CN111179037B - Financial product recommendation method and device - Google Patents
Financial product recommendation method and device Download PDFInfo
- Publication number
- CN111179037B CN111179037B CN201911409557.XA CN201911409557A CN111179037B CN 111179037 B CN111179037 B CN 111179037B CN 201911409557 A CN201911409557 A CN 201911409557A CN 111179037 B CN111179037 B CN 111179037B
- Authority
- CN
- China
- Prior art keywords
- preference
- financial product
- preference model
- financial
- user
- 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
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
- 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
- G06Q40/06—Asset management; Financial planning or analysis
Abstract
The invention provides a recommendation method and device of financial products, wherein the method comprises the following steps: establishing a preference model of the financial product combination, wherein the preference model is used for expressing the preference degree of a user on the financial product combination and comprises preference factors of the financial product, and the preference factors express the preference degree of the user on the financial product; solving the preference model, and determining preference factors in the preference model; after obtaining a plurality of financial product combinations, inputting the plurality of financial product combinations into the solved preference model to obtain the financial product combinations recommended to the user. The invention can accurately recommend financial products to users.
Description
Technical Field
The invention relates to the field of Internet, in particular to a recommendation method and device for financial products.
Background
In the financial industry, various financial products are often required to be recommended to customers, but if the recommendation is blind, the actual needs of the customers may not be met, so how to accurately recommend the financial products to the customers is a problem to be solved.
Disclosure of Invention
The embodiment of the invention provides a recommendation method of financial products, which is used for accurately recommending the financial products to a user, and comprises the following steps:
establishing a preference model of the financial product combination, wherein the preference model is used for expressing the preference degree of a user on the financial product combination and comprises preference factors of the financial product, and the preference factors express the preference degree of the user on the financial product;
solving the preference model, and determining preference factors in the preference model;
after obtaining a plurality of financial product combinations, inputting the plurality of financial product combinations into the solved preference model to obtain the financial product combinations recommended to the user.
The embodiment of the invention provides a recommendation device of financial products, which is used for accurately recommending the financial products to a user and comprises the following steps:
the data acquisition module is used for determining a plurality of financial products to be recommended;
the preference model building module is used for building a preference model of a plurality of financial products, wherein the preference model is used for representing the preference of a user on the plurality of financial products and comprises a combination of preference factors and the financial products;
the preference model solving module is used for solving the preference model and determining preference factors in the preference model;
and the financial product combination determining module is used for determining financial products recommended to the user according to preference factors in preference models of various financial products.
The embodiment of the invention also provides computer equipment, which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the recommendation method of the financial product is realized when the processor executes the computer program.
The embodiment of the invention also provides a computer readable storage medium, wherein the computer readable storage medium stores a computer program for executing the recommendation method of the financial product.
In the embodiment of the invention, a preference model of the financial product combination is established, wherein the preference model is used for expressing the preference degree of a user on the financial product combination, and comprises preference factors of the financial product, and the preference factors express the preference degree of the user on the financial product; solving the preference model, and determining preference factors in the preference model; after obtaining a plurality of financial product combinations, inputting the plurality of financial product combinations into the solved preference model to obtain the financial product combinations recommended to the user. In the process, a preference model of the financial product combination is established, and the preference model contains preference factors, so that after the preference factors are solved, after a plurality of financial product combinations are obtained, the plurality of financial product combinations are input into the solved preference model each time, and the financial product combination preference of the user can be obtained, so that the financial product can be recommended to the user more accurately.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art. In the drawings:
FIG. 1 is a flowchart of a recommendation method for financial products according to an embodiment of the present invention;
fig. 2 is a schematic diagram of a recommending apparatus for financial products according to an embodiment of the invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the embodiments of the present invention will be described in further detail with reference to the accompanying drawings. The exemplary embodiments of the present invention and their descriptions herein are for the purpose of explaining the present invention, but are not to be construed as limiting the invention.
In the description of the present specification, the terms "comprising," "including," "having," "containing," and the like are open-ended terms, meaning including, but not limited to. Reference to the terms "one embodiment," "a particular embodiment," "some embodiments," "for example," etc., means that a particular feature, structure, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present application. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiments or examples. Furthermore, the particular features, structures, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. The sequence of steps involved in the embodiments is used to schematically illustrate the practice of the present application, and is not limited thereto and may be appropriately adjusted as desired.
The inventor finds that when recommending financial products to a user, if the preference of the user for certain financial products can be obtained, the financial products can be accurately recommended to the user, so that if the recommendation accuracy of the financial products is required to be improved, the prediction accuracy of the preference of the user for the financial products can be improved, and based on the recommendation method, the embodiment of the invention provides the following recommendation method for the financial products.
