Risk early warning method and device and electronic equipment

Abstract

The invention discloses a risk early warning method and device and electronic equipment. The method comprises the following steps: acquiring account information of a target user, and acquiring a service type subscribed by the target user from the account information; obtaining business data under the business type in a database, and processing the business data to obtain target data; inputting the business data into the risk prediction model to obtain a prediction result; and determining a target risk level of the account information according to the prediction result, and sending early warning information to the target user according to the target risk level. According to the method and the device, the problem of low accuracy of determining financial risks through artificial experience in related technologies is solved.

Description

Technical Field

[0001] The present application relates to the field of big data, and more specifically, to a risk warning method, device, and electronic device. Background Art

[0002] With the increasing complexity of the financial market and the rapid development of big data technology, the financial risks associated with financial services are also increasing. In order to ensure the safety of users' assets, financial institutions need to predict the financial risks that may arise in users' accounts and provide timely feedback on the prediction results to users, so as to give users early warnings.

[0003] However, when predicting financial risks, we often rely on the experience and judgment of business personnel. For example, business personnel judge whether certain financial risks exist based on the changing state of a certain indicator value, which makes it difficult to make comprehensive and accurate risk predictions.

[0004] Currently, no effective solution has been proposed to address the problem of low accuracy in determining financial risks through manual experience in related technologies. Summary of the invention

[0005] The main purpose of this application is to provide a risk warning method, device and electronic equipment to solve the problem of low accuracy in determining financial risks through manual experience in related technologies.

[0006] In order to achieve the above-mentioned purpose, according to one aspect of the present application, a risk warning method is provided. The method includes: obtaining the account information of the target user, and obtaining the service type subscribed by the target user from the account information; obtaining the service data under the service type in the database, and processing the service data to obtain the target data; inputting the service data into the risk prediction model to obtain the prediction result; determining the target risk level of the account information according to the prediction result, and sending warning information to the target user according to the target risk level.

[0007] Optionally, obtaining the target user's account information and obtaining the type of business subscribed by the target user from the account information includes: sending risk warning permission application information to the target user, and receiving feedback information sent by the target user; when the feedback information indicates that the target user allows risk warning operations, reading the target user's account information from the user database, and determining whether there is subscription data in the account information; when subscription data exists, obtaining the business type to which the subscription data belongs, and obtaining the business type subscribed by the target user; when subscription data does not exist, obtaining the business that the target user has handled, obtaining multiple historical businesses, and analyzing the multiple historical businesses to obtain the business type subscribed by the target user.

[0008] Optionally, processing the business data to obtain target data includes: performing data cleaning operations on the business data to obtain first data; determining whether there is missing data in the first data; if there is missing data, filling the missing data to obtain second data; obtaining data requirements of the risk prediction model, and standardizing the second data according to the data requirements to obtain target data.

[0009] Optionally, the risk prediction model consists of an input layer, a quantum feature extraction layer, a neural network calculation layer and an output layer, and the risk prediction model is trained in the following manner: obtaining multiple groups of first business data and feature information of each group of first business data; combining multiple groups of first business data and corresponding feature information into first sample data to obtain multiple first sample data, and training the quantum feature extraction layer through the multiple first sample data to obtain a trained quantum feature extraction layer; obtaining the risk level corresponding to each group of historical business information, and combining the feature information and corresponding risk level of each group of first business data into second sample data to obtain multiple second sample data; training the neural network calculation layer through the multiple second sample data to obtain a trained neural network calculation layer; obtaining an initial prediction model based on the trained quantum feature extraction layer and the trained neural network calculation layer, and obtaining multiple groups of second business data and risk levels of each group of second business data, wherein the generation time of the second business data is different from that of the first business data; combining multiple groups of second business data and corresponding risk levels into third sample data to obtain multiple third sample data, and using the multiple third sample data to train the initial prediction model to obtain a risk prediction model.

[0010] Optionally, determining the target risk level of the account information according to the prediction results includes: obtaining an initial risk level from the prediction results and obtaining user information of the target user; adjusting the initial risk level according to the user information, account information and business type to obtain the target risk level.

[0011] Optionally, sending warning information to the target user according to the target risk level includes: obtaining user information of the target user, and determining the target style of the warning information based on the user information; generating warning content according to the business type and the target risk level, and generating warning information based on the warning content and the target style; obtaining the preset sending method set by the target user, and sending the warning information to the target user via the preset sending method.

[0012] Optionally, the risk prediction model is composed of a quantum prediction sub-model and a neural network sub-model, and business data is input into the risk prediction model to obtain a prediction result, including: inputting the business data into the quantum prediction sub-model and the neural network sub-model respectively to obtain a first sub-prediction result and a second sub-prediction result; processing the first sub-prediction result and the second sub-prediction result according to preset weights to obtain a prediction result.

[0013] In order to achieve the above-mentioned purpose, according to another aspect of the present application, a risk warning device is provided. The device includes: a first acquisition unit, used to acquire the account information of the target user, and acquire the service type subscribed by the target user from the account information; a first processing unit, used to acquire the service data under the service type in the database, and process the service data to obtain the target data; a first prediction unit, used to input the service data into the risk prediction model to obtain the prediction result; a determination unit, used to determine the target risk level of the account information according to the prediction result, and send warning information to the target user according to the target risk level.

[0014] In order to achieve the above-mentioned purpose, according to another aspect of the present application, an electronic device is provided, the electronic device comprising a memory storing an executable program; and a processor for running the program, wherein the above-mentioned risk warning method is executed when the program is running.

[0015] In order to achieve the above-mentioned purpose, according to another aspect of the present application, a computer program product is provided, including computer instructions, which implement the steps of the above-mentioned risk warning method when executed by a processor.

