Engine configuration method and apparatus, risk assessment method and apparatus, device and storage medium

Abstract

An engine configuration method, which can be applied to the technical field of big data. The engine configuration method comprises: constructing a risk model in a risk assessment engine on the basis of service information related to risk assessment and a rule engine integrated with different decision-making tools; on the basis of a service logic in the service information, integrating a plurality of indicator items defined in the risk model with calculation rules in the decision-making tools for the indicator items, to generate a decision-making flow corresponding to the risk model, wherein the decision-making flow comprises a plurality of decision-making nodes, and each decision-making node corresponds to an assessment strategy determined on the basis of the indicator items and the calculation rules; and configuring the decision-making flow into the risk assessment engine, so as to perform risk assessment using the configured risk assessment engine. Also provided are a risk assessment method, an engine configuration apparatus, a device, a storage medium and a program product.

Description

Engine configuration methods, risk assessment methods, devices, equipment and storage media

[0001] This application claims priority to Chinese patent application No. 202411942960.X, filed on December 26, 2024, the entire contents of which are incorporated herein by reference. Technical Field

[0002] This disclosure relates to the field of big data, and more specifically, to an engine configuration method, a risk assessment method, an apparatus, an equipment, and a storage medium. Background Technology

[0003] During customs clearance and inspection, risk management measures are required. In related technologies, basic information about the object of assessment is entered into a risk assessment system during customs inspection. The system's assessment rules are then used to evaluate the object, thereby completing the inspection.

[0004] In the process of realizing the present invention, the inventors discovered that the related technology has at least the following problems: due to the relatively simple assessment rules in the risk assessment system, the accuracy of the risk assessment results output by the risk assessment system is low when facing different business scenarios. Summary of the Invention

[0005] This disclosure provides an engine configuration method, a risk assessment method, an apparatus, an equipment, a storage medium, and a program product.

[0006] One aspect of this disclosure provides an engine configuration method, comprising: constructing a risk model in a risk assessment engine based on business information related to risk assessment and a rule engine integrated with different decision-making tools; integrating multiple indicator items defined in the risk model and calculation rules for each indicator item in the decision-making tools according to the business logic in the aforementioned business information to generate a decision flow corresponding to the risk model, wherein the decision flow includes multiple decision nodes, and each decision node corresponds to an assessment strategy determined according to the aforementioned indicator items and calculation rules; configuring the decision flow into the risk assessment engine to perform risk assessment using the configured risk assessment engine.

[0007] According to embodiments of this disclosure, the above-mentioned integration of multiple indicator items defined in the risk model and the calculation rules for each indicator item in the decision-making tool, based on the business logic in the above-mentioned business information, to generate a decision flow corresponding to the risk model, includes: defining multiple process nodes, wherein the multiple process nodes include a start node, the above-mentioned decision node, and an end node; integrating the above-mentioned indicator items with the multiple above-mentioned calculation rules respectively to obtain multiple evaluation strategies; and configuring the multiple above-mentioned evaluation strategies into the corresponding decision nodes according to the above-mentioned business logic to orchestrate the multiple above-mentioned process nodes and generate the above-mentioned decision flow.

[0008] According to embodiments of this disclosure, the above-mentioned indicator items are integrated with multiple calculation rules to obtain multiple evaluation strategies, including: determining the indicator threshold corresponding to each of the above-mentioned indicator items; and integrating the multiple indicator thresholds according to the calculation logic in each of the above-mentioned calculation rules and the correlation between the multiple of the above-mentioned indicator items to obtain multiple of the above-mentioned evaluation strategies.

[0009] According to an embodiment of this disclosure, the above-mentioned arrangement of multiple process nodes to generate the above-mentioned decision flow includes: based on the above-mentioned business logic, arranging decision nodes corresponding to different calculation rules to obtain multiple decision branches, wherein the multiple decision branches can be calculated in parallel when performing risk assessment; and connecting the multiple decision branches to the above-mentioned start node and corresponding end node respectively to obtain the above-mentioned decision flow.

[0010] According to embodiments of this disclosure, the method further includes: determining the data source for each of the above-mentioned indicator items in the above-mentioned business information, wherein the data source is connection information between the application system and the application system, and the application system is used to provide the above-mentioned business information; configuring the above-mentioned data source in the above-mentioned risk assessment engine to acquire the data sent by the application system based on the above-mentioned data source information.

[0011] According to embodiments of this disclosure, the method further includes: configuring multiple data processing indicators in the risk assessment engine, wherein the data processing indicators are used to obtain business data required for risk assessment, the business data including database information and service interface information and service framework information used for risk assessment; configuring multiple data calculation indicators in the risk assessment engine according to the calculation logic in the calculation rules, wherein the data calculation indicators are used to operate on the results calculated by the assessment strategy during risk assessment.

[0012] Another aspect of this disclosure provides a risk assessment method, comprising: in response to a received risk assessment request, inputting the data to be assessed in the risk assessment request into a configured risk assessment engine; using the decision flow in the risk assessment engine corresponding to the risk model to perform a risk assessment on the data to be assessed, and outputting a risk assessment result.

[0013] According to embodiments of this disclosure, the above-mentioned risk assessment of the data to be assessed using the decision flow corresponding to the risk model in the risk assessment engine and outputting the risk assessment result includes: determining multiple assessment indicators in the data to be assessed; obtaining corresponding indicator data from business information related to risk assessment based on the multiple assessment indicators; and using the assessment strategy in the decision flow to conduct risk assessment on the indicator data to obtain the risk assessment result.

[0014] Another aspect of this disclosure provides an engine configuration apparatus, comprising: a model building module for constructing a risk model in a risk assessment engine based on business information related to risk assessment and a rule engine integrating different decision-making tools; a decision flow generation module for integrating multiple indicator items defined in the risk model and calculation rules for each indicator item in the decision-making tools according to business logic in the aforementioned business information, to generate a decision flow corresponding to the risk model, wherein the decision flow includes multiple decision nodes, and each decision node corresponds to an assessment strategy determined according to the aforementioned indicator items and calculation rules; and an engine configuration module for configuring the decision flow into the risk assessment engine to perform risk assessment using the configured risk assessment engine.

[0015] Another aspect of this disclosure provides a risk assessment apparatus, comprising: a request output module, configured to, in response to a received risk assessment request, input the data to be assessed in the risk assessment request into a configured risk assessment engine; and a risk assessment module, configured to, using a decision flow in the risk assessment engine corresponding to a risk model, perform a risk assessment on the data to be assessed and output a risk assessment result.

[0016] Another aspect of this disclosure provides an electronic device comprising: one or more processors; and a memory for storing one or more programs, wherein, when the one or more programs are executed by the one or more processors, the one or more processors cause the one or more processors to perform the method as described above.

[0017] Another aspect of this disclosure provides a computer-readable storage medium storing computer-executable instructions, which, when executed, are used to implement the method described above.

