Risk feature management method and device in risk business, equipment and medium

Abstract

The embodiment of the invention relates to the technical field of financial science and technology, and discloses a risk feature management method and device in risk business, equipment and a medium. The method comprises the following steps: classifying risk features according to service lines, service classifications and data sources in risk services to obtain a risk feature directory of a service perspective; according to the root features in the risk feature directory and the application scene information of the risk features, determining corresponding derivative features; pushing the root features and the corresponding derivative features to a risk view and / or a risk model; and obtaining calling information of each risk feature in the risk view and / or the risk model, and generating a risk feature operation result. According to the method, the risk features dispersed in each business system can be managed in a unified manner, repeated development of the risk features is avoided, and the use condition of the risk features can be mastered.

Description

Technical Field

[0001] The present invention relates to the technical field of fintech, and particularly to a risk feature management method, device, equipment and medium in risk business. Background Art

[0002] In financial institutions, the business data volume is huge and the business lines are complex. The risk features of each business line and each institution are scattered in different business systems. Among them, the risk feature is a processed index with the logical meaning of risk business.

[0003] When users use risk features, they need to investigate each business system and screen risk features based on the data middle platform. The risk features are limited by each business system and cannot be reused. And when summarizing the asset situation of risk features, it is necessary to re-develop risk features to understand the call situation of risk features. As a result, the risk feature management level is low and resources are occupied repeatedly. Summary of the Invention

[0004] The present invention provides a risk feature management method, device, equipment and medium in risk business to uniformly manage risk features, master the usage of risk features, and avoid repeated development.

[0005] According to one aspect of the present invention, there is provided a risk feature management method in risk business, the method comprising:

[0006] Classify risk features according to the business line, business classification and data source in risk business to obtain a risk feature catalog from the perspective of business;

[0007] Determine corresponding derivative features according to the root features in the risk feature catalog and the application scenario information of the risk features;

[0008] Push the root features and the corresponding derivative features to a risk view and / or a risk model;

[0009] Obtain the call information of each risk feature in the risk view and / or the risk model, and generate a risk feature operation result.

[0010] According to another aspect of the present invention, there is provided a risk feature management device in risk business, the device comprising:

[0011] A risk feature catalog generation module, configured to classify risk features according to the business line, business classification and data source in risk business to obtain a risk feature catalog from the perspective of business;

[0012] A derivative feature determination module, configured to determine corresponding derivative features according to the root features in the risk feature catalog and the application scenario information of the risk features;

[0013] A feature push module, configured to push the root feature and the corresponding derivative features to a risk view and / or a risk model;

[0014] A risk feature operation result generation module, configured to obtain the call information of each risk feature in the risk view and / or the risk model, and generate a risk feature operation result.

[0015] According to another aspect of the present invention, there is provided an electronic device, including:

[0016] At least one processor; and

[0017] A memory communicatively connected to the at least one processor; wherein,

[0018] The memory stores a computer program executable by the at least one processor, and when the computer program is executed by the at least one processor, the at least one processor is enabled to execute the risk feature management method in the risk service according to any embodiment of the present invention.

[0019] According to another aspect of the present invention, there is provided a computer-readable storage medium storing computer instructions for enabling a processor to implement the risk feature management method in the risk service according to any embodiment of the present invention when executed.

[0020] According to another aspect of the present invention, there is provided a computer program product including a computer program, which implements the risk feature management method in the risk service according to any embodiment of the present invention when executed by a processor.

[0021] The technical solution of the embodiment of the present invention classifies risk features according to business lines, business classifications, and data sources in risk services to obtain a risk feature catalog from a business perspective; determines corresponding derivative features according to the root features in the risk feature catalog and the application scenario information of the risk features; pushes the root features and the corresponding derivative features to a risk view and / or a risk model; obtains the call information of each risk feature in the risk view and / or the risk model, and generates a risk feature operation result, solving the problem that risk features are scattered in each business system and need to be repeatedly developed during management. By generating a risk feature catalog from a business perspective and performing online risk feature management, rapid positioning of risk features can be achieved, the usage situation of risk features can be mastered, and repeated development of risk features can be avoided.

