CN114626894A - Data pushing method, system, device and medium - Google Patents
Data pushing method, system, device and medium Download PDFInfo
- Publication number
- CN114626894A CN114626894A CN202210318535.8A CN202210318535A CN114626894A CN 114626894 A CN114626894 A CN 114626894A CN 202210318535 A CN202210318535 A CN 202210318535A CN 114626894 A CN114626894 A CN 114626894A
- Authority
- CN
- China
- Prior art keywords
- data
- product
- user
- target
- sample
- 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
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0202—Market predictions or forecasting for commercial activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Theoretical Computer Science (AREA)
- Development Economics (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Game Theory and Decision Science (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention relates to the field of artificial intelligence, and provides a data pushing method, which comprises the following steps: receiving user data of a target user provided by a client terminal; obtaining a plurality of product data associated with the user data from a product block chain according to the user data; inputting the user data and the plurality of product data into a pre-trained random forest model, and outputting a product predicted value corresponding to each product data, wherein the product predicted value is used for expressing the association degree of each product data and the target user; selecting one or more target product data from the plurality of product data according to the product predicted value corresponding to each product data; and pushing the one or more target product data to the client terminal. The invention improves the pushing accuracy and the pushing efficiency of the product data.
Description
Technical Field
The embodiment of the invention relates to the field of artificial intelligence, in particular to a data pushing method, a data pushing system, data pushing equipment and a data pushing medium.
Background
At present, products of various banks, rent-merging companies, cash-consuming companies and small credit companies are only displayed in official networks of the companies, and the popularization mode is that various platforms are popularized respectively without unified centralized display, so that information is asymmetric, and much inconvenience is brought to borrowers and credit-assisting institutions. For example, for a borrower, the conventional financing product pushing system is difficult to select a proper financing product suitable for the borrower according to the actual situation of the borrower when the borrower has financing requirements, so that the financing difficulty is improved; for the loan-aid institution, because the information is asymmetric, other intermediaries are easy to charge for one service fee, and the financing difficulty and cost of the user are finally improved; for banks, rental companies and loan companies, there is no centralized carrier for displaying product information, and the respective promotion effects of products are poor. Therefore, how to solve the problems of low data pushing accuracy and low data pushing efficiency of the financing product caused by asymmetric data information in the conventional financing product pushing system becomes a technical problem which needs to be solved urgently at present.
Disclosure of Invention
In view of the above, it is desirable to provide a data pushing method, system, device and readable storage medium, so as to solve the problems of low data pushing accuracy and low data pushing efficiency of financing products caused by asymmetric data information in the existing financing product pushing system.
In order to achieve the above object, an embodiment of the present invention provides a data pushing method, where the method includes:
receiving user data of a target user provided by a client terminal;
obtaining a plurality of product data associated with the user data from a product block chain according to the user data;
inputting the user data and the plurality of product data into a pre-trained random forest model, and outputting a product predicted value corresponding to each product data, wherein the product predicted value is used for expressing the association degree of each product data and the target user;
selecting one or more target product data from the plurality of product data according to the product predicted value corresponding to each product data; and
and pushing the one or more target product data to the client terminal.
Optionally, the step of obtaining a plurality of product data associated with the user data from a product block chain according to the user data includes:
performing security verification on the target user based on the user data, and judging whether the target user has the access right of the product block chain;
and if the target user has the access right of the product block chain, generating a data acquisition request of the product block chain according to the user data, and sending the data acquisition request to the product block chain, so that the product block chain returns a plurality of product data related to the user data according to the data acquisition request.
Optionally, the step of constructing the random forest model includes:
acquiring sample data;
performing product pre-recommendation operation on each sample user in the sample data to obtain a plurality of recommendation result data, wherein the sample data comprises a plurality of sample user data and a plurality of sample product data;
dividing the plurality of sample data into a training set and a verification set;
constructing at least one decision tree model according to the training set and the plurality of recommendation result data;
training each decision tree model through the training set to obtain a plurality of first decision tree models;
verifying and optimizing each first decision tree model through the verification set to obtain a plurality of second decision tree models; and
combining the plurality of second decision tree models to obtain the random forest model.
