Method and device for intelligently recommending financial business based on intelligent wearable device

Abstract

The invention relates to the technical field of artificial intelligence, and discloses an intelligent financial service recommendation method, device and equipment based on intelligent wearable equipment and a medium, and the method comprises the steps: receiving human body feature data of a preset duration collected by the intelligent wearable equipment, and synchronously obtaining the financial behavior data of a user in a financial account; preprocessing the human body feature data and the financial behavior data, and analyzing association rules of the human body feature data and the financial behavior data based on a machine learning algorithm; constructing a user portrait based on the association rule, training a personalized recommendation model according to the user portrait, and determining target business data handled by the user based on the personalized recommendation model; and when a signal that the user opens the financial account page through the intelligent wearable device is obtained, pushing the target business data to the intelligent wearable device based on the personalized recommendation template, and receiving a corresponding target business data handling program executed through the intelligent wearable device. And the precision and timeliness of financial service recommendation are improved.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to a method, device, equipment and medium for intelligently recommending financial services based on a smart wearable device. Background Art

[0002] With the development of financial technology, general financial services are no longer suitable for all customers. Existing financial service recommendations mainly rely on information actively input by users or data from mobile phone apps, computer platform data, etc., which have problems such as incomplete data collection, poor real-time performance, poor data authenticity, and inconvenient operation. As a result, the recommended financial services are not well matched with user needs, and users are less willing to apply for them. Summary of the invention

[0003] The present invention provides an artificial intelligence-based intelligent wearable device-based intelligent recommendation method, device, computer equipment and medium for financial services, so as to solve the technical problems that the recommended financial services are not well matched with user needs and the user's willingness to handle the services is poor due to incomplete data collection, poor real-time performance, poor data authenticity and inconvenient operation.

[0004] In a first aspect, a method for intelligently recommending financial services based on an intelligent wearable device is provided, comprising:

[0005] Receive human feature data collected by smart wearable devices for a preset period of time, and simultaneously obtain the user's financial behavior data in the financial account;

[0006] Preprocess human feature data and financial behavior data, and analyze the association rules between human feature data and financial behavior data based on machine learning algorithms;

[0007] Build user portraits based on association rules, train personalized recommendation models based on user portraits, and determine the target business data handled by users based on the personalized recommendation models;

[0008] When a signal is obtained that the user has opened the financial account page through a smart wearable device, the target business data is pushed to the smart wearable device based on the personalized recommendation template, and the corresponding target business data processing procedure is executed through the smart wearable device.

[0009] In a second aspect, a smart financial service recommendation device based on a smart wearable device is provided, comprising:

[0010] A receiving module, used to receive human feature data collected by a smart wearable device for a preset period of time, and simultaneously obtain the financial behavior data of the user in the financial account;

[0011] An association module is used to pre-process human feature data and financial behavior data, and analyze the association rules between human feature data and financial behavior data based on a machine learning algorithm;

[0012] A model building module is used to build user portraits based on association rules, train personalized recommendation models based on user portraits, and determine the target business data handled by users based on the personalized recommendation models;

[0013] The recommendation module is used to push target business data to the smart wearable device based on the personalized recommendation template when obtaining the signal that the user opens the financial account page through the smart wearable device, and receive the corresponding target business data processing program executed by the smart wearable device.

[0014] In a third aspect, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the above-mentioned method for intelligently recommending financial services based on smart wearable devices are implemented.

[0015] In a fourth aspect, a computer-readable storage medium is provided, which stores a computer program. When the computer program is executed by a processor, the steps of the above-mentioned method for intelligently recommending financial services based on smart wearable devices are implemented.