[0022] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present invention, nor is it used to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for use in the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0024] Figure 1 is a flowchart of a risk feature management method in a risk business provided according to an embodiment of the present invention;

[0025] Figure 2 is a flowchart of another risk feature management method in a risk business provided according to an embodiment of the present invention;

[0026] Figure 3 is an application example diagram of a risk feature management method in a risk business provided according to an embodiment of the present invention;

[0027] Figure 4 is a schematic structural diagram of a risk feature management device in a risk business provided according to an embodiment of the present invention;

[0028] Figure 5 is a schematic structural diagram of an electronic device for implementing the risk feature management method in a risk business of an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0029] In order to enable those skilled in the art to better understand the solution of the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0030] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above drawings are used to distinguish similar objects, and do not necessarily need to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so that the embodiments of the present invention described here can be implemented in an order other than those illustrated or described here. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device that includes a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0031] Figure 1 It is a flowchart of a risk feature management method in a risk business provided according to an embodiment of the present invention. This embodiment is applicable to the situation of online unified management of risk features in a risk business in the field of fintech. This method can be executed by a risk feature management device in the risk business. The risk feature management device in the risk business can be implemented in the form of hardware and / or software, and the risk feature management device in the risk business can be configured in an electronic device. The electronic device can be a mobile device such as a mobile phone, a tablet computer (PAD), a wearable device, etc., or a personal computer (PC, Personal Computer), etc. As Figure 1 shown, the method includes:

[0032] Step 110: Classify risk features according to the business line, business classification, and data source in the risk business to obtain a risk feature catalog from the business perspective.

[0033] The risk business can be a business in a financial institution where there is a risk that a certain amount of financial resources cannot be recovered or recovered overdue. For example, the risk business can be a business related to loans. The business line can be different business departments or operating units within an enterprise or a financial institution divided according to standards such as business type, product type, service function, or customer group. The business classification includes but is not limited to personal business and corporate business. The data source includes but is not limited to the inside and outside of a financial institution. The risk features include but are not limited to: borrowing information, overdue and bad information, collection information, and credit information, etc. The acquisition of risk features is obtained only after user authorization, and the acquisition method is reasonable and legal.

[0034] Classifying the risk features can be a multi-dimensional division according to the business line, business classification, and data source to generate a risk feature catalog from the business perspective. For example, fine classification categories can be set according to the three major dimensions of macro, meso, and micro to obtain the risk feature catalog.

[0035] Among them, the risk feature catalog can be accessed to the metadata management system. The metadata management system can be used to record metadata information of each application processing index. Specifically, the risk feature catalog information recorded by the metadata management system includes but is not limited to: source application, source table, index name, index business meaning, index processing technical logic, and index update frequency, etc.

[0036] In an alternative implementation of the embodiments of the present invention, risk characteristics are classified according to the business lines, business classifications, and data sources in the risk business to obtain a risk characteristic catalog from the business perspective, including: classifying risk characteristics according to at least one piece of information among policy, industry, region, product, user, and debt item to obtain a risk characteristic catalog from the business perspective.

[0037] Specifically, risk characteristics can be classified under multiple sub - categories such as policy, industry, region, product, user, and debt item in two ways: bottom - up and top - down, to generate a risk characteristic catalog. Among them, the top - down method can rely on business experience, and the bottom - up method can be to automatically classify relevant data according to existing data using a large - model method, based on information such as the business department to which the data belongs and the application to which the data belongs, to supplement the risk characteristic classification based on business experience.

[0038] By classifying risk characteristics in multiple dimensions in both bottom - up and top - down ways, the reliability of generating the risk characteristic catalog can be improved, facilitating subsequent screening of risk characteristics based on the risk characteristic catalog.

[0039] Step 120: Determine corresponding derivative characteristics according to the root characteristics in the risk characteristic catalog and the application - scenario information of the risk characteristics.

[0040] The root characteristics can be basic characteristics processed from source data. For example, the root characteristics can be the number of historical overdue times, the number of historical non - performing times, and the historical overdue amount, etc. The application - scenario information can include, but is not limited to, loan - stage information, application - business - line information, and application - channel information, etc. The derivative characteristics can be characteristics derived from the root characteristics through simple logical operations and set time slices, etc. For example, the derivative characteristics can be the number of historical overdue times in the past six months, the overdue and non - performing amount greater than 5000 in the past 12 months, etc.