Optionally, the step of performing a product pre-recommendation operation on each sample user in the sample data to obtain multiple recommendation result data includes:
acquiring basic information of each sample user and historical behavior data of each sample user;
obtaining a plurality of initial recommendation result data of each sample user according to the basic information of each sample user;
screening out initial recommendation result data from a plurality of initial recommendation result data of each sample user according to the historical behavior data of the sample user; and
and taking the screened initial recommendation result data as the recommendation result data of the sample user.
Optionally, the step of selecting one or more target product data from the plurality of product data according to the product predicted value corresponding to each product data includes:
judging whether the predicted value of each product is greater than a preset threshold value or not; and
and respectively defining the product data with the product predicted value larger than the preset threshold value as target product data to obtain one or more target product data.
Optionally, the step of pushing the one or more target product data to the client terminal includes:
sorting the one or more target product data according to the product forecast value of each target product data to obtain a sorting result; and
and generating a push list according to the sorting result, and pushing a preset number of target product data in the push list to the client terminal.
Optionally, the method further includes: uploading the one or more target product data to the product blockchain.
In order to achieve the above object, an embodiment of the present invention further provides a data pushing system, including:
the receiving module is used for receiving user data of a target user provided by a client terminal;
the acquisition module is used for acquiring a plurality of product data related to the user data from a product block chain according to the user data;
the prediction module is used for inputting the user data and the plurality of product data into a pre-trained random forest model and outputting a product prediction value corresponding to each product data, wherein the product prediction value is used for expressing the association degree of each product data and the target user;
the selection module is used for selecting one or more target product data from the plurality of product data according to the product predicted value corresponding to each product data; and
and the pushing module is used for pushing the one or more target product data to the client terminal.
To achieve the above object, an embodiment of the present invention further provides a computer device, where the computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and the computer program, when executed by the processor, implements the steps of the data pushing method as described above.
To achieve the above object, an embodiment of the present invention further provides a computer-readable storage medium, in which a computer program is stored, where the computer program is executable by at least one processor, so as to cause the at least one processor to execute the steps of the data pushing method as described above.
According to the data pushing method, the data pushing system, the computer equipment and the computer readable storage medium, the block chain technology is used for getting through compliance organizations such as banks, rental companies and small credit companies, the problem that the financing product pushing system is asymmetric in data information is solved, and the pushing accuracy and the pushing efficiency of the financing product data are improved; target product data corresponding to each user is obtained through the random forest model, and the pushing accuracy and the pushing efficiency of financing product data are further improved.
Drawings
FIG. 1 is a schematic flow chart of a data pushing method according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of program modules of a second embodiment of a data pushing system according to the present invention;
fig. 3 is a schematic diagram of a hardware structure of a third embodiment of the computer device according to the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention. 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.
It should be noted that the description relating to "first", "second", etc. in the present invention is for descriptive purposes only and is not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the feature. In addition, technical solutions between various embodiments may be combined with each other, but must be realized by a person skilled in the art, and when the technical solutions are contradictory or cannot be realized, such a combination should not be considered to exist, and is not within the protection scope of the present invention.
Example one
Referring to fig. 1, a flowchart illustrating steps of a data pushing method according to an embodiment of the present invention is shown. It is to be understood that the flow charts in the embodiments of the present method are not intended to limit the order in which the steps are performed. The data push system in the present embodiment may be executed in the computer device 2, and the following description is made by taking the computer device 2 as an execution subject. The details are as follows.
Step S100, receiving the user data of the target user provided by the client terminal.