[0016] In the embodiment of the present application, the target user's account information is obtained, and the type of business subscribed by the target user is obtained from the account information; the business data under the business type is obtained in the database, and the business data is processed to obtain the target data; the business data is input into the risk prediction model to obtain the prediction result; the target risk level of the account information is determined according to the prediction result, and an early warning message is sent to the target user according to the target risk level. The business type is determined by obtaining the target user's account information, and the corresponding business data is obtained according to the business type, and then the risk level of the business related to the target user's account information can be predicted according to the business data and the risk prediction model, so that the user can determine the current risk situation of the account according to the risk level, and then by configuring the risk prediction model, the purpose of improving the accuracy of risk prediction is achieved, thereby achieving the technical effect of ensuring the accuracy of risk prediction, and then solving the problem of low accuracy of determining financial risks through artificial experience in related technologies. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The drawings constituting a part of the present application are used to provide a further understanding of the present application. The illustrative embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0018] Figure 1 A hardware structure block diagram of a computer terminal for implementing a risk early warning method is shown;

[0019] Figure 2 is a flow chart of the risk warning method provided in Example 1 of the present application;

[0020] Figure 3 This is a schematic diagram of the structure of an optional risk prediction model provided in Example 1 of the present application. Figure 1 ;

[0021] Figure 4 This is a schematic diagram of the structure of an optional risk prediction model provided in Example 1 of the present application. Figure 2 ;

[0022] Figure 5 is a schematic diagram of a risk warning device provided according to Example 2 of the present application;

[0023] Figure 6 It is a structural block diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0024] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0025] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0026] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0027] It should be noted that the risk warning method, device and electronic device determined in the present disclosure can be used in the field of big data, and can also be used in any field other than the field of big data. The application field of the risk warning method, device and electronic device determined in the present disclosure is not limited.

[0028] It should be noted that the collected information, user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) used in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of relevant data are in compliance with the relevant laws, regulations and standards of the relevant regions, necessary confidentiality measures are taken, and public order and good customs are not violated. Corresponding operation entrances are provided for users to choose to authorize use or refuse use. If the user chooses to refuse, the expert decision-making process is entered. For example, an interface is set between this system and relevant users or institutions. Before obtaining relevant information, it is necessary to send an acquisition request to the aforementioned user or institution through the interface, and obtain relevant information after receiving the consent information fed back by the aforementioned user or institution.

[0029] The embodiments or examples of the present disclosure are not exhaustive, but are only illustrative of some embodiments or examples, and are not intended to be specific limitations on the scope of protection of the present disclosure. In the absence of contradiction, each step in a certain embodiment or example can be implemented as an independent example, and the steps can be combined arbitrarily. For example, the scheme after removing some steps in a certain embodiment or example can also be implemented as an independent example, and the order of the steps in a certain embodiment or example can be arbitrarily exchanged. In addition, the optional methods or optional examples in a certain embodiment or example can be combined arbitrarily; in addition, the various embodiments or examples can be combined arbitrarily, for example, some or all steps of different embodiments or examples can be combined arbitrarily, and a certain embodiment or example can be combined arbitrarily with the optional methods or optional examples of other embodiments or examples.

[0030] For the convenience of description, some nouns or terms involved in the embodiments of the present application are explained below:

[0031] Quantum computing: Using quantum bits (qubits) to replace binary bits in traditional computers for information processing. It has unique properties such as superposition and entanglement, and can achieve exponential acceleration on certain specific problems.

[0032] Example 1

[0033] According to an embodiment of the present application, an embodiment of a risk warning method is also provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0034] The method embodiment provided in the first embodiment of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Figure 1 FIG. 1 shows a hardware structure block diagram of a computer terminal for implementing a risk early warning method. Figure 1 As shown, the computer terminal 10 (or mobile device) may include one or more (102a, 102b, ..., 102n are used to illustrate) processors 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory 104 for storing data, and a transmission device 106 for communication functions. In addition, it may also include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of the BUS bus), a network interface, a power supply and / or a camera. It can be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the above electronic device. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations are shown.

[0035] It should be noted that the one or more processors 102 and / or other data processing circuits described above may generally be referred to herein as "data processing circuits". The data processing circuits may be embodied in whole or in part as software, hardware, firmware, or any other combination thereof. In addition, the data processing circuit may be a single independent processing module, or may be incorporated in whole or in part into any of the other components in the computer terminal 10 (or mobile device). As described in the embodiments of the present application, the data processing circuit acts as a processor control (e.g., selection of a variable resistor terminal path connected to an interface).

[0036] The memory 104 can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the risk warning method in the embodiment of the present application. The processor 102 executes various functional applications and data processing by running the software programs and modules stored in the memory 104, that is, to implement the above-mentioned risk warning method. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories may be connected to the computer terminal 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 a combination thereof.

[0037] The transmission device 106 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of the computer terminal 10. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0038] The display may be, for example, a touch screen liquid crystal display (LCD) that enables a user to interact with a user interface of the computer terminal 10 (or mobile device).

[0039] Under the above operating environment, this application provides Figure 2 The risk warning method shown. Figure 2 is a flow chart of the risk warning method provided in Example 1 of the present application, such as Figure 2 As shown, the method includes:

[0040] Step S201: Acquire the account information of the target user, and acquire the service type subscribed by the target user from the account information.

[0041] It should be noted that the account information may be the target user's asset information in a financial institution and information about the products purchased, for example, the target user purchased financial product A, financial product B, etc. The business type may refer to the type of each financial product or financial business in a financial institution, for example, business A may be a loan, then the type may be a loan type, and product B may be a bond product, then the type may be a bond type.