[0016] In the scheme implemented by the above-mentioned intelligent recommendation financial service method, device, computer equipment and storage medium based on smart wearable devices, the financial behavior data of the user in the financial account can be obtained synchronously by receiving the human feature data of the preset time collected by the smart wearable device; pre-processing the human feature data and the financial behavior data, and analyzing the association rules between the human feature data and the financial behavior data based on the machine learning algorithm; constructing a user portrait based on the association rules, and training a personalized recommendation model based on the user portrait, and determining the target business data handled by the user based on the personalized recommendation model; when the signal that the user opens the financial account page through the smart wearable device is obtained, the target business data is pushed to the smart wearable device based on the personalized recommendation template, and the corresponding target business data handling program is received by the smart wearable device. In the present invention, for the precise push of financial services in smart wearable devices, user data is first collected in real time through the smart wearable device, and quickly analyzed in combination with the intelligent algorithm to realize the instant recommendation of financial services, and improve the accuracy and timeliness of financial service recommendations. And according to the user's physiological data, user behavior data and financial historical transaction data, a personalized user portrait is constructed to provide customized financial service recommendations that meet user needs. Users can directly receive recommended information and perform preliminary operations through smart watches, improving the convenience and interactivity of the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments of the present invention will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative labor.

[0018] Figure 1 is a schematic diagram of an application environment of a method for intelligently recommending financial services based on an intelligent wearable device in one embodiment of the present invention;

[0019] Figure 2 is a flow chart of a method for intelligently recommending financial services based on an intelligent wearable device in one embodiment of the present invention;

[0020] Figure 3 yes Figure 2 A schematic flow chart of a specific implementation of step S10;

[0021] Figure 4 yes Figure 2 A schematic flow chart of a specific implementation of step S50;

[0022] Figure 5 is a schematic diagram of a structure of an intelligent financial service recommendation device in one embodiment of the present invention;

[0023] Figure 6 is a schematic diagram of a structure of a computer device in one embodiment of the present invention;

[0024] Figure 7 It is another structural schematic diagram of a computer device in one embodiment of the present invention. DETAILED DESCRIPTION

[0025] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0026] The intelligent recommendation financial service method based on the intelligent wearable device provided in the embodiment of the present invention can be applied in the following aspects: Figure 1In the application environment, the client communicates with the server through the network. The server can synchronously obtain the financial behavior data of the user in the financial account by receiving the human feature data of the preset time collected by the smart wearable device; pre-process the human feature data and the financial behavior data, and analyze the association rules between the human feature data and the financial behavior data based on the machine learning algorithm; construct a user portrait based on the association rule, and train a personalized recommendation model based on the user portrait, and determine the target business data handled by the user based on the personalized recommendation model; when the signal that the user opens the financial account page through the smart wearable device is obtained, the target business data is pushed to the smart wearable device based on the personalized recommendation template, and the corresponding target business data handling program is received by the smart wearable device. In the present invention, for the precise push of financial services in the smart wearable device, the user data is first collected in real time by the smart wearable device, and the intelligent algorithm is combined for rapid analysis to realize the instant recommendation of financial services, and improve the accuracy and timeliness of the financial service recommendation. Among them, the client can be but not limited to various personal computers, laptops, smart phones, tablet computers and portable wearable devices. The server can be implemented by an independent server or a server cluster composed of multiple servers. The present invention is described in detail below through specific embodiments.

[0027] See also Figure 2 As shown, Figure 2 A flowchart of a method for intelligently recommending financial services based on an intelligent wearable device provided in an embodiment of the present invention includes the following steps:

[0028] S10: receiving human feature data collected by the smart wearable device for a preset period of time, and synchronously obtaining the financial behavior data of the user in the financial account;

[0029] The intelligent recommendation financial service method based on the smart wearable device provided by the present invention can be applied to data synchronization, deep learning and personalized formulation of financial service needs between the smart wearable device and the smart mobile device in various application scenarios. The smart wearable device is used to conveniently collect the user's human characteristic data and has a convenient operation interface. The smart wearable device and the smart mobile device are connected by wireless communication, so that wireless signals can be transmitted between the smart wearable device and the smart mobile device. In this embodiment, the smart wearable device detects the human characteristic data of the wearer through its own sensor, and transmits the human characteristic data to the smart mobile device through wireless communication. The smart mobile device receives the human characteristic data and synchronizes the human characteristic data with the transaction history data of the user in the financial account to generate financial behavior data. A series of processing of the financial behavior data generates a personalized recommendation model and can generate corresponding target business data according to user needs. The smart mobile device transmits the target business data to the smart wearable device through wireless communication, and the smart wearable device displays it through the convenient operation interface of the smart wearable device.