[0018] Another aspect of this disclosure provides a computer program product including computer-executable instructions that, when executed, implement the method described above. Attached Figure Description

[0019] The above and other objects, features and advantages of this disclosure will become clearer from the following description of embodiments with reference to the accompanying drawings, in which:

[0020] Figure 1 schematically illustrates an application scenario of the engine configuration method, risk assessment method, apparatus, device, medium, and program product according to embodiments of the present disclosure;

[0021] Figure 2 schematically illustrates a flowchart of an engine configuration method according to an embodiment of the present disclosure;

[0022] Figure 3 schematically illustrates a risk assessment engine according to an embodiment of the present disclosure;

[0023] Figure 4 schematically illustrates a block diagram of the indicator system of a risk assessment engine according to an embodiment of the present disclosure;

[0024] Figure 5 schematically illustrates a flowchart of an engine configuration method according to another embodiment of the present disclosure;

[0025] Figure 6 schematically illustrates a message service for risk assessment according to an embodiment of the present disclosure;

[0026] Figure 7 schematically illustrates a flowchart of a risk assessment method according to an embodiment of the present disclosure;

[0027] Figure 8 schematically illustrates an assessment flowchart to which the risk assessment method according to embodiments of the present disclosure can be applied;

[0028] Figure 9 schematically illustrates a structural block diagram of an engine configuration device according to an embodiment of the present disclosure;

[0029] Figure 10 schematically illustrates a structural block diagram of a risk assessment apparatus according to an embodiment of the present disclosure; and

[0030] Figure 11 schematically illustrates a block diagram of an electronic device suitable for implementing an engine configuration method and a risk assessment method according to embodiments of the present disclosure. Detailed Implementation

[0031] The embodiments of the present disclosure will now be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the disclosure. In the following detailed description, numerous specific details are set forth to provide a thorough understanding of the embodiments of the present disclosure for ease of explanation. However, it will be apparent that one or more embodiments may be practiced without these specific details. Furthermore, descriptions of well-known structures and techniques are omitted in the following description to avoid unnecessarily obscuring the concepts of the present disclosure.

[0032] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit this disclosure. The terms “comprising,” “including,” etc., as used herein indicate the presence of the stated features, steps, operations, and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, or components.

[0033] All terms used herein (including technical and scientific terms) have the meanings commonly understood by those skilled in the art, unless otherwise defined. It should be noted that the terms used herein are to be interpreted in a manner consistent with the context of this specification, and not in an idealized or overly rigid way.

[0034] When using expressions such as "at least one of A, B, and C", they should generally be interpreted in accordance with the meaning that is commonly understood by a person skilled in the art (e.g., "a system having at least one of A, B, and C" should include, but is not limited to, a system having A alone, a system having B alone, a system having C alone, a system having A and B, a system having A and C, a system having B and C, and / or a system having A, B, and C, etc.).

[0035] In the embodiments disclosed herein, the collection, updating, analysis, processing, use, transmission, provision, disclosure, and storage of data (e.g., including but not limited to user personal information) comply with relevant laws and regulations, are used for legitimate purposes, and do not violate public order and good morals. In particular, necessary measures have been taken to prevent unauthorized access to user personal information data and to safeguard user personal information security and network security.

[0036] In the embodiments disclosed herein, user authorization or consent is obtained before acquiring or collecting user personal information.

[0037] Embodiments of this disclosure provide an engine configuration method, a risk assessment method, an apparatus, a device, a storage medium, and a program product. The engine configuration method includes: constructing a risk model in a risk assessment engine based on business information related to risk assessment and a rule engine integrating different decision-making tools; integrating multiple indicator items defined in the risk model and the calculation rules for each indicator item in the decision-making tools according to the business logic in the business information to generate a decision flow corresponding to the risk model, wherein the decision flow includes multiple decision nodes, and each decision node corresponds to an assessment strategy determined according to the indicator items and calculation rules; configuring the decision flow into the risk assessment engine to perform risk assessment using the configured risk assessment engine.

[0038] Figure 1 schematically illustrates an application scenario of the engine configuration method, risk assessment method, apparatus, device, medium, and program product according to embodiments of the present disclosure. It should be noted that Figure 1 is merely an example of a system architecture to which embodiments of the present disclosure can be applied, to help those skilled in the art understand the technical content of the present disclosure, but does not imply that embodiments of the present disclosure cannot be used in other devices, systems, environments, or scenarios.

[0039] As shown in Figure 1, the system architecture 100 according to this embodiment may include a first terminal device 101, a second terminal device 102, a third terminal device 103, a network 104, and a server 105. The network 104 serves as a medium for providing communication links between the first terminal device 101, the second terminal device 102, the third terminal device 103, and the server 105. The network 104 may include various connection types, such as wired and / or wireless communication links, etc.

[0040] Users can use the first terminal device 101, the second terminal device 102, and the third terminal device 103 to interact with the server 105 via the network 104 to receive or send messages, etc. Various communication client applications can be installed on the first terminal device 101, the second terminal device 102, and the third terminal device 103, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, and / or social media platform software, etc. (for example only).

[0041] The first terminal device 101, the second terminal device 102, and the third terminal device 103 can be various electronic devices with displays and support web browsing, including but not limited to smartphones, tablets, laptops, and desktop computers.

[0042] Server 105 can be a server that provides various services, such as a backend management server that supports websites browsed by users using the first terminal device 101, the second terminal device 102, and the third terminal device 103 (this is just an example). The backend management server can analyze and process data such as received user requests, and feed back the processing results (such as web pages, information, or data obtained or generated according to user requests) to the terminal devices.

[0043] It should be noted that the engine configuration method and risk assessment method provided in this disclosure embodiment can generally be executed by server 105. Correspondingly, the engine configuration device and risk assessment device provided in this disclosure embodiment can generally be located in server 105. The engine configuration method and risk assessment method provided in this disclosure embodiment can also be executed by a server or server cluster that is different from server 105 and capable of communicating with the first terminal device 101, the second terminal device 102, the third terminal device 103, and / or server 105. Correspondingly, the engine configuration device and risk assessment device provided in this disclosure embodiment can also be located in a server or server cluster that is different from server 105 and capable of communicating with the first terminal device 101, the second terminal device 102, the third terminal device 103, and / or server 105. Alternatively, the engine configuration method and risk assessment method provided in this disclosure embodiment can also be executed by the first terminal device 101, the second terminal device 102, or the third terminal device 103, or by other terminal devices different from the first terminal device 101, the second terminal device 102, or the third terminal device 103. Accordingly, the engine configuration device and risk assessment device provided in the embodiments of this disclosure may also be disposed in the first terminal device 101, the second terminal device 102 or the third terminal device 103, or disposed in other terminal devices different from the first terminal device 101, the second terminal device 102 or the third terminal device 103.

[0044] It should be understood that the number of terminal devices, networks, and servers shown in Figure 1 is merely illustrative. Any number of terminal devices, networks, and servers can be used depending on implementation needs.

[0045] Figure 2 schematically illustrates a flowchart of an engine configuration method according to an embodiment of the present disclosure.

[0046] As shown in Figure 2, the method includes operations S201 to S230.

[0047] In operation S210, risk models are constructed in the risk assessment engine based on business information related to risk assessment and a rules engine that integrates different decision-making tools.

[0048] In operation S220, based on the business logic in the business information, multiple indicators defined in the risk model and the calculation rules for each indicator in the decision-making tool are integrated to generate a decision flow corresponding to the risk model. The decision flow includes multiple decision nodes, and each decision node corresponds to an evaluation strategy determined based on the indicator and calculation rules.

[0049] In operation S230, the decision flow is configured into the risk assessment engine to perform risk assessment using the configured risk assessment engine.

[0050] According to embodiments of this disclosure, customs needs to take risk management measures during customs clearance inspections. Specifically, the customs clearance risk application submits basic information about vehicles or personnel to a risk assessment engine for risk assessment, and then feeds back the risk assessment results to the customs clearance risk application. Here, the customs clearance risk application refers to any application system in customs clearance operations that requires risk assessment.

[0051] According to embodiments of this disclosure, the customs clearance risk application will evolve and change according to actual needs. Customs clearance risk applications include types such as general clearance risk applications, vehicle clearance risk applications, and cargo clearance risk applications. The system provides a risk assessment engine client to facilitate communication between the customs clearance risk application and the risk assessment engine. The customs clearance risk application can also directly send risk assessment requests to the risk assessment system through a message queue service and listen for risk assessment results.

