Business process configuration method, business processing method and corresponding devices and equipment

Abstract

The invention provides a business process configuration method, a business processing method and corresponding devices and equipment, and belongs to the technical field of process processing. The business process configuration method comprises the steps of generating a to-be-configured business process according to processing logic of an approval business; according to the sub-evaluation task corresponding to the to-be-configured model node, configuring a target model and a self-maintenance strategy for the to-be-configured model node; and according to the sub-decision task corresponding to the to-be-configured decision node, configuring a decision strategy corresponding to the sub-decision task for the to-be-configured decision node. According to the embodiment of the invention, the accuracy and efficiency of process configuration can be improved, and the operation stability of the business process can also be improved.

Description

Technical Field

[0001] The present application relates to the field of process processing technology, and in particular to a business process configuration method, a business processing method, and corresponding devices and electronic equipment. Background Art

[0002] In the process of business processing, a variety of processing methods may be used. For some common processing methods, they can be packaged into the form of models to facilitate the construction of business processes. In related technologies, if there is a need to change, add or delete a model, it is usually necessary to organize it into an interface document based on the needs, and the developer performs corresponding editing and configuration based on the interface document. This is highly dependent on the accuracy of human operations and the familiarity with the model generation system. Once a configuration error occurs, the entire business process may become unusable. Moreover, this processing method cannot directly perform self-maintenance settings such as current limiting on the interface itself, which is not conducive to the stable operation of the business process. Summary of the invention

[0003] The present application provides a business process configuration method, a business processing method and corresponding devices, electronic devices, and computer-readable storage media, which can improve the accuracy and efficiency of process configuration and also improve the operational stability of business processes.

[0004] In a first aspect, the present application provides a business process configuration method, which includes: generating a business process to be configured according to the processing logic of an approval business, the approval task corresponding to the approval business includes at least one sub-evaluation task and at least one sub-decision task, and the business process to be configured includes a model node to be configured and a decision node to be configured; according to the sub-evaluation task corresponding to the model node to be configured, configuring a target model and a self-maintenance strategy for the model node to be configured, the target model is used to execute the sub-evaluation task, and the self-maintenance strategy is a strategy for executing a target maintenance operation in response to the model node to be configured triggering a preset event during data processing based on the target model; according to the sub-decision task corresponding to the decision node to be configured, configuring a decision strategy corresponding to the sub-decision task for the decision node to be configured.

[0005] In the second aspect, the present application provides a business processing method, which includes: obtaining data to be approved in response to an approval request sent by a user terminal; inputting the data to be approved into a business process for approval processing to obtain an approval result; wherein, the business process is a process obtained by the business process configuration method described in any one of the embodiments of the present application.

[0006] In the third aspect, the present application provides a business process configuration device, which includes: a generation module, which is used to generate a business process to be configured according to the processing logic of the approval business, the approval task corresponding to the approval business includes at least one sub-evaluation task and at least one sub-decision task, and the business process to be configured includes a model node to be configured and a decision node to be configured; a model configuration module, which is used to configure a target model and a self-maintenance strategy for the model node to be configured according to the sub-evaluation task corresponding to the model node to be configured, the target model is used to execute the sub-evaluation task, and the self-maintenance strategy is a strategy for executing a target maintenance operation in response to the model node to be configured triggering a preset event during data processing based on the target model; a strategy configuration module, which is used to configure a decision strategy corresponding to the sub-decision task for the decision node to be configured according to the sub-decision task corresponding to the decision node to be configured.

[0007] In a fourth aspect, the present application provides a business processing device, which includes: an acquisition module, used to obtain data to be approved in response to an approval request sent by a user terminal; an approval module, used to input the data to be approved into a business process for approval processing to obtain an approval result; wherein, the business process is a process obtained by the business process configuration method described in any one of the embodiments of the present application.

[0008] In a fifth aspect, the present application provides an electronic device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores one or more computer programs executable by the at least one processor, and one or more of the computer programs are executed by the at least one processor so that the at least one processor can execute the above-mentioned business process configuration method or business processing method.

[0009] In a sixth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program implements the above-mentioned business process configuration method or business processing method when executed by a processor / processing core.

[0010] The embodiment provided in the present application generates a business process to be configured according to the processing logic of the approval business. The business process to be configured includes multiple process nodes to be configured, thereby determining each process node in the business process and providing a basis for the subsequent configuration of each process node; for the model node to be configured, according to the sub-evaluation task corresponding to the model node to be configured, the target model and self-maintenance strategy are configured for the model node to be configured, and the sub-evaluation task of the model node can be processed through the target model. Since the target model can be obtained only through simple configuration, there is no need to use the corresponding model interface document for configuration for each model node to be configured, which effectively reduces the amount of manual processing and improves The efficiency of configuration is improved, and the possibility of human errors is also reduced accordingly, so the accuracy of configuration can be improved. In addition, since the self-maintenance strategy is configured in the model node to be configured, it provides a guarantee for the operation of subsequent business processes, which is convenient for improving the operation stability of business processes. For the decision nodes to be configured, according to the sub-decision tasks corresponding to the decision nodes to be configured, the decision strategies corresponding to the sub-decision tasks are configured for the decision nodes to be configured, so that each decision node can use the decision strategy to execute its own sub-decision tasks; after completing the configuration of multiple process nodes to be configured, the configured business process is generated, so that the business process can be used to process various approval requests.

[0011] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] The accompanying drawings are used to provide a further understanding of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the present application and do not constitute a limitation of the present application. The above and other features and advantages will become more apparent to those skilled in the art by describing detailed example embodiments with reference to the accompanying drawings. In the accompanying drawings:

[0013] Figure 1 A flowchart of a business process configuration method provided in an embodiment of the present application;

[0014] Figure 2 A schematic diagram of a process to be configured provided in an embodiment of the present application;

[0015] Figure 3 A flowchart of a business process configuration method provided in an embodiment of the present application;

[0016] Figure 4 A schematic diagram of a configuration process of a model node to be configured provided in an embodiment of the present application;

[0017] Figure 5A flowchart of a business processing method provided in an embodiment of the present application;

[0018] Figure 6 A schematic diagram of a processing procedure of a business process provided in an embodiment of the present application;

[0019] Figure 7 A flowchart of a business processing method provided in an embodiment of the present application;

[0020] Figure 8 A block diagram of a business process configuration device provided in an embodiment of the present application;

[0021] Fig. 9 A block diagram of a service processing device provided in an embodiment of the present application;

[0022] Fig.10 A block diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0023] In order to enable those skilled in the art to better understand the technical solution of the present application, the exemplary embodiments of the present application are described below in conjunction with the accompanying drawings, including various details of the embodiments of the present application to facilitate understanding, which should be considered as merely exemplary. Therefore, those of ordinary skill in the art should recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present application. Similarly, for the sake of clarity and conciseness, the description of well-known functions and structures is omitted in the following description.

[0024] In the absence of conflict, the embodiments of the present application and the features therein may be combined with each other.

[0025] As used herein, the term "and / or" includes any and all combinations of one or more of the associated listed items.

