bank financing product; adding interference noise to each element in the first product scoring matrix to obtain a second product scoring matrix; performing iterative training by using a preset algorithm based on the second product scoring matrix until an iteration stopping condition is met, and obtaining the predicted operation times of each mobile phone bank financing product; recommending the first n mobile banking financial products with the highest predicted operation times to the user. The data of the user are protected, the mobile banking financial products can be recommended accurately, the safety of the data of the user is improved, and the user experience is improved.
Description
Technical Field
The invention relates to the technical field of big data, in particular to a recommendation method and a recommendation system for financial management products of a mobile phone bank.
Background
At present, when a mobile banking financial product is pushed by a mobile banking bank, all financial products are generally recommended to a user, but the number of financial products is large, the users need to spend a large amount of time to check all the financial products, and the user experience is poor. In addition, non-banking applications introduced by mobile banking at present can also use related data of users, which may cause leakage of user data and poor security of user data. And for bank users, most users who can buy financial products have certain economic strength, and the users do not want the possibility of leakage of personal privacy data, and the users can easily lose reputation for banks once the user data are leaked.
Disclosure of Invention
In view of this, embodiments of the present invention provide a method and a system for recommending a mobile banking financial product, so as to solve the problems of poor user experience, poor security of user data, and the like in the existing manner of recommending a mobile banking financial product.
In order to achieve the above purpose, the embodiments of the present invention provide the following technical solutions:
the embodiment of the invention discloses a recommendation method of mobile banking financial products in a first aspect, which comprises the following steps:
acquiring the operation times of operating various mobile phone bank financial products by a user, wherein the operation of the mobile phone bank financial products comprises the following steps: clicking the mobile phone bank financing product or purchasing the mobile phone bank financing product;
constructing a first product scoring matrix according to the operation times corresponding to each mobile phone bank financing product, wherein each element in the first product scoring matrix is the operation times corresponding to the mobile phone bank financing product;
adding interference noise to each element in the first product scoring matrix to obtain a second product scoring matrix;
performing iterative training by using a preset algorithm based on the second product scoring matrix until an iteration stopping condition is met, and obtaining the predicted operation times of each mobile phone bank financing product;
recommending the first n mobile banking financial products with the highest predicted operation times to the user.
Preferably, the adding interference noise to each element in the first product scoring matrix to obtain a second product scoring matrix includes:
executing the following steps, processing each element in the first product scoring matrix to obtain a second product scoring matrix;
the following steps include:
for each element in the first product scoring matrix, if the operation frequency corresponding to the element is 0, the element is not processed, and if the operation frequency corresponding to the element is not 0, laplacian noise is added to the element.
Preferably, the performing iterative training by using a preset algorithm based on the second product scoring matrix until an iteration stop condition is met to obtain the predicted operation times of each mobile banking financial product includes:
adding the second product scoring matrix into a matrix decomposition algorithm for iterative training until an iteration stop condition corresponding to a gradient descent algorithm is met, and obtaining a user data matrix and a product data matrix;
and multiplying the user data matrix and the product data matrix to obtain a third product scoring matrix, wherein each element of the third product scoring matrix is the predicted operation times of the mobile phone bank financing product.
Preferably, the method further comprises the following steps:
and in the process of adding the second product scoring matrix into a matrix decomposition algorithm for iterative training, adding Laplace noise to an intermediate result obtained by each iteration.
Preferably, before recommending the top n mobile banking financial products with the highest predicted operation times to the user, the method further includes:
and sequencing the mobile phone bank financing products based on the predicted operation times.
