Service execution method and device, storage medium and electronic equipment

Abstract

The invention discloses a business execution method and device, a storage medium and electronic equipment. The method relates to the field of financial science and technology or other related technical fields, and comprises the following steps: detecting target business information corresponding to a to-be-executed target business; inputting the target service information into a target prediction model to obtain target authorization information corresponding to a target service output by the target prediction model; and under the condition that the target authorization information is used for indicating that the target authorization item passes the authorization check, determining that the target service is allowed to be executed, and executing the target service. Through application of the method and the device, the problem of relatively low efficiency of authorization check of the authorization item required to pass the service execution in the related technology is solved, and the efficiency of authorization check of the authorization item required to pass the service execution is improved.

Description

Technical Field

[0001] This application relates to the field of fintech or other related technical fields. Specifically, it relates to a method and apparatus for executing a service, a storage medium, and an electronic device. Background Art

[0002] In the current business transaction process, after a transaction flows in, the system will, based on historical experience and according to different transaction type configurations, check corresponding authorization check items before different transactions flow in. If the authorization check items fail the check, the transaction will be landed for manual review.

[0003] In related technologies, the check of authorization check items often relies on historical experience. If there are too many authorization check items set, affected by real-time fluctuations of factors such as the system's own performance (memory, CPU (Central Processing Unit), etc.) and network conditions, false alarms are likely to occur, resulting in transactions being landed for manual review and causing waste of business manpower. If there are too few authorization check items set, the risk of missed reports is likely to increase, and effective early warnings cannot be given, and the efficiency of the authorization check for the authorization items required to execute the service is relatively low.

[0004] Aiming at the problem of relatively low efficiency of the authorization check for the authorization items required to execute the service in related technologies, no effective solution has been proposed yet. Summary of the Invention

[0005] The main objective of this application is to provide a method and apparatus for executing a service, a storage medium, and an electronic device, so as to solve the problem of relatively low efficiency of the authorization check for the authorization items required to execute the service in related technologies.

[0006] To achieve the above objective, according to one aspect of this application, a method for executing a service is provided, which is applied to an execution device. The method includes: detecting target service information corresponding to a target service to be executed, where the target service information includes target authorization items required to execute the target service and target authorization data of the target service under the target authorization items; inputting the target service information into a target prediction model to obtain target authorization information corresponding to the target service output by the target prediction model, where the target authorization information is used to indicate whether the target authorization items pass the authorization check, and the target prediction model is obtained by training an initial prediction model with sample service information labeled with sample authorization information; and when the target authorization information is used to indicate that all the target authorization items pass the authorization check, determining to allow the execution of the target service and executing the target service.

[0007] In an exemplary embodiment, the execution device includes a controller and a data acquisition module. The controller is connected to the data acquisition module. The data acquisition module is used to connect to a data lake, and the data lake is used to store business information of the business to be executed. Detecting the target business information corresponding to the target business to be executed includes: controlling, by the controller, the data acquisition module to extract the initial business information corresponding to the target business from the data lake, where the initial business information is used to indicate the initial authorization items corresponding to the target business and the initial authorization data of the target business under the initial authorization items; and determining the target business information according to the initial business information.

[0008] In an exemplary embodiment, a data preprocessing module is further deployed in the execution device. The controller is connected to the data preprocessing module. Determining the target business information according to the initial business information includes: generating, by the controller, a preprocessing request, where the preprocessing request is used to request to perform a preprocessing operation on the initial business information; sending the preprocessing request to the data preprocessing module, and receiving, as the target business information, the processing result returned by the data preprocessing module in response to the preprocessing request, where the data preprocessing module is used to execute the preprocessing request.

[0009] In an exemplary embodiment, after sending the preprocessing request to the data preprocessing module, the method further includes: extracting the target authorization items from the initial authorization items, and screening the target authorization data from the initial authorization data; and / or, screening a set of authorization items from the initial authorization items, and screening the authorization data corresponding to each authorization item in the set of authorization items from the initial authorization data to obtain a set of authorization data; performing a target operation on the first authorization data corresponding to the first authorization item and the second authorization data corresponding to the second authorization item to obtain the third authorization data corresponding to the third authorization item, where the target authorization data includes the third authorization data, the set of authorization items includes the first authorization item and the second authorization item, and performing a target operation on the first authorization data corresponding to the first authorization item and the second authorization data corresponding to the second authorization item includes: performing an addition operation on the first authorization data and the second authorization data, and / or, performing a subtraction operation on the first authorization data and the second authorization data, and / or, performing a multiplication operation on the first authorization data and the second authorization data, and / or, performing a division operation on the first authorization data and the second authorization data.