[0026] The terms used herein are only used to describe specific embodiments and are not intended to limit the present application. As used herein, the singular forms "a" and "the" are also intended to include plural forms, unless the context clearly indicates otherwise. It will also be understood that when the terms "including" and / or "made of" are used in this specification, the presence of the features, wholes, steps, operations, elements and / or components is specified, but the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or groups thereof is not excluded. "Connected" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect.

[0027] Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by those of ordinary skill in the art. It will also be understood that terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant art and this application, and will not be interpreted as having an idealized or overly formal meaning unless explicitly defined herein.

[0028] In the related technology, if a model is needed during the business process configuration, it is usually edited and configured in the connector through the model interface document, which greatly tests the accuracy and proficiency of human operation and cannot guarantee the accuracy and configuration efficiency of the model. In addition, it is impossible to perform self-maintenance processing in the interface, so the stable operation of the model cannot be guaranteed. Moreover, if a model change occurs, relevant personnel need to be notified by email or other means, and the synchronization time is low.

[0029] In view of this, embodiments of the present application provide a business process configuration method, a business processing method and corresponding devices, electronic devices, and computer-readable storage media.

[0030] According to the business process configuration method of the embodiment of the present application, a business process to be configured is generated according to the processing logic of the approval business. The business process to be configured includes multiple process nodes to be configured, thereby determining each process node in the business process, providing a basis for the subsequent configuration of each process node; for the model node to be configured, according to the sub-evaluation task corresponding to the model node to be configured, the target model and self-maintenance strategy are configured for the model node to be configured, and the sub-evaluation task of the model node can be processed through the target model. Since the target model can be obtained only through simple configuration, there is no need to use the corresponding model interface document for configuration for each model node to be configured, which effectively reduces the amount of manual processing. , which improves the efficiency of configuration and reduces the possibility of human errors accordingly, so the accuracy of configuration can be improved. In addition, since the self-maintenance strategy is configured in the model node to be configured, it provides a guarantee for the operation of subsequent business processes, which is convenient for improving the operation stability of business processes. For the decision nodes to be configured, according to the sub-decision tasks corresponding to the decision nodes to be configured, the decision strategies corresponding to the sub-decision tasks are configured for the decision nodes to be configured, so that each decision node can use the decision strategy to execute its own sub-decision tasks; after completing the configuration of multiple process nodes to be configured, the configured business process is generated, so that the business process can be used to process various approval requests.

[0031] The business process configuration method and business processing method according to the embodiment of the present application can be executed by an electronic device such as a terminal device or a server, and the terminal device can be a user equipment (User Equipment, UE), a mobile device, a user terminal, a terminal, a cellular phone, a cordless phone, a personal digital assistant (Personal Digital Assistant, PDA), a handheld device, a computing device, a vehicle-mounted device, a wearable device, etc. The method can be implemented by a processor calling a computer-readable program instruction stored in a memory. The server can be an independent physical server, a server cluster composed of multiple servers, or a cloud server capable of cloud computing.

[0032] In a first aspect, an embodiment of the present application provides a business process configuration method.

[0033] Figure 1 A flowchart of a business process configuration method provided in an embodiment of the present application can be used to perform task configuration on the model nodes to be configured and the decision nodes to be configured involved in the business process to be configured, wherein the model nodes to be configured are process nodes for configuring the model, and the decision nodes to be configured are process nodes for configuring the decision strategy. Figure 1 , the business process configuration method may include the following steps.

[0034] Step S11, generating a business process to be configured according to the processing logic of the approval business.

[0035] In some optional implementations, the approval service may be used to process an approval task, where the approval task includes at least one sub-evaluation task and at least one sub-decision-making task.

[0036] Exemplarily, the loan approval service may be used to process multiple loan approval tasks (eg, a loan approval task with a loan amount of RMB 100,000; a loan approval task with a loan amount of RMB 500,000).

[0037] Exemplarily, the user level upgrade approval service can be used to process user level upgrade approval tasks for multiple users (e.g., processing the upgrade approval task of users upgrading from ordinary level to member level; e.g., processing the upgrade approval task of users upgrading from member level to special member level).

[0038] It should be noted that the above-mentioned approval business is only an example, and the embodiments of the present application do not limit this.

[0039] In some optional implementations, the processing logic may be the rules followed when processing the approval business. When the processing logic of the approval business is clear, the corresponding business process to be configured may be generated according to the processing logic.

[0040] For example, the processing logic of the loan approval business can be: first determine whether the identity of the user applying for the loan approval business is authentic, then review the user's credit report, and when the user's credit report passes the review, the user's asset situation can be verified, and after verifying that the asset situation is correct, determine the amount of loan that can be issued to the user. In other words, through the processing logic of the approval business, a large-scale approval task is divided into multiple relatively small-scale subtasks, and these subtasks have a certain association relationship. Each subtask can correspond to a process node to be configured, and the process node to be configured carries the subtask.

[0041] In some optional implementations, the business process to be configured includes multiple process nodes to be configured, including at least one model node to be configured and at least one decision node to be configured, the model node to be configured is used to execute the sub-evaluation task, and the decision node to be configured is used to execute the sub-decision task. Among them, the sub-evaluation task is a sub-task of the approval task, and the task content of the sub-evaluation task is mainly evaluation processing, and the sub-decision task is also a sub-task of the approval task, and the task content of the sub-decision task is mainly decision processing.

[0042] In some optional implementations, the model node to be configured implements its sub-evaluation task by configuring the model, and the decision node to be configured implements its sub-decision task by configuring the decision strategy. The model has a specific function that can implement the sub-evaluation task, and the decision strategy is a strategy that can implement the decision processing.

[0043] Step S12: configuring a target model and a self-maintenance strategy for the model node to be configured according to the sub-evaluation task corresponding to the model node to be configured.

[0044] Among them, the target model is a model used to execute the sub-evaluation task of the model node to be configured, and the self-maintenance strategy is a strategy for executing the target maintenance operation in response to the model node triggering a preset event during the processing.

[0045] In some optional implementations, a target model and a self-maintenance strategy are configured for the model node to be configured according to the sub-evaluation task corresponding to the model node to be configured, including: determining a target model that matches the sub-evaluation task from multiple candidate models, the candidate models being used to implement multiple evaluation functions; configuring the target model to the model node to be configured corresponding to the target model; determining the sub-business type corresponding to the sub-evaluation task; and, according to the sub-business type, configuring a self-maintenance strategy that matches the sub-business type in the model node to be configured.

[0046] It can be seen that in the embodiments of the present application, some commonly used models or necessary models have been pre-generated, and these models are candidate models. When a model is needed at a certain model node to be configured, a candidate model that can execute the sub-evaluation task of the model node to be configured is directly selected from the candidate models as the target model, and the target model is configured to the model node to be configured. The processing process is relatively simple and fast, and is not prone to errors, so the configuration efficiency and accuracy can be improved.

[0047] In other words, the model configuration in this application is essentially just to perform some simple model selection operations. There is no need to rely on the model interface document, and there is no need to perform corresponding editing and other configuration operations based on the model interface document. The configuration difficulty and workload are reduced, thereby improving the accuracy and success rate of the configuration.