The second aspect of the embodiment of the invention discloses a recommendation system for mobile banking financial products, which comprises:
the acquiring unit is used for acquiring the operation times of operating each mobile phone bank financing product by a user, and the operation of operating the mobile phone bank financing product is as follows: clicking the mobile phone bank financing product or purchasing the mobile phone bank financing product;
the construction unit is used for constructing a first product scoring matrix according to the operation times corresponding to the mobile phone bank financing products, and each element in the first product scoring matrix is the operation times corresponding to the mobile phone bank financing products;
the adding unit is used for adding interference noise to each element in the first product scoring matrix to obtain a second product scoring matrix;
the processing unit is used for carrying out iterative training by using a preset algorithm based on the second product scoring matrix until an iteration stopping condition is met, and obtaining the predicted operation times of each mobile phone bank financing product;
and the recommending unit is used for recommending the first n mobile banking financial products with the highest predicted operation times to the user.
Preferably, the adding unit is specifically configured to: executing the following steps, processing each element in the first product scoring matrix to obtain a second product scoring matrix;
the following steps include:
for each element in the first product scoring matrix, if the operation frequency corresponding to the element is 0, the element is not processed, and if the operation frequency corresponding to the element is not 0, laplacian noise is added to the element.
Preferably, the processing unit includes:
the training module is used for adding the second product scoring matrix into a matrix decomposition algorithm for iterative training until an iteration stop condition corresponding to a gradient descent algorithm is met, and a user data matrix and a product data matrix are obtained;
and the processing module is used for multiplying the user data matrix and the product data matrix to obtain a third product scoring matrix, and each element of the third product scoring matrix is the predicted operation times of the mobile phone bank financing product.
Preferably, the processing unit further includes:
and the adding module is used for adding Laplace noise to the intermediate result obtained by each iteration in the process of adding the second product scoring matrix into the matrix decomposition algorithm for iterative training.
Preferably, the system further comprises:
and the sorting unit is used for sorting the mobile phone bank financing products based on the predicted operation times.
Based on the recommendation method and system for mobile banking financial products provided by the embodiment of the invention, the operation times of the user for operating each mobile banking financial product are obtained; constructing a first product scoring matrix according to the operation times corresponding to each mobile phone bank financing product; adding interference noise to each element in the first product scoring matrix to obtain a second product scoring matrix; performing iterative training by using a preset algorithm based on the second product scoring matrix until an iteration stopping condition is met, and obtaining the predicted operation times of each mobile phone bank financing product; recommending the first n mobile banking financial products with the highest predicted operation times to the user. According to the scheme, after a product scoring matrix is built by using data of a mobile phone bank financing product operated by a user, interference noise is added to the built product scoring matrix, then iterative training is carried out by using the disturbed product scoring matrix to obtain the predicted operation times of the mobile phone bank financing product, and finally the mobile phone bank financing product is recommended to the user according to the predicted operation times, so that the mobile phone bank financing product can be accurately recommended by using the data of the user, the safety of the user data is improved, and the user experience is improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
Fig. 1 is a flowchart of a recommendation method for a mobile banking financial product according to an embodiment of the present invention;
FIG. 2 is a flowchart of obtaining the number of predicted operations of a mobile banking financial product according to an embodiment of the present invention;
fig. 3 is a block diagram of a recommendation system for mobile banking financial products according to an embodiment of the present invention;
fig. 4 is another structural block diagram of a recommendation system for mobile banking financial products according to an embodiment of the present invention;
fig. 5 is a block diagram of another structure of a recommendation system for mobile banking financial products according to an embodiment of the present invention;
fig. 6 is a block diagram of another structure of a recommendation system for mobile banking financial products according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In this application, 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. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
It should be noted that the recommendation method and system for financial products in mobile banking provided by the invention can be used in the field of big data. The above is only an example, and the application field of the method and system for recommending financial products for mobile banking provided by the invention is not limited.
It can be known from the background art that when financial products of a mobile phone bank are pushed, all financial products can be recommended to a user together, the user needs to spend a large amount of time to check the financial products one by one, and the user experience is poor. In addition, non-banking applications introduced by mobile banking at present can also use related data of users, which may cause leakage of user data and poor security of user data.