[0042] Specifically, when issuing early warnings for financial risks to target users, we first need to know the businesses that the users are interested in and handle. At this time, we can obtain the target user's account information and determine which businesses the user is interested in based on the account information. That is, we determine the business that the user needs to predict through the business type, and then issue early warnings for the financial risks of the business, ensuring the accuracy and matching of the early warnings sent to the target users.

[0043] Step S202, obtaining business data under the business type in the database, and processing the business data to obtain target data.

[0044] It should be noted that business data can be financial market data that is associated with the business under the business type, such as sales data of a certain product, or interest rate fluctuation data of a certain loan business, and other financial data that can be monitored and predicted.

[0045] Specifically, when the business type is obtained, historical business data associated with the business type can be obtained from the database, so as to predict the user's account risk based on the business data, and the prediction result can be sent to the user, so that the user can further process the business or products in the account according to the prediction result, thereby reducing the user's account risk.

[0046] It should be noted that before inputting business data into the risk prediction model, the business data needs to be preprocessed, including data cleaning, feature extraction and standardization, so as to ensure the accuracy and reliability of the data while ensuring that the business data input into the model can maintain good compatibility with the model.

[0047] For example, business data can be processed using quantum computing, thereby using the efficient processing capabilities of quantum computing to clean, denoise, and standardize business data to improve the quality of business data and thereby ensure the accuracy of subsequent model processing of the data.

[0048] Step S203, inputting the business data into the risk prediction model to obtain the prediction result.

[0049] Specifically, after obtaining the business data, the business data can be directly input into the risk prediction model to obtain the model prediction results.

[0050] Step S204, determining the target risk level of the account information according to the prediction result, and sending warning information to the target user according to the target risk level.

[0051] It should be noted that the target risk level may be the financial risk of the target user's account determined according to the prediction results given by the model, which may be divided into low risk, medium risk and high risk levels. The early warning information may be the financial risk warning information sent to the target user according to the target risk level to help the user take appropriate preventive measures or adjust the account operation strategy.

[0052] Specifically, after obtaining the prediction results, the target user's account risk level can be determined based on quantitative indicators such as the risk percentage or risk score given in the prediction results, and then corresponding risk warning information can be sent to the user based on the risk level.

[0053] For example, if the model predicts that the foreign exchange market may fluctuate violently in the next few days, and the user has a large amount of foreign exchange investment, the target user's account risk can be "high risk", and warning information can be generated based on the prediction results. For example, in the case of fluctuations in the foreign exchange market, the warning information can be that the foreign exchange business risk is high, and the user is advised to reduce the foreign exchange position or increase hedging to reduce the risk, thereby informing the user of the cause of the risk and the coping strategies that can be used, and then assisting the user to handle the account, reduce the user's account risk, and ensure the safety and stability of the user's assets.

[0054] The risk warning method provided in the embodiment of the present application obtains the account information of the target user, and obtains the type of business subscribed by the target user from the account information; obtains the business data under the business type in the database, and processes the business data to obtain the target data; inputs the business data into the risk prediction model to obtain the prediction result; determines the target risk level of the account information according to the prediction result, and sends warning information to the target user according to the target risk level. The business type is determined by obtaining the account information of the target user, and the corresponding business data is obtained according to the business type, and then the risk level of the business related to the target user's account information can be predicted according to the business data and the risk prediction model, so that the user can determine the current risk situation of the account according to the risk level, and then by configuring the risk prediction model, the purpose of improving the accuracy of risk prediction is achieved, thereby achieving the technical effect of ensuring the accuracy of risk prediction, and then solving the problem of low accuracy of determining financial risks through artificial experience in related technologies.

[0055] Optionally, in the risk warning method provided in the embodiment of the present application, obtaining the account information of the target user, and obtaining the business type subscribed by the target user from the account information includes: sending risk warning permission application information to the target user, and receiving feedback information sent by the target user; when the feedback information indicates that the target user allows risk warning operations, reading the account information of the target user from the user database, and determining whether there is subscription data in the account information; when there is subscription data, obtaining the business type to which the subscription data belongs, and obtaining the business type subscribed by the target user; when there is no subscription data, obtaining the business that the target user has handled, obtaining multiple historical businesses, and analyzing the multiple historical businesses to obtain the business type subscribed by the target user.

[0056] It should be noted that the risk warning permission application information can be a request sent to the user before obtaining the user's account information, which is used to ask the target user whether it can receive and process data related to risk warnings and whether it is willing to receive warning information, thereby ensuring user privacy and data security. Feedback information can be the user's response to the risk warning permission application, which can be permission or rejection.

[0057] Specifically, risk warning permission application information can be sent to the target user through a secure channel (such as email, SMS or in-app message) and the user's response can be awaited. When feedback is received, the decision on whether to continue with the subsequent operation can be made based on the feedback content, thereby ensuring that the user's authorization information for the operation of obtaining account information is obtained before processing the user's sensitive information and issuing risk warnings, thereby ensuring the security of the user's account information.

[0058] When the feedback information indicates that the target user allows risk warning operations, it indicates that the user is allowed to read the account information. At this time, the target user's account information can be read from the user database, and the account information can be identified to determine whether there is subscription data, where the subscription data can be specific business or service information subscribed by the user on the financial platform. For example, user A subscribes to a loan business in a financial institution, and the subscription data can be loan-related data.

[0059] When it is determined that there is subscription data, the business type to which the subscription data belongs can be obtained, thereby determining the business type for which the user needs to perform risk prediction. For example, if user A subscribes to a loan business in a financial institution, the business type may be a loan business.