[0030] Smart wearable devices are portable devices that are worn directly on the body or integrated into the user's clothes or accessories. Smart wearable devices have some computing functions and are portable accessories that can be connected to mobile phones and various terminals. The mainstream product forms include watches supported by the wrist (including watches and wristbands, etc.), shoes supported by the feet (including shoes, socks or other leg-worn products in the future), glasses supported by the head (including glasses, helmets, headbands, etc.), as well as various non-mainstream product forms such as smart clothing, school bags, crutches, accessories, etc.

[0031] Smart mobile devices have the ability to access the Internet and are usually equipped with various operating systems. They can be customized with various functions according to user needs. Smart mobile devices include smartphones, notebooks, PDA smart terminals, tablet computers, and in-vehicle smart terminals.

[0032] Specifically, the human characteristic data collected by smart wearable devices include: user physiological data and user behavior data. User physiological data refers to the physiological indicator data collected from the user's body, such as body temperature, heart rate, blood pressure, breathing, etc.; user behavior data refers to the data generated by the user's various behaviors in life, such as exercise mode, exercise duration, exercise time, exercise cycle, sleep cycle, sleep status, etc.; transaction history data refers to the data generated by the user's various financial operations in the financial account. The transaction history data records every visit, every browse, every click, and every transaction of the user in the financial account. Through the transaction history data, the user experience indicators can be monitored and evaluated more efficiently and dynamically.

[0033] Among them, Figure 3, the steps of synchronously obtaining the financial behavior data of the user in the financial account include:

[0034] S11: when receiving a user instruction to start a financial account, obtaining transaction history data of a preset period of time in the financial account;

[0035] It should be noted that the preset time period is the time period for pulling up user data, and the specific time period is set according to demand. When a user activates a financial account, the financial account will generate an activation instruction. When the processor of the smart mobile device receives the user's instruction to activate the financial account, it pulls up the transaction history data of the preset time period in the financial account and obtains and exports it, where the transaction history data includes but is not limited to the user's access data, browsing data, click data, page dwell time data, and transaction data in the financial account.

[0036] S12: Synchronize the human body feature data within a preset time period with the transaction history data of the financial account to obtain the user's financial behavior data.

[0037] Financial behavior data refers to the data generated by financial operations corresponding to various user behaviors. For example, when the heart rate is high, there is record data of purchasing critical illness insurance. When the sleep condition is poor, there may be record data of applying for a loan or purchasing medical insurance. Through financial behavior data, user financial behavior can be monitored and evaluated more efficiently and dynamically.

[0038] Human feature data and financial account transaction history data are synchronized and overlapped at each time node within a preset time period, and sorted by time series, specifically in the order of occurrence and according to the statistical values. The series is the user's financial behavior data. Time series analysis technology is introduced to consider the impact of time factors on financial business needs and improve the accuracy and timeliness of recommendations.

[0039] S20: pre-processing human feature data and financial behavior data, and analyzing association rules between human feature data and financial behavior data based on machine learning algorithms;

[0040] S21: Cleaning and preprocessing the human feature data and financial behavior data, and removing outliers and noise from the cleaned human feature data and financial behavior data.

[0041] Preprocessing human characteristic data and financial behavior data is to clean and preprocess the human characteristic data and financial behavior data. Specifically, data cleaning refers to operations such as cleaning, organizing, and correcting the original data to eliminate errors, noise, and inaccurate information in the data; data preprocessing refers to operations such as converting, expanding, and normalizing the original data to facilitate subsequent data analysis and model building.

[0042] The association rules between the user's physiological data, user behavior data and financial behavior data are analyzed using machine learning algorithms. Among them, machine learning algorithms include linear regression algorithms, support vector machine algorithms, nearest neighbor / k-nearest neighbor algorithms, logistic regression algorithms, decision tree algorithms, k-means algorithms, random forest algorithms, naive Bayes algorithms, dimensionality reduction algorithms, and gradient enhancement algorithms. The data analysis used in this embodiment includes at least one of the above algorithms.

