Auxiliary card output method and device of intelligent card, computer equipment and storage medium

Abstract

The invention discloses an auxiliary card output method and device of a smart card, computer equipment and a storage medium, relates to the technical field of artificial intelligence, is applied to an auxiliary card recommendation scene of credit cards related to financial services, and comprises the following steps: collecting main card data of smart cards of a plurality of users, constructing user portraits corresponding to a plurality of users according to the main card data of the intelligent card; matching the user portraits corresponding to the plurality of users with a plurality of affiliated card products pre-defined with a plurality of labels to obtain a model training sample; training and verifying a pre-constructed artificial intelligence model based on the model training sample, and generating a corresponding affiliated card recommendation model; according to the obtained main card data of the target smart card of the target user, constructing a target user portrait corresponding to the target user; and based on the target user portrait, outputting a recommended target affiliated card through an affiliated card recommendation model. The matching degree of the auxiliary card recommendation result and the actual demand of the user can be improved by combining the main card data of the intelligent card.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and is applied to supplementary card recommendation scenarios for credit cards related to financial services, and specifically to a supplementary card output method, device, computer equipment, and non-volatile computer-readable storage medium for a smart card. Background Art

[0002] Smart Card is a general term for plastic cards (usually the size of a credit card) with a microchip embedded in them; some smart cards contain a microelectronic chip, and smart cards need to interact with data through readers and writers, including credit cards, debit cards, mobile phone cards, etc.

[0003] At present, with the development of economy and the improvement of people's living standards, credit cards have become one of the important tools for people's daily consumption in the financial field. In the context of fierce competition in the credit card market, banking institutions need to continuously improve users' credit card usage experience, increase user stickiness and loyalty, and also need to improve their own profits. Among them, supplementary cards are one of the important means for banking institutions to improve user stickiness and loyalty. However, the current supplementary card recommendation method of banking institutions is mainly based on users' personal information and consumption habits, such as age, gender, income level and historical consumption. These recommendation methods often lack in-depth analysis of credit card master card data, such as the consumption frequency, consumption category, credit score, etc. of the master card, resulting in the recommendation results of supplementary cards may not match the current actual needs of users, resulting in low accuracy of supplementary card recommendations and poor user experience, which limits the ability of banking institutions to improve user stickiness and loyalty. At the same time, the profits of banking institutions cannot be improved.

[0004] Based on this, how to provide a supplementary card output method, device, computer equipment and non-volatile computer-readable storage medium for smart cards that can be applied to the credit card field, which can improve the matching degree between the supplementary card recommendation results and the actual needs of the user by combining the main card data of the smart card, thereby improving the accuracy of supplementary card recommendations, improving user experience and card application rate, is a problem that needs to be urgently solved by technical personnel in this field. Summary of the invention

[0005] In view of the above-mentioned deficiencies in the prior art, the object of the present invention is to provide a method, device, computer equipment and non-volatile computer-readable storage medium for outputting supplementary cards of smart cards that can be used in financial technology or other related fields, aiming to solve the problem of how to improve the matching degree between the supplementary card recommendation results of the smart card and the actual needs of the user.

[0006] In order to achieve the above object, the present invention adopts the following technical solutions:

[0007] A method for outputting a supplementary card of a smart card, wherein the method comprises:

[0008] Collecting primary card data of smart cards of several users, and constructing user profiles corresponding to the several users according to the primary card data of the smart cards;

[0009] Matching the user portraits corresponding to the plurality of users with a plurality of supplementary card products pre-defined with a plurality of labels to obtain model training samples;

[0010] Based on the model training samples, the pre-built artificial intelligence model is trained and verified to generate a corresponding supplementary card recommendation model;

[0011] Constructing a target user profile corresponding to the target user according to the acquired primary card data of the target smart card of the target user;

[0012] Based on the target user portrait, the recommended target supplementary card is outputted through the supplementary card recommendation model.

[0013] In a further technical solution, the method for outputting a supplementary card of a smart card, wherein the collecting of the main card data of the smart cards of several users and constructing the user profiles corresponding to the several users according to the main card data of the smart cards, comprises:

[0014] Collecting primary card data of smart cards of several users from a business database;

[0015] Preprocessing the collected master card data of the smart card;

[0016] Feature extraction is performed on the preprocessed master card data of the smart card to construct user portraits corresponding to the several users.

[0017] In a further technical solution, the method for outputting a supplementary card of a smart card, wherein the user portraits corresponding to the plurality of users are matched with a plurality of supplementary card products pre-defined with a plurality of labels to obtain a model training sample, comprises:

[0018] Predefine a number of labels for a plurality of the supplementary card products according to product characteristics of the supplementary card products;

[0019] Matching the plurality of supplementary card products with the user portraits corresponding to the plurality of users to obtain an initial data sample;

[0020] After data sorting is performed on the initial data samples, model training samples are obtained.

[0021] In a further technical solution, the method for outputting a supplementary card of a smart card, wherein the pre-built artificial intelligence model is trained and verified based on the model training sample to generate a corresponding supplementary card recommendation model, comprises:

[0022] Pre-constructing an artificial intelligence model, and using a training set in the model training sample to train the artificial intelligence model to generate an initial model;

[0023] The initial model is verified using a verification set in the model training sample, and a corresponding supplementary card recommendation model is generated after the verification passes.