[0010] In an exemplary embodiment, the step of inputting the target service information into the target prediction model to obtain the target authorization information corresponding to the target service output by the target prediction model includes: detecting a first similarity between the target authorization item and the reference authorization item of the executed reference service, and detecting a second similarity between the target authorization data and the reference authorization data of the reference service under the reference authorization item, where the reference authorization item and the reference authorization data pass the authorization check; in the case where the first similarity is greater than or equal to the first similarity threshold and the second similarity is greater than or equal to the second similarity threshold, generating a first identifier corresponding to the target service, where the target authorization information includes the first identifier, and the first identifier is used to indicate that the target authorization item passes the authorization check.

[0011] In an exemplary embodiment, before inputting the target service information into the target prediction model to obtain the target authorization information corresponding to the target service output by the target prediction model, the method further includes: inputting the sample service information into the initial prediction model to obtain the first candidate authorization information corresponding to the sample service output by the initial prediction model, where the sample service information includes the sample authorization item passed by the executed sample service and the sample authorization data of the sample service under the sample authorization item; performing a quotient operation on the first quantity of the first authorization information and the second quantity of the sample authorization information to obtain a first ratio, where the first authorization information is the authorization information that is the same as the sample authorization information in the first candidate authorization information; in the case where the first ratio is greater than or equal to the ratio threshold, determining the initial prediction model as the target prediction model.

[0012] In an exemplary embodiment, in the case where the first ratio is less than the ratio threshold, the method further includes: adjusting the model parameters of the initial prediction model to obtain a candidate prediction model; inputting the candidate service information into the candidate prediction model to obtain the second candidate authorization information corresponding to the candidate service output by the candidate prediction model, where the candidate service information is the service information corresponding to the executed candidate service, and the candidate service information includes the candidate authorization item passed by the candidate service and the candidate authorization data of the candidate service under the candidate authorization item; performing a quotient operation on the third quantity of the second authorization information and the fourth quantity of the candidate authorization information to obtain a second ratio, where the second authorization information is the authorization information that is the same as the candidate authorization information in the second candidate authorization information; in the case where the second ratio is greater than or equal to the ratio threshold, ending the training and determining the candidate prediction model as the target prediction model.

[0013] To achieve the above object, according to another aspect of the present application, there is provided an execution device for a service, which is applied to an execution device. The device includes: a detection module, configured to detect target service information corresponding to a target service to be executed, where the target service information includes a target authorization item required to execute the target service and target authorization data of the target service under the target authorization item; a first input module, configured to input the target service information into a target prediction model to obtain target authorization information corresponding to the target service output by the target prediction model, where the target authorization information is used to indicate whether the target authorization item passes an authorization check, and the target prediction model is obtained by training an initial prediction model using sample service information labeled with sample authorization information; a first processing module, configured to determine to allow execution of the target service and execute the target service when the target authorization information is used to indicate that all target authorization items pass the authorization check.

[0014] In an embodiment of the present application, in order to quickly determine whether the authorization check for a target service passes, the target service information is input into a target prediction model to obtain target authorization information corresponding to the target service output by the target prediction model, so as to automatically determine whether the authorization check passes, thereby realizing the efficient automation of the service execution process, significantly improving the speed of service processing, and at the same time improving the efficiency of the authorization check for the authorization items required for executing the service, the accuracy of business transaction risk warning, and the warning efficiency of business transaction risks, and solving the technical problem of low efficiency of the authorization check for the authorization items required for executing the service. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] The accompanying drawings constituting a part of the present application are used to provide a further understanding of the present application. The schematic embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation to the present application. In the drawings:

[0016] Figure 1 A hardware structure block diagram of a computer terminal for implementing a service execution method is shown;

[0017] Figure 2 It is a flowchart of a service execution method provided by an embodiment of the present application;

[0018] Figure 3 It is a structure block diagram of an optional execution device according to an embodiment of the present application;

[0019] Figure 4 It is a specific working flowchart of an optional service execution method according to an embodiment of the present application;

[0020] Figure 5 It is a schematic diagram of a service execution device provided by an embodiment of the present application;