[0060] In the absence of subscription data, it indicates that the user has not retained subscription data in the financial institution. At this time, the business types that the user is more interested in or associated with the user can be determined based on the business that the target user has handled in the financial institution, thereby obtaining the business types subscribed by the target user.

[0061] For example, user B has not subscribed to data in a financial institution. At this time, if it is determined that user B has handled a loan business, it can be determined that the business type can be a loan business.

[0062] This embodiment obtains user authorization and takes corresponding actions based on user feedback. It directly obtains the subscribed service types or infers the user's possible areas of interest through historical business analysis, so as to accurately determine the business types related to the target user. Then, the data under the business type can be analyzed to obtain risk warning results, which not only improves the pertinence and effectiveness of risk warnings, but also enhances user trust and satisfaction.

[0063] Optionally, in the risk warning method provided in the embodiment of the present application, processing the business data to obtain the target data includes: performing data cleaning operations on the business data to obtain first data; determining whether there is missing data in the first data; if there is missing data, filling the missing data to obtain second data; obtaining the data requirements of the risk prediction model, and standardizing the second data according to the data requirements to obtain the target data.

[0064] Specifically, business data can be raw financial market data obtained from the database and related to the business type subscribed by the target user. When business data is obtained, it is necessary to use the efficient data processing capabilities of quantum computing to perform data cleaning operations, including identifying and removing erroneous data points, outliers, and inconsistent data records to ensure the data quality of subsequent analysis, thereby improving the reliability of the data and reducing analysis bias caused by erroneous or abnormal data.

[0065] When the first data after data cleaning is obtained, it is necessary to determine whether there is missing data in the first data. If there is missing data, the missing data needs to be filled to obtain the second data, so as to ensure the integrity and accuracy of the business data. For example, when the system detects that there are missing values ​​in the first data, the missing data can be filled using the average value, median, predicted filling and other methods to restore the integrity of the data. It should be noted that the filling strategy may include using the average value of neighboring data points, predictive filling through other relevant features, or using more complex machine learning methods, which are not limited here.

[0066] It should be noted that the data requirements may be specific data formats and ranges required for model training and prediction, such as numerical ranges, time series formats, etc., and the standardization process may be to convert the data into a unified format or numerical range so that the model can process it more effectively. After obtaining the second data, since the data format of the business data may not be unified or may not match the model, it is also necessary to standardize the second data according to the data requirements of the risk prediction model, so as to obtain the target data that the risk prediction model can identify and process, thereby ensuring the accuracy of the risk prediction model.

[0067] This embodiment removes errors and outliers through data cleaning, then completes the data set through a missing data filling strategy, and finally performs standardization processing according to the model requirements, thereby ensuring the accuracy, completeness and consistency of the business data, providing a solid foundation for subsequent risk prediction through the risk prediction model, and ensuring the accuracy of the risk prediction operation.

[0068] Optionally, in the risk warning method provided in the embodiment of the present application, the risk prediction model is composed of an input layer, a quantum feature extraction layer, a neural network calculation layer and an output layer, and the risk prediction model is trained in the following manner: obtaining multiple groups of first business data and feature information of each group of first business data; combining multiple groups of first business data and corresponding feature information into first sample data to obtain multiple first sample data, and training the quantum feature extraction layer through the multiple first sample data to obtain a trained quantum feature extraction layer; obtaining the risk level corresponding to each group of historical business information, and combining the feature information and the corresponding risk level of each group of first business data into second sample data to obtain multiple second sample data; training the neural network calculation layer through the multiple second sample data to obtain a trained neural network calculation layer; obtaining an initial prediction model according to the trained quantum feature extraction layer and the trained neural network calculation layer, and obtaining multiple groups of second business data and the risk level of each group of second business data, wherein the generation time of the second business data is different from that of the first business data; combining multiple groups of second business data and corresponding risk levels into third sample data to obtain multiple third sample data, and using the multiple third sample data to train the initial prediction model to obtain a risk prediction model.

[0069] It should be noted that Figure 3 This is a schematic diagram of the structure of an optional risk prediction model provided in Example 1 of the present application. Figure 1 ,like Figure 3 As shown in the figure, the risk prediction model consists of an input layer, a quantum feature extraction layer, a neural network computing layer and an output layer, wherein the input layer is used to receive pre-processed business data as the starting point for model analysis and prediction. The quantum feature extraction layer is used to extract key features from the input data using the parallel processing capability of quantum computing. The neural network computing layer is used to apply neuromorphic computing, perform deep learning based on the extracted features, and identify complex patterns and relationships. The output layer is used to generate model prediction results. By combining the quantum feature extraction layer and the neural network computing layer, the quantum feature extraction layer uses the super parallelism and quantum interference effect of quantum computing to quickly and efficiently extract key features from large-scale financial market data, and the neural network computing layer identifies and learns complex data patterns, and accurately predicts based on the features. By combining with the quantum feature extraction layer, the features extracted by quantum can be further deeply analyzed and modeled to enhance the accuracy of financial risk prediction.

[0070] It should be noted that when training the risk prediction model, it is first necessary to train the quantum feature extraction layer and the neural network calculation layer separately. After the training is completed, the trained quantum feature extraction layer and the neural network calculation layer are combined into an initial prediction model, and the initial prediction model is further trained to obtain a risk prediction model, thereby ensuring the accuracy of the risk prediction model.

[0071] Specifically, it is necessary to first access the database and extract multiple sets of first business data from historical records, which involve different business types and business data. At the same time, the revolving door and measurement device of quantum neurons are used, combined with the pattern recognition ability of neuromorphic computing, to pre-process these data to extract characteristic information related to financial market risks.