[0024] In a further technical solution, the method for outputting a supplementary card of a smart card, wherein the step of constructing a target user portrait corresponding to the target user according to the acquired primary card data of the target smart card of the target user comprises:

[0025] Acquire primary card data of a target smart card of a target user from the service database;

[0026] The acquired primary card data of the target smart card is preprocessed and feature extracted to construct a target user portrait corresponding to the target user.

[0027] In a further technical solution, the method for outputting a supplementary card of a smart card, wherein the outputting a recommended target supplementary card through the supplementary card recommendation model based on the target user portrait comprises:

[0028] Inputting the constructed target user portrait into the pre-trained supplementary card recommendation model to generate an initial recommendation list;

[0029] Rearranging the initial recommendation list based on a preset sorting strategy to generate a target recommendation list;

[0030] Based on the target recommendation list, a recommended target subsidiary card is output to the target user.

[0031] In a further technical solution, the method for outputting a supplementary card of a smart card, wherein the step of outputting a recommended target supplementary card to the target user based on the target recommendation list comprises:

[0032] Based on the target recommendation list, determining a recommended target supplementary card according to the target user's interaction history and preference settings;

[0033] The recommended target supplementary card is output to the target user through a designated channel.

[0034] A supplementary card output device for a smart card, wherein the device comprises:

[0035] A collection module, used to collect primary card data of smart cards of several users, and construct user portraits corresponding to the several users according to the primary card data of the smart cards;

[0036] A matching module, used for matching the user portraits corresponding to the plurality of users with a plurality of supplementary card products pre-defined with a plurality of tags, to obtain a model training sample;

[0037] A training module, used to train and verify the pre-built artificial intelligence model based on the model training samples, and generate a corresponding supplementary card recommendation model;

[0038] An acquisition module, used to construct a target user portrait corresponding to the target user according to the acquired primary card data of the target smart card of the target user;

[0039] An output module is used to output a recommended target supplementary card based on the target user portrait through the supplementary card recommendation model.

[0040] A computer device, wherein the computer device comprises at least one processor; and

[0041] a memory communicatively connected to the at least one processor; wherein,

[0042] The memory stores a computer program that can be executed by the at least one processor. When the computer program is executed by the at least one processor, the method for outputting a supplementary card of a smart card as described in any one of the above items can be implemented.

[0043] A non-volatile computer-readable storage medium stores a computer program, wherein the computer program, when executed by at least one processor, can implement the supplementary card output method of the smart card as described in any one of the above.

[0044] Compared with the prior art, the present invention provides a method, device, computer equipment and non-volatile computer-readable storage medium for outputting supplementary cards of smart cards, wherein the method includes: collecting the main card data of the smart cards of several users, and constructing user portraits corresponding to the several users according to the main card data of the smart cards; matching the user portraits corresponding to the several users with a plurality of supplementary card products pre-defined with several tags to obtain model training samples; based on the model training samples, training and verifying the pre-constructed artificial intelligence model to generate a corresponding supplementary card recommendation model; constructing a target user portrait corresponding to the target user according to the main card data of the target smart card obtained; and outputting a recommended target supplementary card through the supplementary card recommendation model based on the target user portrait. In this way, the method of the present invention can improve the matching degree between the supplementary card recommendation results and the actual needs of users by combining the main card data of the smart card, thereby improving the supplementary card recommendation accuracy, user experience and card application rate. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0046] Figure 1 A schematic flow chart of a method for outputting a supplementary card of a smart card provided by an embodiment of the present invention.

[0047] Figure 2 A schematic diagram of functional modules of a supplementary card output device for a smart card provided by an embodiment of the present invention.

[0048] Figure 3 A schematic diagram of the hardware structure of a computer device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0049] In order to make the purpose, technical solution and effect of the present invention clearer and more specific, the present invention is further described in detail with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0050] In the description of the present invention, the terms "include", "including", "have", "contain", etc. are all open terms, which mean including but not limited to. The descriptions with reference to the terms "one embodiment", "a specific embodiment", "some embodiments", "for example", etc. mean that the specific features, structures or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures or characteristics described may be combined in a suitable manner in any one or more embodiments or examples. The order of steps involved in each embodiment is used to schematically illustrate the implementation of the present application, and the order of steps therein is not limited and can be appropriately adjusted as needed.

[0051] Various non-limiting embodiments of the present invention are described in detail below in conjunction with the accompanying drawings.

[0052] Smart Card is a general term for plastic cards (usually the size of a credit card) with a microchip embedded in them; some smart cards contain a microelectronic chip, and smart cards need to interact with data through readers and writers, including credit cards, debit cards, mobile phone cards, etc.