[0052] According to embodiments of this disclosure, the risk assessment engine requires a large amount of business information from other customs systems when conducting risk assessments. Due to the differences in systems and data provision methods, many different communication protocols are involved, such as database protocols and RESTful (Representational State Transfer) interface protocols. To facilitate the acquisition of business information from different systems through different protocols, the risk assessment engine employs an indicator system. This indicator system supports the acquisition of assessment indicators from numerous different protocols and allows for plug-in extension of new protocols, facilitating easy capability expansion.

[0053] According to embodiments of this disclosure, business information may include the following types of information: real-time information, information generated by the relevant business, such as customs declaration information for goods undergoing customs inspection; historical information, historical information of the relevant business, such as records of drivers or customs brokers failing to comply with regulations, and passenger travel records; and related information, other auxiliary information of the relevant business, such as special lists recently reviewed by customs. It should be noted that the personal information used in this technical solution is limited to information for which separate consent has been obtained.

[0054] According to embodiments of this disclosure, business information may specifically include data from various different businesses. Common business information related to customs clearance risks includes: Enterprise information, including basic enterprise information such as registration, operation, management, and certification information; Customs supervision information, including historical statistics of relevant enterprise supervision information, especially alarms and processing information generated by supervision; Non-compliance information, including historical records of non-compliance by relevant enterprises, vehicles, drivers, passengers, etc.; Tax information, including historical tax records of relevant enterprises or tax payment information of goods, such as tax arrears and tax payment scale; Logistics information, including information on logistics companies, vehicles, drivers, and transportation-related information; Cargo information, including cargo declaration information, cargo origin information, and cargo price information; Transaction information, including basic information of buyers and sellers, their relationship, transaction amount, and transaction characteristics; Environmental information, including policy information, market change information, and information on key inspection keywords or goods.

[0055] Figure 3 schematically illustrates a risk assessment engine according to an embodiment of the present disclosure.

[0056] According to embodiments of this disclosure, the risk assessment engine consists of three parts: a real-time risk calculation engine 310, a risk engine management system 320, and a risk assessment configuration management system 330. The real-time risk calculation engine 310 is the core component of the risk assessment engine, responsible for executing actual risk calculation tasks. The risk engine management system 320 is responsible for monitoring and managing the real-time risk calculation engine. The risk assessment configuration management system 330 configures and builds the risk model through a visual configuration system. After configuring the risk model, the risk assessment configuration management system 330 sends the risk model to the risk engine management system 320 for model publication through an operation decision flow publication action. The risk engine management system 320 parses the risk model, allocates computing resource instances according to resource configuration, publishes the decision flow to the real-time risk calculation engine 310, and returns the publication result to the risk assessment configuration management system 330 after the publication action is completed. During daily operation, the real-time risk calculation engine 310 sends its running status to the risk engine management system 320, facilitating the risk engine management system 320's monitoring and management of all risk calculation resources.

[0057] According to embodiments of this disclosure, during the construction of the risk model, the objectives and requirements of the risk model are determined based on business information, mainly including the data types to be processed, the business scenarios for risk assessment, and the complexity of the decision-making process. After determining the objectives and requirements, the risk model is designed to construct a risk model that meets the objectives and requirements and integrates different decision-making tools.

[0058] According to embodiments of this disclosure, multiple indicator items defined in the risk model and calculation rules for each indicator item in each decision tool are determined. The decision tools include tools such as decision tables, decision trees, scoring cards, complex rule sets, and scripts. An evaluation strategy is determined based on the multiple indicator items and calculation rules; each risk model has a specific evaluation strategy.

[0059] According to embodiments of this disclosure, multiple indicator items and their calculation rules are integrated based on business logic within the business information to generate a decision flow corresponding to the risk model. The decision flow is essentially a flowchart that integrates indicator items and evaluation strategies. Specifically, the decision flow can be configured visually and is used to control the calculation process of indicator items and evaluation strategies. The decision flow consists of nodes and connections. Nodes represent the evaluation strategies or control processes being executed, connections represent the execution order between nodes, and nodes also provide attribute configurations to define their execution characteristics.

[0060] According to embodiments of this disclosure, the configured decision flow is published to the risk assessment engine for risk assessment. The decision flow publication submits a request to the risk engine management via a message service, and simultaneously receives the publication results from the risk engine management via the message service, returning the publication results to the risk assessment configuration management. During risk assessment, assessment strategies and computational tasks related to indicator items are created according to the definition of the risk model, and the decision flow computation service coordinates the risk model assessment process.

[0061] According to embodiments of this disclosure, a risk model is constructed within a risk assessment engine based on business information related to risk assessment and a rule engine integrating different decision-making tools. This enables the selection of the appropriate risk model for risk assessment when facing different business scenarios. Based on the business logic within the business information, multiple indicator items defined in the risk model and the calculation rules for each indicator item in the decision-making tools are integrated to generate a decision flow corresponding to the risk model. Since the decision flow is generated based on business logic and includes assessment decisions corresponding to multiple calculation rules, configuring the decision flow into the risk assessment engine makes the target risk assessment engine more accurate and effectively improves the efficiency of risk verification.

[0062] According to embodiments of this disclosure, based on business logic in business information, multiple indicator items defined in the risk model and calculation rules for each indicator item in the decision-making tool are integrated to generate a decision flow corresponding to the risk model. This includes: defining multiple process nodes, wherein the multiple process nodes include a start node, a decision node, and an end node; integrating the indicator items with multiple calculation rules respectively to obtain multiple evaluation strategies; and configuring the multiple evaluation strategies into the corresponding decision nodes according to business logic to orchestrate the multiple process nodes and generate a decision flow.

[0063] According to embodiments of this disclosure, decision flows can be configured visually. The configuration of a decision flow mainly includes process nodes and connections between nodes. Nodes represent executed strategies or control execution flows, and connections represent the execution order of nodes. Process nodes mainly include the following types: Start node: A decision flow has one and only one start node, which is the entry point for decision flow calculation. Strategy node: A decision flow has multiple strategy nodes. Each strategy node can select an evaluation strategy to calculate the risk assessment result. The calculation result can be assigned to basic indicators and used as calculation parameters for other evaluation strategies. End node: There can be one or more end nodes. When the decision flow calculation reaches any end node, the decision flow calculation is complete, and after the result is fed back, the task ends.

[0064] According to embodiments of this disclosure, after defining multiple process nodes, indicator items are integrated with multiple calculation rules to obtain multiple evaluation strategies. Specifically, each evaluation strategy may include the calculation of multiple indicator items, and there are correlations between the multiple indicator items. Multiple evaluation strategies are configured into corresponding decision nodes according to business logic to orchestrate multiple process nodes and generate a decision flow. The business logic is the business logic applied to each customs clearance risk. By configuring evaluation strategies and integrating them with indicator items to generate a decision flow, the decision flow is made more consistent with business logic, enabling targeted risk assessment for different characteristics and resulting in more accurate risk assessment.

[0065] According to embodiments of this disclosure, multiple evaluation strategies are obtained by integrating indicator items with multiple calculation rules, including: determining the indicator threshold corresponding to each indicator item; and integrating multiple indicator thresholds according to the calculation logic in each calculation rule and the correlation between multiple indicator items to obtain multiple evaluation strategies.

[0066] According to embodiments of this disclosure, each indicator item has a corresponding indicator threshold. When comparing the indicator data corresponding to an indicator item with the indicator threshold, the indicator data is first converted into numerical form for comparison. Based on the calculation logic in each calculation rule and the correlation between multiple indicator items, multiple indicator thresholds are integrated to obtain a multi-evaluation strategy.