[0072] Optionally, the business data and feature information of each business data can be paired to form a first sample data set. The data set is used to train the quantum feature extraction layer, and the parameters of the quantum gates and quantum neurons are adjusted through multiple iterations to improve the accuracy and efficiency of the quantum feature extraction layer in extracting features from the business data, so that it can more effectively identify key features from the business data and provide optimized input for subsequent deep learning.

[0073] Optionally, it is also necessary to determine the risk level of each first business data, and associate the feature data with the risk level to obtain second sample data, so as to use the second sample data to train the neural network computing layer to obtain a trained neural network computing layer, so that the neural network computing layer can perform accurate risk prediction operations based on the feature information extracted by the quantum feature extraction layer to obtain more accurate risk prediction results.

[0074] It should be noted that after the training of the quantum feature extraction layer and the neural network calculation layer is completed, the trained quantum feature extraction layer and the neural network calculation layer can be integrated to form an initial prediction model. Subsequently, the second business data generated at a different time from the first business data but also containing risk level information is obtained, and the initial prediction model is trained using the second business data. The model parameters are adjusted through a machine learning algorithm to improve the prediction accuracy and stability, thereby further integrating the quantum feature extraction layer and the neural network calculation layer to ensure the accuracy of the risk prediction results.

[0075] This embodiment trains the quantum feature extraction layer and the neural network calculation layer separately, and further trains the quantum feature extraction layer and the neural network calculation layer after combining them, thereby ensuring the accuracy of the prediction results of the risk prediction model.

[0076] Optionally, in the risk warning method provided in the embodiment of the present application, determining the target risk level of account information based on the prediction results includes: obtaining an initial risk level from the prediction results and obtaining user information of the target user; adjusting the initial risk level according to the user information, account information and business type to obtain the target risk level.

[0077] Specifically, after obtaining the prediction results, the initial risk level can be obtained from the prediction results. The initial risk level can be represented by different levels or by scores. Since the same business data corresponds to different risk levels for different target users, after obtaining the initial risk level, the user information of the target user can be obtained, so as to adjust the initial risk level according to the user information and account information as well as the business type of the business, and then complete the personalized risk level adjustment to ensure that the risk management recommendations match the user's actual situation.

[0078] For example, user information, account information and business type are combined with the initial risk level, and the initial risk level is adjusted by analyzing the user's risk tolerance, financial status and the risk characteristics of specific businesses. If the user has a higher risk tolerance or holds lower-risk assets in the account, the risk level can be lowered to ensure a match between the risk prediction results and the user.

[0079] This embodiment generates an initial risk level based on the prediction results, and then adjusts the initial level by collecting and analyzing detailed information of the user, including risk preferences, account information, and business type, to generate a more customized risk level, thereby improving the accuracy of risk management, ensuring the pertinence and practicality of the risk prediction results, and helping target users to better understand the actual risk level of their accounts and take appropriate risk management measures based on their own circumstances.

[0080] Optionally, in the risk warning method provided in the embodiment of the present application, sending warning information to the target user according to the target risk level includes: obtaining user information of the target user, and determining the target style of the warning information based on the user information; generating warning content according to the business type and the target risk level, and generating warning information according to the warning content and the target style; obtaining the preset sending method set by the target user, and sending the warning information to the target user through the preset sending method.

[0081] Specifically, when providing feedback on warning information, the target user's information, including risk preferences, communication preferences, etc., can be accessed first to understand the user's specific needs and preferences, and based on this information, determine the optimal presentation method for the warning information. For example, for users who prefer detailed information, the warning information may contain more data and analysis, and for users who prefer concise notifications, the warning information will be more concise.

[0082] After obtaining the target style, it is also necessary to comprehensively consider the business type and target risk level to generate the corresponding warning content, which may include a clear description of the risk level, potential market changes, impact assessment on users, and recommended response strategies, etc. Subsequently, according to the previously determined target style, the warning content is formatted and designed to generate the final warning information.

[0083] When receiving warning information, you can query the sending method pre-selected by the target user in the personal settings, and then send the warning information through the communication channel specified by the user to ensure that the information can reach the user in a timely and accurate manner.

[0084] This embodiment determines the target style of warning information by analyzing user information, ensures that the information presentation method best meets the needs of users, and generates warning content based on business type and target risk level, so that the information content is directly related to the user's account status, and provides targeted risk management suggestions. Finally, the warning information is sent through the user's preset sending method, which ensures the immediacy of information and the convenience of user reception, thereby significantly enhancing the user experience and improving the efficiency and effectiveness of the warning service.

[0085] Optionally, in the risk warning method provided in the embodiment of the present application, the risk prediction model is composed of a quantum prediction sub-model and a neural network sub-model, and the business data is input into the risk prediction model to obtain the prediction result, including: inputting the business data into the quantum prediction sub-model and the neural network sub-model respectively to obtain a first sub-prediction result and a second sub-prediction result; processing the first sub-prediction result and the second sub-prediction result according to preset weights to obtain a prediction result.

[0086] It should be noted that the quantum prediction sub-model can be a computing model designed for risk prediction based on quantum computing characteristics, such as quantum bits, quantum gates, and quantum parallelism. The preset weight can be a weight allocated between the quantum prediction sub-model and the neural network sub-model, which is used to adjust the contribution of the two sub-models to the prediction results.