[0053] At present, with the development of economy and the improvement of people's living standards, credit cards have become one of the important tools for people's daily consumption in the financial field. In the context of fierce competition in the credit card market, banking institutions need to continuously improve users' credit card usage experience, increase user stickiness and loyalty, and also need to improve their own profits. Among them, supplementary cards are one of the important means for banking institutions to improve user stickiness and loyalty. However, the current supplementary card recommendation method of banking institutions is mainly based on users' personal information and consumption habits, such as age, gender, income level and historical consumption. These recommendation methods often lack in-depth analysis of credit card master card data, such as the consumption frequency, consumption category, credit score, etc. of the master card, resulting in the recommendation results of supplementary cards may not match the current actual needs of users, resulting in low accuracy of supplementary card recommendations and poor user experience, which limits the ability of banking institutions to improve user stickiness and loyalty. At the same time, the profits of banking institutions cannot be improved.

[0054] Based on this, how to provide a supplementary card output method, device, computer equipment and non-volatile computer-readable storage medium for smart cards that can be applied to the credit card field, which can improve the matching degree between the supplementary card recommendation results and the actual needs of the user by combining the main card data of the smart card, thereby improving the accuracy of supplementary card recommendations, improving user experience and card application rate, is a problem that needs to be urgently solved by technical personnel in this field.

[0055] To solve the above problems, see Figure 1The embodiment of the present invention provides a method for outputting a supplementary card of a smart card, wherein the method comprises the steps of:

[0056] S100, collecting primary card data of smart cards of several users, and constructing user profiles corresponding to the several users according to the primary card data of the smart cards;

[0057] S200, matching the user portraits corresponding to the plurality of users with a plurality of supplementary card products pre-defined with a plurality of labels to obtain a model training sample;

[0058] S300: Based on the model training samples, train and verify the pre-built artificial intelligence model to generate a corresponding supplementary card recommendation model;

[0059] S400, constructing a target user portrait corresponding to the target user according to the acquired primary card data of the target smart card of the target user;

[0060] S500: Based on the target user portrait, output a recommended target supplementary card through the supplementary card recommendation model.

[0061] Specifically, it should be noted that the smart cards referred to in the present invention are all general terms for smart cards that include a main card and corresponding supplementary card application scenarios, such as credit cards, debit cards, mobile phone cards, etc.; it should be emphasized that individual smart cards that do not have a main card and corresponding supplementary card application scenarios are not included in the scope of smart cards referred to in the present invention, nor are they included in the scope of protection claimed by the present invention, such as identity cards, access control cards, etc.;

[0062] Among them, when describing the embodiments of the present invention in detail, the application scenario of the smart card as a credit card is specifically described, that is, the embodiments of the present invention are applied to the supplementary card recommendation scenario of a credit card related to financial services.

[0063] Furthermore, in the method for outputting supplementary cards of smart cards, the step S100 of collecting the main card data of smart cards of several users and constructing user profiles corresponding to the several users according to the main card data of the smart cards specifically includes:

[0064] Collecting primary card data of smart cards of several users from a business database;

[0065] Preprocessing the collected master card data of the smart card;

[0066] Feature extraction is performed on the preprocessed master card data of the smart card to construct user portraits corresponding to the several users.

[0067] In the specific implementation, in this embodiment, the primary card data of the smart cards of several users are collected from the business database; the collected primary card data of the smart cards are preprocessed; and feature extraction is performed on the preprocessed primary card data of the smart cards to construct user portraits corresponding to the several users; wherein the specific implementation process is roughly as follows:

[0068] 1) Data Collection

[0069] Collect the primary credit card data of several users from the bank's business database through SQL query or using data extraction tools (such as ETL tools);

[0070] Ensure that the collected primary card data includes the user's consumption history, repayment history, credit score, etc.;

[0071] 2) Data preprocessing

[0072] Clean the data, remove duplicate records, and handle missing values ​​and outliers, such as filling in missing transaction data through interpolation methods;

[0073] Verify the consistency and accuracy of data, such as checking the plausibility of transaction dates and the accuracy of amounts;

[0074] Convert data into a consistent format for easier analysis, such as standardizing date formats and numerical units;

[0075] 3) Feature Selection

[0076] Extract useful features for building user profiles from preprocessed data, such as consumption category, consumption frequency, consumption amount, repayment record, overdue status, etc.

[0077] Apply statistical analysis methods, such as cluster analysis or correlation analysis, to determine which features are most closely associated with user behaviors and preferences;

[0078] 4) User portrait construction

[0079] Dimension division: According to business needs and data characteristics, user portraits are divided into multiple dimensions, such as consumption habits, repayment ability, credit status, etc.;

[0080] Label generation: Generate corresponding labels for the features under each dimension; for example, generate labels such as "high-frequency consumer" and "large-amount consumer" based on consumption frequency and consumption amount; generate labels such as "stable repayer" and "occasional overdue payer" based on repayment record and overdue situation;

[0081] Portrait integration: Integrate labels from multiple dimensions into a complete user portrait for subsequent recommendations;

[0082] Through the above process, it is possible to construct a user portrait corresponding to the user based on the primary card data.