[0041] In the embodiments of the present invention, based on the root characteristics and the application - scenario information, appropriate time slices and characteristic thresholds can be determined, so as to derive the root characteristics to obtain derivative characteristics. For example, the time slices can include, but are not limited to: the past month, the past three months, the past six months, and the past nine months, etc. The characteristic thresholds can include, but are not limited to: greater than 500, greater than 1000, less than 50%, etc. The required time slices and characteristic thresholds can be different under different application - scenario information to accurately predict the risks in this business.

[0042] In the embodiments of the present invention, a mapping relationship can be established for time slices and feature thresholds of different application scenario information, so as to determine the corresponding time slices and feature thresholds according to the mapping relationship. Alternatively, a network model can be pre-trained to recommend appropriate time slices and feature thresholds according to the network model. Thus, derivative features are obtained based on the time slices and feature thresholds.

[0043] In an alternative embodiment of the embodiments of the present invention, determining corresponding derivative features according to the root features in the risk feature catalog and the application scenario information of the risk features includes: determining corresponding derivative features according to the loan stage information, application business line information, application channel information in the application scenario information, and the root features in the risk feature catalog.

[0044] Among them, the loan stage information includes: pre-loan information, in-loan information, and post-loan information. The application business line information may be information of different financial business products. For example, the application business line information may be inclusive loan information, or housing mortgage loan, etc. The application channel information may include, but is not limited to, online loans, and offline loans, etc.

[0045] Appropriate time slices and feature thresholds can be recommended through a network model according to the loan stage information, application business line information, and application channel information in the business. Derivative processing is performed on the root features of the risk features according to the time slices and feature thresholds to obtain derivative features.

[0046] Exemplarily, the application scenario information of the business can be divided into pre-loan, in-loan, and post-loan scenarios, and at the same time, the risk feature application products or business lines can be further subdivided. For example, for the inclusive customer business loan application scenario: inclusive customer business loan application. The network model can locate the root features applicable to the inclusive online loan product, and at the same time, according to the application scenario information being pre-loan, intelligent recommendation of derivative features can be performed. According to the derivative method of previous pre-loan + inclusive + online loan products, intelligent recommendation is automatically performed. For example, if the selected root feature is "historical number of overdue times", then according to the derivative method of previous inclusive online loan pre-loan applications or other similar loan products in the pre-loan scenario, "historical number of overdue times in the past six months" can be automatically recommended. For a single risk feature, information such as feature name, business logic, and technical processing logic is provided. Derivative features can be defined by dragging and dropping. For example, if it is necessary to count the "number of overdue and bad times", then two root features "number of overdue times" and "number of bad times" can be selected and added to generate a derivative risk feature.

[0047] By combining application scenario information for automatic derivative feature recommendation, the accuracy of risk feature screening can be improved, the consumption of labor costs can be reduced, and the comprehensiveness and reliability of the assessment can be ensured when conducting risk assessment of risk operations.

[0048] Step 130: Push the root feature and corresponding derivative features to the risk view and / or risk model.

[0049] Risk features are factors for constructing risk models and risk views. A risk model can be an early warning and monitoring model for risk assessment in risk operations. For example, a risk model can be an early warning and monitoring model constructed to predict the likelihood of overdue payments for personal housing mortgages in the past 6 months. A risk view can be a view formed by applying risk features for risk operation prediction. For example, a risk view can be generated by selecting corresponding risk features and performing operations such as dragging and dropping. The risk view supports configuring statistical tables, bar charts, pie charts, line charts, and customizing the view color scheme.

[0050] Specifically, the root feature and corresponding derivative features of risk features can be connected to a preset visualization generation platform to generate a risk view, enabling diverse applications of risk features and improving the display effect. The root feature and corresponding derivative features of risk features can be connected to a modeling platform to generate a risk model, enabling the rapid launch of the risk model and enabling various types of applications of risk features.

[0051] Step 140: Obtain the call information of each risk feature in the risk view and / or risk model, and generate the operation result of the risk feature.

[0052] The call information includes, but is not limited to: the name of the called feature, the calling institution, and the feature usage method (risk model and / or risk view). The operation result of the risk feature can be the statistical result of the call information. For example, the call situation of features can be analyzed according to feature classification and calling institution. When generating the operation result of the risk feature, the stability of application data from each source can also be analyzed. When generating the operation result of the risk feature, the coverage of risk features can also be analyzed. For example, the number of risk features under each classification. By generating the operation result of the risk feature, a unified view of risk feature usage can be formed, saving the labor cost of manual summarization and improving the efficiency of statistical analysis of call situations and data stability according to feature classification, data source, and institution.