Therefore, the embodiment of the invention provides a method and a system for recommending mobile phone bank financing products, wherein after a product scoring matrix is constructed by using data of a user operating the mobile phone bank financing products, interference noise is added to the constructed product scoring matrix, then iterative training is carried out by using the disturbed product scoring matrix to obtain the predicted operation times of the mobile phone bank financing products, and finally the mobile phone bank financing products are recommended to the user according to the predicted operation times, so that the data of the user are protected, the mobile phone bank financing products can also be accurately recommended, and the safety of the user data is improved and the user experience is improved.
Referring to fig. 1, a flowchart of a recommendation method for a mobile banking financial product according to an embodiment of the present invention is shown, where the recommendation method includes:
step S101: and acquiring the operation times of the user for operating each mobile phone bank financing product.
It should be noted that, operating a certain mobile phone bank financing product is: clicking the mobile phone bank financing product or purchasing the mobile phone bank financing product. That is to say, the operation times of each mobile banking financial product are as follows: the number of clicks of each mobile phone bank financing product, or the number of purchases of each mobile phone bank financing product.
In the process of implementing the step S101 specifically, operation history data of the user is acquired, and according to the acquired operation history data, the operation times of the user for operating each mobile banking financial product can be determined.
It should be noted that, for a certain mobile phone bank financial product provided to the user, the operation frequency of the user operating the mobile phone bank financial product may be 0 (that is, the user has not operated the mobile phone bank financial product), and the operation frequency of the user operating the mobile phone bank financial product may not be 0 (that is, the user has operated the mobile phone bank financial product).
That is, after the processing of step S101, the determined number of operations corresponding to a certain mobile banking product may or may not be 0.
Step S102: and constructing a first product scoring matrix according to the operation times corresponding to each mobile phone bank financing product.
It should be noted that each element in the first product scoring matrix is the operation frequency corresponding to the mobile banking financial product.
In the process of implementing step S102 specifically, a first product scoring matrix is constructed by using the operation times of the user operating each mobile banking financial product, and each element in the first product scoring matrix corresponds to the operation times corresponding to the mobile banking financial product.
That is to say, the first product scoring matrix includes the operation times corresponding to each mobile banking financial product, for example: assuming that the number of clicks (i.e., the number of operations) corresponding to the mobile banking product a is 0 and the number of clicks corresponding to the mobile banking product B is 10, the value of the element corresponding to the mobile banking product a in the first product scoring matrix is 0 and the value of the element corresponding to the mobile banking product B is 10.
It should be noted that, because the types and the number of the mobile banking financial products provided for the user are large, the user may only be interested in a small range of mobile banking financial products, and therefore, the values of more elements in the first product scoring matrix are 0, that is, more mobile banking financial products are not operated by the user, and the constructed first product scoring matrix may be regarded as a sparse matrix.
It can be understood that, in the first product scoring matrix, a row identifies a user, a column identifies a mobile banking product, and assuming that m users and m mobile banking products exist, the first product scoring matrix is a matrix of m × m, and since a certain user only operates certain mobile banking products in the m mobile banking products (that is, the mobile banking products in which the user is interested only relate to a small range), the first product scoring matrix can be regarded as a sparse matrix.
Step S103: and adding interference noise to each element in the first product scoring matrix to obtain a second product scoring matrix.
In the process of specifically implementing step S103, adding interference noise to each element in the first product scoring matrix to obtain a second product scoring matrix, where a specific manner of adding interference noise to each element in the first product scoring matrix is as follows: for each element in the first product scoring matrix, if the operation frequency corresponding to the element is 0, the element is not processed, and if the operation frequency corresponding to the element is not 0, laplacian noise is added to the element.
That is, the elements of the first product scoring matrix with the median of 0 do not add interference noise, and the elements of the first product scoring matrix with the median of non-0 add laplacian noise. Through the method, the data contained in the first product scoring matrix is subjected to privacy protection, and even if other applications intercept the first product scoring matrix, accurate data cannot be acquired, so that the user data is protected.
And (4) processing each element in the first product scoring matrix to obtain a second product scoring matrix.