[0043] In one embodiment, the machine learning algorithm is specifically a decision tree algorithm. The decision tree is used for classification and regression tasks. Decisions are made in a tree structure. Each internal node represents a feature, each branch represents a test result of a feature, and each leaf node represents a classification or regression result.

[0044] 1. Node: Each node in the decision tree represents a human feature, and the node divides the data set into subsets according to different values ​​of the human feature; 2. Branch: The line segment extending from the node represents the division of the data set into subsets according to different values ​​of the human feature; 3. Leaf node: The terminal node of the decision tree, which represents the final classification or regression result, which is financial behavior in this embodiment; 4. Splitting criterion: The standard used to select the best features and splitting points. Commonly used splitting criteria include information gain (ID3 algorithm), gain rate (C4.5 algorithm) and Gini index (CART algorithm); 5. Pruning: In order to avoid overfitting, the decision tree can be simplified by pruning. The pruning method includes pre-pruning and post-pruning. Pre-pruning is to limit its growth during the tree construction process, and post-pruning is to delete unnecessary nodes after the tree is built; 6. Overfitting: Decision trees are prone to overfitting, especially without proper pruning, the decision tree will become very complex, resulting in good performance on the training set but poor performance on the test set.

[0045] The workflow of the decision tree: 1. Starting from the root node, select the best split based on the human features and split criteria of the current node; 2. Divide the dataset into subsets based on the split results, and create a new node for each subset; 3. Repeat steps 1 and 2 for each new node until the stopping condition is met (for example, all instances belong to the same class, or the maximum depth is reached); 4. Label the final leaf node as the corresponding classification or regression result.

[0046] S30: construct a user profile based on the association rules, train a personalized recommendation model based on the user profile, and determine the target business data handled by the user based on the personalized recommendation model;

[0047] Using machine learning algorithms, we determine the association rules between user physiological data, user behavior data, and financial behavior data, and build user portraits based on the association rules. User portraits are an abstraction of a user's business profile by analyzing the user's social attributes, living habits, consumption habits, risk preferences, capital flows, and other major information. The core of user portraits is to "label" the user. Each label is usually a human-defined feature identifier that describes a type of person with highly refined features, such as age, gender, and interest preferences. These different labels can be integrated through a structured data system to combine different user portraits.

[0048] Risk preference is the attitude of actively pursuing risks and preferring volatility of returns to stability of returns. Risk preference is divided into risk avoiders, risk seekers and risk neutrals. The attitude of risk avoiders in choosing assets is: when the expected returns are the same, they prefer assets with low risks, and for assets with the same risks, they prefer assets with high expected returns. In contrast to risk avoiders, risk seekers usually actively pursue risks and prefer volatility of returns to stability of returns. When the expected returns are the same, they choose assets with greater risks because this will bring them greater utility. Risk neutrals usually neither avoid risks nor actively pursue risks, and expect the size of returns regardless of the risk situation.

[0049] Consumption habits are the psychological manifestation of the stable preference for certain consumer items formed by the consumer subject in long-term consumption practice. It is a relatively stereotyped consumption behavior pattern formed by consumers in their daily consumption life. For example, consumers like to use a certain brand of a certain product and buy it frequently without selection and comparison due to certain needs, motivations, emotions, experiences or psychological preferences. It is specifically manifested in: consumers' preference for a certain product; consumers' preference for product brands; consumers' preference for consumption behavior.

[0050] The law of capital flow studies the flow and direction of funds: the proportional relationship between capital inflow and capital occupation; the changes in the user's total capital income and expenditure (including investment and withdrawal amounts) and its impact on the effectiveness of capital utilization; changes in capital inflow and occupation structure.

[0051] User portrait generation steps: Data labeling maps the collected user physiological data, user behavior data, and financial behavior data to the constructed label system, and assigns different weights to the labels. The choice of labels will directly affect the richness and accuracy of the final portrait, and needs to be combined with the functions and characteristics of the product itself; Dynamic tracking of user behavior: Confirm user preferences and needs by analyzing the user's behavior trajectory in different scenarios; Generate user portraits: Generate user portraits through corresponding models or tools, which can be Excel tables that include various labels, or a visual portrait. After completing the construction of the user portrait, train a personalized recommendation model based on the user portrait.

