CN115375494A - Financial product recommendation method, device, storage medium and equipment - Google Patents
Financial product recommendation method, device, storage medium and equipment Download PDFInfo
- Publication number
- CN115375494A CN115375494A CN202211043055.1A CN202211043055A CN115375494A CN 115375494 A CN115375494 A CN 115375494A CN 202211043055 A CN202211043055 A CN 202211043055A CN 115375494 A CN115375494 A CN 115375494A
- Authority
- CN
- China
- Prior art keywords
- product
- financial
- products
- financing
- hot
- 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
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
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/06—Asset management; Financial planning or analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- 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
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Business, Economics & Management (AREA)
- Operations Research (AREA)
- Development Economics (AREA)
- Mathematical Physics (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Optimization (AREA)
- Mathematical Analysis (AREA)
- Computational Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- General Business, Economics & Management (AREA)
- Evolutionary Biology (AREA)
- Human Resources & Organizations (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Technology Law (AREA)
- Strategic Management (AREA)
- Probability & Statistics with Applications (AREA)
- Marketing (AREA)
- Algebra (AREA)
- Economics (AREA)
- Software Systems (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The application discloses a financial product recommendation method, device, storage medium and equipment, which can be applied to the field of big data, and the method comprises the following steps: carrying out big data analysis on the historical behavior log to obtain a target financial product; screening a plurality of hot financing products from each financing product; scoring each thermal financial product according to the behavior times of each thermal financial product to obtain a customer score of each thermal financial product; similarity calculation is carried out on each hot financial product and the target financial product to obtain the similarity between each hot financial product and the target financial product; calculating the priority of each hot financing product based on the customer score and the similarity; the method has the advantages that the hot money management products with the priority levels larger than the preset priority level threshold value are selected from all the hot money management products and serve as the money management products recommended to the clients to be detected, so that the money management products recommended to the clients to be detected can be ensured to arouse the interests of the clients to be detected, and the user experience of the clients to be detected is effectively improved.
Description
Technical Field
The application relates to the field of big data, in particular to a financial product recommendation method, device, storage medium and equipment.
Background
As the number and types of financial products of banks are rapidly increased, convenience is brought to customers, and meanwhile, the customers also need to spend a great deal of time and energy to seek products suitable for the customers. However, the traditional search can not meet the personalized requirements of the customers, and therefore, a financial product recommendation system needs to be provided.
At present, the existing financial product recommendation system can only recommend a financial product which is made in advance to a client, for example, a new financial product is put on the market, and then the financial product is directly recommended to the client. However, the financial products recommended by the existing recommendation method cannot be guaranteed to be liked by the client, and may be objectionable to the client, thereby reducing the experience of the client.
Therefore, how to recommend financial products which can arouse the interest of the customers to the customers becomes a problem which needs to be solved urgently in the field.
Disclosure of Invention
The application provides a financial product recommendation method, device, storage medium and equipment, and aims to recommend a financial product which can arouse the interest of a client to the client so as to improve the experience of the client.
In order to achieve the above object, the present application provides the following technical solutions:
a financial product recommendation method comprising:
carrying out big data analysis on a pre-acquired historical behavior log of a client to be detected to obtain a target financing product; the target financing product is a financing product which can arouse the interest of the client to be tested;
screening a plurality of popular financial products from various financial products contained in a business system;
scoring each thermal management product according to the behavior frequency of the customer to be tested on each thermal management product obtained from the service system to obtain a customer score of each thermal management product;
carrying out similarity calculation on each hot financial management product and the target financial management product to obtain the similarity between each hot financial management product and the target financial management product;
calculating the priority of each hot financial product based on the customer score of each hot financial product and the similarity between each hot financial product and the target financial product;
and selecting the hot money management products with the priority greater than a preset priority threshold value from the hot money management products as the money management products recommended to the client to be tested.