The user data includes the age, gender, identification number, home address, academic calendar, occupation, working age, annual income, marital status, risk tolerance, product access path, etc. of the target user. The target user can log in an information sharing platform through the client terminal, and basic information of the target user, such as age, sex, identity card number, family address, academic history, occupation, working year, annual income and marital status, is edited on the information sharing platform; the information sharing platform can also analyze the risk bearing capacity of the target user according to the basic information of the target user and acquire the product access path of the target user according to the historical behavior data of the target user. The client terminal can upload the user data of the target user on the information sharing platform to a data pushing system.
Step S102, a plurality of product data related to the user data are obtained from a product block chain according to the user data.
After obtaining the user data, a plurality of product data may be matched from a product blockchain according to age, gender, identification number, home address, academic history, occupation, working age, average monthly income flow, annual income, marital status, risk tolerance of the target user. Whether the product data is matched with the target user or not can be determined according to the product label of each product data. For example, the label for a large running water credit may be: and when the average monthly income running water of the target user is greater than or equal to 4 ten thousand, matching the target user with the large running water credit of the target user, namely, the large running water credit is the product data associated with the target user.
The product block chain can be a product information sharing database commonly maintained by each home-held financial institution, and the product information sharing database has the characteristics of non-counterfeiting, whole-course trace, traceability, public transparency, collective maintenance and the like. The product block chain can also get through compliance organizations such as banks, rental companies, small credit companies and the like, and 1 or more nodes can be distributed according to the scale of each organization, so that each organization can compile financial product information in the nodes, and the product block chain can classify product characteristics according to certain rules. Taking loan product information as an example: the loan product information may be classified into 7 categories or 17 categories. The 7 major classes are: fixed property mortgage type loans, supply chain loans, car loans, entrepreneur loans, fixed professional group loans, free professional loans, network micropayments. Subclass 17 is respectively: fixed-asset mortgage-type loans: 1. property mortgage loans (including residential houses, house-to-house rooms, economically applicable rooms, commercial and residential dual-purpose rooms and the like); 2. mortgages of commercial nature (including office buildings, shops, plants, land, etc.); 3. other fixed assets (e.g., gas stations, hydroelectric power plants, large non-mobile industrial equipment, etc.). Supply chain loan: 4. small supply chain financing (within 300 million); 5. medium and large supply chains (300 million and more) are financed. Vehicle loan: 6. vehicle credit (GPS credit, pure credit without GPS, mortgage credit); 7. vehicle credit for mortgage (GPS credit, pure credit without GPS, mortgage credit). And (3) loan of the entrepreneur: 8. the major business owner is credited (more than 20 staff or more than 100 ten thousand taxes per year meet one of the credits); 9. small business owner credit (20 employees and 100 million taxes per year); 10. individual industrial and commercial businesses are credited. Loan of fixed professional population: 11. excellent occupation credit (monthly accumulation fund payment base > 2000); 12. and (4) ordinary professional loan. Free occupational loan: 13. large running water credits (monthly income running water >4 ten thousand); 14. ordinary free occupational loan. Consumption of financial/network petty loans: 15. less than 2 ten thousand petty loans; 16. 2-10 ten thousand petty loans; 17. over 10 ten thousand small loans.
Wherein, the confirmation of each block needs to obtain the consent of more than 80% of the members, and when a new card holding mechanism wants to join the chain, the consent of more than 80% of the members in the chain needs to be obtained. The chain provides an API interface for the platform, and the platform calls the interface to acquire all product information and faces the C end, so that the authenticity of all products can be ensured, all borrowed users can directly connect financing products of banks, loan-blending companies and small credit companies, illegal charging in intermediate links can be avoided, the financing threshold of the users is reduced, the financing cost is reduced, and information asymmetry is eliminated.