[0087] Specifically, Figure 4 This is a schematic diagram of the structure of an optional risk prediction model provided in Example 1 of the present application. Figure 2 ,like Figure 4 As shown in the figure, when predicting risks, a risk prediction model composed of a quantum prediction sub-model and a neural network sub-model can also be used for risk prediction. First, the business data is input into the quantum prediction sub-model and the neural network sub-model respectively, and the parallel processing capability of quantum computing is used for rapid analysis, and the deep learning capability of neuromorphic computing is used for pattern recognition, thereby generating two sub-prediction results.

[0088] After obtaining the first sub-prediction result and the second sub-prediction result, the weights of the quantum prediction sub-model and the neural network sub-model can be set based on factors such as historical prediction accuracy or business needs, and the first sub-prediction result and the second sub-prediction result are weighted and fused according to the weights to obtain the final prediction result, thereby balancing the contributions of the quantum prediction sub-model and the neural network sub-model to ensure the accuracy and reliability of the prediction results. By fusing the prediction results of the two sub-models, the limitations of a single model can be overcome, the overall prediction performance can be improved, and the accuracy of the model prediction results can be guaranteed.

[0089] This embodiment uses two sub-models to analyze business data from different angles, generates two sub-prediction results, and integrates the prediction results of the two sub-models through weighted fusion with preset weights to obtain an optimized prediction result, thereby ensuring the accuracy of the model prediction results.

[0090] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0091] Example 2

[0092] The embodiment of the present application also provides a risk warning device. It should be noted that the risk warning device of the embodiment of the present application can be used to execute the risk warning method provided in the above embodiment. The risk warning device provided in the embodiment of the present application is introduced below.

[0093] According to an embodiment of the present application, a device for implementing the above risk warning method is also provided. Figure 5 is a schematic diagram of a risk warning device provided according to Example 2 of the present application, such as Figure 5 As shown, the device comprises:

[0094] The first acquisition unit 51 is used to acquire the account information of the target user, and acquire the service type subscribed by the target user from the account information.

[0095] The first processing unit 52 is used to obtain business data under the business type in the database, and process the business data to obtain target data.

[0096] The first prediction unit 53 is used to input business data into the risk prediction model to obtain a prediction result.

[0097] The determination unit 54 is used to determine the target risk level of the account information according to the prediction result, and send warning information to the target user according to the target risk level.

[0098] The risk warning device provided in the embodiment of the present application obtains the target user's account information through the first acquisition unit 51, and obtains the service type subscribed by the target user from the account information; the first processing unit 52 obtains the business data under the business type in the database, and processes the business data to obtain the target data; the first prediction unit 53 inputs the business data into the risk prediction model to obtain the prediction result; the determination unit 54 is used to determine the target risk level of the account information according to the prediction result, and send warning information to the target user according to the target risk level. The business type is determined by obtaining the target user's account information, and the corresponding business data is obtained according to the business type, and then the risk level of the business related to the target user's account information can be predicted according to the business data and the risk prediction model, so that the user can determine the current risk situation of the account according to the risk level, and then by configuring the risk prediction model, the purpose of improving the accuracy of risk prediction is achieved, thereby achieving the technical effect of ensuring the accuracy of risk prediction, and then solving the problem of low accuracy of determining financial risks through artificial experience in related technologies.

[0099] Optionally, in the risk warning device provided in the embodiment of the present application, the first acquisition unit 51 includes: a first sending module, used to send risk warning authority application information to the target user, and receive feedback information sent by the target user; a first judgment module, used to read the target user's account information from the user database and determine whether there is subscription data in the account information when the feedback information indicates that the target user allows risk warning operations; the first acquisition module, used to obtain the business type to which the subscription data belongs when the subscription data exists, and obtain the business type subscribed by the target user; the second acquisition module, used to obtain the business that the target user has handled when the subscription data does not exist, obtain multiple historical businesses, and analyze the multiple historical businesses to obtain the business type subscribed by the target user.

[0100] Optionally, in the risk warning device provided in the embodiment of the present application, the first processing unit 52 includes: a cleaning module, used to perform data cleaning operations on business data to obtain first data; a second judgment module, used to judge whether there is missing data in the first data; a filling module, used to fill the missing data when there is missing data, to obtain second data; a third acquisition module, used to obtain the data requirements of the risk prediction model, and standardize the second data according to the data requirements to obtain target data.

[0101] Optionally, in the risk warning device provided in the embodiment of the present application, the risk prediction model is composed of an input layer, a quantum feature extraction layer, a neural network calculation layer and an output layer, and the risk prediction model is trained in the following manner: a second acquisition unit is used to obtain multiple groups of first business data and feature information of each group of first business data; a first combination unit is used to combine multiple groups of first business data and corresponding feature information into first sample data to obtain multiple first sample data, and train the quantum feature extraction layer through the multiple first sample data to obtain a trained quantum feature extraction layer; a third acquisition unit is used to obtain the risk level corresponding to each group of historical business information, and combine the feature information of each group of first business data and the corresponding risk level The levels are combined into second sample data to obtain multiple second sample data; a training unit is used to train the neural network calculation layer through the multiple second sample data to obtain the trained neural network calculation layer; a fourth acquisition unit is used to obtain an initial prediction model according to the trained quantum feature extraction layer and the trained neural network calculation layer, and obtain multiple groups of second business data, and the risk level of each group of second business data, wherein the second business data is generated at a different time from the first business data; a second combination unit is used to combine the multiple groups of second business data and the corresponding risk levels into third sample data to obtain multiple third sample data, and use the multiple third sample data to train the initial prediction model to obtain a risk prediction model.

[0102] Optionally, in the risk warning device provided in an embodiment of the present application, the determination unit 54 includes: a fourth acquisition module, used to obtain the initial risk level from the prediction result and obtain the user information of the target user; an adjustment module, used to adjust the initial risk level according to the user information, account information and business type to obtain the target risk level.