[0052] The step of determining the target business data handled by the user based on the personalized recommendation model includes:

[0053] S31: Receive the user's real-time human feature data, predict the predicted financial behavior of the user's operation corresponding to the real-time human feature data based on the personalized recommendation model, and determine the target business data handled by the user.

[0054] After the personalized recommendation model is established, in a specific embodiment, the smart mobile device receives the real-time human feature data of the user collected by the smart wearable device, predicts the predicted financial behavior that meets the real-time human feature data conditions in the personalized recommendation model, and determines the target business data handled by the user based on the predicted financial behavior. The target business data is financial business, including loan products, financial products, savings products, credit products, insurance services, etc.

[0055] S40: When a signal is obtained that the user opens a financial account page through a smart wearable device, the target business data is pushed to the smart wearable device based on a personalized recommendation template, and a corresponding target business data processing program is executed through the smart wearable device.

[0056] After determining the target business data to be handled by the user, wait for the user to trigger the start signal of the smart wearable device. When the signal that the user opens the financial account page through the smart wearable device is obtained, the smart mobile terminal pushes the target business data to the smart wearable device through wireless communication. When the user browses the target business data, the user has the intention to handle it and can click on the processing procedure in the smart wearable device. The smart mobile terminal receives the target business data and executes the corresponding target business data processing procedure through the smart wearable device.

[0057] In one embodiment, when a user opens a financial account page, a target business recommendation window pops up on a smart phone or smart wearable device, and the user can click on the target business recommendation window to learn about and handle the corresponding business. Of course, the user is allowed to perform preliminary screening and confirmation through the smart wearable device, or directly jump to the mobile phone APP for detailed understanding and operation.

[0058] S50: When the corresponding target business data processing procedure is not received through the smart wearable device, the personalized recommendation model is optimized, and the optimized target business data is re-determined according to the optimized personalized recommendation model;

[0059] like Figure 4 When a signal is obtained that the user opens the financial account page through the smart wearable device, the optimized target business data is pushed to the smart wearable device based on the personalized recommendation template, and the corresponding optimized target business data processing procedure is executed through the smart wearable device.

[0060] The user has not processed the target business, and the smart mobile device has not received the corresponding target business data processing procedure executed through the smart wearable device. The smart wearable device transmits the user's intention to the smart wearable device, optimizes the personalized recommendation model, and re-determines the optimized target business data based on the optimized personalized recommendation model, and executes step S40.

[0061] It can be seen that in the above scheme, for the precise push of financial services in smart wearable devices, user data is first collected in real time through smart wearable devices, and then quickly analyzed in combination with intelligent algorithms to achieve instant recommendation of financial services, thereby improving the accuracy and timeliness of financial service recommendations. And based on user physiological data, user behavior data and financial historical transaction data, a personalized user portrait is constructed to provide customized financial service recommendations that meet user needs. Users can directly receive recommendation information and perform preliminary operations through smart watches, thereby improving the convenience and interactivity of user experience. For the precise push of financial services in smart wearable devices, user data is first collected in real time through smart wearable devices, and then quickly analyzed in combination with intelligent algorithms to achieve instant recommendation of financial services, thereby improving the accuracy and timeliness of financial service recommendations.

[0062] It should be understood that the order of execution of the steps in the above embodiment does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.

[0063] In one embodiment, a smart financial service recommendation device based on a smart wearable device is provided, and the smart financial service recommendation device based on a smart wearable device corresponds one-to-one to the smart financial service recommendation method based on a smart wearable device in the above embodiment. Figure 5 As shown, the intelligent financial service recommendation device includes a receiving module 101, an association module 102, a model building module 103, and a recommendation module 104. The detailed description of each functional module is as follows:

[0064] The receiving module 101 is used to receive the human feature data of a preset time period collected by the smart wearable device, and simultaneously obtain the financial behavior data of the user in the financial account;

[0065] An association module 102 is used to pre-process the human feature data and the financial behavior data, and analyze the association rules between the human feature data and the financial behavior data based on a machine learning algorithm;

[0066] A model building module 103 is used to build a user profile based on association rules, train a personalized recommendation model based on the user profile, and determine the target business data handled by the user based on the personalized recommendation model;

[0067] The recommendation module 104 is used to push the target business data to the smart wearable device based on the personalized recommendation template when a signal that the user opens the financial account page through the smart wearable device is obtained, and receive the corresponding target business data processing program executed by the smart wearable device.