[0048] In some optional implementations, the target model and the self-maintenance strategy can be configured in the model node to be configured, or a model proxy can be set in the model to be configured, so as to configure the target model and the self-maintenance strategy in the model proxy. The main function of setting the model proxy is to create a relatively independent and secure model running environment in the model node to be configured, thereby reducing mutual interference between models and model nodes.

[0049] Exemplarily, before configuring the target model and the self-maintenance strategy for the model node to be configured according to the sub-evaluation task, the method also includes: configuring a corresponding model agent for the model node to be configured, the model agent being used to create an independent model operating environment in the model node to be configured; correspondingly, configuring the target model and the self-maintenance strategy for the model node to be configured according to the sub-evaluation task, including: configuring the target model and the self-maintenance strategy in the model agent of the model node to be configured according to the sub-evaluation task.

[0050] In addition, in the configuration stage, the possibility of abnormal operation or failure of future business processes during use is fully considered. Therefore, according to the sub-business type corresponding to the sub-evaluation task of each model node to be configured, a self-maintenance strategy matching the sub-business type is configured for each model node to be configured. Once the model node triggers a preset event during the processing process, the target maintenance operation can be automatically performed. Through this target maintenance operation, the stable operation of the business process can be guaranteed to a certain extent.

[0051] In some optional implementations, the self-maintenance strategy includes at least one of a circuit breaker strategy, a current limiting strategy, and a downgrade strategy; wherein the policy parameters of the circuit breaker strategy include a circuit breaker count threshold and a circuit breaker duration, the policy parameters of the current limiting strategy include a call count threshold, and the policy parameters of the downgrade strategy include a call waiting threshold.

[0052] It should be noted that in the embodiment of the present application, for the model node to be configured, the target model can be configured into the model node to be configured only through simple configuration operations, without having to generate a corresponding target model for each model node to be configured, and without having to rely on the model interface document to perform complex editing and configuration processing, which greatly simplifies the configuration workload and configuration difficulty, can reduce the possibility of human errors, and thus improve the accuracy of the configuration.

[0053] Step S13, according to the sub-decision task corresponding to the decision node to be configured, configure the decision strategy corresponding to the sub-decision task for the decision node to be configured.

[0054] In some optional implementations, different decision nodes to be configured have different sub-decision tasks, and the required decision strategies are also different. Therefore, for each decision node to be configured, a decision strategy matching the sub-decision task can be selected and configured into the decision node to be configured according to the sub-decision task of the decision node to be configured, so as to generate a configured decision node.

[0055] In some optional implementations, after completing the configuration of the model node to be configured and obtaining the configured model node, the method may also include: upon receiving a model change message, determining a candidate update model node corresponding to the model change message, the model change message being a message used to indicate that a candidate model has changed; and upon determining that the model needs to be reconfigured based on the model change message, reconfiguring the target model in the candidate update model node.

[0056] That is to say, once the candidate model is updated, the business process configuration device (or model node, model agent in the model node) can promptly perceive this change through the model change message, and thus promptly determine whether the model node configured with the candidate model needs to be reconfigured to ensure that each model node can accurately and smoothly execute its respective sub-evaluation tasks.

[0057] In the embodiment of the present application, according to the processing logic of the approval business, a business process to be configured is generated, and the business process to be configured includes multiple process nodes to be configured, thereby determining each process node in the business process, and providing a basis for the subsequent configuration of each process node; for the model node to be configured, according to the sub-evaluation task corresponding to the model node to be configured, the target model and the self-maintenance strategy are configured for the model node to be configured, and the sub-evaluation task of the model node can be processed through the target model. Since the target model can be obtained only through simple configuration, there is no need to use the corresponding model interface document for configuration for each model node to be configured, which effectively reduces the amount of manual processing and improves The efficiency of configuration is improved, and the possibility of human errors is also reduced accordingly, so the accuracy of configuration can be improved. In addition, since a self-maintenance strategy is configured in the model node, it provides a guarantee for the operation of subsequent business processes, which is convenient for improving the operation stability of business processes. For the decision nodes to be configured, according to the sub-decision tasks corresponding to the decision nodes to be configured, the decision strategies corresponding to the sub-decision tasks are configured for the decision nodes to be configured, so that each decision node can use the decision strategy to execute its own sub-decision tasks; after completing the configuration of multiple process nodes to be configured, the configured business process is generated, so that the business process can be used to process various approval requests.

[0058] Combine the following Figure 2 An example description of the business process to be configured is given.

[0059] Figure 2 A schematic diagram of a process to be configured provided in an embodiment of the present application. Figure 2 As shown, the approval business is a loan approval business, and the processing logic is: first, conduct a user identity review to ensure the authenticity and legality of the user's identity; second, conduct a user credit review to ensure that the user's credit risk is small and has a high credit ability; in addition, conduct a user asset check to determine the user's asset status and the legality of the assets; then, verify the loan amount to determine the bandwidth quota that can be issued to the user; further, sign a loan contract to form a written guarantee; finally, issue the loan.

[0060] In some optional implementations, a credit assessment model and an asset assessment model are pre-generated for credit review and asset review, and the two constitute candidate models, wherein the credit assessment model is used to assess the user's credit, and the asset assessment model is used to assess the user's assets; in addition, an amount decision strategy is also pre-set, which can be used to determine the loan amount issued to the user.

[0061] In summary, a business process to be configured can be generated, which includes: a user identity review node to be configured, a user credit review node to be configured, a user asset verification node to be configured, a loan amount verification node to be configured, a loan contract signing node to be configured, and a loan issuance node to be configured.

[0062] Among them, for the user credit review node to be configured, considering that the sub-evaluation task of this node is to evaluate the user's credit, the credit evaluation model can be selected from the candidate models as the target model, and the credit evaluation model can be configured in the user credit review node to be configured. For the user asset verification node to be configured, considering that the sub-evaluation task of this node is to evaluate the user's assets, the asset evaluation model can be selected from the candidate models as the target model, and the asset evaluation model can be configured in the user asset verification node to be configured. For the loan amount confirmation node to be configured, considering that the sub-decision task of this node is to decide the loan amount, the amount decision strategy can be configured in the loan amount confirmation node to be configured.

[0063] In addition, self-maintenance strategy 1 and self-maintenance strategy 2 are also pre-set, and self-maintenance strategy 1 is applicable to processing the credit review sub-business, and self-maintenance strategy 2 is applicable to processing the asset review sub-business. Based on this, self-maintenance strategy 1 can be configured in the user credit review to be configured node, and self-maintenance strategy 2 can be configured in the user asset verification to be configured node.

[0064] In summary, Figure 2 The business process to be configured shown includes two model nodes to be configured, namely the user credit review node to be configured and the user asset verification node to be configured, and also includes a decision node to be configured - the loan amount verification node to be configured. The remaining three nodes are other types of nodes to be configured, and the functions of their respective subtasks can be configured in them. After completing the configuration of all nodes to be configured, the configured business process is generated, and the business process can be used to process various approval requests.

[0065] Figure 3 A flowchart of a business process configuration method provided in an embodiment of the present application. Figure 3 , the business process configuration method may include the following steps.

[0066] Step S301: create multiple candidate models and manage the multiple candidate models through a model registration center.