Optionally, the screening out a plurality of hot financing products from the financing products included in the business system includes:
acquiring the times of customer behaviors of each financial product in a preset time period from a business system;
sequencing the financial products according to the sequence of the number of times of the customer behaviors from large to small to obtain a financial product sequence;
selecting front n financial products from the financial product sequence, and marking the front n financial products as popular financial products; n is a positive integer.
Optionally, the screening out a plurality of hot financing products from the financing products included in the business system includes:
and acquiring the time of coming into market of each financing product from the business system, and identifying the financing product with the time of coming into market in a preset time range as a hot financing product.
Optionally, the screening out a plurality of hot financing products from the financing products included in the business system includes:
and acquiring the historical evaluation times of each financial product from the business system, and identifying the financial products with the historical evaluation times larger than a preset threshold as hot financial products.
Optionally, the calculating the priority of each of the thermal financial products based on the customer score of each of the thermal financial products and the similarity between each of the thermal financial products and the target financial product includes:
sequencing the hot money management products according to the sequence of similarity from high to low to obtain a hot money management product sequence;
selecting the top m hot money management products from the hot money management product sequence, and identifying the hot money management products as candidate money management products; m is a positive integer;
and calculating the priority of each candidate financing product based on the customer score of each candidate financing product and the similarity between each candidate financing product and the target financing product.
Optionally, the selecting a popular money management product with a priority greater than a preset priority threshold from the popular money management products as a money management product recommended to the customer to be tested includes:
selecting candidate financing products with the priority higher than a preset priority threshold from the candidate financing products as financing products to be recommended;
and constructing a financing product list recommended to the client to be tested based on each financing product to be recommended, and displaying the financing product list to the client to be tested through a front-end interface.
A financial product recommendation device comprising:
the analysis unit is used for carrying out big data analysis on the pre-acquired historical behavior log of the client to be tested to obtain a target financial product; the target financing product is a financing product which can arouse the interest of the client to be tested;
the screening unit is used for screening a plurality of hot financing products from each financing product contained in the business system;
the scoring unit is used for scoring each thermal financial product according to the behavior frequency of the client to be tested on each thermal financial product, which is obtained from the service system, so as to obtain a client score of each thermal financial product;
the similarity calculation unit is used for calculating the similarity of each thermal financial product and the target financial product to obtain the similarity between each thermal financial product and the target financial product;
the priority calculating unit is used for calculating the priority of each thermal management product based on the customer score of each thermal management product and the similarity between each thermal management product and the target management product;
and the selecting unit is used for selecting the hot money management products with the priority greater than a preset priority threshold value from the hot money management products as the money management products recommended to the client to be tested.
Optionally, the screening unit is specifically configured to:
acquiring the times of customer behaviors of each financial product in a preset time period from a business system;
sequencing the financial products according to the sequence of the number of times of the customer behaviors from large to small to obtain a financial product sequence;
selecting front n financial products from the financial product sequence, and marking the front n financial products as popular financial products; n is a positive integer.
A computer-readable storage medium comprising a stored program, wherein the program executes the financial product recommendation method.
A financial product recommendation apparatus comprising: a processor, a memory, and a bus; the processor and the memory are connected through the bus;
the memory is used for storing programs, and the processor is used for running the programs, wherein the program executes the financial product recommendation method during running.
According to the technical scheme, big data analysis is carried out on the historical behavior log of the client to be tested, which is acquired in advance, so that the target financial product is obtained. And screening a plurality of popular financial management products from the various financial management products contained in the business system. And scoring each thermal financial product according to the behavior times of the customer to be tested on each thermal financial product, which are obtained from the business system, to obtain the customer score of each thermal financial product. And carrying out similarity calculation on each hot financial product and the target financial product to obtain the similarity between each hot financial product and the target financial product. And calculating the priority of each thermal financial product based on the client score of each thermal financial product and the similarity between each thermal financial product and the target financial product. And selecting the hot money management products with the priority greater than a preset priority threshold value from all the hot money management products as money management products recommended to the client to be tested. According to the method and the device, the financial product recommended to the client to be tested is determined based on the similarity between the hot financial product and the target financial product and the client score of the hot financial product as a reference basis, and the target financial product is the financial product capable of arousing the interest of the client to be tested, so that the interest of the client to be tested can be aroused by the financial product recommended to the client to be tested, and the user experience of the client to be tested is effectively improved.