[0067] According to embodiments of this disclosure, the evaluation strategy calculates a comprehensive measurement value that represents specific meanings within a risk model, based on indicator items. Evaluation strategies are mature models and represent a primary methodology for risk assessment. Specifically, evaluation strategies mainly include the following: Decision tables, used to determine hit features using a decision table model and calculate a comprehensive quantitative measurement value; Decision trees, used to determine hit features using a decision tree model and calculate a comprehensive quantitative measurement value; Scorecards, used to calculate a comprehensive result of multiple quantitative measurement values ​​using a scorecard model; Complex rule sets, used to verify hit conditions using rule patterns, thereby calculating quantitative measurement values; Script strategies, used to establish customized strategy models using a custom scripting language and calculate measurement values; and Machine learning models, used to import trained machine learning models into the evaluation strategy and calculate strategy values ​​based on parameter indicators.

[0068] According to embodiments of this disclosure, the assessment strategy is configured through a visual configuration method that configures the structure, rules, and attributes. The assessment strategy is calculated based on the risk model configuration and input parameters to obtain corresponding measurement values. By configuring the assessment strategy, multiple risk assessment methods can be implemented, making the risk assessment results more accurate.

[0069] According to embodiments of this disclosure, multiple process nodes are orchestrated to generate a decision flow, including: orchestrating decision nodes corresponding to different calculation rules based on business logic to obtain multiple decision branches, wherein the multiple decision branches can be computed in parallel when performing risk assessment; and connecting the multiple decision branches to a start node and a corresponding end node to obtain a decision flow.

[0070] According to embodiments of this disclosure, the decision flow is the final presentation of the risk model, integrating relevant indicators and assessment strategies. By controlling the execution process and coordinating calculation rules, it calculates the final risk assessment result. The decision flow is the core module that responds to risk assessment requests and calculates the risk assessment results. A visualized decision flow flowchart is configured, and then the real-time risk calculation engine is responsible for calculating and executing the flowchart. The flowchart configuration mainly includes process nodes and connections between nodes. Nodes represent executed strategies or control execution processes, and connections represent the execution order of nodes. Process nodes mainly include start nodes, strategy nodes, and end nodes.

[0071] According to embodiments of this disclosure, the decision flow also includes control nodes for controlling the computation process, including branching and grouping, parallel branching, and convergence / merging. The decision flow supports multiple control methods to allow computation based on rules and requested parameters. These control methods utilize different strategies or sequences for computation, primarily including the following: branching and grouping, configuring multiple risk models within the decision flow, and selecting different risk models to calculate risk assessment results using the branching and grouping method. Branching and grouping can be based on weights, attributes, or rules. The branching and grouping method facilitates A / B testing and allows for the use of different risk models for assessment based on different characteristics.

[0072] According to embodiments of this disclosure, the control method further includes branch parallelism, which allows the process to be branched according to rules, with multiple branches capable of parallel computation. Each branch can also be configured to execute based on rules. Convergence and merging allows the processes of multiple parallel branches to be converged and merged, summarizing the computational results of each branch to calculate the measurement value of the comprehensive model.

[0073] According to embodiments of this disclosure, to better reuse decision flow configurations, the decision flow system also supports sub-processes, which can utilize the calculation results of merged decision flows. In the risk assessment embodiment, it is necessary to evaluate the effectiveness of risk models. The decision flow system also supports champion challenges, which can simultaneously calculate and compare multiple risk models, and compare them with measured values ​​or actual effects to evaluate the effectiveness of risk models. By setting multiple control methods according to decision branches, the risk assessment process becomes more diversified.

[0074] According to embodiments of this disclosure, the engine configuration method further includes: determining the data source for each indicator item in the business information, wherein the data source is connection information between the application system and the application system, which provides the business information; configuring the data source in the risk assessment engine to acquire the data sent by the application system based on the data source information.

[0075] According to embodiments of this disclosure, the data source includes connection information such as the application system's communication protocol, address, username, password, and parameters. Here, the application system refers to the customs third-party system in the risk assessment-related business information. Different application systems provide different protocol methods; therefore, the data source configuration also supports different protocols, including but not limited to relational databases, key-value (KV) databases, graph databases, RESTful interfaces, and Web Service (programmable network) application interfaces. Configuring the data source in the risk assessment engine enables the acquisition of data corresponding to each indicator item from the business information, effectively improving risk assessment efficiency.

[0076] Figure 4 schematically illustrates a block diagram of the indicator system of a risk assessment engine according to an embodiment of the present disclosure.

[0077] According to embodiments of this disclosure, the engine configuration method further includes: configuring multiple data processing indicators in the risk assessment engine, wherein the data processing indicators are used to obtain business data required for risk assessment, and the business data includes database information and service interface information and service framework information used for risk assessment; configuring multiple data calculation indicators in the risk assessment engine according to the calculation logic in the calculation rules, wherein the data calculation indicators are used to operate on the results calculated by the assessment strategy when performing risk assessment.

[0078] According to embodiments of this disclosure, in order to effectively utilize the indicator data provided by various application systems, the risk assessment engine indicator system supports multiple data sources. The indicator system is the internal support of the risk assessment system, including data processing indicators for acquiring data from external application systems, as well as data calculation indicators corresponding to the relevant functional modules of the indicator system.

[0079] As shown in Figure 4, the data processing metrics 410 mainly include the following: database metrics, used to obtain relevant metrics from database 431 in the business data center, including relational databases and non-relational databases. Non-relational databases include: key-value databases, document databases, and graph databases, etc. The specific data is provided by the database part of the business data center. Database metrics can obtain specific data items, aggregated statistical values, or retrieved relational values, and can be configured as needed.

[0080] According to embodiments of this disclosure, data processing metrics 410 further include interface metrics, used to obtain relevant metrics from data services 432 in the business data center, typically data services provided through RESTful or Webservice interfaces. Stream computing metrics are used to obtain relevant metrics provided by stream processing services 433 from the business data center, where stream processing services 433 include Spark, Storm, and Flink (an open-source stream processing framework). The computing metrics generated by stream processing services 433 can be cached in a real-time metric cache 434 service, through which stream processing services 433 obtain real-time stream computing metric values.

[0081] According to embodiments of this disclosure, the data calculation indicators 420 mainly include the following types: derived indicators, which are indirect indicator values ​​obtained through calculations using other indicator items and can be configured via scripts; constant indicators, which are constant indicators used for convenient configuration and maintenance; and basic indicators, which are indicator items used to transmit and store intermediate calculation results.

[0082] According to embodiments of this disclosure, the indicator system configures the data sources and related parameters for various indicator items through the indicator configuration function, and then publishes them to the real-time risk calculation engine. The indicator calculation function then calculates the real-time indicator values. Since some indicators are used frequently but their values ​​do not change in a short period, these values ​​are cached, and when querying indicators, the cached values ​​are retrieved first. This indicator configuration ensures the normal execution of the risk assessment service.

[0083] Figure 5 schematically illustrates a flowchart of an engine configuration method according to another embodiment of the present disclosure.

[0084] According to embodiments of this disclosure,

[0085] When operating S510, design a risk model.

[0086] When operating S520, prepare risk indicator data.

[0087] When operating the S530, configure the risk data source.

[0088] When operating the S540, configure risk indicators.

[0089] When operating the S550, configure the evaluation strategy.

[0090] When operating S560, configure the decision flow.

[0091] When operating S570, publish the decision flow.

[0092] When operating S580, perform a risk assessment.