[0083] Furthermore, the method for outputting supplementary cards of a smart card, wherein the step S200, matching the user portraits corresponding to the plurality of users with a plurality of supplementary card products pre-defined with a plurality of tags to obtain a model training sample, specifically includes:

[0084] Predefine a number of labels for a plurality of the supplementary card products according to product characteristics of the supplementary card products;

[0085] Matching the plurality of supplementary card products with the user portraits corresponding to the plurality of users to obtain an initial data sample;

[0086] After data sorting is performed on the initial data samples, model training samples are obtained.

[0087] In the specific implementation, in this embodiment, a plurality of labels are defined for the plurality of supplementary card products in advance according to the product characteristics of the supplementary card products; the plurality of supplementary card products are matched with the user portraits corresponding to the plurality of users to obtain an initial data sample; the initial data sample is sorted to obtain a model training sample; wherein the specific implementation process is roughly as follows:

[0088] 1) Define the supplementary card product label

[0089] First, analyze the existing supplementary card products available to banking institutions and identify their key features, such as annual fees, reward programs, insurance coverage, credit limit range, applicable age, etc.

[0090] Based on these characteristics, assign one or more labels to each supplementary card product; for example, a supplementary card may be labeled "low annual fee", "travel rewards" and "suitable for young people" at the same time;

[0091] 2) Matching user profiles with supplementary card products

[0092] The user profile is constructed using the credit card master card data, including the user's consumption habits (such as preferred types, consumption frequency), repayment ability (such as repayment records, overdue conditions), credit status (such as credit score), etc.

[0093] Match the user profile with the labels of supplementary card products to find products that may meet the user's needs; for example, if a user travels frequently and has a high credit score, supplementary cards with the labels "travel rewards" and "high credit limit" may be a match;

[0094] 3) Generate initial data samples

[0095] Organize the results of the matching process into initial data samples, each of which contains a user profile and a set of recommended supplementary card products;

[0096] These data samples will be used for subsequent model training to determine the effectiveness and accuracy of the recommendations;

[0097] 4) Data collation

[0098] Further organize the initial data samples to obtain model training samples, including data cleaning, feature engineering and sample labeling;

[0099] Data cleaning may involve removing incomplete or inaccurate data records to ensure data quality in the sample;

[0100] Feature engineering involves selecting the features that are most useful for model prediction, such as the user’s average monthly spending, favorite consumer categories, etc.

[0101] Sample labeling determines the degree of match between each user and the recommended additional cards, which can be binary (match / no match) or multivariate (high match, partial match, etc.);

[0102] Through the above process, the model training samples required for training in the subsequent process can be obtained.

[0103] Furthermore, the method for outputting a supplementary card of a smart card, wherein the step S300, based on the model training sample, trains and verifies the pre-built artificial intelligence model to generate a corresponding supplementary card recommendation model, specifically includes:

[0104] Pre-constructing an artificial intelligence model, and using a training set in the model training sample to train the artificial intelligence model to generate an initial model;

[0105] The initial model is verified using a verification set in the model training sample, and a corresponding supplementary card recommendation model is generated after the verification passes.

[0106] In the specific implementation, in this embodiment, an artificial intelligence model is pre-built, and the training set in the model training sample is used to train the artificial intelligence model to generate an initial model; the verification set in the model training sample is used to verify the initial model, and after the verification is passed, a corresponding supplementary card recommendation model is generated; wherein, the specific implementation process is roughly as follows:

[0107] 1) Select model algorithm

[0108] Select appropriate AI model algorithms based on the complexity of credit card user profiles and supplementary card product features; possible algorithms include decision trees, random forests, gradient boosting machines, neural networks, etc.;

[0109] Consider factors such as model interpretability, accuracy, training time, and resource consumption, and choose the algorithm that best suits current data and business needs;

[0110] 2) Prepare the model training environment

[0111] Set up the model training environment, including hardware resources (such as GPU acceleration), software frameworks (such as TensorFlow, PyTorch, Scikitlearn), and necessary libraries;

[0112] Make sure the model training samples have been divided into training and validation sets, usually using cross-validation to optimize model parameters and prevent overfitting;

[0113] 3) Model training

[0114] Use the training set data to train the selected artificial intelligence model; this process includes model initialization, parameter learning, and model optimization;

[0115] Through the iterative training process, the model parameters are adjusted until the model achieves satisfactory performance indicators on the training data, such as accuracy, recall or F1 score;

[0116] 4) Model Validation

[0117] Apply the trained initial model to the validation set data to evaluate the model's generalization ability; the validation set should contain independent data that was not used in the training process;

[0118] Monitor the performance of the model on the validation set to ensure that the model is not overfitting and can accurately predict unseen data;

[0119] 5) Model tuning and generation

[0120] Based on the verification results, the model is tuned, which may include adjusting the model structure, adding or reducing features, adjusting the learning rate, etc.

[0121] Perform multiple iterations of training and validation until the model achieves optimal performance on the validation set;

[0122] After verification, save the model as a supplementary card recommendation model and prepare to deploy it to the production environment;

[0123] 6) Model deployment and monitoring

[0124] Deploy the trained and verified supplementary card recommendation model to the production environment to recommend supplementary cards to target users;

[0125] Regularly retrain and update models with new data to adapt to user behavior and market changes;

[0126] Through the above process, a corresponding supplementary card recommendation model can be generated.