Fig. 1 is a flowchart of a recommending method of financial products according to an embodiment of the present invention, as shown in fig. 1, the method includes:
step 101, establishing a preference model of the financial product combination, wherein the preference model is used for expressing the preference degree of a user on the financial product combination and comprises preference factors of the financial product, and the preference factors express the preference degree of the user on the financial product;
step 102, solving the preference model, and determining preference factors in the preference model;
step 103, after obtaining a plurality of financial product combinations, inputting the plurality of financial product combinations into the solved preference model to obtain the financial product combinations recommended to the user.
In the embodiment of the invention, the preference model of the financial product combination is established, and the preference model contains the preference factors, so that after the preference factors are solved, after a plurality of financial product combinations are obtained, the financial product combinations are input into the solved preference model each time, and the financial product combination preference of the user can be obtained, so that the financial product can be recommended to the user more accurately.
In particular, the plurality of financial products to be recommended may be any type of financial product, funds, bonds, stocks, etc.
In one embodiment, the preference model is expressed using the following formula:
wherein, the liquid crystal display device comprises a liquid crystal display device,a financial product combination recommended to the user;
is a preference factor;
p is a plurality of financial product combinations of a plurality of financial products;
to correct errors.
In the above embodiment, only if the preference factor is determined, after a plurality of financial product combinations are input each time, the preference degree of the user for the plurality of financial product combinations may be determined, so as to determine the optimal financial product combination.
In particular, there are a plurality of algorithms for solving the preference model, which are specific to the formula (1)Typical estimation algorithms, the minimum mean square error algorithm, are also 2-norm algorithms, where in reality P tends to be sparse, i.e. the number of 1 s in the matrix P tends to be small, and therefore +.>Can be regarded as a sparse vector, and many existing algorithms are trying to solve the problem of sparse vector estimation, L 0 The algorithm is the most accurate estimation algorithm, however due to L 0 The algorithm is an NP-hard problem and cannot be directly solved, so most algorithms try to approach L 0 Algorithm, wherein greedy algorithm and L 1 The algorithms (LASSO algorithm, LS algorithm, etc.) are more classical algorithms, L 1 The algorithm converts the NP-hard problem into a solution problem of a convex function, so that the complexity of the algorithm is greatly reduced, and the accuracy is also reduced. The accuracy of the LASSO algorithm is greatly improved over LS, but its complexity is higher than LS. The inventors found that L 1/2 The algorithm can well replace L p Algorithm where 0 < p < 1, i.e. L 1/2 Can infinitely approach L 0 An algorithm. Thus L is 1/2 The estimation accuracy of the algorithm is far higher than that of the minimum mean square error algorithm, and the complexity is far lower than that of L 0 An algorithm.
Thus, in one embodiment, solving the preference model, determining preference factors in the preference model, includes:
by L 1/2 Algorithm solves the preference model and determines the preference modelIs included in the preference factor.
In the concrete implementation, L is adopted 1/2 Algorithms solve the preference model and there are a number of ways to determine preference factors in the preference model, one of which is given below.
In one embodiment, L is employed 1/2 Algorithm solving the preference model, determining preference factors in the preference model, comprising:
determining the number of financial products and the number of financial product combinations;
determining selection data of historical financial product combinations of a user;
determining a maximum iteration number and a threshold value of iteration stop;
and solving the preference model according to the quantity of financial products and the quantity of financial product combinations, the selection data of the historical financial product combinations of the user, the maximum iteration number and the threshold value of iteration stopping, and determining preference factors in the preference model.
In the above embodiment, the number of financial products refers to the data of the types of financial products, for example, 10 financial products may be provided, and the 10 financial products may be provided withSeed financial product combination from 2 10 -selecting the number of financial product combinations required for the training from the 1 financial product combinations, for example, determining that the number of the historically pushed financial product combinations is 5; then, determining selection data of historical financial product combinations of the user, including total selection times of the user and selection times of each of the 5 financial product combinations, for example, the total selection times of the user is 1000 times, and the selection times of the financial product combination A is a, then y corresponding to the financial product combination A A =a/1000, thus, can get +.>From the above analysis, it can be seen that y 1 +y 2 +…+y 5 The dimension of p is 5×10, and the user is for 10 kinds of theoryPreference factor of property product->Is 10 x 1. Correction error->In P, 1 and 0 are used to represent whether the financial product is sold or not, for example, in the following P matrix, each column represents the financial product A, B, C respectively, then the financial product combination in the first row is a+c, the financial product combination in the second row is a+b, and the financial product combination in the third row is b+c.