[0067] In some optional implementations, for some commonly used or important evaluation functions, candidate models for implementing various evaluation functions may be created in advance. In addition, in order to facilitate the management of multiple candidate models, these candidate models may be managed through a preset model registration center.

[0068] In some optional implementations, with business updates and functional iterations, some updates can be made to existing candidate models, and some new candidate models can be added. For example, in the case of expanding the function of a candidate model, a model change message can be sent to the model registration center; for example, in the case of upgrading the version of a candidate model, a model change message can be sent to the model registration center; for example, after adding a new candidate model, a model registration message can be sent to the model registration center so that the model registration center is informed of the addition of a new candidate model through the model registration message. The model registration center can timely understand the latest functions of each candidate model through the model change messages received from each candidate model, which facilitates efficient and accurate model management.

[0069] Step S302: Generate a business process to be configured according to the processing logic of the approval business.

[0070] Step S303: configure a corresponding model proxy for the model node to be configured.

[0071] In some optional implementations, the model proxy can be used to create an independent model running environment in the model node to be configured. The model running environment created by the model proxy allows the target model to run in a relatively independent environment. Even if the operation of the target model is abnormal, it will not affect the interference between the candidate model corresponding to the target model and other candidate models, and can also alleviate the interference of each model node during operation.

[0072] In some optional implementations, the model agent may also establish a communication connection with the model registration center and receive model change messages to determine whether the target model in the model node needs to be reconfigured based on the model change messages, or receive model registration messages to determine whether the target model in the model node needs to be replaced based on the model registration messages.

[0073] Step S304: According to the sub-evaluation task of the model node to be configured, a target model matching the sub-evaluation task is determined from multiple candidate models.

[0074] Step S305: configure the target model into the model proxy of the to-be-configured model node corresponding to the target model.

[0075] In some optional implementations, the model configuration data of the target model can be obtained through the model interface opened by the model registration center, and based on the model configuration data of the target model, the model configuration operation is performed in the model proxy of the model node to be configured corresponding to the target model, so that the corresponding target model is configured in the model node to be configured.

[0076] Exemplarily, the target model executes the sub-evaluation task through a preset target function; accordingly, the model configuration data includes function configuration parameters and environment configuration parameters, and the model configuration operation is used to load the target function into the model node to be configured according to the function configuration parameters, and configure the execution environment of the target function in the model node to be configured according to the environment configuration parameters. In other words, the execution of the target function depends on the preset execution environment. Through the model configuration data, on the one hand, the target function can be configured in the model node to be configured, and on the other hand, the execution environment of the target function can be configured in the model node to be configured to ensure that the target function can run normally.

[0077] Exemplarily, if the sub-evaluation task of the model node to be configured is a user credit evaluation task, then the candidate model that can execute the user credit evaluation task is determined to be a credit evaluation model. "Credit Evaluation Model" can be entered in the model name of the model agent, and the appropriate version can be selected to fill the input and output parameters of this version of the credit evaluation model into the model agent.

[0078] Step S306, determining the sub-business type corresponding to the sub-evaluation task of the model node to be configured.

[0079] In some optional implementations, the sub-business type is used to reflect the business type of the sub-assessment task. For example, the sub-business type includes a credit assessment business type, an asset assessment business type, a consumer capacity assessment business type, and the like.

[0080] Step S307: According to the sub-business type, a self-maintenance strategy matching the sub-business type is configured in the model agent of the model node to be configured.

[0081] In some optional implementations, a mapping relationship between sub-service types and self-maintenance policies is pre-established. Therefore, after the sub-service type is determined, the self-maintenance policy matching the sub-service type can be determined according to the mapping relationship.

[0082] Step S308, according to the sub-decision task corresponding to the decision node to be configured, configure the decision strategy corresponding to the sub-decision task for the decision node to be configured.

[0083] Figure 4 A schematic diagram of a configuration process of a model node to be configured provided in an embodiment of the present application. Figure 4 As shown, for the model node to be configured, a model proxy is configured in it, and a relatively safe and independent model running environment is created in the model node to be configured through the model proxy, so that the target model can run safely and independently in the model running environment.

[0084] Exemplarily, there are k candidate models under the model registration center, namely candidate model 1, candidate model 2, ..., candidate model k (k ≥ 1). According to the sub-evaluation task of the model node to be configured, a candidate model that can execute the sub-evaluation task is screened out from the k candidate models, and the candidate model is used as the target model of the model node to be configured. The target model can execute the sub-evaluation task of the model node to be configured through a preset objective function, and the execution of the objective function depends on a preset execution environment. In other words, the target model can realize the sub-evaluation task by executing the objective function, and the objective function needs to be successfully executed in a preset execution environment.

[0085] After determining the target model, the model configuration data of the target model is obtained through the model registration center, wherein the model configuration data includes function configuration parameters and environment configuration parameters. The target function is loaded into the node of the model to be configured through the function configuration parameters, and the execution environment of the target function is configured in the node of the model to be configured through the environment configuration parameters. Through the above configuration processing, the target model is configured in the node of the model to be configured.

[0086] In addition, a plurality of self-maintenance strategies are preset, including self-maintenance strategy 1, self-maintenance strategy 2, ..., self-maintenance strategy p (p≥1). According to the sub-assessment task type corresponding to the sub-assessment task of the model node to be configured, a target self-maintenance strategy matching the sub-assessment task type is selected from a plurality of self-maintenance strategies, and the target self-maintenance strategy is configured to the model node to be configured, thereby generating a configured model node.

[0087] In some optional implementations, with the iteration of functions and business updates, some updates can be made to the candidate models. For example, the functions of the candidate models can be expanded, the versions of the candidate models can be upgraded, and so on. The model registration center can obtain the model change messages of each candidate model. In addition, the model proxy can maintain a communication connection with the model registration center to obtain the model change message. Therefore, when the model proxy obtains the model change message and determines that the model change message points to the current model node, it can reconfigure the target model in the current model node so that the target model in the model node is the latest model. The method for updating the target model can refer to the method for configuring the target model, which will not be described in detail here.

[0088] In a second aspect, an embodiment of the present application provides a business processing method.

[0089] Figure 5 A flowchart of a business processing method provided in an embodiment of the present application. Figure 5 , the business processing method may include the following steps.

[0090] Step S51, in response to the approval request sent by the user terminal, obtaining the data to be approved.

[0091] In some optional implementations, the approval request is a request initiated by a user to approve a certain approval task. The data to be approved may be data carried in the approval request or data obtained from other data sources based on the approval request. This embodiment of the present application does not limit this.

[0092] Exemplarily, a user terminal initiates a loan approval request and carries the user's identity information in the loan approval request. The business system carrying the business process responds to the loan approval request and obtains the user's identity information as data to be approved.

[0093] Exemplarily, a user terminal initiates a service upgrade approval request and carries a user service identifier in the service upgrade approval request. The service system carrying the service process responds to the service upgrade approval request and obtains the user's identity information and historical service records from the system database as data to be approved based on the user service identifier.

[0094] Step S52: input the data to be approved into the business process for approval processing to obtain the approval result.

[0095] Among them, the business process is a process obtained through the business process configuration method of any one of the embodiments of the present application.