[0127] Furthermore, in the method for outputting a supplementary card of a smart card, the step S400 of constructing a target user portrait corresponding to the target user according to the acquired primary card data of the target smart card of the target user specifically includes:

[0128] Acquire primary card data of a target smart card of a target user from the service database;

[0129] The acquired primary card data of the target smart card is preprocessed and feature extracted to construct a target user portrait corresponding to the target user.

[0130] Furthermore, the method for outputting a supplementary card of a smart card, wherein the step S500, outputting a recommended target supplementary card through the supplementary card recommendation model based on the target user portrait, specifically includes:

[0131] Inputting the constructed target user portrait into the pre-trained supplementary card recommendation model to generate an initial recommendation list;

[0132] Rearranging the initial recommendation list based on a preset sorting strategy to generate a target recommendation list;

[0133] Based on the target recommendation list, a recommended target subsidiary card is output to the target user.

[0134] Furthermore, the method for outputting a supplementary card of a smart card, wherein the step of outputting a recommended target supplementary card to the target user based on the target recommendation list specifically includes:

[0135] Based on the target recommendation list, determining a recommended target supplementary card according to the target user's interaction history and preference settings;

[0136] The recommended target supplementary card is output to the target user through a designated channel.

[0137] In specific implementation, in this embodiment, the main card data of the target smart card of the target user is obtained from the business database; the main card data of the target smart card obtained is preprocessed and feature extracted to construct a target user portrait corresponding to the target user; the constructed target user portrait is input into the pre-trained supplementary card recommendation model to generate an initial recommendation list; the initial recommendation list is rearranged based on a preset sorting strategy to generate a target recommendation list; based on the target recommendation list, the recommended target supplementary card is determined according to the interaction history and preference settings of the target user; the recommended target supplementary card is output to the target user through a designated channel; wherein the specific implementation process is roughly as follows:

[0138] 1) Data acquisition and preprocessing

[0139] Obtain the target user's credit card primary card data from the bank's business database through secure database query technology, including but not limited to transaction history, repayment record, credit score, etc.;

[0140] Clean the acquired data, process missing values, outliers, and remove duplicate records to ensure data quality and consistency;

[0141] 2) Feature extraction and user portrait construction

[0142] Extract key features from preprocessed data, such as spending habits, preferred transaction types, credit history, etc.

[0143] Use these features to build a profile of the target user, which may involve using cluster analysis, decision trees, or other machine learning algorithms to identify user behavior patterns and preferences;

[0144] 3) Model input and initial recommendation generation

[0145] Input the constructed target user portrait into the pre-trained supplementary card recommendation model;

[0146] The model analyzes the matching degree between the user profile and the features of the supplementary card products and generates an initial recommendation list;

[0147] 4) Recommended list optimization

[0148] According to the preset sorting strategy, such as the matching degree between the user profile and the supplementary card features, the popularity of the supplementary card, historical user feedback, etc., the initial recommendation list is re-sorted and screened to generate a target recommendation list;

[0149] The optimization process may include reapplying the machine learning model to ensure the relevance and personalization of the recommendation list;

[0150] 5) Final recommendation determination and output

[0151] Based on the target user's interaction history and preference settings, determine the target supplementary card that is ultimately recommended to the user from the optimized target recommendation list;

[0152] Send recommendations to target users through the communication channels selected by users, such as email, SMS, mobile app push, etc.; ensure that the presentation of recommendations is consistent with users' reading habits and preferences;

[0153] 6) Effect tracking and feedback loop

[0154] Track user responses to recommended supplementary cards, including indicators such as click-through rate, application rate, and user satisfaction;

[0155] Collect user feedback and use it as input for model optimization, continuously adjust and improve the recommendation algorithm to improve the accuracy of recommendations and user satisfaction;

[0156] Through the above process, we can analyze the credit card main card data and combine it with the user's actual consumption record, repayment record, credit score and other factors to intelligently recommend supplementary cards suitable for the user, thereby improving the recommendation accuracy and usage experience of the user's supplementary cards and improving the customer satisfaction of banking institutions. At the same time, the increase in the number of supplementary cards issued has also brought increased benefits to banking institutions and increased the profits of banking institutions.

[0157] It can be seen from the above method embodiments that the method for outputting supplementary cards of smart cards provided by the present invention includes: collecting the main card data of the smart cards of several users, and constructing user portraits corresponding to the several users according to the main card data of the smart cards; matching the user portraits corresponding to the several users with a plurality of supplementary card products pre-defined with several tags to obtain model training samples; training and verifying the pre-constructed artificial intelligence model based on the model training samples to generate a corresponding supplementary card recommendation model; constructing a target user portrait corresponding to the target user according to the main card data of the target smart card obtained; and outputting a recommended target supplementary card through the supplementary card recommendation model based on the target user portrait. In this way, the method of the present invention can improve the matching degree between the supplementary card recommendation results and the actual needs of users by combining the main card data of the smart card, thereby improving the accuracy of supplementary card recommendations, user experience and card application rate.