In an exemplary embodiment, the step S102 may include a step S200 to a step S202, where: step S200, carrying out safety verification on the target user based on the user data, and judging whether the target user has the access right of the product block chain; step S202, if the target user has the access right of the product block chain, a data acquisition request of the product block chain is generated according to the user data, and the data acquisition request is sent to the product block chain, so that the product block chain returns a plurality of product data related to the user data according to the data acquisition request. The embodiment may verify the user data to determine whether a user associated with the user data has an authority to acquire data from a product block chain, and if the user has the authority to acquire data from the product block chain, open a product data query entry for a client terminal associated with the user. The threshold and difficulty of information acquisition of the target user are reduced, the information is more transparent, the authenticity of data is improved, and the access efficiency of a financial institution and the user is improved; and the data security is improved by carrying out security verification on the target user. In this embodiment, a product data query entry is opened according to the authority of the user, for example, security verification may be performed on the target user according to an identity card number or other user identification of the user to determine whether the target user has the usage authority of the product data query entry, and security of user data is ensured by performing security verification on the target user. The system can intelligently recommend proper products according to behavior data of the system, avoids unqualified borrowing products such as high interest loan and road set loan, applies for the products by one key, reduces the threshold and difficulty of information acquisition and improves the financing efficiency; for the intermediary institutions, the products of the financial institutions in all the alliance chains can be connected in one access mode, legal risks possibly caused by agency of non-compliant products are avoided, the access efficiency of the financial institutions is greatly improved, and the information is more transparent; the system carries out intelligent recommendation, so that the training threshold of the intermediary staff is saved; for financial institutions, the loan service recommendation system opens own product information, is convenient for loan service development and brand propagation, and systematically recommends products to appropriate users, so that the overdue rate of loan products is reduced, and a larger service development space is brought.
And S104, inputting the user data and the plurality of product data into a pre-trained random forest model, and outputting a product predicted value corresponding to each product data, wherein the product predicted value is used for expressing the association degree of each product data and the target user.
The association degree between each product data and the target user can be determined by the matching degree between the label of each product data and the user data of the target user. For example, the labels for large running water credits are: the running water of monthly income is 4 ten thousand, and the matching degree of the target user whose average running water of monthly income is 4 ten thousand may be previously defined as 1, the matching degree of the target user whose average running water of monthly income is more than 3 ten thousand and less than 4 ten thousand may be defined as 0.6, and the matching degree of the target user whose average running water of monthly income is more than 1 ten thousand and less than 3 ten thousand may be defined as 0.3.
The embodiment may construct the random forest model according to sample user data of a plurality of sample users (borrower behavior data that may affect product recommendation results in the user data), sample product data of a plurality of sample products (real financial product data stored in a product block chain), and a plurality of recommendation result data (recommendation results obtained by pre-recommending products for each sample user), and may specifically include the following steps: step S300 to step S312, wherein: step S300, sample data is obtained; step S302, performing product pre-recommendation operation on each sample user in the sample data to obtain a plurality of recommendation result data, wherein the sample data comprises a plurality of sample user data and a plurality of sample product data; step S304, dividing the plurality of sample data into a training set and a verification set; step S306, constructing at least one decision tree model according to the training set and the plurality of recommendation result data; step S308, training each decision tree model through the training set to obtain a plurality of first decision tree models; step S310, carrying out verification optimization on each first decision tree model through the verification set to obtain a plurality of second decision tree models; and step S312, combining the plurality of second decision tree models to obtain the random forest model. In this embodiment, preliminary product matching may be performed on the sample user according to the user basic information to match a plurality of products (a plurality of recommendation result data) for the sample user. For convenience of understanding, the present embodiment also provides a specific example of constructing a decision tree model according to the training set and the sample product data: taking sample user data and sample product data of the training set as a first branch of a first node in a decision tree (i.e., an input of the decision tree); taking the recommendation data as a first branch of a second node in the decision tree (i.e., the output of the decision tree); at least one decision tree is constructed based on the first branch of the first node and the first branch of a second node.