[0096] In some optional implementations, the business process includes at least one model node and at least one decision node; wherein the model node is used to call the configured target model to process the data input to the model node, obtain a model score, and input the model score to the next adjacent process node, or the model node is used to call the configured target model to obtain auxiliary input parameters, process the data and auxiliary input parameters input to the model node through the target model, obtain a model score, and output the model score to the next adjacent process node; the decision node is used to perform decision processing on the data input to the decision node according to the configured decision strategy, obtain a node decision result, and output the node decision result to the next adjacent process node; the approval result is the result output by the last process node of the approval business process.

[0097] In some optional implementations, the model node is used to process a sub-evaluation task, and the model score of the model node is the score obtained after the target model in the model node performs the evaluation processing.

[0098] For example, a credit assessment model is configured in the model node, and the data input to the model node includes the user's historical credit data. After being processed by the credit assessment model, a model score is output, and the model score can reflect the user's credit evaluation status.

[0099] In some optional implementations, in order to improve the accuracy of the model score of the model node, in addition to the data input into the model node by the previous process node adjacent to the model node, some auxiliary input parameters can also be obtained from an external data source, so as to jointly determine the model score by combining the auxiliary input parameters and the input data.

[0100] It should be noted that a self-maintenance strategy may be configured in the model node or the model agent of the model node. When a preset event is triggered during the processing of the model node, the target maintenance operation can be performed based on the self-maintenance strategy configured in the model node or the model agent of the model node.

[0101] In some optional implementations, the self-maintenance strategy may include at least one of a fuse strategy, a current limiting strategy, and a degradation strategy. Among them, the current limiting strategy aims to control the flow, such as abandoning the flow call according to a preset percentage. The main purpose is to reduce the pressure of downstream calls. When the pressure is restored or the capacity is expanded, the current limiting can be turned off to ensure the normal operation of the approval business. The fuse strategy is usually applied when the service is completely unavailable, and often occurs after the current limiting strategy. The degradation strategy is a response strategy for long-term waiting for the service, which aims to relieve service pressure without affecting the normal overall approval business.

[0102] In some optional implementations, when the self-maintenance strategy includes a fuse strategy, and the preset event is that the number of failures of the model node to call the target model is greater than the fuse number threshold, the target maintenance operation includes setting the target model to a fuse state, and the duration of the fuse state is equal to the fuse duration; when the self-maintenance strategy includes a current limiting strategy, and the preset event is that the number of call requests for the model node is greater than the call number threshold, the target maintenance operation includes losing or queuing the call requests that exceed the call number threshold; when the self-maintenance strategy includes a downgrade strategy, and the preset event is that the call waiting time of the model node is greater than the call waiting threshold, the target maintenance operation includes adding a downgrade label to the output data of the model node, and the downgrade label is used to initiate a downgrade request to the decision node.

[0103] Exemplarily, the number of times a model node fails to call a target model can be recorded. For example, a time window of 5 minutes is used to record the number of call failures (the scanning interval of the time window can be set to 1 minute / time). If it is detected that the number of call failures exceeds a preset fuse threshold, the target model is set to a blown state, and the duration of the blown state is equal to the preset fuse duration.

[0104] Exemplarily, the number of call requests of the model node within a preset time period is monitored. When the number of call requests is greater than a call number threshold, the call requests exceeding the call number threshold are lost or queued for processing.

[0105] In some optional implementations, when the data input to the decision node includes a downgrade label, the decision node is used to determine whether to approve the downgrade request of the model node based on the importance level of the sub-evaluation task of the model node that generates the downgrade label.

[0106] Exemplarily, the importance level of the sub-assessment task includes a core level and a non-core level. Accordingly, when the call waiting time of the model node is greater than the call waiting threshold, a downgrade label is issued to the adjacent decision node. After the decision node receives the downgrade label, if the sub-assessment task of the model node is a core level, the downgrade request of the model node is rejected. If the sub-assessment task of the model node is a non-core level, the downgrade request of the model node is received and the downgrade time (for example, 10 seconds, 20 seconds) is set. When the downgrade time is exceeded, the service level of the model node is restored.

[0107] In some optional implementations, in order to improve the rationality of decisions, decision nodes may need multiple rounds of decision iterations when executing decisions based on decision strategies to obtain more accurate and reasonable decision results.

[0108] It should be noted that the business process includes multiple process nodes, and these process nodes can form a chain process structure or a tree process structure with a branch structure, which is not limited in the embodiments of the present application. Correspondingly, when using a business process with a branch structure to process an approval task, due to the difference in approval tasks, it may flow to different process branches, so that only some process nodes may be used in a business processing process. However, whether all or some of the process nodes are used, the processing process of each used process node is similar.

[0109] In an embodiment of the present application, in response to an approval request sent by a user terminal, data to be approved is obtained, and the data objects to be processed subsequently are clarified; and since the business process has been pre-configured, the data to be approved can be input into the business process for approval processing, so that the approval result can be obtained conveniently and accurately, thereby improving business processing efficiency; in addition, since the model node in the business process is pre-configured with a self-maintenance strategy, even if a preset event is triggered during operation, the target maintenance operation can still be automatically performed, thereby improving the operational stability of the business process.

[0110] Figure 6 A schematic diagram of the processing procedure of a business process provided in an embodiment of the present application.

[0111] Reference Figure 6,The business process includes multiple process nodes including model node i and decision node j. Each process node can execute its own node task, and finally realize the approval task and obtain the approval result, i>1, j>1.

[0112] First, the user terminal initiates an approval request and carries the data to be approved in the approval request. The data to be approved is used as the input data of the first process node of the business process. After being processed by i-1 process nodes, the output data of the i-1th process node is obtained.

[0113] like Figure 6 As shown, the model node i is configured with a target model i. When the output data of the process node i-1 is input to the model node i, the model node i calls the target model i to obtain the external data source and the external variable from the outside as auxiliary input parameters, and processes the output data, the external data source and the external variable of the process node i-1 through the target model i to obtain the model score i. The model score i is used as the output data of the model node i and input into the process node i+1, and the process node i+1 performs the corresponding process processing using the input data.

[0114] For decision node j, decision strategy j is configured. When the output data of process node j-1 is input to decision node j, decision node j calls decision strategy j to perform one or more rounds of decision judgment, obtains the decision result, and inputs the decision result as the output data of decision node j to process node j+1, and process node j+1 performs corresponding process processing using the input data. Finally, the approval result is output by the last process node of the business process.

[0115] Figure 7 A flowchart of a business processing method provided in an embodiment of the present application.

[0116] Reference Figure 7 During the operation of the model node, the operation status of the model node can be monitored to timely determine whether a preset event is triggered, so as to timely perform the target maintenance operation. For example, for any model node i (1≤i≤n, n≥1) among model node 1, model node 2, ..., model node n, the call status of the model node i can be monitored during the operation.

[0117] Step S701, obtaining the call result code of model node i.

[0118] Exemplarily, the calling result code can be used to determine whether the model node i can normally call the target model configured therein.

[0119] Step S702, determine whether the call result code indicates a call error.

[0120] Exemplarily, the call result code may have multiple values. When the call result code code!=200 or 10000, it is determined that the call error is represented, and the process may jump to step S703; otherwise, the process may jump to step S701 to continue monitoring the operation of the model node i.