[0053] In an alternative embodiment of the present invention, obtaining the call information of each risk feature in the risk view and / or risk model and generating the operation result of the risk feature includes: obtaining the tick information of the root feature and derivative features of each risk feature in the risk view and / or risk model, and the re-derivation information of the derivative features; generating the operation result of the risk feature according to the tick information, re-derivation information, and corresponding call information of each risk feature.

[0054] Among them, the root features and derivative features can be synchronized to the modeling platform and the preset visualization generation platform. When applying features, users can check the root features and derivative features. If users find that the existing derivative features cannot meet their needs, they can directly derive again based on the root features. By re-deriving features, the flexibility of risk feature application can be improved.

[0055] Exemplarily, the large language model technology can be used. Input “Build a warning monitoring model for predicting the likelihood of overdue payments on personal housing mortgages in the past 6 months” into the model, then the large language model can automatically recommend model factors and determine whether there are relevant features in the same institution and the same business line. If there is no such model, intelligent recommendations are made according to the warning monitoring model, such as “Overdue and non-performing amount in the past 12 months is greater than 5000”, to achieve the regeneration of derivative information and quickly put the risk model online. Furthermore, according to the checked information of each risk feature, the re-derived information, and the corresponding call information, statistics on the usage information of risk features can be carried out to generate the operation results of risk features.

[0056] The technical solution of this embodiment classifies risk features according to the business line, business classification, and data source in risk operations to obtain a risk feature catalog from the business perspective; determines corresponding derivative features according to the root features in the risk feature catalog and the application scenario information of risk features; pushes the root features and the corresponding derivative features to the risk view and / or risk model; obtains the call information of each risk feature in the risk view and / or risk model, and generates risk feature operation results, solving the problem that risk features are scattered in various business systems and need to be repeatedly developed during management. By generating a risk feature catalog from the business perspective and performing online risk feature management, the rapid positioning of risk features can be achieved. By connecting the risk feature metadata to the metadata management system, it is convenient to master the usage of risk features, avoiding repeated development of risk features and manual statistics.

[0057] Figure 2 It is a flowchart of another risk feature management method in risk operations according to an embodiment of the present invention. This embodiment further refines the above technical solution, and the technical solution in this embodiment can be combined with each optional solution in one or more of the above embodiments. As Figure 2 shown, the method includes:

[0058] Step 210: Classify risk features according to at least one piece of information among policy, industry, region, product, user, and debt item to obtain a risk feature catalog from the business perspective.

[0059] Step 220: Determine corresponding derivative features according to the loan stage information, application business line information, application channel information in the application scenario information, and the root features in the risk feature catalog.

[0060] Among them, the loan stage information includes: pre-loan information, in-loan information, and post-loan information.

[0061] Step 230: Push the root feature and the corresponding derivative features to the risk view and / or the risk model.

[0062] Step 240: Obtain the tick information of the root feature and the derivative features of each risk feature in the risk view and / or the risk model, as well as the re-derivation information of the derivative features.

[0063] Step 250: Generate the operation result of the risk feature according to the tick information, the re-derivation information, and the corresponding call information of each risk feature.

[0064] When generating the operation result of the risk feature, the operation result of the risk feature corresponding to the corresponding range can be generated according to different monitoring ranges. In an optional implementation manner of the embodiment of the present invention, obtaining the call information of each risk feature in the risk view and / or the risk model and generating the operation result of the risk feature includes: obtaining the call information of each risk feature in the risk view and / or the risk model and generating the operation results of the risk feature corresponding to the first monitoring range and the second monitoring range respectively; the first monitoring range is larger than the second monitoring range; wherein, the operation result of the risk feature corresponding to the first monitoring range includes at least one of the following: the call situation of the risk feature within the entire range, the hit situation of the risk feature, and the source data quality of the risk feature; the operation result of the risk feature corresponding to the second monitoring range includes at least one of the following: the call name of the risk feature within the second monitoring range, the usage scenario, the monitored product, and the hit rate of the risk feature.