By the above description, a set of training data is constructed, i.e. determinedP and->Thus, after determining the maximum number of iterations L and the threshold ζ of iteration stop, one can rely on L 1/2 Norm algorithm finds ++>A specific solving procedure is given below.
First, L 1/2 The problem of solving the norm can be expressed in terms of the following model:
in the solution of the formula (2), the problem is a function which is not convex or smooth, so that the model is further simplified when the model is solved, and the formula (2) can be solved by using a complex-valued iterative algorithm to calculate:
wherein, the liquid crystal display device comprises a liquid crystal display device,is a half-threshold operating factor.
Substituting formula (1) into formula (3)The calculation formula of (2) is as follows:
x l+1 ＝H λμ,1/2 (B μ (x l )) (5)
wherein, |B μ (x l )| k Is |B μ (x l ) K-th largest value in i.
L based on equation (4) -equation (7) 1/2 The specific flow of the algorithm is as follows:
step 1: initialization ofA maximum number of iterations L, and a threshold ζ of iteration stop.
Step 2, iteration solving:
While l＜L do
step 2.1, calculating a half-threshold operating factor according to (4)
Step 2.2, for variablesAssigning a value of 0;
step 2.3, calculating λ according to equation (7) l ；
When (when)Stopping iteration;
will x l As the final preference factor;
otherwise l=l+1.
End while
Above L 1/2 The algorithm has low complexity and high precision, and therefore, L is adopted 1/2 The accuracy of the preference factors solved by the algorithm is high, and the finally obtained financial product combination recommended to the user is high in accuracy.
The following describes specific applications of the recommendation method of financial products according to the present invention, taking fund as an example.
First, a preference model of the fund combination expressed by the formula (1) is established, wherein the types of the funds are 100, and the 100 kinds of funds can be generatedA seed foundation combination from this->Selecting 50 number of fund combinations required for the training; determining historical selection data for the user for the combinations of funds, including a total number of selections of 1000, and a number of selections for each of the 100 combinations of funds, e.g., a number of selections for combination A, then y for combination A A =a/1000, thus, can be obtainedFrom the above analysis, it can be seen that y 1 +y 2 +…+y 50 The dimension of p is 50×100, and the preference factor of the user for 100 funds +.>Is 100 x 1. Correction error->In P, 1 and 0 are used to represent whether the fund is sold or not. A set of training data is constructed as described above, i.e. a +.>P and->Thus, after determining the maximum number of iterations L and the threshold ζ of iteration stop, one can rely on L 1/2 Norm algorithm finds ++>L based on the formula (4) -formula (7) is adopted 1/2 Specific flow of algorithm, preference factor +.>And after a plurality of fund combinations are obtained, inputting the plurality of fund combinations into the solved preference model to obtain the fund combinations recommended to the user, so that accurate marketing is realized.
In summary, in the method provided by the embodiment of the present invention, a preference model of the financial product combination is established, where the preference model is used to represent the preference degree of the user for the financial product combination, and the preference model includes preference factors of the financial product, and the preference factors represent the preference degree of the user for the financial product; solving the preference model, and determining preference factors in the preference model; after a bank pushes out a plurality of financial product combinations, the financial product combinations are input into the solved preference model, so that the preference degree of the user for different financial product combinations can be obtained, and the financial product combination which is recommended to the user and is most interesting to the user can be obtained. In the process, a preference model of the financial product combination is established, and the preference model contains preference factors, so that after the preference factors are solved, after a plurality of financial product combinations are obtained, the plurality of financial product combinations are input into the solved preference model each time, and the financial product combination preference of the user can be obtained, so that the financial product can be recommended to the user more accurately.
Based on the same inventive concept, the embodiment of the invention also provides a recommending device of financial products, as described in the following embodiment. Since the principles of solving the problems are similar to those of the recommending device of the financial product, the implementation of the device can be referred to the implementation of the method, and the repetition is omitted.
Fig. 2 is a schematic diagram of a recommendation device for financial products according to an embodiment of the present invention, as shown in fig. 2, the device includes:
a preference model building module 201, configured to build a preference model of a financial product combination, where the preference model is used to represent a preference degree of a user for the financial product combination, and the preference model includes preference factors of the financial product, and the preference factors represent a preference degree of the user for the financial product;
a preference model solving module 202, configured to solve the preference model, and determine preference factors in the preference model;
and the financial product combination determining module 203 is configured to, after obtaining a plurality of financial product combinations, input the plurality of financial product combinations into the solved preference model to obtain a financial product combination recommended to the user.