In an exemplary embodiment, the step S302 may include a step S400 to a step S406, where: step S400, acquiring basic information of each sample user and historical behavior data of each sample user; step S402, obtaining a plurality of initial recommendation result data of each sample user according to the basic information of each sample user; step S404, screening out one initial recommendation result data from a plurality of initial recommendation result data of each sample user according to the historical behavior data of the sample user; and step S406, taking the screened initial recommendation result data as the recommendation result data of the sample user. In this embodiment, the user preference may be determined according to the historical behavior data of the user, and one initial recommendation result data is screened out from a plurality of initial recommendation result data according to the user preference; wherein the historical behavior data may be historical behavior data used on the financial platform, such as ordering data, browsing data, purchasing data, and the like; the basic information comprises gender, age, height and/or weight, occupation and income range; the operation behavior comprises the searching condition of the product, the click rate of the product, the browsing duration of the product and the selection condition of the product. According to the embodiment, the recommendation result data is obtained through the basic information and the historical behavior data of the sample user, so that the accuracy of the recommendation result data is improved, and the pushing efficiency is improved.
And S106, selecting one or more target product data from the plurality of product data according to the product predicted value corresponding to each product data.
When the product predicted value corresponding to each product data is obtained, one or more target product data may be selected from the plurality of product data according to the size of the product predicted value corresponding to each product data. Specifically, a preset value may be preconfigured to select one or more target product data with a product predicted value greater than the preset value from the plurality of product data.
In an exemplary embodiment, the step S106 may include a step S500 to a step S502, where: step S500, judging whether the predicted value of each product is greater than a preset threshold value; and step S502, respectively defining the product data with the product predicted value larger than the preset threshold value as target product data to obtain one or more target product data. In order to improve the accuracy of the product data, the embodiment filters the product data with a low product prediction value through a preset threshold value, so that the accuracy of the product data is improved.
Step S108, pushing the one or more target product data to the client terminal.
In an exemplary embodiment, the step S108 may include a step S600 to a step S602, wherein: s600, sorting the one or more target product data according to the product forecast value of each target product data to obtain a sorting result; and step S602, generating a push list according to the sorting result, and pushing the preset number of target product data in the push list to the client terminal. In the embodiment, one or more target product data are sequenced, and the target product data with the preset quantity in the push list are pushed to the client terminal, so that the problem of excessive pushed products is avoided.
According to the embodiment, compliance organizations such as banks, rental companies and small credit companies are reached based on the block chain technology, the problem that the financing product pushing system is asymmetric in data information is solved, and the pushing accuracy and the pushing efficiency of the financing product data are improved; target product data corresponding to each user is obtained through the random forest model, and the pushing accuracy and the pushing efficiency of financing product data are further improved.
In an exemplary embodiment, the data pushing method may further include step S700: uploading the one or more target product data to a product blockchain.
For example, uploading the one or more target product data to a product blockchain may ensure its security and fair transparency. The product block chain referred to in this example is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, consensus mechanism, encryption algorithm, and the like. A block chain (Blockchain), which is essentially a decentralized database, is a series of data blocks associated by using a cryptographic method, and each data block contains information of a batch of network transactions, so as to verify the validity (anti-counterfeiting) of the information and generate a next block. The blockchain may include a blockchain underlying platform, a platform product service layer, an application service layer, and the like.
Example two
Fig. 2 is a schematic diagram of program modules of a data pushing system according to a second embodiment of the present invention. The data pushing system 20 may include or be divided into one or more program modules, which are stored in a storage medium and executed by one or more processors to implement the present invention and implement the data pushing method described above. The program modules referred to in the embodiments of the present invention refer to a series of computer program instruction segments capable of performing specific functions, and are more suitable than the program itself for describing the execution process of the data push system 20 in the storage medium. The following description will specifically describe the functions of the program modules of the present embodiment:
a receiving module 200, configured to receive user data of a target user provided by a client terminal.
An obtaining module 202, configured to obtain, according to the user data, a plurality of product data associated with the user data from a product block chain.
The prediction module 204 is configured to input the user data and the plurality of product data into a pre-trained random forest model, and output a product prediction value corresponding to each product data, where the product prediction value is used to represent a degree of association between each product data and the target user.
A selecting module 206, configured to select one or more target product data from the multiple product data according to the product predicted value corresponding to each product data.
A pushing module 208, configured to push the one or more target product data to the client terminal.