[0065] Among them, the first monitoring range may be the overall department of the financial institution. The second monitoring range may be the branch department of the financial institution. By generating the operation results of the risk feature under the first monitoring range and the second monitoring range respectively, the call situation of the risk feature and the data quality situation can be summarized.

[0066] In the embodiment of the present invention, the source data quality of the risk feature includes: data interruption situation, delay situation, and abnormal fluctuation situation. Optionally, on the basis of the above implementation manner, the method further includes: performing abnormal monitoring on the source data quality of the risk feature and giving an abnormal alarm when an abnormality is monitored. When the source data has an abnormal data fluctuation resulting in an abnormal fluctuation of the feature value, a reminder can be given in a timely manner, and the source data can be urged to rectify the data quality in a timely manner, saving additional statistical and monitoring time.

[0067] The technical solution of the embodiment of the present invention generates risk characteristic operation results respectively under the first monitoring range and the second monitoring range. On the one hand, at the overall department management level, it can understand the construction and usage of risk characteristics of each business line, so as to master the coverage of all risk characteristic assets, effectively avoid duplicate construction of each business line, accurately locate the missing sectors, realize the optimal allocation of resources, and improve efficiency. On the other hand, each branch department can also master the risk characteristics that can be called under its authority, support the branch department to use them out of the box, quickly deploy risk models or risk views, improve the risk management level of the branch department, and create more value.

[0068] Figure 3 It is an application example diagram of a risk characteristic management method in a risk business provided by an embodiment of the present invention. As Figure 3 shown, by clarifying the risk characteristic classification, generating a risk characteristic catalog; selecting the root characteristics of the risk characteristics, flexibly setting time slices and thresholds to generate derivative characteristics; connecting the root characteristics and derivative characteristics of the risk characteristics to the risk model and / or risk view; statistically analyzing the usage of the risk characteristics to generate risk characteristic operation results, a low-code risk characteristic usage solution can be realized, including the whole process such as risk characteristic positioning and screening, risk characteristic invocation, and risk characteristic operation, solving the problem that the original risk characteristics are scattered in each business system for processing, cannot be quickly reused and launched, avoiding the problem of duplicate development of risk characteristics between business systems, and the problem that the risk characteristic invocation situation and data quality situation need to be summarized separately, enabling the overall department to master the asset coverage of all risk characteristics, and the branch department can use the risk characteristics out of the box, master the risk characteristic invocation situation within its authority, quickly deploy risk models or risk views, and improve the risk characteristic management level.

[0069] Figure 4 It is a structural schematic diagram of a risk characteristic management device in a risk business provided by an embodiment of the present invention. As Figure 4 shown, the device includes: a risk characteristic catalog generation module 410, a derivative characteristic determination module 420, a characteristic push module 430, and a risk characteristic operation result generation module 440. Among them:

[0070] The risk characteristic catalog generation module 410 is used to classify the risk characteristics according to the business lines, business classifications, and data sources in the risk business to obtain a risk characteristic catalog from the business perspective;

[0071] The derivative characteristic determination module 420 is used to determine the corresponding derivative characteristics according to the root characteristics in the risk characteristic catalog and the application scenario information of the risk characteristics;

[0072] The characteristic push module 430 is used to push the root characteristics and the corresponding derivative characteristics to the risk view and / or the risk model;

[0073] The risk characteristic operation result generation module 440 is configured to obtain the call information of each risk characteristic in the risk view and / or risk model, and generate a risk characteristic operation result.

[0074] Optionally, the risk characteristic catalog generation module 410 includes:

[0075] The risk characteristic catalog generation unit is configured to classify the risk characteristics according to at least one piece of information among policies, industries, regions, products, users, and debt items, and obtain a risk characteristic catalog from the business perspective.

[0076] Optionally, the derivative feature determination module 420 includes:

[0077] The derivative feature determination unit is configured to determine corresponding derivative features according to the loan stage information, application business line information, application channel information in the application scenario information, and the root features in the risk characteristic catalog;

[0078] Wherein, the loan stage information includes: pre-loan information, in-loan information, and post-loan information.