[0093] According to embodiments of this disclosure, before risk assessment, a risk model must first be designed, including the data involved, data sources, and assessment methods. Then, risk indicator data is prepared, identifying all application systems that need to provide indicator data, and the methods for obtaining this data. After clarifying the methods for obtaining indicator data, risk data sources are configured, determining the data sources for various indicator items. Next, risk indicators are configured, such as database indicators, interface indicators, and basic indicators. Based on this, an assessment strategy is configured to obtain and calculate complex comprehensive indicators.

[0094] According to embodiments of this disclosure, after configuring the indicators and evaluation strategies, a decision flow can be configured, including its nodes, processes, and related attributes. Once the decision flow is configured, the risk model can be published. When publishing the decision flow, the data sources, indicators, and evaluation strategies are published together. After the decision flow is published, risk assessment can be executed. Application systems requiring risk assessment send a risk assessment request message to the message service, which will then execute the assessment and return the result to the message service. At this point, the risk assessment implementation steps are complete.

[0095] According to embodiments of this disclosure, data sources, indicators, and assessment strategies can be shared among different risk models. In customs clearance risk applications, many different risk models may be involved, and these different models may use many of the same indicator data. For reusable indicator items and assessment strategies, reconfiguration is unnecessary. To improve the efficiency of indicator data acquisition, the system caches indicator values. When configuring indicator items, the validity period of the cache needs to be determined to prevent untimely updates of cached indicator values ​​from affecting the assessment.

[0096] According to embodiments of this disclosure, risk engine management acts as the scheduler, coordinator, and manager of the risk assessment engine. Its main functions include allocating execution instance resources for risk models, monitoring the operational status of the real-time risk calculation engine, and repairing faults. In one embodiment of the risk assessment engine, there is one risk engine management instance and multiple real-time risk calculation engine instances. The risk engine management module is responsible for the resource allocation and monitoring management of all real-time risk calculation engine instances. Risk engine management includes the following main functions:

[0097] Resource allocation is used to allocate computing resources among the real-time risk computing engines. Based on the computing capabilities of each real-time risk computing engine and the computing resource requirements of the risk models, the computing instances of each real-time risk computing engine are allocated in a balanced manner to help maintain a balanced overall system performance. When allocating computing resources for risk models, efforts are made to distribute risk models across multiple different real-time risk computing engine services to ensure that the evaluation calculations of relevant risk models are always available.

[0098] The deployment of compute instances involves publishing or depublishing risk model compute instances to the real-time risk computation engine service based on resource allocation results. The deployment of compute instances is coordinated through a messaging service, which reduces the coupling between modules and facilitates independent expansion of each module.

[0099] Resource operation monitoring: The risk engine management module manages multiple real-time risk computing engine instances. These instances are registered with the risk engine management service, which monitors the operation of each instance. The monitoring of the risk real-time computing engines by the risk engine management module is also conducted asynchronously via a message service. This not only increases the utilization of computing resources and improves computing throughput, but also enhances the flexibility of switching between risk engine management modules, facilitating deployment and maintenance.

[0100] Computational resource recovery is used to restore faulty computing resources. When the system detects a computing resource failure, it rebalances the computing resources based on the current overall operating status, redistributing the faulty computing resources evenly across available real-time computing engines. Packet loss or intermittent interruptions can occur in network communication, leading to inaccurate status assessments. Furthermore, some failures recover quickly and automatically, making it unnecessary to incur additional costs for computing resource recovery. Therefore, time requirements are set for failure assessment; failures that can recover quickly and automatically, or false failures, do not require switchover recovery. For prolonged failures, the system will reallocate the computing instances of the faulty system to other computing resource services through resource reallocation.

[0101] Figure 6 schematically illustrates a block diagram of a risk assessment messaging service according to an embodiment of the present disclosure.

[0102] According to embodiments of this disclosure, risk assessment in customs applications involves a large number of assessment objects, has high real-time requirements, and needs to provide risk assessment services for many different systems. The risk assessment system mainly communicates and coordinates through messaging services to ensure service performance and convenience.

[0103] As shown in Figure 6, when requesting indicator data and providing feedback on indicator data results with the third-party system related to risk assessment 610, the communication protocol of the relevant information system is required, while other modules communicate with each other using message service 620.

[0104] According to the embodiments of this disclosure, the message service 620 of the customs clearance risk assessment system adopts a message queue service, which can ensure the timeliness of messages and the loose coupling of modules. At the same time, the asynchronous non-blocking communication mode is conducive to improving system throughput, shortening system response time, and enhancing user experience.

[0105] According to embodiments of this disclosure, when a risk assessment system needs to calculate a certain risk value, the user visually configures the risk model through the risk assessment configuration management 630, and triggers a risk model publishing command by sending a risk model publishing message to the message service 620. After the message is sent, the user receives the model publishing result from the message service 620 using the message listening service. When the risk assessment system finishes processing the publishing command, it sends the processing result of the publishing command to the message service 620. The risk assessment configuration management 630 can understand the execution status of the risk model publishing by receiving this message and provide feedback to the user.

[0106] According to an embodiment of this disclosure, the risk engine management 640 listens for model publishing instruction messages on the message service 620. Once a model publishing command is received, it immediately performs publishing processing, allocates computing resources, sends a model allocation command to the message service 620, and receives the processing result of the allocation command through message listening.

[0107] According to embodiments of this disclosure, the real-time risk calculation engine 650 listens for model publication messages on the message service 620. Upon receiving a message, it creates a calculation instance and a message queue, starts a listening service for relevant risk assessment requests, and prepares to respond to related processing requests. After the model publication execution is completed, it sends the command execution result to the message service 620.

[0108] According to embodiments of this disclosure, the real-time risk calculation engine 650 is the core of the risk assessment engine, and all risk value calculations are performed by this module. Based on the definition of the risk model, the real-time risk calculation engine 650 decomposes the model into different calculation units such as indicators, strategies, and decision flows, and performs calculations on each unit separately. The system coordinates the results and processes of each different calculation unit through a message service 620. This separates the I / O-intensive indicator calculations from the CPU-intensive strategy calculations, allowing for optimized resource allocation. The real-time risk calculation engine 650 employs an asynchronous, non-blocking task scheduling model for overall model scheduling and coordination, effectively utilizing computing resources and improving the overall system throughput. The real-time risk calculation engine 650 includes the following main functions:

[0109] Metric calculation is used to obtain and calculate the metric items defined in the risk model. Metric acquisition is mainly an I / O-intensive task. The system supports the concurrent execution of calculations for multiple metrics. Through an asynchronous non-blocking thread model, it can support the concurrent execution of as many metrics as possible, thereby improving the overall response efficiency.

[0110] Strategy computation is used to calculate the rules and logic defined in the strategy model within the risk model, and to obtain the measured values ​​of the strategy model. The strategy model mainly calculates indicators according to the model design rules and logic, which is a CPU-intensive task. The system controls the number of strategy instances to avoid the impact of a large number of thread switching on CPU utilization during thread concurrency.

[0111] Decision flow computation coordinates the execution order and process of indicators and strategies in the risk model, calculating and obtaining risk assessment values. During execution, decision flow computation decomposes the process, sends calculation tasks for indicators and strategies, receives the calculation results, and controls further execution based on feedback. To reduce network data transmission efficiency, strategy and indicator tasks sent by the decision flow are preferentially sent to the current real-time risk computation engine 650 for execution. During overall process control, an asynchronous non-blocking control model is used to improve the resource utilization and overall throughput of the risk model.

[0112] Local resource management is used to manage the local computing resources of the Risk Real-Time Computing Engine 650, mainly involving the creation, allocation, and maintenance of metric, strategy, and decision flow computing instances. This function also maintains current resource usage and records computing resource load; when the load is high, new computing tasks will be preferentially assigned to other Risk Real-Time Computing Engines 650 for execution.