[0158] It should be understood that, although the present application provides method operation steps as described in the embodiments or flowcharts, more or less operation steps may be included based on conventional or non-creative labor, and these operation steps are not necessarily performed in sequence according to the embodiment or flowchart. The order of steps listed in the embodiment or flowchart is only one way of executing the order of many steps, and does not represent the only execution order. It should be noted that there is not necessarily a certain order between the above steps. A person of ordinary skill in the art can understand from the description of the embodiment of the present invention that in different embodiments, the above steps may have different execution orders, that is, they may be executed in parallel, or they may be executed in exchange, etc. Moreover, at least a part of the steps in the embodiment or flowchart may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but may be executed at different times, and the execution order of these sub-steps or stages is not necessarily performed in sequence, but may be executed in turn, alternately or synchronously with other steps or at least a part of the sub-steps or stages of other steps.

[0159] Based on the above method embodiment, please refer to Figure 2 Another embodiment of the present invention further provides a supplementary card output device for a smart card, wherein the device comprises:

[0160] A collection module 11 is used to collect primary card data of smart cards of several users, and construct user portraits corresponding to the several users according to the primary card data of the smart cards;

[0161] A matching module 12, used for matching the user portraits corresponding to the plurality of users with a plurality of supplementary card products pre-defined with a plurality of tags, to obtain a model training sample;

[0162] A training module 13 is used to train and verify the pre-built artificial intelligence model based on the model training samples to generate a corresponding supplementary card recommendation model;

[0163] An acquisition module 14 is used to construct a target user portrait corresponding to the target user according to the acquired primary card data of the target smart card of the target user;

[0164] The output module 15 is used to output the recommended target supplementary card through the supplementary card recommendation model based on the target user portrait.

[0165] Furthermore, in the smart card supplementary card output device, the collection module 11 specifically includes:

[0166] A collection unit, used for collecting primary card data of smart cards of several users from a service database;

[0167] A preprocessing unit, used for preprocessing the collected master card data of the smart card;

[0168] A feature extraction unit is used to extract features from the preprocessed master card data of the smart card to construct user portraits corresponding to the plurality of users.

[0169] Furthermore, in the supplementary card output device of the smart card, the matching module 12 specifically includes:

[0170] A definition unit, used to pre-define a number of labels for a plurality of supplementary card products according to product characteristics of the supplementary card products;

[0171] A matching unit, configured to match the plurality of supplementary card products with the user portraits corresponding to the plurality of users to obtain an initial data sample;

[0172] The data sorting unit is used to sort the initial data samples to obtain model training samples.

[0173] Furthermore, in the supplementary card output device of the smart card, the training module 13 specifically includes:

[0174] A training unit, used to pre-build an artificial intelligence model, train the artificial intelligence model using a training set in the model training sample, and generate an initial model;

[0175] The verification unit is used to verify the initial model using the verification set in the model training sample, and generate a corresponding supplementary card recommendation model after the verification is passed.

[0176] Furthermore, in the smart card supplementary card output device, the acquisition module 14 specifically includes:

[0177] An acquisition unit, used for acquiring primary card data of a target smart card of a target user from the service database;

[0178] A construction unit is used to preprocess and extract features of the acquired primary card data of the target smart card to construct a target user portrait corresponding to the target user.

[0179] Furthermore, in the supplementary card output device of the smart card, the output module 15 specifically comprises:

[0180] An input unit, used for inputting the constructed target user portrait into the pre-trained supplementary card recommendation model to generate an initial recommendation list;

[0181] A rearrangement unit, configured to rearrange the initial recommendation list based on a preset sorting strategy to generate a target recommendation list;

[0182] An output unit is used to output the recommended target subsidiary card to the target user based on the target recommendation list.

[0183] Furthermore, the device for outputting a supplementary card of a smart card, wherein the step of outputting a recommended target supplementary card to the target user based on the target recommendation list specifically includes:

[0184] Based on the target recommendation list, determining a recommended target supplementary card according to the target user's interaction history and preference settings;

[0185] The recommended target supplementary card is output to the target user through a designated channel.

[0186] The specific implementation process and effects of the device embodiment of the present invention can be found in the above method embodiment, which will not be described in detail here.

[0187] It can be known from the above device embodiments that the supplementary card output device of the smart card provided by the present invention includes: a collection module, which is used to collect the main card data of the smart cards of several users, and construct user portraits corresponding to the several users according to the main card data of the smart cards; a matching module, which is used to match the user portraits corresponding to the several users with a plurality of supplementary card products pre-defined with several tags to obtain model training samples; a training module, which is used to train and verify the pre-constructed artificial intelligence model based on the model training samples to generate a corresponding supplementary card recommendation model; an acquisition module, which is used to construct a target user portrait corresponding to the target user according to the main card data of the target smart card of the target user obtained; an output module, which is used to output the recommended target supplementary card through the supplementary card recommendation model based on the target user portrait. In this way, the device of the present invention can improve the matching degree between the supplementary card recommendation results and the actual needs of the user by combining the main card data of the smart card, thereby improving the accuracy of supplementary card recommendations, user experience and card application rate.