[0103] Optionally, in the risk warning device provided in the embodiment of the present application, the determination unit 54 includes: a fifth acquisition module, used to obtain user information of the target user, and determine the target style of the warning information based on the user information; a generation module, used to generate warning content according to the business type and the target risk level, and generate warning information according to the warning content and the target style; a second sending module, used to obtain the preset sending method set by the target user, and send the warning information to the target user through the preset sending method.

[0104] Optionally, in the risk warning device provided in the embodiment of the present application, the risk prediction model is composed of a quantum prediction sub-model and a neural network sub-model, and the business data is input into the risk prediction model to obtain a prediction result including: a second prediction unit, used to input the business data into the quantum prediction sub-model and the neural network sub-model respectively, to obtain a first sub-prediction result and a second sub-prediction result; a second processing unit, used to process the first sub-prediction result and the second sub-prediction result according to preset weights to obtain a prediction result.

[0105] It should be noted that the first acquisition unit 51, the first processing unit 52, the first prediction unit 53, and the determination unit 54 correspond to steps S201 to S204 in Embodiment 1, and the two modules and the corresponding steps implement the same examples and application scenarios, but are not limited to the contents disclosed in Embodiment 1. It should be noted that the above modules or units may be hardware components or software components stored in a memory (e.g., memory 104) and processed by one or more processors (e.g., processors 102a, 102b, ..., 102n), and the above modules may also be part of a device and run in the computer terminal 10 provided in Embodiment 1.

[0106] Example 3

[0107] An embodiment of the present application may provide an electronic device, Figure 6 is a structural block diagram of an electronic device according to an embodiment of the present application. Figure 6 As shown, the electronic device may include: one or more ( Figure 6 (only one is shown) processor 1002, memory 1004, storage controller, and peripheral interface, wherein the peripheral interface is connected to the radio frequency module, audio module and display.

[0108] Among them, the memory can be used to store software programs and modules, such as program instructions / modules corresponding to the methods and devices in the embodiments of the present application, and the processor executes various functional applications and data processing by running the software programs and modules stored in the memory, that is, realizing the above-mentioned method. The memory may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory may further include a memory remotely arranged relative to the processor, and these remote memories may be connected to the terminal 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.

[0109] The processor can call the information and application stored in the memory through the transmission device to perform the following steps: obtain the account information of the target user, and obtain the service type subscribed by the target user from the account information; obtain the business data under the business type in the database, and process the business data to obtain the target data; input the business data into the risk prediction model to obtain the prediction result; determine the target risk level of the account information according to the prediction result, and send warning information to the target user according to the target risk level.

[0110] The processor can call the information and application stored in the memory through the transmission device to perform the following steps: send risk warning authority application information to the target user and receive feedback information sent by the target user; when the feedback information indicates that the target user allows the risk warning operation, read the target user's account information from the user database and determine whether there is subscription data in the account information; when subscription data exists, obtain the business type to which the subscription data belongs, and obtain the business type subscribed by the target user; when subscription data does not exist, obtain the business that the target user has handled, obtain multiple historical businesses, and analyze the multiple historical businesses to obtain the business type subscribed by the target user.

[0111] The processor can call the information and application programs stored in the memory through the transmission device to execute the following steps: perform data cleaning operations on the business data to obtain the first data; determine whether there is missing data in the first data; if there is missing data, fill the missing data to obtain the second data; obtain the data requirements of the risk prediction model, and standardize the second data according to the data requirements to obtain the target data.

[0112] The processor can call the information and application stored in the memory through the transmission device to perform the following steps: the risk prediction model is composed of an input layer, a quantum feature extraction layer, a neural network calculation layer and an output layer, and the risk prediction model is trained in the following manner: obtaining multiple groups of first business data and feature information of each group of first business data; combining the multiple groups of first business data and the corresponding feature information into first sample data to obtain multiple first sample data, and training the quantum feature extraction layer through the multiple first sample data to obtain the trained quantum feature extraction layer; obtaining the risk level corresponding to each group of historical business information, and combining the feature information and the corresponding risk level of each group of first business data into second sample data to obtain multiple second sample data; training the neural network calculation layer through the multiple second sample data to obtain the trained neural network calculation layer; obtaining the initial prediction model according to the trained quantum feature extraction layer and the trained neural network calculation layer, and obtaining multiple groups of second business data and the risk level of each group of second business data, wherein the generation time of the second business data is different from that of the first business data; combining the multiple groups of second business data and the corresponding risk levels into third sample data to obtain multiple third sample data, and using the multiple third sample data to train the initial prediction model to obtain the risk prediction model.

[0113] The processor can call the information and application stored in the memory through the transmission device to perform the following steps: obtain the initial risk level from the prediction results and obtain the user information of the target user; adjust the initial risk level according to the user information, account information and business type to obtain the target risk level.

[0114] The processor can call the information and application stored in the memory through the transmission device to perform the following steps: obtain the user information of the target user, and determine the target style of the warning information based on the user information; generate warning content according to the business type and target risk level, and generate warning information based on the warning content and the target style; obtain the preset sending method set by the target user, and send the warning information to the target user through the preset sending method.

[0115] The processor can call the information and application programs stored in the memory through the transmission device to perform the following steps: the risk prediction model is composed of a quantum prediction sub-model and a neural network sub-model, and the business data is input into the risk prediction model to obtain the prediction result, including: inputting the business data into the quantum prediction sub-model and the neural network sub-model respectively to obtain the first sub-prediction result and the second sub-prediction result; processing the first sub-prediction result and the second sub-prediction result according to preset weights to obtain the prediction result.