[0068] In one embodiment, the receiving module 101 is specifically configured to:

[0069] When receiving a user's instruction to activate a financial account, obtaining transaction history data of a preset period of time in the financial account;

[0070] Synchronize human feature data within a preset time period with the transaction history data of the financial account to obtain the user's financial behavior data.

[0071] In one embodiment, the association module 102 is specifically configured to:

[0072] Clean and preprocess the human feature data and financial behavior data, and remove outliers and noise from the cleaned human feature data and financial behavior data.

[0073] In one embodiment, the model building module 103 is specifically used to:

[0074] Receive the user's real-time human feature data, predict the predicted financial behavior of the user's operation corresponding to the real-time human feature data based on the personalized recommendation model, and determine the target business data handled by the user.

[0075] In one embodiment, the recommendation module 104 is further configured to:

[0076] When the corresponding target business data processing procedure is not received through the smart wearable device, the personalized recommendation model is optimized, and the optimized target business data is re-determined based on the optimized personalized recommendation model;

[0077] When a signal is obtained that the user has opened the financial account page through a smart wearable device, the optimized target business data is pushed to the smart wearable device based on the personalized recommendation template, and the corresponding optimized target business data processing procedure is executed through the smart wearable device.

[0078] The present invention provides an intelligent financial service recommendation device, which can synchronously obtain the financial behavior data of users in financial accounts by receiving human feature data of a preset time collected by intelligent wearable devices; pre-processing human feature data and financial behavior data, and analyzing the association rules between human feature data and financial behavior data based on machine learning algorithms; constructing user portraits based on association rules, and training personalized recommendation models based on user portraits, and determining target business data handled by users based on personalized recommendation models; when a signal that a user opens a financial account page through an intelligent wearable device is obtained, the target business data is pushed to the intelligent wearable device based on a personalized recommendation template, and the corresponding target business data handling program is received and executed through the intelligent wearable device. In the present invention, for the precise push of financial services in intelligent wearable devices, user data is first collected in real time through intelligent wearable devices, and then quickly analyzed in combination with intelligent algorithms to achieve instant recommendation of financial services, thereby improving the accuracy and timeliness of financial service recommendations.

[0079] For the specific definition of the intelligent recommendation financial service device, please refer to the definition of the intelligent question and answer method above, which will not be repeated here. Each module in the above-mentioned intelligent recommendation financial service device can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0080] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 6 As shown. The computer device includes a processor, a memory, a network interface and a database connected via a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile and / or volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external client through a network connection. When the computer program is executed by the processor, it realizes the functions or steps on the service side of a smart recommendation financial business method based on a smart wearable device.

[0081] In one embodiment, a computer device is provided. The computer device may be a client, and its internal structure diagram may be as follows: Figure 7 As shown. The computer device includes a processor, a memory, a network interface, a display screen and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external server via a network connection. When the computer program is executed by the processor, it implements the functions or steps of the client side of a method for intelligently recommending financial services based on a smart wearable device

[0082] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the following steps when executing the computer program:

[0083] Receive human feature data collected by smart wearable devices for a preset period of time, and simultaneously obtain the user's financial behavior data in the financial account;

[0084] Preprocess human feature data and financial behavior data, and analyze the association rules between human feature data and financial behavior data based on machine learning algorithms;

[0085] Build user portraits based on association rules, train personalized recommendation models based on user portraits, and determine the target business data handled by users based on the personalized recommendation models;

[0086] When a signal is obtained that the user has opened the financial account page through a smart wearable device, the target business data is pushed to the smart wearable device based on the personalized recommendation template, and the corresponding target business data processing procedure is executed through the smart wearable device.