Illustratively, the obtaining module 202 is further configured to: performing security verification on the target user based on the user data to judge whether the target user has the access right of the product block chain; and if the target user has the access right of the product block chain, generating a data acquisition request of the product block chain according to the user data, and sending the data acquisition request to the product block chain, so that the product block chain returns a plurality of product data related to the user data according to the data acquisition request.
Illustratively, the data pushing system 20 further includes a building module, configured to obtain sample data; performing product pre-recommendation operation on each sample user in the sample data to obtain a plurality of recommendation result data, wherein the sample data comprises a plurality of sample user data and a plurality of sample product data; dividing the plurality of sample data into a training set and a verification set; constructing at least one decision tree model according to the training set and the plurality of recommendation result data; training each decision tree model through the training set to obtain a plurality of first decision tree models; verifying and optimizing each first decision tree model through the verification set to obtain a plurality of second decision tree models; and combining the plurality of second decision tree models to obtain the random forest model.
Illustratively, the building module is further configured to: acquiring basic information of each sample user and historical behavior data of each sample user on the financial platform; obtaining a plurality of initial recommendation result data of each sample user according to the basic information of each sample user; screening out initial recommendation result data from a plurality of initial recommendation result data of each sample user according to the historical behavior data of the sample user; and taking the screened initial recommendation result data as the recommendation result data of the sample user.
Illustratively, the selecting module 206 is further configured to: judging whether the predicted value of each product is greater than a preset threshold value or not; and respectively defining the product data with the product predicted value larger than the preset threshold value as target product data to obtain one or more target product data.
Illustratively, the pushing module 208 is further configured to: sorting the one or more target product data according to the product forecast value of each target product data to obtain a sorting result; and generating a push list according to the sorting result, and pushing a preset number of target product data in the push list to the client terminal.
Illustratively, the data pushing system 20 further comprises an uploading module, which is configured to upload the one or more target product data to a product blockchain.
EXAMPLE III
Fig. 3 is a schematic diagram of a hardware architecture of a computer device according to a third embodiment of the present invention. In the present embodiment, the computer device 2 is a device capable of automatically performing numerical calculation and/or information processing in accordance with a command set in advance or stored. The computer device 2 may be a rack server, a blade server, a tower server or a rack server (including an independent server or a server cluster composed of a plurality of servers), and the like. As shown, the computer device 2 includes, but is not limited to, at least a memory 21, a processor 22, a network interface 23, and a data push system 20 communicatively coupled to each other via a system bus.
In this embodiment, the memory 21 includes at least one type of computer-readable storage medium including a flash memory, a hard disk, a multimedia card, a card-type memory (e.g., SD or DX memory, etc.), a Random Access Memory (RAM), a Static Random Access Memory (SRAM), a Read Only Memory (ROM), an Electrically Erasable Programmable Read Only Memory (EEPROM), a Programmable Read Only Memory (PROM), a magnetic memory, a magnetic disk, an optical disk, and the like. In some embodiments, the storage 21 may be an internal storage unit of the computer device 2, such as a hard disk or a memory of the computer device 2. In other embodiments, the memory 21 may also be an external storage device of the computer device 2, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like, provided on the computer device 2. Of course, the memory 21 may also comprise both internal and external memory units of the computer device 2. In this embodiment, the memory 21 is generally used for storing an operating system installed in the computer device 2 and various application software, such as the program codes of the data pushing system 20 in the second embodiment. Further, the memory 21 may also be used to temporarily store various types of data that have been output or are to be output.
The network interface 23 may comprise a wireless network interface or a wired network interface, and the network interface 23 is typically used for establishing a communication connection between the computer device 2 and other electronic apparatuses. For example, the network interface 23 is used to connect the computer device 2 to an external terminal through a network, establish a data transmission channel and a communication connection between the computer device 2 and the external terminal, and the like. The network may be a wireless or wired network such as an Intranet (Intranet), the Internet (Internet), a Global System of Mobile communication i/On (GSM), a Wideband Code Division Multiple Access (WCDMA), a 4G network, a 5G network, Bluetooth (Bluetooth), Wi-Fi, and the like.