In some embodiments, in the process of adding laplacian noise to the elements having values other than 0 in the first product scoring matrix, the laplacian noise function (or laplacian method) may be specifically used to add laplacian noise to the elements having values other than 0. When the laplacian noise is added by using the laplacian noise function, the privacy parameter and the sensitivity parameter need to be determined according to the actual situation to prevent the added laplacian noise from being too large or too small, that is, the laplacian noise is added on the premise of ensuring the safety and the usability of data. Specifically, for a first product scoring matrix, a laplacian noise matrix with the same dimension as the first product scoring matrix can be generated through a laplacian noise function, and a second product scoring matrix can be obtained by adding the first product scoring matrix and the laplacian noise matrix. For example: and assuming that the first product scoring matrix is an m x m matrix, generating an m x m laplacian noise matrix through a laplacian noise function, and adding the m x m laplacian noise matrix and the m x m laplacian noise matrix to obtain a second product scoring matrix.
Step S104: and based on the second product scoring matrix, performing iterative training by using a preset algorithm until an iteration stopping condition is met, and obtaining the predicted operation times of each mobile phone bank financing product.
In the process of implementing step S104, the second product scoring matrix (i.e., the first product scoring matrix added with the interference noise) is added to the preset algorithm to perform iterative training until the iteration stop condition is satisfied, so as to obtain the predicted operation times of each mobile banking financial product.
It should be noted that, as can be seen from the content in the foregoing step S102, a plurality of elements with a value of 0 (that is, the mobile banking financial product with an operation frequency of 0) exist in the first product scoring matrix, and through the processing in step S104, the predicted operation frequency of all mobile banking financial products (including the mobile banking financial product with the previous operation frequency of 0) can be obtained, and the predicted operation frequency of a certain mobile banking financial product can indicate the number of times that the mobile banking financial product is likely to be operated by the user.
In some embodiments, the preset algorithm for performing the iterative training may be a matrix decomposition algorithm, and the iteration stop condition may be a training termination condition (including at least the number of iterations and the amount of change) corresponding to the gradient descent algorithm.
That is to say, the second product scoring matrix is used as training data, iterative training is carried out through a matrix decomposition algorithm and a gradient descent algorithm, and finally the predicted operation times of each mobile banking financial product can be obtained.
Preferably, after obtaining the predicted operation times of each mobile phone bank financial product, sorting each mobile phone bank financial product based on the predicted operation times, for example: and sequencing the financial products of each mobile phone bank according to the sequence of the predicted operation times from high to low.
Step S105: recommending the first n mobile banking financial products with the highest predicted operation times to the user.
In the process of implementing step S105 specifically, the first n mobile banking financial products with the highest number of predicted operations are recommended to the user, where n is an integer greater than 0.
It should be noted that after the mobile phone bank financial products are sorted according to the predicted operation times, the first n mobile phone bank financial products with the highest predicted operation times are selected as the mobile phone bank financial products which are most likely to be interested by the user, and the first n mobile phone bank financial products with the highest predicted operation times are recommended to the user, so that accurate recommendation is achieved.
In the embodiment of the invention, after a product scoring matrix is constructed by using data of a mobile phone bank financing product operated by a user, interference noise is added to the constructed product scoring matrix, then iterative training is carried out by using the disturbed product scoring matrix to obtain the predicted operation times of the mobile phone bank financing product, and finally the mobile phone bank financing product is recommended to the user according to the predicted operation times, so that the data of the user is protected, the mobile phone bank financing product can be accurately recommended, the safety of the data of the user is improved, and the user experience is improved.
In the above-mentioned embodiment of the present invention, referring to fig. 2, the process of obtaining the predicted operation times of the mobile banking financial product in step S104 in fig. 1 shows a flowchart of obtaining the predicted operation times of the mobile banking financial product according to the embodiment of the present invention, which includes the following steps:
step S201: and adding the second product scoring matrix into the matrix decomposition algorithm for iterative training until an iteration stop condition corresponding to the gradient descent algorithm is met, and obtaining a user data matrix and a product data matrix.