[0113] Task scheduling coordinates and schedules the execution of all computing tasks. The Risk Real-Time Computing Engine 650 employs asynchronous task scheduling to ensure engine throughput. The computational tasks for metrics, strategies, and decision flows are all controlled and executed by task scheduling. For tasks waiting for I / O execution, computing instance resources are relinquished and the task waits in a queue. Upon receiving the result, an execution request is immediately issued, awaiting allocation of computing instance resources. Once a computing instance is acquired, task execution resumes immediately.

[0114] Status reporting: The real-time risk calculation engine 650 periodically reports its operating status, enabling the risk engine management 640 to monitor the operating status of the real-time risk calculation engine 650 in order to balance resource utilization or recover from failures.

[0115] Message processing is used for communication with external systems, responding to service requests, and coordinating task execution. The customs clearance risk application 660 sends a risk calculation request message through the message service 620. Upon receiving the message, the real-time risk calculation engine 650 parses it and triggers the calculation task. The calculation results are also fed back to the requester through message processing. Message processing is also responsible for coordinating tasks between indicators, strategies, and decision flows.

[0116] According to an embodiment of this disclosure, when the customs clearance risk application 660 needs to assess the risk value of an object, it sends a risk assessment request and related parameter messages of the object to the message service 620, and then listens for the feedback results from the message service 620.

[0117] According to embodiments of this disclosure, after receiving a risk assessment request, the real-time risk calculation performs a risk assessment calculation service through a calculation instance. After the calculation is completed, the risk assessment value is sent to the message service 620 to provide feedback to the risk assessment requesting end.

[0118] According to embodiments of this disclosure, when the real-time risk calculation engine 650 assesses risk, it decomposes the risk model into multiple different calculation instances. The creation, execution, and result feedback of each calculation instance on the different real-time risk calculation engines 650 are also provided through the message service 620.

[0119] According to the embodiments of this disclosure, the real-time risk calculation engine 650 periodically sends running status messages to the message service 620. The risk engine management 640 obtains relevant messages through the message listening service and updates the running status of the real-time risk calculation engine 650. For computing instances that have failed, they are reallocated to other computing resources. The allocation process is also conducted through the message service 620.

[0120] Figure 7 schematically illustrates a flowchart of a risk assessment method according to an embodiment of the present disclosure.

[0121] When operating S710, in response to the received risk assessment request, the data to be assessed in the risk assessment request is input into the configured risk assessment engine.

[0122] When operating the S720, the decision flow corresponding to the risk model in the risk assessment engine is used to perform risk assessment on the data to be assessed and output the risk assessment results.

[0123] According to embodiments of this disclosure, when a customs clearance risk application needs to assess the risk value of an object, it sends a risk assessment request and the relevant parameters of the object to be assessed (i.e., the data to be assessed) to a risk assessment engine, and then listens for the feedback risk assessment results. Upon receiving the risk assessment request, the risk assessment engine uses the decision flow corresponding to the risk model to perform a risk assessment on the data to be assessed, thus obtaining the risk assessment result.

[0124] According to embodiments of this disclosure, a risk assessment is performed on the data to be assessed using a decision flow corresponding to a risk model in a risk assessment engine, and a risk assessment result is output. This includes: determining multiple assessment indicators in the data to be assessed; obtaining corresponding indicator data from business information related to risk assessment based on the multiple assessment indicators; and performing a risk assessment on the indicator data using an assessment strategy in the decision flow to obtain a risk assessment result.

[0125] According to embodiments of this disclosure, attribute analysis is performed on the data to be evaluated to determine multiple evaluation indicators. Based on the data source corresponding to each evaluation indicator, the remaining indicator data corresponding to the evaluation object in the data to be evaluated are obtained. Both the data to be evaluated and the indicator data are input into a risk assessment engine, and risk assessment is performed using the assessment strategy in the decision flow. The risk model can be selected based on the type of indicator data to improve the accuracy of the risk assessment.

[0126] Figure 8 schematically illustrates an assessment flowchart to which the risk assessment method according to embodiments of the present disclosure can be applied.

[0127] As shown in Figure 8, risk assessment mainly includes two systems: a risk assessment system 810 and a customs clearance and inspection system 820. The following description uses this system as an example to illustrate an applicable assessment process.

[0128] According to embodiments of this disclosure, upon arrival at the port, customs obtains basic information about the vehicle or personnel. The customs clearance and inspection system submits this basic information to the risk assessment system for risk assessment. Upon receiving a risk assessment request, the real-time risk calculation engine 811 uses the risk indicator information database 812 to obtain relevant indicators and conduct a risk assessment. The assessment is primarily based on historical information, identity information, and key customs inspection information. After the risk assessment is completed, the results are fed back to the customs clearance and inspection system. After obtaining the risk assessment value, the customs clearance and inspection system determines whether inspection is necessary based on the risk value and the system's own rules and strategies. If no inspection is required, the process ends.

[0129] According to embodiments of this disclosure, if inspection is required, vehicles or personnel are inspected using personnel and equipment. After inspection, the inspection results for the vehicles or personnel are submitted. After obtaining the inspection results, data such as the basic information of the vehicles or personnel, the current risk value, and the inspection results can be submitted to a risk assessment system to perform a risk assessment.

[0130] According to embodiments of this disclosure, after completing the risk assessment, the risk assessment system 810 feeds back the risk assessment results to the customs clearance and inspection system 820. After obtaining the risk assessment value, the customs clearance and inspection system 820 further determines whether further inspection is needed based on the risk value and the system's own rules and strategies. If no inspection is needed, the process ends. If inspection is needed, the process continues to the next step and repeats until no further inspection is required. Inspection is not required when the final step of inspection has been reached, such as manual inspection, or when the risk assessment value is below a threshold. After the inspection is completed, the inspection results need to be sent back to the risk data indicator database 812, which can be used to improve the database and the risk assessment process.

[0131] According to embodiments of this disclosure, risk assessment can be requested multiple times, each time requesting a different risk model. Even when using the same risk model, the results may not be the same each time because the data is constantly changing, and the risk model may contain some random values. The term "risk indicator information database" is a general term; it does not mean there is only one indicator information database, and any valid data source can be added or removed.

[0132] According to embodiments of this disclosure, the customs clearance inspection system obtains the risk assessment results of the assessed object from the risk assessment system by sending a risk assessment request, so as to determine the inspection plan during customs clearance, make reasonable use of scarce inspection resources such as inspection equipment and personnel, and improve customs clearance efficiency.

[0133] Figure 9 schematically illustrates a structural block diagram of an engine configuration device according to an embodiment of the present disclosure.

[0134] As shown in Figure 9, the engine configuration device 900 includes a model building module 910, a decision flow generation module 920, and an engine configuration module 930.

[0135] Model building module 910 is used to build risk models in the risk assessment engine based on business information related to risk assessment and a rules engine that integrates different decision-making tools.

[0136] The decision flow generation module 920 is used to integrate multiple indicator items defined in the risk model and the calculation rules for each indicator item in the decision-making tool according to the business logic in the business information, and generate a decision flow corresponding to the risk model. The decision flow includes multiple decision nodes, and each decision node corresponds to an evaluation strategy determined according to the indicator items and calculation rules.

[0137] Engine configuration module 930 is used to configure the decision flow into the risk assessment engine so as to perform risk assessment using the configured risk assessment engine.

[0138] According to embodiments of this disclosure, the decision flow generation module 920 includes a node definition submodule, a strategy generation submodule, and a strategy flow generation submodule.