[0188] Based on the above method embodiment, please refer to Figure 3 Another embodiment of the present invention further provides a computer device, wherein the computer device 10 includes:

[0189] memory 120 and one or more processors 110, Figure 3 A processor 110 is used as an example for description. The processor 110 and the memory 120 may be connected via a communication bus or other means. Figure 3 The example of connecting via a communication bus is taken as an example.

[0190] The processor 110 is used to complete various control logics of the computer device 10. It can be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA), a single-chip microcomputer, an ARM (Acorn RISC Machine) or other programmable logic device, a discrete gate or transistor logic, a discrete hardware component, or any combination of these components. In addition, the processor 110 can also be any traditional processor, microprocessor or state machine. The processor 110 can also be implemented as a combination of computing devices, for example, a combination of a DSP and a microprocessor, a plurality of microprocessors, one or more microprocessors combined with a DSP, or any other such configuration.

[0191] The memory 120, as a non-volatile computer-readable storage medium, can be used to store non-volatile software programs, non-volatile computer executable programs and modules, such as the computer program corresponding to the method for outputting the supplementary card of the smart card in any of the above-mentioned method embodiments of the present invention. The processor 110 executes various functional applications and data processing of the computer device 10 by running the non-volatile software programs, instructions and units stored in the memory 120, that is, implements the method for outputting the supplementary card of the smart card in any of the above-mentioned method embodiments.

[0192] The memory 120 may include a program storage area and a data storage area, wherein the program storage area may store an application required for operating the device or at least one function; the data storage area may store data created according to the use of the computer device 10, etc. In addition, the memory 120 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some embodiments, the memory 120 may optionally include a memory remotely arranged relative to the processor 110, and these remote memories may be connected to the computer device 10 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0193] One or more units are stored in the memory 120. When executed by one or more processors 110, the method for outputting the supplementary card of the smart card in any of the above method embodiments can be implemented. For example, the method described above can be implemented. Figure 1 The method comprises steps S100 to S500.

[0194] It can be seen from the above computer device embodiments that the computer device provided by the present invention can achieve: collecting the main card data of the smart cards of several users, and constructing the user portraits corresponding to the several users according to the main card data of the smart cards; matching the user portraits corresponding to the several users with multiple supplementary card products pre-defined with several tags to obtain model training samples; training and verifying the pre-constructed artificial intelligence model based on the model training samples to generate a corresponding supplementary card recommendation model; constructing the target user portrait corresponding to the target user according to the main card data of the target smart card obtained; and outputting the recommended target supplementary card through the supplementary card recommendation model based on the target user portrait. In this way, the computer device of the present invention can improve the matching degree between the supplementary card recommendation results and the actual needs of users by combining the main card data of the smart card, thereby improving the accuracy of supplementary card recommendations, user experience and card application rate.

[0195] Those skilled in the art will understand that Figure 3The hardware structure diagram shown in the figure is only a schematic diagram of a partial structure related to the solution of the present invention, and does not constitute a limitation on the computer device to which the solution of the present invention is applied. The specific computer device may include more components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0196] Based on the above method embodiments, another embodiment of the present invention further provides a non-volatile computer-readable storage medium, wherein the non-volatile computer-readable storage medium stores a computer program, and when the computer program is executed by at least one processor, the method for outputting a supplementary card of a smart card in any of the above method embodiments can be implemented, for example, the method described above can be implemented. Figure 1 The method comprises steps S100 to S500.

[0197] As an example, the non-volatile storage medium can include a read-only memory (ROM), a programmable ROM (PROM), an electrically programmable ROM (EPROM), an electrically erasable ROM (EEPROM), or a flash memory. Volatile memory can include a random access memory (RAM) as an external cache memory. By way of illustration and not limitation, RAM can be obtained in many forms such as synchronous RAM (SRAM), dynamic RAM, (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), Synch link DRAM (SLDRAM), and direct Rambus RAM (DRRAM). The disclosed memory components or memories of the operating environment described herein are intended to include one or more of these and / or any other suitable types of memory.

[0198] Based on the above method embodiments, another embodiment of the present invention further provides a computer program product, the computer program product includes a computer program stored on a non-volatile computer-readable storage medium, the computer program includes program instructions, when the program instructions are executed by a processor, the smart card auxiliary card output method in any of the above method embodiments can be implemented, for example, the above described Figure 1 The method comprises steps S100 to S500.

[0199] The embodiments described above are merely illustrative, in which the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0200] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a general hardware platform, and of course can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the relevant technology can be embodied in the form of a software product, and the computer software product can exist in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods of each embodiment or some parts of the embodiment.

[0201] Conditional language such as "can," "can," "might," or "may," unless specifically stated otherwise or otherwise understood within the context as used, is generally intended to convey, among other things, that a particular embodiment can include (while other embodiments do not) a particular feature, element, and / or operation. Thus, such conditional language is also generally intended to imply that a feature, element, and / or operation is required for one or more embodiments anyway or that one or more embodiments must include logic for determining, with or without input or prompting, whether such features, elements, and / or operations are included or will be performed in any particular embodiment.