In the process of specifically implementing step S201, a second product scoring matrix (i.e., the first product scoring matrix added with the interference noise) is added to the matrix decomposition algorithm for iterative training until the iterative training satisfies an iteration stop condition corresponding to the gradient descent algorithm, where an obtained final result includes two matrices, each of which is: a user data matrix and a product data matrix.
It should be noted that the main function of the matrix decomposition algorithm is a Loss function (such as a flat method).
It can be understood that, in the process of adding the second product scoring matrix to the matrix decomposition algorithm for iterative training, multiple iterations are required, each iteration will obtain a corresponding intermediate result (non-final result), and in order to further ensure the security of the user data, it is preferable that, in the process of adding the second product scoring matrix to the matrix decomposition algorithm for iterative training, laplacian noise is added to the intermediate result obtained by each iteration. By the method, the safety of the user data is further improved.
In some embodiments, in the process of adding the second product scoring matrix to the matrix decomposition algorithm for iterative training, each iteration obtains an intermediate result of the user data matrix and the product scoring matrix corresponding to the iteration, at this time, a laplacian noise matrix having the same dimension as the intermediate result is synchronously generated, a prediction error value of the current iteration is calculated according to the intermediate result, and the prediction error value is introduced into the gradient descent algorithm and used for calculating the user data matrix and the product data matrix of the next iteration until the iteration is finished.
Step S202: and multiplying the user data matrix and the product data matrix to obtain a third product scoring matrix.
It should be noted that each element of the third product score matrix is the predicted operation times of the mobile banking financial product.
It can be known from the content in the step S201 that the final result obtained by performing the iterative training includes two matrices, i.e., a user data matrix and a product data matrix, and in the process of specifically implementing the step S202, the user data matrix and the product data matrix are multiplied by each other to obtain a third product scoring matrix, where each element in the third product scoring matrix is the number of times of the prediction operation of the mobile banking financial product.
That is, the third product scoring matrix obtained by multiplying the user data matrix and the product data matrix includes the predicted operation times of each mobile banking financial product.
As can be seen from the content in fig. 1 in the embodiment of the present invention, each row of elements in the third product score matrix represents the number of times of the predicted operation of a certain user on all the mobile banking financial products, and the first n mobile banking financial products with the highest number of times of the predicted operation can be selected from the row of elements and recommended to the user corresponding to the row of elements.
In the embodiment of the invention, the second product scoring matrix obtained by adding interference noise processing is added into a matrix decomposition algorithm for iterative training, Laplace noise is added to the intermediate result obtained by each iteration in the iterative process until the iteration stop condition corresponding to the gradient descent algorithm is met, a third product scoring matrix containing the predicted operation times of each mobile phone bank financing product is obtained, and finally the mobile phone bank financing product is recommended to the user according to the predicted operation times, so that the data of the user is further protected, the mobile phone bank financing product can be accurately recommended, the data security of the user is improved, and the user experience is improved.
Corresponding to the recommendation method for mobile banking financial products provided by the embodiment of the present invention, referring to fig. 3, the embodiment of the present invention further provides a structural block diagram of a recommendation system for mobile banking financial products, where the recommendation system includes: an acquisition unit 301, a construction unit 302, an addition unit 303, a processing unit 304, and a recommendation unit 305;
an obtaining unit 301, configured to obtain operation times for a user to operate each mobile banking product, where the operation of operating a mobile banking product is: clicking the mobile phone bank financing product or purchasing the mobile phone bank financing product.
The constructing unit 302 is configured to construct a first product scoring matrix according to the operation times corresponding to each mobile banking financial product, where each element in the first product scoring matrix is the operation time corresponding to the mobile banking financial product.
The adding unit 303 is configured to add interference noise to each element in the first product scoring matrix to obtain a second product scoring matrix.