In one embodiment, the preference model is expressed using the following formula:
wherein, the liquid crystal display device comprises a liquid crystal display device,reason for recommendation to usersCombining property products;
is a preference factor;
p is a plurality of financial product combinations of a plurality of financial products;
to correct errors.
In one embodiment, the preference model solving module 202 is specifically configured to:
by L 1/2 An algorithm solves the preference model and determines preference factors in the preference model.
In one embodiment, the preference model solving module 202 is specifically configured to:
determining the number of financial products and the number of financial product combinations;
determining selection data of historical financial product combinations of a user;
determining a maximum iteration number and a threshold value of iteration stop;
and solving the preference model according to the quantity of financial products and the quantity of financial product combinations, the selection data of the historical financial product combinations of the user, the maximum iteration number and the threshold value of iteration stopping, and determining preference factors in the preference model.
In summary, in the device provided by the embodiment of the invention, a preference model of the financial product combination is established, wherein the preference model is used for expressing the preference degree of the user on the financial product combination, the preference model comprises preference factors of the financial product, and the preference factors express the preference degree of the user on the financial product; solving the preference model, and determining preference factors in the preference model; after a bank pushes out a plurality of financial product combinations, the financial product combinations are input into the solved preference model, so that the preference degree of the user for different financial product combinations can be obtained, and the financial product combination which is recommended to the user and is most interesting to the user can be obtained. In the process, a preference model of the financial product combination is established, and the preference model contains preference factors, so that after the preference factors are solved, after a plurality of financial product combinations are obtained, the plurality of financial product combinations are input into the solved preference model each time, and the financial product combination preference of the user can be obtained, so that the financial product can be recommended to the user more accurately.
It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The foregoing description of the embodiments has been provided for the purpose of illustrating the general principles of the invention, and is not meant to limit the scope of the invention, but to limit the invention to the particular embodiments, and any modifications, equivalents, improvements, etc. that fall within the spirit and principles of the invention are intended to be included within the scope of the invention.
Claims (8)
1. A method for recommending financial products, comprising:
establishing a preference model of the financial product combination, wherein the preference model is used for expressing the preference degree of a user on the financial product combination and comprises preference factors of the financial product, and the preference factors express the preference degree of the user on the financial product;
solving the preference model, and determining preference factors in the preference model;
after a plurality of financial product combinations are obtained, inputting the plurality of financial product combinations into the solved preference model to obtain the financial product combinations recommended to the user;
the preference model is expressed by the following formula:
wherein, the liquid crystal display device comprises a liquid crystal display device,a financial product combination recommended to the user;
is a preference factor;
p is a plurality of financial product combinations of a plurality of financial products;
to correct errors.
2. The method of recommending financial products according to claim 1, wherein solving the preference model to determine preference factors in the preference model comprises:
by L 1/2 An algorithm solves the preference model and determines preference factors in the preference model.
3. The recommendation method of financial products as claimed in claim 2, wherein L is adopted 1/2 Algorithm solving the preference model, determining preference factors in the preference model, comprising:
determining the number of financial products and the number of financial product combinations;
determining selection data of historical financial product combinations of a user;
determining a maximum iteration number and a threshold value of iteration stop;
and solving the preference model according to the quantity of financial products and the quantity of financial product combinations, the selection data of the historical financial product combinations of the user, the maximum iteration number and the threshold value of iteration stopping, and determining preference factors in the preference model.
4. A recommendation device for financial products, comprising:
the preference model building module is used for building a preference model of the financial product combination, wherein the preference model is used for representing the preference degree of a user on the financial product combination, and comprises preference factors of the financial product, and the preference factors represent the preference degree of the user on the financial product;
the preference model solving module is used for solving the preference model and determining preference factors in the preference model;
the financial product combination determining module is used for inputting the financial product combinations into the solved preference model after obtaining the financial product combinations, so as to obtain the financial product combinations recommended to the user;
the preference model is expressed by the following formula:
wherein, the liquid crystal display device comprises a liquid crystal display device,a financial product combination recommended to the user;
is a preference factor;
p is a plurality of financial product combinations of a plurality of financial products;
to correct errors.
5. The financial product recommendation device of claim 4, wherein the preference model solving module is specifically configured to:
by L 1/2 An algorithm solves the preference model and determines preference factors in the preference model.