[0121] Step S703, updating the number of call failures.

[0122] Exemplarily, each time after determining that a model node i has a call error, the number of call failures d=++d is updated.

[0123] Step S704, determine whether the fuse is triggered.

[0124] Exemplarily, based on the comparison between the updated number of call failures and the preset fuse threshold, when the number of call failures is greater than the fuse threshold, it is determined that the fuse is triggered and jumps to step S705; otherwise, jumps to step S701 and continues to monitor the operation status of model node i.

[0125] Step S705, executing the fuse processing of the model node i.

[0126] It can be understood that the above-mentioned various method embodiments mentioned in this application can be combined with each other to form a combined embodiment without violating the principle logic. Due to space limitations, this application will not go into details. Those skilled in the art can understand that in the above-mentioned method of the specific implementation method, the specific execution order of each step should be determined by its function and possible internal logic.

[0127] In a third aspect, an embodiment of the present application provides a business process configuration device.

[0128] Figure 8 A block diagram of a business process configuration device provided in an embodiment of the present application.

[0129] Reference Figure 8 The embodiment of the present application provides a business process configuration device, which can be used to perform task configuration on the model nodes to be configured and the decision nodes to be configured involved in the business process to be configured. The model nodes to be configured are process nodes used to configure the model, and the decision nodes to be configured are process nodes used to configure the decision strategy. The business process configuration device 800 may include the following modules.

[0130] The generation module 801 is used to generate a business process to be configured according to the processing logic of the approval business. The approval task corresponding to the approval business includes at least one sub-evaluation task and at least one sub-decision task. The business process to be configured includes a model node to be configured and a decision node to be configured.

[0131] The model configuration module 802 is used to configure a target model and a self-maintenance strategy for the model node to be configured according to the sub-evaluation task corresponding to the model node to be configured, wherein the target model is used to perform the sub-evaluation task, and the self-maintenance strategy is a strategy for performing a target maintenance operation in response to a preset event being triggered by the model node to be configured during data processing based on the target model;

[0132] The policy configuration module 803 is used to configure a decision policy corresponding to the sub-decision task for the decision node to be configured according to the sub-decision task corresponding to the decision node to be configured.

[0133] In some optional implementations, when the model configuration module configures the target model and the self-maintenance strategy for the model node to be configured according to the sub-evaluation task corresponding to the model node to be configured, the following steps are performed:

[0134] Determine a target model that matches the sub-evaluation task from the candidate models, where the candidate models are used to implement multiple evaluation functions;

[0135] Configuring the target model to the to-be-configured model node corresponding to the target model;

[0136] Determine the sub-business type corresponding to the sub-assessment task;

[0137] According to the sub-business type, a self-maintenance strategy matching the sub-business type is configured in the model node to be configured.

[0138] In some optional implementations, configuring the target model to a to-be-configured model node corresponding to the target model includes:

[0139] Obtain the model configuration data of the target model through the model interface opened by the model registration center;

[0140] Based on the model configuration data of the target model, a model configuration operation is performed in the to-be-configured model node corresponding to the target model, so that the to-be-configured model node is configured with the corresponding target model.

[0141] In some optional implementations, the target model performs the sub-evaluation task through a preset objective function;

[0142] The model configuration data includes function configuration parameters and environment configuration parameters. The model configuration operation is used to load the target function into the model node to be configured according to the function configuration parameters, and configure the execution environment of the target function in the model node to be configured according to the environment configuration parameters.

[0143] In some optional implementations, before the model configuration module configures the target model and the self-maintenance strategy for the model node to be configured according to the sub-evaluation task of the model node to be configured, the business process configuration device is further used to perform the following steps:

[0144] Configure a corresponding model agent for the model node to be configured. The model agent is used to create an independent model running environment in the model node to be configured.

[0145] Correspondingly, when the model configuration module configures the target model and self-maintenance strategy for the model node to be configured according to the sub-evaluation task, it performs the following steps:

[0146] According to the sub-evaluation tasks, the target model and self-maintenance strategy are configured in the model agent of the model node to be configured.

[0147] In some optional implementations, the self-maintenance strategy includes at least one of a fuse strategy, a current limiting strategy, and a degradation strategy;

[0148] Among them, the policy parameters of the circuit breaker strategy include the circuit breaker number threshold and the circuit breaker duration, the policy parameters of the current limiting strategy include the call number threshold, and the policy parameters of the degradation strategy include the call waiting threshold.

[0149] In some optional implementations, after configuring the target model and the self-maintenance strategy for the model node to be configured according to the sub-evaluation task, the method further includes:

[0150] Upon receiving a model change message, determining a candidate update model node corresponding to the model change message, wherein the model change message is a message used to indicate that a candidate model has been changed;

[0151] When it is determined based on the model change message that the model needs to be reconfigured, the target model in the candidate update model node is reconfigured.

[0152] In an embodiment of the present application, a generation module generates a business process to be configured according to the processing logic of the approval business. The business process to be configured includes multiple process nodes to be configured, thereby determining each process node in the business process, providing a basis for the subsequent configuration of each process node; for the model nodes to be configured, the model configuration module configures the target model and self-maintenance strategy for each model node to be configured according to the sub-evaluation tasks corresponding to each model node to be configured, and the sub-evaluation tasks of the model node can be processed through the target model. Since the target model can be obtained only through simple configuration, there is no need to use the corresponding model interface document for configuration of each model node to be configured, which effectively reduces the amount of manual processing. , which improves the efficiency of configuration and reduces the possibility of human errors accordingly, so the accuracy of configuration can be improved. In addition, since the self-maintenance strategy is configured in the model node to be configured, it provides a guarantee for the operation of subsequent business processes, which is convenient for improving the operation stability of business processes. For the decision nodes to be configured, through the strategy configuration module, according to the sub-decision tasks corresponding to each decision node to be configured, a decision strategy corresponding to the sub-decision task is configured for each decision node, so that each decision node can use the decision strategy to execute its own sub-decision task; after completing the configuration of multiple process nodes to be configured, the configured business process is generated, so that the business process can be used to process various approval requests.

[0153] In a fourth aspect, an embodiment of the present application provides a business processing device.

[0154] Fig. 9 A block diagram of a business processing device provided in an embodiment of the present application.

[0155] Reference Fig. 9 , an embodiment of the present application provides a business processing device, and the business processing device 900 may include the following modules.

[0156] The acquisition module 901 is used to acquire the data to be approved in response to the approval request sent by the user terminal;

[0157] The approval module 902 is used to input the data to be approved into the business process for approval processing and obtain the approval result.

[0158] Among them, the business process is a process obtained through the business process configuration method of any one of the embodiments of the present application.

[0159] In some optional implementations, the business process includes at least one model node and at least one decision node; wherein the model node is used to call the configured target model to process the data input to the model node, obtain a model score, and input the model score to the next adjacent process node, or the model node is used to call the configured target model to obtain auxiliary input parameters, process the data and auxiliary input parameters input to the model node through the target model, obtain a model score, and output the model score to the next adjacent process node; the decision node is used to perform decision processing on the data input to the decision node according to the configured decision strategy, obtain a node decision result, and output the node decision result to the next adjacent process node; the approval result is the result output by the last process node of the approval business process.