In a specific implementation, the adding unit 303 is specifically configured to: executing the following steps, processing each element in the first product scoring matrix to obtain a second product scoring matrix; the method comprises the following steps: for each element in the first product scoring matrix, if the operation frequency corresponding to the element is 0, the element is not processed, and if the operation frequency corresponding to the element is not 0, laplacian noise is added to the element.
And the processing unit 304 is configured to perform iterative training by using a preset algorithm based on the second product scoring matrix until an iteration stop condition is met, so as to obtain the predicted operation times of each mobile banking financial product.
And the recommending unit 305 is used for recommending the top n mobile banking financial products with the highest predicted operation times to the user.
In the embodiment of the invention, after a product scoring matrix is constructed by using data of a mobile phone bank financing product operated by a user, interference noise is added to the constructed product scoring matrix, then iterative training is carried out by using the disturbed product scoring matrix to obtain the predicted operation times of the mobile phone bank financing product, and finally the mobile phone bank financing product is recommended to the user according to the predicted operation times, so that the data of the user is protected, the mobile phone bank financing product can be accurately recommended, the safety of the data of the user is improved, and the user experience is improved.
Preferably, referring to fig. 4 in conjunction with fig. 3, another structural block diagram of a recommendation system for mobile banking financial products according to an embodiment of the present invention is shown, where the processing unit 304 includes: a training module 3041 and a processing module 3042;
the training module 3041 is configured to add the second product scoring matrix to the matrix decomposition algorithm for iterative training until an iteration stop condition corresponding to the gradient descent algorithm is met, so as to obtain a user data matrix and a product data matrix.
The processing module 3042 is configured to multiply the user data matrix and the product data matrix to obtain a third product scoring matrix, where each element of the third product scoring matrix is a predicted operation frequency of the mobile banking financial product.
Preferably, referring to fig. 5 in combination with fig. 4, a further structural block diagram of a recommendation system for mobile banking financial products according to an embodiment of the present invention is shown, where the processing unit 304 further includes:
the adding module 3043 is configured to add laplacian noise to an intermediate result obtained by each iteration in the process of adding the second product scoring matrix to the matrix decomposition algorithm for iterative training.
In the embodiment of the invention, the second product scoring matrix obtained by adding interference noise processing is added into a matrix decomposition algorithm for iterative training, Laplace noise is added to the intermediate result obtained by each iteration in the iterative process until the iteration stop condition corresponding to the gradient descent algorithm is met, a third product scoring matrix containing the predicted operation times of each mobile phone bank financing product is obtained, and finally the mobile phone bank financing product is recommended to the user according to the predicted operation times, so that the data of the user is further protected, the mobile phone bank financing product can be accurately recommended, the data security of the user is improved, and the user experience is improved.
Preferably, referring to fig. 6 in combination with fig. 3, there is shown another structural block diagram of a recommendation system for mobile banking financial products according to an embodiment of the present invention, where the recommendation system further includes:
and the sorting unit 306 is used for sorting the financial products of each mobile phone bank based on the predicted operation times.
In summary, embodiments of the present invention provide a method and a system for recommending a mobile banking financial product, where after a product scoring matrix is constructed by using data of a mobile banking financial product operated by a user, interference noise is added to the constructed product scoring matrix, iterative training is performed by using the disturbed product scoring matrix to obtain a predicted operation frequency of the mobile banking financial product, and finally the mobile banking financial product is recommended to the user according to the predicted operation frequency, so that the data of the user is protected, the mobile banking financial product can be accurately recommended, and the security of the data of the user is improved and the user experience is improved.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, the system or system embodiments are substantially similar to the method embodiments and therefore are described in a relatively simple manner, and reference may be made to some of the descriptions of the method embodiments for related points. The above-described system and system embodiments are only illustrative, wherein the units described as separate parts may or may not be physically separate, and the parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Those of skill would further appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative components and steps have been described above generally in terms of their functionality in order to clearly illustrate this interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. A recommendation method for mobile banking financial products is characterized by comprising the following steps:
acquiring the operation times of operating various mobile phone bank financial products by a user, wherein the operation of the mobile phone bank financial products comprises the following steps: clicking the mobile phone bank financing product or purchasing the mobile phone bank financing product;
constructing a first product scoring matrix according to the operation times corresponding to each mobile phone bank financing product, wherein each element in the first product scoring matrix is the operation times corresponding to the mobile phone bank financing product;
adding interference noise to each element in the first product scoring matrix to obtain a second product scoring matrix;
performing iterative training by using a preset algorithm based on the second product scoring matrix until an iteration stopping condition is met, and obtaining the predicted operation times of each mobile phone bank financing product;
recommending the first n mobile banking financial products with the highest predicted operation times to the user.