Drawings
In order to more clearly illustrate the embodiments of the present application 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 some embodiments of the present application, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1a is a schematic flowchart of a method for recommending financial products according to an embodiment of the present application;
FIG. 1b is a schematic flowchart of a method for recommending financial products according to an embodiment of the present application;
FIG. 2 is a schematic flow chart diagram illustrating another method for recommending financial products according to an embodiment of the present application;
fig. 3 is a schematic structural diagram of a financial product recommendation device according to an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, 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 application.
As shown in fig. 1a and fig. 1b, a flow chart of a method for recommending financial products provided by an embodiment of the present application is schematically shown, and the method includes the following steps:
s101: and acquiring personal information and a historical behavior log of a client to be tested in advance from a service system.
The personal information of the customer to be tested includes but is not limited to sex, employment situation, home address, age, and the like. The historical behavior log of the client to be tested comprises but is not limited to purchased financial products, browsed financial products, concerned financial products and the like.
S102: and carrying out big data analysis on the historical behavior log of the client to be tested to obtain the product preference information of the client to be tested.
Wherein the product preference information comprises financial products which can arouse the interest of the client to be tested.
S103: and acquiring the times of customer behaviors of each financial product in a preset time period from the business system.
The number of the customer behaviors comprises browsing behaviors, purchasing behaviors and attention behaviors of a plurality of customers on the financial products.
In the embodiment of the application, the number of times of customer behaviors in a preset time period from each financial product in the business system can be obtained by calling a Flink sliding window algorithm.
Specifically, a Flink sliding window algorithm is called, the number of times of client behaviors of each financial product in the 5-minute time is collected from the business system every 5 minutes, and the number of times of the client behaviors of each financial product collected in 4 5 minutes is counted to obtain the number of times of the client behaviors of each financial product in 20 minutes.
It should be noted that, in the process of invoking the Flink sliding window algorithm, the formulation of the water line (i.e., setting the acquisition time), the formulation of the sliding window size (i.e., selecting a financial product as an acquisition object), and the formulation of the window aggregation (i.e., setting the preset time period) may all be set by a technician according to actual situations.
S104: and sequencing the financial products according to the sequence of the number of times of the client behaviors from large to small to obtain a financial product sequence.
S105: and selecting the first n financial products from the financial product sequence, and identifying the products as popular financial products.
N is a positive integer, and the value of n can be set by a technician according to an actual situation, which is not limited in the embodiments of the present application.
S106: and acquiring the time of coming into market of each financing product from the business system, and identifying the financing product with the time of coming into market in a preset time range as a hot financing product.
The financial products with the time of coming into the market within the preset time range are marked as hot financial products, so that the latest financial products coming into the market can be ensured to be used as the hot financial products, and generally speaking, the latest financial products coming into the market are all required to be recommended to clients.
S107: and acquiring the historical evaluation times of each financial product from the business system, and identifying the financial products with the historical evaluation times larger than a preset threshold as hot financial products.
Wherein the historical favorable evaluation times comprise the behavior that the financial product is evaluated as excellent by a plurality of clients.
S108: and acquiring the behavior times of the client to be tested on each hot financial management product from the service system.
The behavior frequency of the client to be tested on the hot money management product comprises a behavior of the client to be tested in purchasing the hot money management product, a behavior of paying attention to the hot money management product and a behavior of browsing the hot money management product.
S109: and scoring each hot money management product based on the behavior frequency of the client to be tested on each hot money management product to obtain the client score of each hot money management product.