[0160] In some optional implementations, when a preset event is triggered during the processing of a model node, a target maintenance operation is performed based on a self-maintenance strategy configured in the model node.

[0161] In some optional implementations, when the self-maintenance strategy includes a fuse strategy, and the preset event is that the number of failures of the model node to call the target model is greater than the fuse number threshold, the target maintenance operation includes setting the target model to a fuse state, and the duration of the fuse state is equal to the fuse duration;

[0162] When the self-maintenance strategy includes a current limiting strategy and the preset event is that the number of call requests of the model node is greater than the call number threshold, the target maintenance operation includes dropping or queuing the call requests that exceed the call number threshold;

[0163] When the self-maintenance strategy includes a downgrade strategy, and the preset event is that the call waiting time of the model node is greater than the call waiting threshold, the target maintenance operation includes adding a downgrade label to the output data of the model node, and the downgrade label is used to initiate a downgrade request to the decision node.

[0164] In some optional implementations, when the data input to the decision node includes a downgrade label, the decision node is used to determine whether to approve the downgrade request of the model node based on the importance level of the sub-evaluation task of the model node that generates the downgrade label.

[0165] In an embodiment of the present application, the acquisition module responds to the approval request sent by the user terminal, obtains the data to be approved, and clarifies the data objects to be processed subsequently; and because the business process has been pre-configured, the data to be approved can be input into the business process for approval through the approval module, so as to obtain the approval result conveniently and accurately, thereby improving the business processing efficiency; in addition, since the model node in the business process is pre-configured with a self-maintenance strategy, even if a preset event is triggered during the operation, the target maintenance operation can still be automatically performed, thereby improving the operation stability of the business process.

[0166] Each module in the above-mentioned business process configuration device or business processing device can be implemented in whole or in part by software, hardware or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each module above.

[0167] In addition, the present application also provides electronic devices and computer-readable storage media, which can be used to implement any business process configuration method or business processing method provided by the present application. The corresponding technical solutions and descriptions are referred to in the corresponding records of the method part and will not be repeated here.

[0168] Fig.10 A block diagram of an electronic device provided in an embodiment of the present application.

[0169] Reference Fig.10 An embodiment of the present application provides an electronic device, which includes: at least one processor 1001; at least one memory 1002, and one or more I / O interfaces 1003, connected between the processor 1001 and the memory 1002; wherein the memory 1002 stores one or more computer programs that can be executed by at least one processor 1001, and the one or more computer programs are executed by at least one processor 1001 so that the at least one processor 1001 can execute the above-mentioned business process configuration method, or business processing method.

[0170] Each module in the above electronic device can be implemented in whole or in part by software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each module.

[0171] The embodiment of the present application also provides a computer-readable storage medium on which a computer program is stored, wherein the computer program implements the above-mentioned business process configuration method or business processing method when executed by a processor / processing core. The computer-readable storage medium can be a volatile or non-volatile computer-readable storage medium.

[0172] An embodiment of the present application also provides a computer program product, including a computer-readable code, or a non-volatile computer-readable storage medium carrying the computer-readable code. When the computer-readable code runs in a processor of an electronic device, the processor in the electronic device executes the above-mentioned business process configuration method, or business processing method.

[0173] It will be appreciated by those skilled in the art that all or some of the steps, systems, and functional modules / units in the methods disclosed above may be implemented as software, firmware, hardware, and appropriate combinations thereof. In a hardware implementation, the division between the functional modules / units mentioned in the above description does not necessarily correspond to the division of physical components; for example, a physical component may have multiple functions, or a function or step may be performed by several physical components in cooperation. Some or all physical components may be implemented as software executed by a processor, such as a central processing unit, a digital signal processor, or a microprocessor, or may be implemented as hardware, or may be implemented as an integrated circuit, such as an application-specific integrated circuit. Such software may be distributed on a computer-readable storage medium, which may include a computer storage medium (or a non-transitory medium) and a communication medium (or a temporary medium).

[0174] As is known to those of ordinary skill in the art, the term computer storage media includes volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable program instructions, data structures, program modules or other data). Computer storage media include, but are not limited to, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), static random access memory (SRAM), flash memory or other memory technology, portable compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical disk storage, magnetic cassettes, magnetic tapes, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to store desired information and can be accessed by a computer. In addition, it is known to those of ordinary skill in the art that communication media typically contain computer-readable program instructions, data structures, program modules or other data in a modulated data signal such as a carrier wave or other transmission mechanism, and may include any information delivery medium.

[0175] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to each computing / processing device, or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network can include copper transmission cables, optical fiber transmissions, wireless transmissions, routers, firewalls, switches, gateway computers, and / or edge servers. The network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in the computer-readable storage medium in each computing / processing device.

[0176] The computer program instructions for performing the operation of the present application can be assembler instructions, instruction set architecture (ISA) instructions, machine instructions, machine-related instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages, such as Smalltalk, C++, etc., and conventional procedural programming languages, such as "C" language or similar programming languages. Computer-readable program instructions can be executed completely on a user's computer, partially on a user's computer, executed as an independent software package, partially on a user's computer, partially on a remote computer, or completely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (for example, using an Internet service provider to connect through the Internet). In some embodiments, by using the state information of a computer-readable program instruction to personalize an electronic circuit, such as a programmable logic circuit, a field programmable gate array (FPGA) or a programmable logic array (PLA), the electronic circuit can execute a computer-readable program instruction, thereby realizing various aspects of the present application.

[0177] The computer program product described herein may be implemented in hardware, software, or a combination thereof. In one optional embodiment, the computer program product is embodied as a computer storage medium, and in another optional embodiment, the computer program product is embodied as a software product, such as a software development kit (SDK), etc.

[0178] Various aspects of the present application are described herein with reference to the flowcharts and / or block diagrams of the methods, devices (systems) and computer program products according to the embodiments of the present application. It should be understood that each box in the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram can be implemented by computer-readable program instructions.

[0179] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, thereby producing a machine, so that when these instructions are executed by the processor of the computer or other programmable data processing device, a device that implements the functions / actions specified in one or more boxes in the flowchart and / or block diagram is generated. These computer-readable program instructions can also be stored in a computer-readable storage medium, and these instructions cause the computer, programmable data processing device, and / or other equipment to work in a specific manner, so that the computer-readable medium storing the instructions includes a manufactured product, which includes instructions for implementing various aspects of the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0180] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device so that a series of operating steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to implement the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0181] The flow chart and block diagram in the accompanying drawings show the possible architecture, function and operation of the system, method and computer program product according to multiple embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a part of a module, program segment or instruction, and a part of the module, program segment or instruction includes one or more executable instructions for realizing the logical function of the specification. In some alternative implementations, the function marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two continuous square boxes can actually be executed substantially in parallel, and they can also be executed in the opposite order sometimes, depending on the function involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be realized by a dedicated hardware-based system that performs the function or action of the specification, or can be realized by a combination of special-purpose hardware and computer instructions.