2. The method of claim 1, wherein said adding interference noise to each element in said first product scoring matrix to obtain a second product scoring matrix comprises:
executing the following steps, processing each element in the first product scoring matrix to obtain a second product scoring matrix;
the following steps include:
for each element in the first product scoring matrix, if the operation frequency corresponding to the element is 0, the element is not processed, and if the operation frequency corresponding to the element is not 0, laplacian noise is added to the element.
3. The method according to claim 1, wherein the obtaining of the predicted operation times of each mobile banking financial product by performing iterative training by using a preset algorithm until an iteration stop condition is met based on the second product scoring matrix comprises:
adding the second product scoring matrix into a matrix decomposition algorithm for iterative training until an iteration stop condition corresponding to a gradient descent algorithm is met, and obtaining a user data matrix and a product data matrix;
and multiplying the user data matrix and the product data matrix to obtain a third product scoring matrix, wherein each element of the third product scoring matrix is the predicted operation times of the mobile phone bank financing product.
4. The method of claim 3, further comprising:
and in the process of adding the second product scoring matrix into a matrix decomposition algorithm for iterative training, adding Laplace noise to an intermediate result obtained by each iteration.
5. The method according to claim 1, wherein before recommending the top n mobile banking financial products with the highest number of predicted operations to the user, further comprising:
and sequencing the mobile phone bank financing products based on the predicted operation times.
6. A recommendation system for mobile banking financial products, the system comprising:
the acquiring unit is used for acquiring the operation times of operating each mobile phone bank financing product by a user, and the operation of operating the mobile phone bank financing product is as follows: clicking the mobile phone bank financing product or purchasing the mobile phone bank financing product;
the construction unit is used for constructing a first product scoring matrix according to the operation times corresponding to the mobile phone bank financing products, and each element in the first product scoring matrix is the operation times corresponding to the mobile phone bank financing products;
the adding unit is used for adding interference noise to each element in the first product scoring matrix to obtain a second product scoring matrix;
the processing unit is used for carrying out iterative training by using a preset algorithm based on the second product scoring matrix until an iteration stopping condition is met, and obtaining the predicted operation times of each mobile phone bank financing product;
and the recommending unit is used for recommending the first n mobile banking financial products with the highest predicted operation times to the user.
7. The system according to claim 6, wherein the adding unit is specifically configured to: executing the following steps, processing each element in the first product scoring matrix to obtain a second product scoring matrix;
the following steps include:
for each element in the first product scoring matrix, if the operation frequency corresponding to the element is 0, the element is not processed, and if the operation frequency corresponding to the element is not 0, laplacian noise is added to the element.
8. The system of claim 6, wherein the processing unit comprises:
the training module is used for adding the second product scoring matrix into a matrix decomposition algorithm for iterative training until an iteration stop condition corresponding to a gradient descent algorithm is met, and a user data matrix and a product data matrix are obtained;
and the processing module is used for multiplying the user data matrix and the product data matrix to obtain a third product scoring matrix, and each element of the third product scoring matrix is the predicted operation times of the mobile phone bank financing product.
9. The system of claim 8, wherein the processing unit further comprises:
and the adding module is used for adding Laplace noise to the intermediate result obtained by each iteration in the process of adding the second product scoring matrix into the matrix decomposition algorithm for iterative training.