It is noted that fig. 3 only shows the computer device 2 with components 20-23, but it is to be understood that not all shown components are required to be implemented, and that more or less components may be implemented instead.
In this embodiment, the data pushing system 20 stored in the memory 21 can be further divided into one or more program modules, and the one or more program modules are stored in the memory 21 and executed by one or more processors (in this embodiment, the processor 22) to complete the present invention.
For example, fig. 2 shows a schematic diagram of program modules for implementing the data pushing system 20 according to the second embodiment of the present invention, in this embodiment, the data pushing system 20 may be divided into a receiving module 200, an obtaining module 202, a predicting module 204, a selecting module 206, and a pushing module 208. The program modules referred to herein are a series of computer program instruction segments that can perform specific functions, and are more suitable than programs for describing the execution process of the data push system 20 in the computer device 2. The specific functions of the program modules 200 and 208 have been described in detail in the second embodiment, and are not described herein again.
Example four
The present embodiment also provides a computer-readable storage medium, such as a flash memory, a hard disk, a multimedia card, a card-type memory (e.g., SD or DX memory, etc.), a Random Access Memory (RAM), a Static Random Access Memory (SRAM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a programmable read-only memory (PROM), a magnetic memory, a magnetic disk, an optical disk, a server, an App application mall, etc., on which a computer program is stored, which when executed by a processor implements corresponding functions. The computer-readable storage medium data pushing system 20 of the present embodiment, when executed by a processor, implements the data pushing method of the first embodiment.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner.
The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (10)
1. A method for pushing data, the method comprising:
receiving user data of a target user provided by a client terminal;
obtaining a plurality of product data associated with the user data from a product block chain according to the user data;
inputting the user data and the plurality of product data into a pre-trained random forest model, and outputting a product predicted value corresponding to each product data, wherein the product predicted value is used for representing the association degree of each product data and the target user;
selecting one or more target product data from the plurality of product data according to the product predicted value corresponding to each product data; and
and pushing the one or more target product data to the client terminal.
2. The data pushing method of claim 1, wherein the step of obtaining a plurality of product data associated with the user data from a product blockchain according to the user data comprises:
performing security verification on the target user based on the user data, and judging whether the target user has the access right of the product block chain; and
and if the target user has the access right of the product block chain, generating a data acquisition request of the product block chain according to the user data, and sending the data acquisition request to the product block chain, so that the product block chain returns a plurality of product data related to the user data according to the data acquisition request.
3. A data push method as claimed in claim 1, characterized in that the step of constructing the random forest model comprises:
acquiring sample data;
performing product pre-recommendation operation on each sample user in the sample data to obtain a plurality of recommendation result data, wherein the sample data comprises a plurality of sample user data and a plurality of sample product data;
dividing the plurality of sample data into a training set and a verification set;
constructing at least one decision tree model according to the training set and the plurality of recommendation result data;
training each decision tree model through the training set to obtain a plurality of first decision tree models;
verifying and optimizing each first decision tree model through the verification set to obtain a plurality of second decision tree models; and
combining the plurality of second decision tree models to obtain the random forest model.
4. The data pushing method of claim 3, wherein the step of performing a product pre-recommendation operation on each sample user in the sample data to obtain a plurality of recommendation result data comprises:
acquiring basic information of each sample user and historical behavior data of each sample user;
obtaining a plurality of initial recommendation result data of each sample user according to the basic information of each sample user;
screening out initial recommendation result data from a plurality of initial recommendation result data of each sample user according to the historical behavior data of the sample user; and
and taking the screened initial recommendation result data as the recommendation result data of the sample user.
5. The data pushing method according to claim 1, wherein the step of selecting one or more target product data from the plurality of product data according to the product predicted value corresponding to each product data comprises:
judging whether the predicted value of each product is greater than a preset threshold value or not; and
and respectively defining the product data with the product predicted value larger than the preset threshold value as target product data to obtain one or more target product data.