The behavior frequency of the client to be tested on the hot money management product is more, the client score of the hot money management product is higher, and conversely, the behavior frequency of the client to be tested on the hot money management product is less, the client score of the hot money management product is lower.
It should be noted that, when scoring is performed on each thermal management product based on the behavior frequency of the customer to be tested on each thermal management product, the specifically adopted scoring algorithm includes, but is not limited to, an Alternating Least Square (ALS) algorithm, specifically, the behavior frequency of the customer to be tested on each thermal management product is input into a pre-trained ALS algorithm model, and each thermal management product is scored according to the behavior frequency of the customer to be tested on each thermal management product through the ALS algorithm model, so as to obtain the customer score of each thermal management product.
Generally speaking, the training process of the ALS algorithm model is well known to those skilled in the art, and will not be described herein.
S110: and identifying the financing product which can arouse the interest of the client to be tested as the target financing product.
S111: and carrying out similarity calculation on each hot financial product and the target financial product to obtain the similarity between each hot financial product and the target financial product.
The specific implementation process of the similarity calculation is common knowledge familiar to those skilled in the art, and is not described herein again.
S112: and sequencing the hot financial management products according to the sequence of the similarity from high to low to obtain a hot financial management product sequence.
S113: and selecting the top m hot money management products from the hot money management product sequence, and identifying the hot money management products as candidate money management products.
Wherein m is a positive integer, and the value of m can be set by a technician according to an actual situation, which is not limited in the embodiments of the present application.
S114: and calculating the priority of each candidate financing product based on the customer score of each candidate financing product and the similarity between each candidate financing product and the target financing product.
Wherein, the specific calculation process of calculating the priority of each candidate financing product is obtained based on the customer score of each candidate financing product and the similarity between each candidate financing product and the target financing product, which can be shown in formula (1).
In the formula (1), E uq Representing the priority of the candidate financing product, R representing the index of the candidate financing product, sim (q, R) representing the similarity between the candidate financing product and the target financing product, q representing the index of the target financing product, R r Representing the customer scores of the candidate financing products, sim _ sum representing the total number of the candidate financing products, incount representing the minimum value of the customer scores of the candidate financing products, count representing the maximum value of the customer scores of the candidate financing products, and max { } representing the function of taking the maximum value.
S115: and selecting candidate financing products with the priority greater than a preset priority threshold value from the candidate financing products as the financing products to be recommended.
S116: and constructing a financial product list recommended to the client to be tested based on each financial product to be recommended, and displaying the financial product list to the client to be tested through a front-end interface.
Optionally, the financial product list of the client to be tested can be stored in the preset database.
To sum up, the embodiment determines the financial product recommended to the client to be tested based on the similarity between the hot financial product and the target financial product and the client score of the hot financial product as reference basis, and the target financial product is a financial product capable of arousing the interest of the client to be tested, so that the interest of the client to be tested can be aroused by the financial product recommended to the client to be tested, and the user experience of the client to be tested is effectively improved.
It should be noted that, in the above embodiment, the step S101 is an optional implementation manner of the financial product recommendation method according to the embodiment of the present application. In addition, S116 mentioned in the above embodiments is also an optional implementation manner of the method for recommending a financial product according to the embodiment of the present application. For this reason, the flow mentioned in the above embodiment can be summarized as the method described in fig. 2.
As shown in fig. 2, a schematic flow chart of another method for recommending financial products according to the embodiment of the present application includes the following steps:
s201: and carrying out big data analysis on the pre-acquired historical behavior log of the client to be tested to obtain the target financial product.
Wherein, the target financing product is a financing product which can arouse the interest of the client to be tested.
S202: and screening a plurality of popular financial management products from the financial management products contained in the business system.
S203: and scoring each thermal financial product according to the behavior times of the client to be detected on each thermal financial product, which are obtained from the business system, to obtain the client score of each thermal financial product.