10. The system of claim 6, further comprising:
and the sorting unit is used for sorting the mobile phone bank financing products based on the predicted operation times.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111039375.5A CN113674066A (en) | 2021-09-06 | 2021-09-06 | Recommendation method and system for mobile banking financing products |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111039375.5A CN113674066A (en) | 2021-09-06 | 2021-09-06 | Recommendation method and system for mobile banking financing products |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113674066A true CN113674066A (en) | 2021-11-19 |
Family
ID=78548754
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111039375.5A Pending CN113674066A (en) | 2021-09-06 | 2021-09-06 | Recommendation method and system for mobile banking financing products |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113674066A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107392049A (en) * | 2017-07-26 | 2017-11-24 | 安徽大学 | Recommendation method based on differential privacy protection |
| WO2019056573A1 (en) * | 2017-09-25 | 2019-03-28 | 深圳大学 | Differential privacy-based system and method for collaborative web quality-of-service prediction for privacy protection |
| WO2019056572A1 (en) * | 2017-09-25 | 2019-03-28 | 深圳大学 | Model-based collaborative filtering method for collaborative web quality-of-service prediction for privacy protection |
| CN110837603A (en) * | 2019-11-09 | 2020-02-25 | 安徽大学 | Integrated recommendation method based on differential privacy protection |
-
2021
- 2021-09-06 CN CN202111039375.5A patent/CN113674066A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107392049A (en) * | 2017-07-26 | 2017-11-24 | 安徽大学 | Recommendation method based on differential privacy protection |
| WO2019056573A1 (en) * | 2017-09-25 | 2019-03-28 | 深圳大学 | Differential privacy-based system and method for collaborative web quality-of-service prediction for privacy protection |
| WO2019056572A1 (en) * | 2017-09-25 | 2019-03-28 | 深圳大学 | Model-based collaborative filtering method for collaborative web quality-of-service prediction for privacy protection |
| CN110837603A (en) * | 2019-11-09 | 2020-02-25 | 安徽大学 | Integrated recommendation method based on differential privacy protection |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Cantwell et al. | Message passing on networks with loops | |
| CN112085172B (en) | Method and device for training graph neural network | |
| Eswaran et al. | Zoobp: Belief propagation for heterogeneous networks | |
| EP3508990A1 (en) | Natural language library generation method and device | |
| CN107301181B (en) | Account recommendation method and device | |
| CN103763361A (en) | Method and system for recommending applications based on user behavior and recommending server | |
| CN110020124A (en) | The method and device excavated for Related product | |
| CN106998314B (en) | Account interaction method and device | |
| CN108334494B (en) | Method and device for constructing user relationship network | |
| CN110659416A (en) | Recommendation method and recommendation device for browsing resources and readable storage medium | |
| Attia et al. | A formula for the value of a stochastic game | |
| CN113342791A (en) | Data quality monitoring method and device | |
| Fibich et al. | Averaging principle for second-order approximation of heterogeneous models with homogeneous models | |
| CN109460930B (en) | Method for determining risk account and related equipment | |
| CN103390021A (en) | Method and apparatus for extracting social relations from calling time data | |
| CN113674066A (en) | Recommendation method and system for mobile banking financing products | |
| CN109345252A (en) | A kind of online trading control method, device and computer equipment | |
| CN110085292B (en) | Medicine recommendation method and device and computer-readable storage medium | |
| CN112163929A (en) | Service recommendation method and device, computer equipment and storage medium | |
| CN110300049B (en) | Message shielding method, device and system based on instant messaging | |
| CN111160738A (en) | Event processing method and device, storage medium and electronic device | |
| CN112256691A (en) | Data mapping method and device and electronic equipment | |
| CN113674036A (en) | Recommendation method and system for mobile banking advertisements | |
| CN117033760A (en) | Object recommendation method, device, equipment, storage medium and program product | |
| CN110610373A (en) | Potential customer mining processing method and device |
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 |