[0087] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0088] Receive human feature data collected by smart wearable devices for a preset period of time, and simultaneously obtain the user's financial behavior data in the financial account;

[0089] Preprocess human feature data and financial behavior data, and analyze the association rules between human feature data and financial behavior data based on machine learning algorithms;

[0090] Build user portraits based on association rules, train personalized recommendation models based on user portraits, and determine the target business data handled by users based on the personalized recommendation models;

[0091] When a signal is obtained that the user has opened the financial account page through a smart wearable device, the target business data is pushed to the smart wearable device based on the personalized recommendation template, and the corresponding target business data processing procedure is executed through the smart wearable device.

[0092] It should be noted that the above functions or steps that can be implemented by the computer-readable storage medium or computer device can refer to the relevant descriptions on the server side and the client side in the aforementioned method embodiment. To avoid repetition, they will not be described one by one here.

[0093] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0094] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0095] The embodiments described above are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A method for intelligently recommending financial services based on intelligent wearable devices, characterized in that: include: Receive human feature data collected by smart wearable devices for a preset period of time, and simultaneously obtain the user's financial behavior data in the financial account; Preprocess human feature data and financial behavior data, and analyze the association rules between human feature data and financial behavior data based on machine learning algorithms; Build user profiles based on association rules, train personalized recommendation models based on user profiles, and determine the target business data handled by users based on the personalized recommendation models; When a signal is obtained that the user has opened the financial account page through a smart wearable device, the target business data is pushed to the smart wearable device based on the personalized recommendation template, and the corresponding target business data processing procedure is executed through the smart wearable device.

2. The intelligent financial service recommendation method based on the intelligent wearable device according to claim 1, characterized in that: The step of synchronously acquiring the financial behavior data of the user in the financial account comprises: When receiving a user's instruction to activate a financial account, obtaining transaction history data of a preset period of time in the financial account; Synchronize human feature data within a preset time period with the transaction history data of the financial account to obtain the user's financial behavior data.

3. The intelligent financial service recommendation method based on the intelligent wearable device according to claim 1, characterized in that: The step of preprocessing human feature data and financial behavior data comprises: Clean and preprocess the human feature data and financial behavior data, and remove outliers and noise from the cleaned human feature data and financial behavior data.

4. The intelligent recommendation financial service method based on the intelligent wearable device according to claim 1, characterized in that: User profiles include at least one of risk preferences, consumption habits, and capital flow patterns.

5. The intelligent financial service recommendation method based on the intelligent wearable device according to claim 1, characterized in that: The step of determining the target business data handled by the user based on the personalized recommendation model includes: Receive the user's real-time human feature data, predict the predicted financial behavior of the user's operation corresponding to the real-time human feature data based on the personalized recommendation model, and determine the target business data handled by the user.

6. The intelligent recommendation financial service method based on the intelligent wearable device according to claim 1, characterized in that: The step of pushing the target service data to the smart wearable device based on the personalized recommendation template further includes: When the corresponding target business data processing procedure is not received through the smart wearable device, the personalized recommendation model is optimized, and the optimized target business data is re-determined based on the optimized personalized recommendation model; When a signal is obtained that the user has opened the financial account page through a smart wearable device, the optimized target business data is pushed to the smart wearable device based on the personalized recommendation template, and the corresponding optimized target business data processing procedure is executed through the smart wearable device.

7. The intelligent financial service recommendation method based on the intelligent wearable device according to claim 1, characterized in that: Human characteristic data includes: user physiological data and behavioral data.

8. An intelligent financial service recommendation device based on an intelligent wearable device, characterized in that: include: A receiving module, used to receive human feature data collected by a smart wearable device for a preset period of time, and simultaneously obtain the financial behavior data of the user in the financial account; An association module is used to pre-process human feature data and financial behavior data, and analyze the association rules between human feature data and financial behavior data based on a machine learning algorithm; A model building module is used to build user portraits based on association rules, train personalized recommendation models based on user portraits, and determine the target business data handled by users based on the personalized recommendation models; The recommendation module is used to push target business data to the smart wearable device based on the personalized recommendation template when obtaining the signal that the user opens the financial account page through the smart wearable device, and receive the corresponding target business data processing program executed by the smart wearable device.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method for intelligently recommending financial services based on a smart wearable device are implemented as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method for intelligently recommending financial services based on a smart wearable device are implemented as described in any one of claims 1 to 7.

Images