S204: and calculating the similarity of each popular financial product and the target financial product to obtain the similarity between each popular financial product and the target financial product.
S205: and calculating the priority of each thermal financial product based on the client score of each thermal financial product and the similarity between each thermal financial product and the target financial product.
S206: and selecting the hot money management products with the priority greater than a preset priority threshold value from all the hot money management products as money management products recommended to the client to be tested.
To sum up, the embodiment determines the financial product recommended to the client to be tested based on the similarity between the hot financial product and the target financial product and the client score of the hot financial product as reference basis, and the target financial product is a financial product capable of arousing the interest of the client to be tested, so that the interest of the client to be tested can be aroused by the financial product recommended to the client to be tested, and the user experience of the client to be tested is effectively improved.
It should be noted that the financial product recommendation provided by the present invention can be used in the artificial intelligence field, the block chain field, the distributed field, the cloud computing field, the big data field, the internet of things field, the mobile internet field, the network security field, the chip field, the virtual reality field, the augmented reality field, the holographic technology field, the quantum computing field, the quantum communication field, the quantum measurement field, the digital twin field, or the financial field. The above description is only an example and does not limit the application field of the financial product recommendation provided by the present invention.
The financial product recommendation provided by the invention can be used in the financial field or other fields, for example, can be used in transaction application scenes in the financial field. The other fields are arbitrary fields other than the financial field, for example, the electric power field. The above description is only an example and does not limit the application field of the financial product recommendation provided by the present invention.
Corresponding to the financial product recommendation method provided by the embodiment of the application, the embodiment of the application also provides a financial product recommendation device.
As shown in fig. 3, an architecture diagram of a financial product recommendation device provided in the embodiment of the present application includes:
the analysis unit 100 is used for performing big data analysis on a pre-acquired historical behavior log of a client to be tested to obtain a target financial product; the target financing product is a financing product which can arouse the interest of the client to be tested.
The screening unit 200 is used for screening a plurality of hot financial management products from the financial management products contained in the business system.
Optionally, the screening unit 200 is specifically configured to: acquiring the times of customer behaviors of each financial product in a preset time period from a business system; sequencing each financing product according to the sequence of the number of times of the client behaviors from large to small to obtain a financing product sequence; selecting front n financial products from the financial product sequence, and marking the front n financial products as popular financial products; n is a positive integer.
The screening unit 200 is specifically configured to: and acquiring the time of coming into market of each financing product from the business system, and identifying the financing product with the time of coming into market in a preset time range as a hot financing product.
The screening unit 200 is specifically configured to: and acquiring the historical evaluation times of each financial product from the business system, and identifying the financial products with the historical evaluation times larger than a preset threshold as hot financial products.
And the scoring unit 300 is configured to score each thermal financial product according to the behavior frequency of the to-be-tested customer on each thermal financial product, which is obtained from the business system, so as to obtain a customer score of each thermal financial product.
And the similarity calculation unit 400 is used for calculating the similarity between each thermal management product and the target management product to obtain the similarity between each thermal management product and the target management product.
And the priority calculating unit 500 is used for calculating the priority of each thermal management product based on the customer score of each thermal management product and the similarity between each thermal management product and the target management product.
Optionally, the priority calculating unit 500 is specifically configured to: sequencing each hot financial product according to the sequence of similarity from high to low to obtain a hot financial product sequence; selecting the top m hot money management products from the hot money management product sequence, and identifying the hot money management products as candidate money management products; m is a positive integer; and calculating the priority of each candidate financing product based on the customer score of each candidate financing product and the similarity between each candidate financing product and the target financing product.
The selecting unit 600 is configured to select a hot money management product with a priority greater than a preset priority threshold from the hot money management products, and use the hot money management product as a money management product recommended to the customer to be tested.