[0139] The node definition submodule is used to define multiple process nodes, including start nodes, decision nodes, and end nodes.

[0140] The strategy generation submodule is used to integrate indicator items with multiple calculation rules to obtain multiple evaluation strategies.

[0141] The strategy flow generation submodule is used to configure multiple evaluation strategies into corresponding decision nodes according to business logic, so as to orchestrate multiple process nodes and generate decision flows.

[0142] According to embodiments of this disclosure, the strategy generation submodule includes a threshold determination unit and a strategy generation unit.

[0143] The threshold determination unit is used to determine the threshold value corresponding to each indicator item.

[0144] The strategy generation unit is used to integrate multiple indicator thresholds based on the calculation logic in each calculation rule and the correlation between multiple indicator items to obtain multiple evaluation strategies.

[0145] According to embodiments of this disclosure, the strategy flow generation submodule includes a node orchestration unit and a decision flow generation unit.

[0146] The node orchestration unit is used to orchestrate decision nodes corresponding to different calculation rules based on business logic to obtain multiple decision branches, which can be computed in parallel when performing risk assessment.

[0147] The decision flow generation unit is used to connect multiple decision branches to the start node and the corresponding end node to obtain the decision flow.

[0148] According to embodiments of this disclosure, the engine configuration device 900 further includes a source determination module and a source configuration module.

[0149] The source determination module is used to determine the data source of each indicator item in the business information. The data source is the connection information between the data source and the application system, which is used to provide the business information.

[0150] The source configuration module is used to configure the data source in the risk assessment engine so as to obtain the data sent by the application system based on the data source information.

[0151] According to embodiments of this disclosure, the engine configuration device 900 further includes a processing index configuration module and a calculation index configuration module.

[0152] The data processing indicator configuration module is used to configure multiple data processing indicators in the risk assessment engine. These indicators are used to obtain the business data required for risk assessment, including database information and service interface and service framework information used in the risk assessment.

[0153] The calculation indicator configuration module is used to configure multiple data calculation indicators in the risk assessment engine according to the calculation logic in the calculation rules. The data calculation indicators are used to operate on the results obtained from the calculation of the assessment strategy when conducting risk assessment.

[0154] Figure 10 schematically illustrates a structural block diagram of a risk assessment apparatus according to an embodiment of the present disclosure.

[0155] As shown in Figure 10, the risk assessment device 1000 includes a request output module 1010 and a risk assessment module 1020.

[0156] The request output module 1010 is used to respond to the received risk assessment request and input the data to be assessed in the risk assessment request into the configured risk assessment engine.

[0157] The risk assessment module 1020 is used to perform risk assessment on the above-mentioned data to be assessed by utilizing the decision flow corresponding to the risk model in the risk assessment engine and output the risk assessment results.

[0158] According to embodiments of this disclosure, the risk assessment module 1020 further includes an indicator determination submodule, a data acquisition submodule, and a risk assessment submodule.

[0159] The indicator determination submodule is used to determine multiple evaluation indicators in the data to be evaluated.

[0160] The data acquisition submodule is used to obtain corresponding indicator data from business information related to risk assessment based on multiple evaluation indicators.

[0161] The risk assessment submodule is used to perform risk assessment on indicator data using assessment strategies in the decision flow, and obtain risk assessment results.

[0162] Any one or more of the modules, submodules, units, and subunits according to embodiments of the present disclosure, or at least part of the functions of any one or more of them, can be implemented in one module. Any one or more of the modules, submodules, units, and subunits according to embodiments of the present disclosure can be implemented by dividing them into multiple modules. Any one or more of the modules, submodules, units, and subunits according to embodiments of the present disclosure can be at least partially implemented as hardware circuitry, such as Field Programmable Gate Arrays (FPGAs), Programmable Logic Arrays (PLAs), Systems-on-Chip, Systems-on-Substrate, Systems-on-Package, Application-Specific Integrated Circuits (ASICs), or implemented in hardware or firmware by any other reasonable means of integrating or packaging circuitry, or implemented in software, hardware, or firmware, or in any suitable combination of any of these three implementation methods. Alternatively, one or more of the modules, submodules, units, and subunits according to embodiments of the present disclosure can be at least partially implemented as computer program modules, which, when run, can perform corresponding functions.

[0163] For example, any and multiple modules among the model building module 910, decision flow generation module 920, engine configuration module 930, request output module 1010, and risk assessment module 1020 can be combined into a single module / unit / subunit, or any one of these modules / units / subunits can be split into multiple modules / units / subunits. Alternatively, at least some of the functionality of one or more of these modules / units / subunits can be combined with at least some of the functionality of other modules / units / subunits and implemented in a single module / unit / subunit. According to embodiments of this disclosure, at least one of the model building module 910, decision flow generation module 920, engine configuration module 930, request output module 1010, and risk assessment module 1020 can be at least partially implemented as hardware circuitry, such as a field-programmable gate array (FPGA), programmable logic array (PLA), system-on-a-chip, system-on-a-substrate, system-on-package, application-specific integrated circuit (ASIC), or any other reasonable means of integrating or packaging circuitry, or implemented in software, hardware, or firmware, or in any suitable combination of any of these three implementation methods. Alternatively, at least one of the model building module 910, decision flow generation module 920, engine configuration module 930, request output module 1010, and risk assessment module 1020 can be at least partially implemented as a computer program module, which, when run, can perform corresponding functions.

[0164] It should be noted that the engine configuration device and risk assessment device in the embodiments of this disclosure correspond to the engine configuration method and risk assessment method in the embodiments of this disclosure. For a detailed description of the engine configuration device and risk assessment device, please refer to the engine configuration method and risk assessment method, which will not be repeated here.

[0165] Figure 11 schematically illustrates a block diagram of an electronic device suitable for implementing an engine configuration method and a risk assessment method according to embodiments of the present disclosure. The electronic device shown in Figure 11 is merely an example and should not be construed as limiting the functionality and scope of the embodiments of the present disclosure.

[0166] As shown in FIG11, an electronic device 1100 according to an embodiment of the present disclosure includes a processor 1101, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1102 or a program loaded from a storage portion 1108 into a random access memory (RAM) 1103. The processor 1101 may include, for example, a general-purpose microprocessor (e.g., a CPU), an instruction set processor and / or an associated chipset and / or a special-purpose microprocessor (e.g., an application-specific integrated circuit (ASIC)), etc. The processor 1101 may also include onboard memory for caching purposes. The processor 1101 may include a single processing unit or multiple processing units for performing different actions of the method flow according to an embodiment of the present disclosure.

[0167] RAM 1103 stores various programs and data required for the operation of electronic device 1100. Processor 1101, ROM 1102, and RAM 1103 are interconnected via bus 1104. Processor 1101 performs various operations of the method flow according to embodiments of the present disclosure by executing programs in ROM 1102 and / or RAM 1103. It should be noted that the programs may also be stored in one or more memories other than ROM 1102 and RAM 1103. Processor 1101 may also perform various operations of the method flow according to embodiments of the present disclosure by executing programs stored in said one or more memories.

[0168] According to embodiments of this disclosure, the electronic device 1100 may further include an input / output (I / O) interface 1105, which is also connected to a bus 1104. The electronic device 1100 may also include one or more of the following components connected to the input / output (I / O) interface 1105: an input section 1106 including a keyboard, mouse, etc.; an output section 1107 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 1108 including a hard disk, etc.; and a communication section 1109 including a network interface card such as a LAN card, modem, etc. The communication section 1109 performs communication processing via a network such as the Internet. A drive 1110 is also connected to the input / output (I / O) interface 1105 as needed. A removable medium 1111, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on the drive 1110 as needed so that computer programs read from it can be installed into the storage section 1108 as needed.