6. The data pushing method of claim 1, wherein the step of pushing the one or more target product data to the client terminal comprises:
sorting the one or more target product data according to the product forecast value of each target product data to obtain a sorting result; and
and generating a push list according to the sorting result, and pushing a preset number of target product data in the push list to the client terminal.
7. The data pushing method of any one of claims 1 to 6, further comprising: uploading the one or more target product data to the product blockchain.
8. A data push system, comprising:
the receiving module is used for receiving user data of a target user provided by a client terminal;
the acquisition module is used for acquiring a plurality of product data related to the user data from a product block chain according to the user data;
the prediction module is used for inputting the user data and the plurality of product data into a pre-trained random forest model and outputting a product prediction value corresponding to each product data, wherein the product prediction value is used for expressing the association degree of each product data and the target user;
the selection module is used for selecting one or more target product data from the plurality of product data according to the product predicted value corresponding to each product data; and
and the pushing module is used for pushing the one or more target product data to the client terminal.
9. A computer arrangement comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the computer program, when executed by the processor, implements the steps of the data push method according to any of claims 1 to 7.
10. A computer-readable storage medium, in which a computer program is stored which is executable by at least one processor to cause the at least one processor to perform the steps of the data push method according to any one of claims 1 to 7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210318535.8A CN114626894A (en) | 2022-03-29 | 2022-03-29 | Data pushing method, system, device and medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210318535.8A CN114626894A (en) | 2022-03-29 | 2022-03-29 | Data pushing method, system, device and medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN114626894A true CN114626894A (en) | 2022-06-14 |
Family
ID=81905162
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210318535.8A Pending CN114626894A (en) | 2022-03-29 | 2022-03-29 | Data pushing method, system, device and medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114626894A (en) |
-
2022
- 2022-03-29 CN CN202210318535.8A patent/CN114626894A/en active Pending
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Aretz et al. | Access to collateral and the democratization of credit: France's reform of the Napoleonic Security Code | |
CN111881158B (en) | Processing method, device, computer system and readable storage medium for managing report data | |
CN103700003A (en) | House online direct renting method and system based on wish conformity matching | |
CN111861716B (en) | Method for generating monitoring early warning level in credit based on software system | |
CN110503564A (en) | Save case processing method, system, equipment and storage medium from damage based on big data | |
CN109325845A (en) | A kind of financial product intelligent recommendation method and system | |
CN112817939A (en) | Construction method of data wind control model and data wind control model | |
CN110349039A (en) | Complaint risk appraisal procedure, system, computer equipment and readable storage medium storing program for executing | |
CN113205402A (en) | Account checking method and device, electronic equipment and computer readable medium | |
CN111433806A (en) | System and method for analyzing crowd funding platform | |
Grize | Applications of statistics in the field of general insurance: An overview | |
CN110197426B (en) | Credit scoring model building method, device and readable storage medium | |
CN102496126A (en) | Custody asset transaction data monitoring equipment | |
CN115605903A (en) | System and method for quickly composing, launching and configuring a customizable second-level migration structure with a built-in audit and monitoring structure | |
CN115170294A (en) | Client classification method and device and server | |
CN110544165B (en) | Credit risk score card creating method and device and electronic equipment | |
CN114626894A (en) | Data pushing method, system, device and medium | |
CN112288559B (en) | Stock right-based financial data accounting method, device, equipment and storage medium | |
CN116091242A (en) | Recommended product combination generation method and device, electronic equipment and storage medium | |
CN116703555A (en) | Early warning method, early warning device, electronic equipment and computer readable medium | |
CN114693428A (en) | Data determination method and device, computer readable storage medium and electronic equipment | |
CN112598499A (en) | Method and device for determining credit limit | |
CN111899025A (en) | Processing method and device for loan service | |
CN111984704A (en) | Data screening method and device | |
EP2924632A1 (en) | Insurance product compilation system |
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 |