Optionally, the selecting unit 600 is specifically configured to: selecting candidate financing products with the priority greater than a preset priority threshold value from the candidate financing products as financing products to be recommended; and constructing a financing product list recommended to the client to be tested based on each financing product to be recommended, and displaying the financing product list to the client to be tested through a front-end interface.
To sum up, the embodiment determines the financial product recommended to the client to be tested based on the similarity between the hot financial product and the target financial product and the client score of the hot financial product as reference basis, and the target financial product is a financial product capable of arousing the interest of the client to be tested, so that the interest of the client to be tested can be aroused by the financial product recommended to the client to be tested, and the user experience of the client to be tested is effectively improved.
The application also provides a computer readable storage medium, which comprises a stored program, wherein the program executes the financial product recommendation method provided by the application.
The application also provides a financial product recommendation device, including: a processor, memory, and a bus. The processor is connected with the memory through a bus, the memory is used for storing programs, and the processor is used for running the programs, wherein when the programs are run, the financial product recommendation method provided by the application is executed, and the method comprises the following steps:
big data analysis is carried out on a history behavior log of a client to be detected, which is obtained in advance, so that a target financial product is obtained; the target financing product is a financing product which can arouse the interest of the client to be tested;
screening a plurality of popular financial products from various financial products contained in a business system;
scoring each thermal management product according to the behavior frequency of the customer to be tested on each thermal management product obtained from the service system to obtain a customer score of each thermal management product;
carrying out similarity calculation on each hot financial management product and the target financial management product to obtain the similarity between each hot financial management product and the target financial management product;
calculating the priority of each hot financial product based on the customer score of each hot financial product and the similarity between each hot financial product and the target financial product;
and selecting the hot money management products with the priority greater than a preset priority threshold value from the hot money management products as the money management products recommended to the client to be tested.
Specifically, on the basis of the above embodiment, the screening out a plurality of hot money management products from the money management products included in the business system includes:
acquiring the times of customer behaviors of each financial product in a preset time period from a business system;
sequencing the financial products according to the sequence of the number of times of the customer behaviors from large to small to obtain a financial product sequence;
selecting front n financial products from the financial product sequence, and marking the front n financial products as popular financial products; n is a positive integer.
Specifically, on the basis of the above embodiment, the screening out a plurality of hot money management products from the money management products included in the business system includes:
and acquiring the time to market of each financing product from the business system, and identifying the financing products with the time to market within a preset time range as hot financing products.
Specifically, on the basis of the above embodiment, the screening out a plurality of hot money management products from the money management products included in the business system includes:
and acquiring the historical evaluation times of each financial product from the business system, and identifying the financial products with the historical evaluation times larger than a preset threshold as hot financial products.
Specifically, on the basis of the above embodiment, the calculating the priority of each of the thermal financial products based on the customer score of each of the thermal financial products and the similarity between each of the thermal financial products and the target financial product includes:
sequencing the hot money management products according to the sequence of similarity from high to low to obtain a hot money management product sequence;
selecting the top m hot money management products from the hot money management product sequence, and identifying the hot money management products as candidate money management products; m is a positive integer;
and calculating the priority of each candidate financing product based on the customer score of each candidate financing product and the similarity between each candidate financing product and the target financing product.
Specifically, on the basis of the above embodiment, selecting a hot money management product with a priority greater than a preset priority threshold from among the hot money management products as a money management product recommended to the customer to be tested includes:
selecting candidate financing products with the priority greater than a preset priority threshold value from the candidate financing products as financing products to be recommended;
and constructing a financing product list recommended to the client to be tested based on each financing product to be recommended, and displaying the financing product list to the client to be tested through a front-end interface.
The functions described in the method of the embodiment of the present application, if implemented in the form of software functional units and sold or used as independent products, may be stored in a storage medium readable by a computing device. Based on such understanding, part of the contribution to the prior art of the embodiments of the present application or part of the technical solution may be embodied in the form of a software product stored in a storage medium and including several instructions for causing a computing device (which may be a personal computer, a server, a mobile computing device or a network device) to execute all or part of the steps of the method described in the embodiments of the present application. And the aforementioned storage medium includes: u disk, removable hard disk, read only memory, random access memory, magnetic or optical disk, etc. for storing program codes.