[0182] Example embodiments have been disclosed herein, and although specific terms are employed, they are used and should be interpreted only in a general illustrative sense and not for limiting purposes. In some instances, it will be apparent to those skilled in the art that, unless otherwise expressly noted, features, characteristics, and / or elements described in conjunction with a particular embodiment may be used alone or in combination with features, characteristics, and / or elements described in conjunction with other embodiments. Therefore, those skilled in the art will appreciate that various changes in form and detail may be made without departing from the scope of the present application as set forth in the appended claims.

Claims

1. A business process configuration method, characterized in that: The method comprises: Generate a business process to be configured according to the processing logic of the approval business, wherein the approval task corresponding to the approval business includes at least one sub-evaluation task and at least one sub-decision task, and the business process to be configured includes a model node to be configured and a decision node to be configured; According to the sub-evaluation task corresponding to the model node to be configured, a target model and a self-maintenance strategy are configured for the model node to be configured, wherein the target model is used to execute the sub-evaluation task, and the self-maintenance strategy is a strategy for executing a target maintenance operation in response to the triggering of a preset event by the model node to be configured during data processing based on the target model; According to the sub-decision task corresponding to the decision node to be configured, a decision strategy corresponding to the sub-decision task is configured for the decision node to be configured.

2. The method according to claim 1, characterized in that The configuring a target model and a self-maintenance strategy for the model node to be configured according to the sub-evaluation task corresponding to the model node to be configured includes: Determining a target model matching the sub-evaluation task from candidate models, wherein the candidate models are used to implement multiple evaluation functions; Configuring the target model to the to-be-configured model node corresponding to the target model; Determine the sub-business type corresponding to the sub-assessment task; According to the sub-service type, a self-maintenance strategy matching the sub-service type is configured in the model node to be configured.

3. The method according to claim 2, characterized in that The configuring the target model to the to-be-configured model node corresponding to the target model includes: Obtaining model configuration data of the target model through a model interface opened by a model registration center; Based on the model configuration data of the target model, a model configuration operation is performed in a to-be-configured model node corresponding to the target model, so that the to-be-configured model node is configured with the corresponding target model.

4. The method according to claim 3, characterized in that The target model performs the sub-evaluation task through a preset target function; The model configuration data includes function configuration parameters and environment configuration parameters. The model configuration operation is used to load the target function into the model node to be configured according to the function configuration parameters, and configure the execution environment of the target function in the model node to be configured according to the environment configuration parameters.

5. The method according to any one of claims 1 to 4, characterized in that: Before configuring the target model and the self-maintenance strategy for the model node to be configured according to the sub-evaluation task corresponding to the model node to be configured, the method further includes: Configuring a corresponding model agent for the model node to be configured, wherein the model agent is used to create an independent model running environment in the model node to be configured; The configuring a target model and a self-maintenance strategy for the model node to be configured according to the sub-evaluation task corresponding to the model node to be configured includes: According to the sub-evaluation task, the target model and the self-maintenance strategy are configured in the model agent of the model node to be configured.

6. The method according to claim 1 or 2, characterized in that: The self-maintenance strategy includes at least one of a fuse strategy, a current limiting strategy and a degradation strategy; Among them, the policy parameters of the circuit breaker strategy include the circuit breaker number threshold and the circuit breaker duration, the policy parameters of the current limiting strategy include the call number threshold, and the policy parameters of the degradation strategy include the call waiting threshold.

7. The method according to claim 1, characterized in that After configuring the target model and the self-maintenance strategy for the model node to be configured according to the sub-evaluation task corresponding to the model node to be configured, the method further includes: In the case of receiving a model change message, determining a candidate update model node corresponding to the model change message, wherein the model change message is a message used to indicate that a candidate model has been changed; In the case where it is determined based on the model change message that the model needs to be reconfigured, the target model in the candidate update model node is reconfigured.

8. A business processing method, characterized in that: include: Responding to the approval request sent by the user terminal, obtaining the data to be approved; Input the data to be approved into the business process for approval and obtain the approval result; The business process is a process obtained by the business process configuration method according to any one of claims 1 to 7.

9. The method according to claim 8, characterized in that The business process includes at least one model node and at least one decision node; The model node is used to call the configured target model to process the data input to the model node to obtain a model score, and input the model score to the next adjacent process node; or, the model node is used to call the configured target model to obtain auxiliary input parameters, and process the data input to the model node and the auxiliary input parameters through the target model to obtain a model score, and output the model score to the next adjacent process node; The decision node is used to perform decision processing on the data input to the decision node according to the configured decision strategy, obtain a node decision result, and output the node decision result to the next adjacent process node; The approval result is the result output by the last process node of the approval business process.

10. The method according to claim 9, characterized in that The method further comprises: When a preset event is triggered during the processing of the model node, a target maintenance operation is performed based on the self-maintenance strategy configured in the model node.

11. The method according to claim 10, characterized in that When the self-maintenance strategy includes a fuse strategy, and the preset event is that the number of failures of the model node to call the target model is greater than the fuse number threshold, the target maintenance operation includes setting the target model to a fuse state, and the duration of the fuse state is equal to the fuse duration; When the self-maintenance strategy includes a current limiting strategy, and the preset event is that the number of call requests of the model node is greater than a call number threshold, the target maintenance operation includes dropping or queuing the call requests that exceed the call number threshold; When the self-maintenance strategy includes a downgrade strategy, and the preset event is that the call waiting time of the model node is greater than the call waiting threshold, the target maintenance operation includes adding a downgrade tag to the output data of the model node, and the downgrade tag is used to initiate a downgrade request to the decision node.

12. The method according to claim 11, characterized in that In the case where the data input to the decision node includes the downgrade label, the decision node is used to determine whether to approve the downgrade request of the model node according to the importance level of the sub-evaluation task of the model node that generates the downgrade label.

13. A business process configuration device, characterized in that: The device comprises: A generation module, used to generate a business process to be configured according to the processing logic of the approval business, wherein the approval task corresponding to the approval business includes at least one sub-evaluation task and at least one sub-decision task, and the business process to be configured includes a model node to be configured and a decision node to be configured; A model configuration module, configured to configure a target model and a self-maintenance strategy for the model node to be configured according to the sub-evaluation task corresponding to the model node to be configured, wherein the target model is used to perform the sub-evaluation task, and the self-maintenance strategy is a strategy for performing a target maintenance operation in response to the triggering of a preset event by the model node to be configured during data processing based on the target model; The strategy configuration module is used to configure the decision strategy corresponding to the sub-decision task for the decision node to be configured according to the sub-decision task corresponding to the decision node to be configured.

14. A service processing device, characterized in that: include: An acquisition module, used to acquire the data to be approved in response to the approval request sent by the user terminal; An approval module is used to input the data to be approved into the business process for approval processing to obtain the approval result; The business process is a process obtained by the business process configuration method according to any one of claims 1 to 7.

15. An electronic device, characterized in that: include: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores one or more computer programs that can be executed by the at least one processor, and the one or more computer programs are executed by the at least one processor so that the at least one processor can execute the business process configuration method described in any one of claims 1 to 7, or the business processing method described in any one of claims 8 to 12.

16. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the computer program implements the business process configuration method according to any one of claims 1 to 7, or the business processing method according to any one of claims 8 to 12.

Images