[0169] According to embodiments of this disclosure, the method flow according to embodiments of this disclosure can be implemented as a computer software program. For example, embodiments of this disclosure include a computer program product comprising a computer program carried on a computer-readable storage medium, the computer program containing program code for performing the methods shown in the flowchart. In such embodiments, the computer program can be downloaded and installed from a network via communication section 1109, and / or installed from removable medium 1111. When the computer program is executed by processor 1101, it performs the functions defined in the system of embodiments of this disclosure. According to embodiments of this disclosure, the systems, devices, apparatuses, modules, units, etc., described above can be implemented by computer program modules.

[0170] This disclosure also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiments; or it may exist independently and not assembled into the device / apparatus / system. The computer-readable storage medium carries one or more programs that, when executed, implement the method according to the embodiments of this disclosure.

[0171] According to embodiments of this disclosure, the computer-readable storage medium can be a non-volatile computer-readable storage medium. Examples include, but are not limited to: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this disclosure, the computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0172] For example, according to embodiments of this disclosure, a computer-readable storage medium may include one or more memories other than the ROM 1102 and / or RAM 1103 described above and / or ROM 1102 and RAM 1103.

[0173] Embodiments of this disclosure also include a computer program product comprising a computer program containing program code for performing the methods provided in the embodiments of this disclosure. When the computer program product is run on an electronic device, the program code is used to enable the electronic device to implement the engine configuration method and risk assessment method provided in the embodiments of this disclosure.

[0174] When the computer program is executed by the processor 1101, it performs the functions defined in the system / apparatus of this disclosure embodiments. According to embodiments of this disclosure, the systems, apparatuses, modules, units, etc., described above can be implemented by computer program modules.

[0175] In one embodiment, the computer program may rely on a tangible storage medium such as an optical storage device or a magnetic storage device. In another embodiment, the computer program may also be transmitted and distributed in the form of signals over a network medium, and may be downloaded and installed via the communication section 1109, and / or installed from the removable medium 1111. The program code contained in the computer program can be transmitted using any suitable network medium, including but not limited to: wireless, wired, etc., or any suitable combination thereof.

[0176] According to embodiments of this disclosure, program code for executing the computer programs provided in embodiments of this disclosure can be written in any combination of one or more programming languages. Specifically, these computational programs can be implemented using high-level procedural and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages ​​include, but are not limited to, languages ​​such as Java, C++, Python, "C", or similar programming languages. The program code can execute entirely on the user's computing device, partially on the user's device, partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0177] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions. Those skilled in the art will understand that the features described in the various embodiments of the present disclosure can be combined and / or combined in various ways, even if such combinations are not explicitly described in the present disclosure. In particular, the features described in the various embodiments of this disclosure may be combined and / or combined in various ways without departing from the spirit and teachings of this disclosure. All such combinations and / or combinations fall within the scope of this disclosure.

[0178] The embodiments of this disclosure have been described above. However, these embodiments are for illustrative purposes only and are not intended to limit the scope of this disclosure. Although various embodiments have been described above, this does not mean that the measures in the various embodiments cannot be used advantageously in combination. Various substitutions and modifications can be made by those skilled in the art without departing from the scope of this disclosure, and all such substitutions and modifications should fall within the scope of this disclosure.

Claims

1. An engine configuration method, comprising: Based on business information related to risk assessment and a rule engine that integrates different decision-making tools, a risk model is constructed in the risk assessment engine; Based on the business logic in the business information, multiple indicator items defined in the risk model and the calculation rules for each indicator item in the decision tool are integrated to generate a decision flow corresponding to the risk model. The decision flow includes multiple decision nodes, and each decision node corresponds to an evaluation strategy determined according to the indicator items and the calculation rules. The decision flow is configured into the risk assessment engine to perform risk assessment using the configured risk assessment engine.

2. The method of claim 1, wherein, The step of integrating multiple indicator items defined in the risk model and the calculation rules for each indicator item in the decision tool according to the business logic in the business information to generate a decision flow corresponding to the risk model includes: Define multiple process nodes, wherein the multiple process nodes include a start node, a decision node, and an end node; By integrating the aforementioned indicator items with multiple calculation rules, multiple evaluation strategies are obtained. According to the business logic, multiple evaluation strategies are configured into corresponding decision nodes to orchestrate multiple process nodes and generate the decision flow.

3. The method of claim 2, wherein, The process of integrating the indicator items with multiple calculation rules to obtain multiple evaluation strategies includes: Determine the threshold value corresponding to each of the aforementioned indicator items; Based on the calculation logic in each calculation rule and the correlation between multiple indicator items, multiple indicator thresholds are integrated to obtain multiple evaluation strategies.

4. The method of claim 2, wherein, The orchestration of multiple process nodes to generate the decision flow includes: Based on the business logic, decision nodes corresponding to different calculation rules are arranged to obtain multiple decision branches, wherein the multiple decision branches can be calculated in parallel when performing risk assessment. The decision branches are connected to the start node and the corresponding end node to obtain the decision flow.

5. The method according to claim 1, further comprising: The data source for each indicator item in the business information is determined, wherein the data source is connection information between the application system and the application system, which provides the business information; The data source is configured in the risk assessment engine to acquire data sent by the application system based on the data source information.

6. The method according to claim 1, further comprising: Multiple data processing metrics are configured in the risk assessment engine. These metrics are used to obtain the business data required for risk assessment. The business data includes database information and service interface information and service framework information used for risk assessment. According to the calculation logic in the calculation rules, multiple data calculation indicators are configured in the risk assessment engine, wherein the data calculation indicators are used to operate on the results calculated by the assessment strategy when performing risk assessment.

7. A risk assessment method, comprising: In response to a received risk assessment request, the data to be assessed in the risk assessment request is input into the risk assessment engine configured according to any one of claims 1 to 6; Using the decision flow corresponding to the risk model in the risk assessment engine, the data to be assessed is risk-assessed, and the risk assessment results are output.

8. The method of claim 7, wherein, The step of using the decision flow corresponding to the risk model in the risk assessment engine to perform risk assessment on the data to be assessed and outputting the risk assessment result includes: Identify multiple evaluation indicators in the data to be evaluated; Based on the multiple assessment indicators, obtain the corresponding indicator data from business information related to risk assessment; The risk assessment results are obtained by using the evaluation strategy in the decision flow to assess the risk of the indicator data.

9. An engine configuration device, comprising: The model building module is used to build risk models in the risk assessment engine based on business information related to risk assessment and a rules engine that integrates different decision-making tools. The decision flow generation module is used to integrate multiple indicator items defined in the risk model and the calculation rules for each indicator item in the decision tool according to the business logic in the business information, and generate a decision flow corresponding to the risk model. The decision flow includes multiple decision nodes, and each decision node corresponds to an evaluation strategy determined according to the indicator items and the calculation rules. as well as An engine configuration module is used to configure the decision flow into the risk assessment engine so as to perform risk assessment using the configured risk assessment engine.

10. An electronic device, comprising: One or more processors; Memory, used to store one or more programs. Wherein, when the one or more programs are executed by the one or more processors, the one or more processors cause the one or more processors to implement the method of any one of claims 1 to 6 or claim 7 or claim 8.

11. A computer-readable storage medium having stored thereon executable instructions that, when executed by a processor, cause the processor to perform the method of any one of claims 1 to 6, or claim 7, or claim 8.

12. A computer program product comprising a computer program that, when executed by a processor, implements the method according to any one of claims 1 to 6, or claim 7, or claim 8.

Images