The embodiments are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same or similar parts among the embodiments are referred to each other.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. 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 application. Thus, the present application 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 financial product recommendation method, comprising:
carrying out big data analysis on a pre-acquired historical behavior log of a client to be detected to obtain a target financing product; the target financing product is a financing product which can arouse the interest of the client to be tested;
screening a plurality of hot financing products from each financing product contained in the business system;
scoring each thermal management product according to the behavior frequency of the customer to be tested on each thermal management product obtained from the service system to obtain a customer score of each thermal management product;
carrying out similarity calculation on each popular financial management product and the target financial management product to obtain the similarity between each popular financial management product and the target financial management product;
calculating the priority of each popular financial product based on the customer score of each popular financial product and the similarity between each popular financial product and the target financial product;
and selecting the hot money management products with the priority greater than a preset priority threshold value from the hot money management products as the money management products recommended to the client to be tested.
2. The method of claim 1, wherein screening a plurality of popular financial products from the various financial products included in the business system comprises:
acquiring the times of customer behaviors of each financial product in a preset time period from a business system;
sequencing the financial products according to the sequence of the number of times of the customer behaviors from large to small to obtain a financial product sequence;
selecting front n financial products from the financial product sequence, and marking the front n financial products as popular financial products; n is a positive integer.
3. The method of claim 1, wherein screening a plurality of popular financial products from the various financial products included in the business system comprises:
and acquiring the time of coming into market of each financing product from the business system, and identifying the financing product with the time of coming into market in a preset time range as a hot financing product.
4. The method of claim 1, wherein said screening a plurality of hot financial products from the various financial products included in the business system comprises:
and acquiring the historical evaluation times of each financial product from the business system, and identifying the financial products with the historical evaluation times larger than a preset threshold as hot financial products.
5. The method of claim 1, wherein said calculating a priority for each of said thermal financial products based on a customer score for each of said thermal financial products and a similarity between each of said thermal financial products and said target financial product comprises:
sequencing the hot money management products according to the sequence of similarity from high to low to obtain a hot money management product sequence;
selecting the top m hot money management products from the hot money management product sequence, and identifying the hot money management products as candidate money management products; m is a positive integer;
and calculating the priority of each candidate financing product based on the customer score of each candidate financing product and the similarity between each candidate financing product and the target financing product.
6. The method as claimed in claim 5, wherein said selecting a hot money management product with a priority greater than a preset priority threshold from among said hot money management products as the money management product recommended to said customer to be tested comprises:
selecting candidate financing products with the priority greater than a preset priority threshold value from the candidate financing products as financing products to be recommended;
and constructing a financing product list recommended to the client to be tested based on each financing product to be recommended, and displaying the financing product list to the client to be tested through a front-end interface.
7. A financial product recommendation device, comprising:
the analysis unit is used for carrying out big data analysis on the pre-acquired historical behavior log of the client to be tested to obtain a target financial product; the target financing product is a financing product which can arouse the interest of the client to be tested;
the screening unit is used for screening a plurality of hot financial management products from the financial management products contained in the business system;
the scoring unit is used for scoring each thermal financial product according to the behavior frequency of the client to be tested on each thermal financial product, which is obtained from the service system, so as to obtain a client score of each thermal financial product;
the similarity calculation unit is used for calculating the similarity of each thermal management product and the target management product to obtain the similarity between each thermal management product and the target management product;
the priority calculating unit is used for calculating the priority of each thermal management product based on the customer score of each thermal management product and the similarity between each thermal management product and the target management product;
and the selecting unit is used for selecting the hot money management products with the priority greater than a preset priority threshold value from the hot money management products as the money management products recommended to the client to be tested.