[0116] It can be understood by those skilled in the art that Figure 6The structure shown is for illustration only, and the electronic device may also be a smart phone (such as an Android phone, an iOS phone, etc.), a tablet computer, a PDA, a mobile Internet device (Mobile Internet Devices, MID), a PAD, or other terminal devices. Figure 6 The structure of the electronic device is not limited. Figure 6 More or fewer components (such as network interfaces, display devices, etc.) shown in, or having Figure 6 Different configurations are shown.

[0117] A person of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing the hardware related to the terminal device through a program, and the program can be stored in a computer-readable storage medium, and the storage medium may include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0118] Example 4

[0119] The embodiment of the present application further provides a storage medium. Optionally, in this embodiment, the storage medium can be used to store the program code executed by the risk warning method provided in the first embodiment.

[0120] Optionally, in this embodiment, the above storage medium may be located in any computer terminal in a computer terminal group in a computer network, or in any mobile terminal in a mobile terminal group.

[0121] An embodiment of the present application also provides a computer program product, which, when executed on a data processing device, is suitable for executing the steps of the risk warning method.

[0122] An embodiment of the present application further provides a computer-readable storage medium, which includes a stored executable program, wherein when the executable program runs, the device where the computer-readable storage medium is located is controlled to execute the above-mentioned risk warning method.

[0123] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0124] In the above embodiments of the present application, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0125] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0126] 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 units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0127] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0128] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or optical disk and other media that can store program codes.

[0129] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A risk early warning method, characterized in that: include: Acquire the account information of the target user, and acquire the service type subscribed by the target user from the account information; Acquire business data under the business type in the database, and process the business data to obtain target data; Inputting the business data into a risk prediction model to obtain a prediction result; A target risk level of the account information is determined according to the prediction result, and a warning message is sent to the target user according to the target risk level.

2. The method according to claim 1, characterized in that: Acquiring the target user's account information, and acquiring the service type subscribed by the target user from the account information includes: Send risk warning permission application information to the target user, and receive feedback information sent by the target user; When the feedback information indicates that the target user allows the risk warning operation, reading the account information of the target user from the user database, and determining whether there is subscription data in the account information; If the subscription data exists, obtaining the service type to which the subscription data belongs, and obtaining the service type subscribed by the target user; In the absence of the subscription data, the services handled by the target user are acquired to obtain a plurality of historical services, and the plurality of historical services are analyzed to obtain the service type subscribed by the target user.

3. The method according to claim 1, characterized in that The business data is processed to obtain target data including: Performing a data cleaning operation on the business data to obtain first data; Determine whether there is missing data in the first data; In the case where the missing data exists, filling the missing data to obtain second data; The data requirements of the risk prediction model are obtained, and the second data is standardized according to the data requirements to obtain the target data.

4. The method according to claim 1, characterized in that: The risk prediction model is composed of an input layer, a quantum feature extraction layer, a neural network calculation layer and an output layer. The risk prediction model is trained in the following way: Acquire multiple groups of first service data and characteristic information of each group of first service data; Combining the multiple groups of first business data and corresponding feature information into first sample data to obtain multiple first sample data, and training the quantum feature extraction layer by using the multiple first sample data to obtain a trained quantum feature extraction layer; Obtaining the risk level corresponding to each group of historical business information, and combining the characteristic information and the corresponding risk level of each group of first business data into second sample data, to obtain a plurality of second sample data; Training the neural network computing layer using the plurality of second sample data to obtain a trained neural network computing layer; Obtaining an initial prediction model according to the trained quantum feature extraction layer and the trained neural network calculation layer, and acquiring multiple groups of second business data and risk levels of each group of second business data, wherein the second business data and the first business data are generated at different times; The multiple groups of second business data and the corresponding risk levels are combined into third sample data to obtain multiple third sample data, and the initial prediction model is trained using the multiple third sample data to obtain the risk prediction model.

5. The method according to claim 1, characterized in that Determining the target risk level of the account information according to the prediction result includes: Obtaining an initial risk level from the prediction result, and obtaining user information of the target user; The initial risk level is adjusted according to the user information, the account information and the business type to obtain the target risk level.

6. The method according to claim 1, characterized in that Sending warning information to the target user according to the target risk level includes: Acquire user information of the target user, and determine a target style of the warning information according to the user information; Generate warning content according to the business type and the target risk level, and generate the warning information according to the warning content and the target style; The preset sending method set by the target user is obtained, and the warning information is sent to the target user through the preset sending method.

7. The method according to claim 1, characterized in that The risk prediction model is composed of a quantum prediction sub-model and a neural network sub-model. The business data is input into the risk prediction model to obtain prediction results including: Inputting the business data into the quantum prediction sub-model and the neural network sub-model respectively to obtain a first sub-prediction result and a second sub-prediction result; The first sub-prediction result and the second sub-prediction result are processed according to preset weights to obtain the prediction result.

8. A risk warning device, characterized in that: include: A first acquisition unit is used to acquire the account information of a target user, and acquire the service type subscribed by the target user from the account information; A first processing unit is used to obtain business data of the business type in a database, and process the business data to obtain target data; A first prediction unit, used for inputting the business data into a risk prediction model to obtain a prediction result; A determination unit is used to determine a target risk level of the account information according to the prediction result, and send warning information to the target user according to the target risk level.

9. A computer program product comprising computer instructions, characterized in that When the computer instructions are executed by a processor, the steps of the risk warning method described in any one of claims 1 to 7 are implemented.

10. An electronic device, characterized in that: include: A memory storing an executable program; A processor is used to run the program, wherein the risk warning method described in any one of claims 1 to 7 is executed when the program is run.

Images