[0079] Optionally, the risk characteristic operation result generation module 440 includes:

[0080] The feature acquisition unit is configured to obtain the tick information of the root features and derivative features of each risk characteristic in the risk view and / or risk model, and the re-derivative information of the derivative features;

[0081] The risk characteristic operation result generation unit is configured to generate a risk characteristic operation result according to the tick information, re-derivative information, and corresponding call information of each risk characteristic.

[0082] Optionally, the risk characteristic operation result generation module 440 includes:

[0083] The risk characteristic operation result generation unit within the monitoring range is configured to obtain the call information of each risk characteristic in the risk view and / or risk model, and generate risk characteristic operation results corresponding to the first monitoring range and the second monitoring range respectively; the first monitoring range is greater than the second monitoring range;

[0084] Wherein, the risk characteristic operation result corresponding to the first monitoring range includes at least one of the following: the call situation of risk characteristics within the entire range, the hit situation of risk characteristics, and the quality of risk characteristic source data;

[0085] The risk characteristic operation result corresponding to the second monitoring range includes at least one of the following: the call name, usage scenario, monitored product, and risk characteristic hit rate of risk characteristics within the second monitoring range.

[0086] Optionally, the risk characteristic source data quality includes: data interruption situation, latency situation, and abnormal fluctuation situation;

[0087] The device further includes:

[0088] An abnormal alarm module, configured to perform abnormal monitoring on the risk characteristic source data quality and give an abnormal alarm when an abnormality is monitored.

[0089] The risk characteristic management device in the risk service provided by the embodiments of the present invention can execute the risk characteristic management method in the risk service provided by any embodiment of the present invention, and has corresponding functional modules and beneficial effects for executing the method.

[0090] In the technical solution of the embodiments of the present invention, the collection, storage, use, processing, transmission, provision, and disclosure of information related to risk services and risk characteristics all comply with the provisions of relevant laws and regulations and do not violate public order and good customs.

[0091] The information collected is information and data authorized by the user or fully authorized by all parties, and the processing of relevant data such as collection, storage, use, processing, transmission, provision, disclosure, and application all comply with the relevant laws, regulations, and standards of relevant countries and regions, take necessary confidentiality measures, do not violate public order and good customs, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0092] When performing data analysis based on information related to risk services and risk characteristics and making an automated decision, a corresponding operation entrance is provided for the user to choose to agree or refuse the automated decision result; if the user chooses to refuse, the expert decision-making process is entered.

[0093] Figure 5 FIG. shows a schematic structural diagram of an electronic device 10 that can be used to implement the embodiments of the present invention. The electronic device is intended to represent various forms of digital computers, such as, for example, a laptop computer, a desktop computer, a workbench, a personal digital assistant, a server, a blade server, a mainframe computer, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as, for example, a personal digital processor, a cellular phone, a smart phone, a wearable device (such as a helmet, glasses, a watch, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present invention described and / or claimed herein.

[0094] As Figure 5As shown, the electronic device 10 includes at least one processor 11 and a memory communicatively connected to the at least one processor 11, such as read-only memory (ROM) 12, random access memory (RAM) 13, etc. The memory stores a computer program executable by the at least one processor. The processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 into the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, ROM 12, and RAM 13 are connected to each other via a bus 14. The input / output (I / O) interface 15 is also connected to the bus 14.

[0095] Multiple components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a magnetic disk, an optical disc, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0096] The processor 11 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the risk feature management method in the risk business.

[0097] In some embodiments, the risk feature management method in the risk business can be implemented as a computer program tangibly embodied in a computer-readable storage medium, such as the storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed onto the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the risk feature management method in the risk business described above can be executed. Alternatively, in other embodiments, the processor 11 can be configured to execute the risk feature management method in the risk business by any other suitable means (e.g., by means of firmware).

[0098] The various embodiments of the systems and techniques described above in this specification can be implemented in digital electronic circuitry, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on a chip (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include: being implemented in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be a special-purpose or general-purpose programmable processor that receives data and instructions from, and transmits data and instructions to, a storage system, at least one input device, and at least one output device.

[0099] The computer programs for implementing the methods of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions / operations specified in the flowchart and / or block diagram to be implemented. The computer programs can be executed entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.