[0202] What has been described herein, in this specification and in the drawings includes examples of methods, devices, computer equipment, and non-volatile computer-readable storage media that can provide an auxiliary card output for a smart card. Of course, it is not possible to describe every conceivable combination of elements and / or methods for the purpose of describing the various features of the present disclosure, but it can be recognized that many other combinations and permutations of the disclosed features are possible. Therefore, it is obvious that various modifications can be made to the present disclosure without departing from the scope or spirit of the present disclosure, but all these various modifications should belong to the scope of protection of the claims attached to the present invention. In addition, or in an alternative, other embodiments of the present disclosure may be obvious from consideration of the present specification and the drawings and from the practice of the present disclosure as presented herein. It is intended that the examples proposed in the present specification and the drawings are considered to be illustrative and not restrictive in all respects. Although specific terms are used herein, they are used in a general and descriptive sense and are not used for limiting purposes.

Claims

1. A method for outputting a supplementary card of a smart card, characterized in that: The method comprises: Collecting primary card data of smart cards of several users, and constructing user profiles corresponding to the several users according to the primary card data of the smart cards; Matching the user portraits corresponding to the plurality of users with a plurality of supplementary card products pre-defined with a plurality of labels to obtain model training samples; Based on the model training samples, the pre-built artificial intelligence model is trained and verified to generate a corresponding supplementary card recommendation model; Constructing a target user profile corresponding to the target user according to the acquired primary card data of the target smart card of the target user; Based on the target user portrait, the recommended target supplementary card is outputted through the supplementary card recommendation model.

2. The method for outputting a supplementary card of a smart card according to claim 1, characterized in that: The collecting of primary card data of smart cards of a plurality of users and constructing user profiles corresponding to the plurality of users according to the primary card data of the smart cards includes: Collecting primary card data of smart cards of several users from a business database; Preprocessing the collected master card data of the smart card; Feature extraction is performed on the preprocessed master card data of the smart card to construct user portraits corresponding to the several users.

3. The method for outputting a supplementary card of a smart card according to claim 2, characterized in that: The matching of the user portraits corresponding to the plurality of users with a plurality of supplementary card products pre-defined with a plurality of labels to obtain a model training sample includes: Predefine a plurality of labels for a plurality of the supplementary card products according to product characteristics of the supplementary card products; Matching the plurality of supplementary card products with the user portraits corresponding to the plurality of users to obtain an initial data sample; After data sorting is performed on the initial data samples, model training samples are obtained.

4. The method for outputting a supplementary card of a smart card according to claim 3, characterized in that: The method of training and verifying the pre-built artificial intelligence model based on the model training sample to generate a corresponding supplementary card recommendation model includes: Pre-constructing an artificial intelligence model, and using a training set in the model training sample to train the artificial intelligence model to generate an initial model; The initial model is verified using a verification set in the model training sample, and a corresponding supplementary card recommendation model is generated after the verification passes.

5. The method for outputting a supplementary card of a smart card according to claim 4, characterized in that: The step of constructing a target user portrait corresponding to the target user according to the acquired primary card data of the target smart card of the target user includes: Acquire primary card data of a target smart card of a target user from the service database; The acquired primary card data of the target smart card is preprocessed and feature extracted to construct a target user portrait corresponding to the target user.

6. The method for outputting a supplementary card of a smart card according to claim 5, characterized in that: The outputting a recommended target supplementary card through the supplementary card recommendation model based on the target user portrait includes: Inputting the constructed target user portrait into the pre-trained supplementary card recommendation model to generate an initial recommendation list; Rearranging the initial recommendation list based on a preset sorting strategy to generate a target recommendation list; Based on the target recommendation list, a recommended target subsidiary card is output to the target user.

7. The method for outputting a supplementary card of a smart card according to claim 6, characterized in that: The step of outputting the recommended target supplementary card to the target user based on the target recommendation list includes: Based on the target recommendation list, determining a recommended target supplementary card according to the target user's interaction history and preference settings; The recommended target supplementary card is output to the target user through a designated channel.

8. A supplementary card output device for a smart card, characterized in that: The device comprises: A collection module, used to collect primary card data of smart cards of several users, and construct user portraits corresponding to the several users according to the primary card data of the smart cards; A matching module, used for matching the user portraits corresponding to the plurality of users with a plurality of supplementary card products pre-defined with a plurality of tags, to obtain a model training sample; A training module, used to train and verify the pre-built artificial intelligence model based on the model training samples, and generate a corresponding supplementary card recommendation model; An acquisition module, used to construct a target user portrait corresponding to the target user according to the acquired primary card data of the target smart card of the target user; An output module is used to output a recommended target supplementary card based on the target user portrait through the supplementary card recommendation model.

9. A computer device, characterized in that: The computer device comprises at least one processor; and, a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor. When the computer program is executed by the at least one processor, the supplementary card output method of the smart card as described in any one of claims 1-7 can be implemented.

10. A non-volatile computer-readable storage medium, characterized in that: The non-volatile computer-readable storage medium stores a computer program, and when the computer program is executed by at least one processor, the supplementary card output method of the smart card as described in any one of claims 1 to 7 can be implemented.

Images