6. The financial product recommendation device of claim 5, wherein the preference model solving module is specifically configured to:
determining the number of financial products and the number of financial product combinations;
determining selection data of historical financial product combinations of a user;
determining a maximum iteration number and a threshold value of iteration stop;
and solving the preference model according to the quantity of financial products and the quantity of financial product combinations, the selection data of the historical financial product combinations of the user, the maximum iteration number and the threshold value of iteration stopping, and determining preference factors in the preference model.
7. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the method of any of claims 1 to 3 when executing the computer program.
8. A computer readable storage medium, characterized in that the computer readable storage medium stores a computer program for executing the method of any one of claims 1 to 3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911409557.XA CN111179037B (en) | 2019-12-31 | 2019-12-31 | Financial product recommendation method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911409557.XA CN111179037B (en) | 2019-12-31 | 2019-12-31 | Financial product recommendation method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111179037A CN111179037A (en) | 2020-05-19 |
| CN111179037B true CN111179037B (en) | 2023-07-25 |
Family
ID=70657730
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911409557.XA Active CN111179037B (en) | 2019-12-31 | 2019-12-31 | Financial product recommendation method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111179037B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107437198A (en) * | 2017-05-26 | 2017-12-05 | 阿里巴巴集团控股有限公司 | Determine method, information recommendation method and the device of consumer's risk preference |
| CN108665323A (en) * | 2018-05-20 | 2018-10-16 | 北京工业大学 | A kind of integrated approach for finance product commending system |
| CN110223137A (en) * | 2019-05-22 | 2019-09-10 | 平安科技（深圳）有限公司 | Product mix recommended method, device, computer equipment and storage medium |
| WO2020048051A1 (en) * | 2018-09-04 | 2020-03-12 | 深圳壹账通智能科技有限公司 | Financial product recommendation method, server and computer readable storage medium |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9092739B2 (en) * | 2010-07-22 | 2015-07-28 | Alcatel Lucent | Recommender system with training function based on non-random missing data |
-
2019
- 2019-12-31 CN CN201911409557.XA patent/CN111179037B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107437198A (en) * | 2017-05-26 | 2017-12-05 | 阿里巴巴集团控股有限公司 | Determine method, information recommendation method and the device of consumer's risk preference |
| CN108665323A (en) * | 2018-05-20 | 2018-10-16 | 北京工业大学 | A kind of integrated approach for finance product commending system |
| WO2020048051A1 (en) * | 2018-09-04 | 2020-03-12 | 深圳壹账通智能科技有限公司 | Financial product recommendation method, server and computer readable storage medium |
| CN110223137A (en) * | 2019-05-22 | 2019-09-10 | 平安科技（深圳）有限公司 | Product mix recommended method, device, computer equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111179037A (en) | 2020-05-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR102170105B1 (en) | Method and apparatus for generating neural network structure, electronic device, storage medium | |
| US20210256348A1 (en) | Automated methods for conversions to a lower precision data format | |
| WO2018227800A1 (en) | Neural network training method and device | |
| CN111464154B (en) | Control pulse calculation method and device | |
| CN109298940B (en) | Computing task allocation method and device, electronic equipment and computer storage medium | |
| JP7267985B2 (en) | Systems, methods, and computer programs for recommending items using direct neural network structures | |
| WO2019240911A1 (en) | System and method for implementing a neural network | |
| CN106327340B (en) | Abnormal node set detection method and device for financial network | |
| US20220147877A1 (en) | System and method for automatic building of learning machines using learning machines | |
| CN112819169B (en) | Quantum control pulse generation method, device, equipment and storage medium | |
| CN112955907A (en) | Long-short term memory neural network for quantitative training | |
| CN104750731A (en) | Method and device for obtaining complete user portrait | |
| CN110288637A (en) | Multi-angle DSA contrastographic picture blood vessel matching process and device | |
| CN113592095B (en) | Model training method and device based on quantum computation | |
| EP2732387A1 (en) | Generation of recommendation values | |
| CN111179037B (en) | Financial product recommendation method and device | |
| CN116167446B (en) | Quantum computing processing method and device and electronic equipment | |
| US11158059B1 (en) | Image reconstruction based on edge loss | |
| CN109584020A (en) | A kind of information processing method and electronic equipment | |
| CN115099514A (en) | Data processing method and device, electronic equipment and storage medium | |
| JP6172315B2 (en) | Method and apparatus for mixed model selection | |
| JP6954346B2 (en) | Parameter estimator, parameter estimator, and program | |
| US20190347765A1 (en) | Method of creating an image chain | |
| Charlier et al. | VecHGrad for solving accurately complex tensor decomposition | |
| CN116151383B (en) | Quantum computing processing method and device and electronic equipment |
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 |