[0100] In the context of the present invention, a computer-readable storage medium can be a tangible medium that can contain or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer-readable storage medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, the computer-readable storage medium can be a machine-readable signal medium. More specific examples of the machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0101] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and a pointing device (e.g., a mouse or a trackball) through which the user can provide input to the electronic device. Other kinds of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0102] The systems and techniques described herein can be implemented in a computing system including backend components (e.g., as a data server), or a computing system including middleware components (e.g., an application server), or a computing system including frontend components (e.g., a user computer having a graphical user interface or a web browser through which the user can interact with an implementation of the systems and techniques described herein), or a computing system including any combination of such backend components, middleware components, or frontend components. The components of the system can be interconnected to each other by digital data communication in any form or medium (e.g., a communication network). Examples of communication networks include: local area network (LAN), wide area network (WAN), blockchain network, and the Internet.

[0103] The computing system can include a client and a server. The client and the server are generally far from each other and usually interact through a communication network. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or a cloud host, which is a host product in the cloud computing service system and solves the defects of difficult management and weak business scalability existing in traditional physical hosts and VPS services.

[0104] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps recited in the present invention can be executed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of the present invention can be achieved, and no limitation is imposed herein.

[0105] The above specific embodiments do not constitute a limitation on the protection scope of the present invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A method for managing risk characteristics in risk business, characterized in that: include: Classify risk characteristics according to business lines, business classifications, and data sources in risk businesses to obtain a risk characteristic catalog from a business perspective; Determine the corresponding derived features based on the root features in the risk feature catalog and the application scenario information of the risk features; Pushing the root feature and the corresponding derived features into the risk view and / or risk model; Obtain the call information of each risk feature in the risk view and / or risk model, and generate risk feature operation results.

2. The method according to claim 1, characterized in that According to the business lines, business classifications and data sources in the risk business, the risk characteristics are classified to obtain a risk characteristic catalog from the business perspective, including: According to at least one of the information of policy, industry, region, product, user, and debt, the risk characteristics are classified to obtain a risk characteristic catalog from a business perspective.

3. The method according to claim 1, characterized in that According to the root features in the risk feature catalog and the application scenario information of the risk features, the corresponding derived features are determined, including: Determine the corresponding derivative features based on the loan stage information, application business line information, application channel information in the application scenario information, and the root features in the risk feature catalog; The loan stage information includes: pre-loan information, mid-loan information, and post-loan information.

4. The method according to claim 1, characterized in that: Obtain the call information of each risk feature in the risk view and / or risk model, and generate risk feature operation results, including: Obtain the check information of the root features and derived features of each risk feature in the risk view and / or risk model, as well as the re-derivation information of the derived features; Generate risk feature operation results based on the check information, re-derivation information, and corresponding call information of each risk feature.

5. The method according to claim 1, characterized in that Obtain the call information of each risk feature in the risk view and / or risk model, and generate risk feature operation results, including: Acquire call information of each risk feature in the risk view and / or risk model, and generate risk feature operation results corresponding to a first monitoring scope and a second monitoring scope respectively; the first monitoring scope is larger than the second monitoring scope; The risk feature operation results corresponding to the first monitoring scope include at least one of the following: the risk feature call status, risk feature hit status, and risk feature source data quality within the entire scope; The risk feature operation results corresponding to the second monitoring scope include at least one of the following: the risk feature call name, usage scenario, monitoring product and risk feature hit rate within the second monitoring scope.

6. The method according to claim 5, characterized in that The risk characteristic source data quality includes: data interruption, delay and abnormal fluctuation; The method further comprises: The risk feature source data quality is monitored for abnormalities, and an abnormality alarm is issued when an abnormality is monitored.

7. A risk characteristic management device in risk business, characterized in that: include: The risk feature catalog generation module is used to classify risk features according to the business lines, business classifications and data sources in the risk business to obtain a risk feature catalog from a business perspective; A derived feature determination module is used to determine corresponding derived features based on the root features in the risk feature catalog and the application scenario information of the risk features; A feature pushing module, used to push the root feature and the corresponding derived features to the risk view and / or risk model; The risk feature operation result generation module is used to obtain the call information of each risk feature in the risk view and / or risk model and generate the risk feature operation result.

8. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the risk feature management method in the risk business according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the risk characteristic management method in a risk business according to any one of claims 1 to 6 when executed.

10. A computer program product, comprising a computer program, which, when executed by a processor, implements the risk feature management method in a risk business according to any one of claims 1 to 6.

Images