8. The device according to claim 7, characterized in that the screening unit is particularly configured to:
acquiring the times of customer behaviors of each financial product in a preset time period from a business system;
sequencing all the financial products according to the sequence of the number of times of the client behaviors from small to large to obtain a financial product sequence;
selecting front n financial products from the financial product sequence, and marking the front n financial products as popular financial products; n is a positive integer.
9. A computer-readable storage medium, characterized in that the computer-readable storage medium comprises a stored program, wherein the program executes the financial product recommendation method of any one of claims 1-6.
10. A financial product recommendation apparatus, comprising: a processor, a memory, and a bus; the processor and the memory are connected through the bus;
the memory is used for storing a program, and the processor is used for running the program, wherein the program is used for executing the financial product recommendation method of any one of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211043055.1A CN115375494A (en) | 2022-08-29 | 2022-08-29 | Financial product recommendation method, device, storage medium and equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211043055.1A CN115375494A (en) | 2022-08-29 | 2022-08-29 | Financial product recommendation method, device, storage medium and equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115375494A true CN115375494A (en) | 2022-11-22 |
Family
ID=84070604
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211043055.1A Pending CN115375494A (en) | 2022-08-29 | 2022-08-29 | Financial product recommendation method, device, storage medium and equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115375494A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116385102A (en) * | 2023-03-15 | 2023-07-04 | 中电金信软件有限公司 | Information recommendation method, device, computer equipment and storage medium |
-
2022
- 2022-08-29 CN CN202211043055.1A patent/CN115375494A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116385102A (en) * | 2023-03-15 | 2023-07-04 | 中电金信软件有限公司 | Information recommendation method, device, computer equipment and storage medium |
| CN116385102B (en) * | 2023-03-15 | 2024-05-31 | 中电金信软件有限公司 | Information recommendation method, device, computer equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108363821A (en) | A kind of information-pushing method, device, terminal device and storage medium | |
| US9251292B2 (en) | Search result ranking using query clustering | |
| CN110689438A (en) | Enterprise financial risk scoring method and device, computer equipment and storage medium | |
| CN109063966A (en) | The recognition methods of adventure account and device | |
| JP2002092305A (en) | Score calculating method, and score providing method | |
| EP2778985A1 (en) | Search result ranking by department | |
| CN112435137B (en) | Cheating information detection method and system based on community mining | |
| CN111046297A (en) | Service intelligent matching recommendation method, device, equipment and storage medium based on machine learning algorithm | |
| CN111695938B (en) | Product pushing method and system | |
| CN111966886A (en) | Object recommendation method, object recommendation device, electronic equipment and storage medium | |
| CN111090807A (en) | Knowledge graph-based user identification method and device | |
| CN111626767B (en) | Resource data issuing method, device and equipment | |
| CN111127185A (en) | Credit fraud identification model construction method and device | |
| CN110807667B (en) | Method and device for activating sleeping clients | |
| CN113569162A (en) | Data processing method, device, equipment and storage medium | |
| CN108076032B (en) | Abnormal behavior user identification method and device | |
| CN111429214A (en) | Transaction data-based buyer and seller matching method and device | |
| CN113791837B (en) | Page processing method, device, equipment and storage medium | |
| CN115375494A (en) | Financial product recommendation method, device, storage medium and equipment | |
| CN114896291A (en) | Training method and sequencing method of multi-agent model | |
| CN112449002B (en) | Method, device and equipment for pushing object to be pushed and storage medium | |
| CN113468394A (en) | Data processing method and device, electronic equipment and storage medium | |
| CN110796379B (en) | Risk assessment method, device and equipment of business channel and storage medium | |
| CN116976995A (en) | Multi-target recommendation processing method and device | |
| CN115293291B (en) | Training method and device for sequencing model, sequencing method and device, electronic equipment and medium |
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 |