[0021] Figure 6 It is a block diagram of a structure of an electronic device according to an embodiment of the present application. Detailed implementation manners

[0022] In order to enable those skilled in the art to better understand the solution of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

[0023] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily need to be used to describe a specific order or sequence. It should be understood that such used data can be interchanged under appropriate circumstances so that the embodiments of the present application described here can be implemented in an order different from those illustrated or described here. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device including a series of steps or units does not necessarily need to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0024] It should be noted that the information collected in the present application (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for display, data for analysis, etc.) are information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application and other processing of the relevant data all comply with relevant laws, regulations and standards, take necessary confidentiality measures, do not violate public order and good customs, and provide corresponding operation entrances for users to choose to authorize or refuse. For example, an interface is set between the present system and relevant users or institutions to provide corresponding operation entrances for users to choose to agree or refuse the automated decision-making results; if the user chooses to refuse, the expert decision-making process will be entered.

[0025] Embodiment 1

[0026] According to an embodiment of the present application, an embodiment of a method for executing a service is also provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that here.

[0027] The method embodiment provided in the first embodiment of this application can be executed on a mobile terminal, a computer terminal, or a similar computing device. Figure 1 The following shows a hardware block diagram of a computer terminal (or mobile device) for implementing an execution method of a service. As Figure 1 shown, the computer terminal 10 (or mobile device) may include one or more processors 102 (illustrated as 102a, 102b,..., 102n in the figure) (the processor 102 may include, but is not limited to, a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory 104 for storing data, and a transmission device 106 for communication functions. In addition, it may further include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports in the BUS bus), a network interface, a power supply, and / or a camera. Those of ordinary skill in the art can understand that Figure 1 the structure shown is only illustrative and does not limit the structure of the above-mentioned electronic device. For example, the computer terminal 10 may further include more or fewer components than Figure 1 shown, or have a different configuration from Figure 1 shown.

[0028] It should be noted that the above one or more processors 102 and / or other data processing circuits are generally referred to as "data processing circuits" in this article. The data processing circuit may be embodied in whole or in part as software, hardware, firmware, or any other combination. In addition, the data processing circuit may be a single independent processing module, or be incorporated in whole or in part into any one of the other elements in the computer terminal 10 (or mobile device). As involved in the embodiments of this application, the data processing circuit is a kind of processor control (such as the selection of a variable resistance terminal path connected to an interface).

[0029] The memory 104 can be used to store software programs and modules of application software, such as the program instructions / data storage devices corresponding to the service execution method in the embodiments of this application. The processor 102 executes various functional applications and data processing by running the software programs and modules stored in the memory 104, that is, implements the above-mentioned service execution method. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memories, or other non-volatile solid-state memories. In some instances, the memory 104 may further include a memory remotely set relative to the processor 102, and these remote memories can be connected to the computer terminal 10 through a network. Examples of the above network include, but are not limited to, the Internet, an enterprise intranet, a local area network, a mobile communication network, and combinations thereof.

[0030] The transmission device 106 is used to receive or send data via a network. Specific examples of the above network may include a wireless network provided by the communication provider of the computer terminal 10. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a Radio Frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0031] The display can be, for example, a touch-screen liquid crystal display (LCD), which enables the user to interact with the user interface of the computer terminal 10 (or mobile device).

[0032] Under the above operating environment, this application provides an execution method for the service as shown in Figure 2 the following. Figure 2 It is a flowchart of the execution method of the service according to Embodiment 1 of this application.

[0033] Step S202, detect the target service information corresponding to the target service to be executed, where the target service information includes the target authorization item required to execute the target service and the target authorization data of the target service under the target authorization item;

[0034] Step S204, input the target service information into the target prediction model, and obtain the target authorization information corresponding to the target service output by the target prediction model, where the target authorization information is used to indicate whether the target authorization item passes the authorization check, and the target prediction model is obtained by training an initial prediction model using sample service information labeled with sample authorization information;

[0035] Step S206, when the target authorization information is used to indicate that all the target authorization items pass the authorization check, determine to allow the execution of the target service, and execute the target service.

[0036] In the technical solution provided in the above step S202, the initial service information can be extracted through, but not limited to, a data acquisition module, and the target service information can be determined through, but not limited to, a data preprocessing module according to the initial service information.

[0037] Optionally, in this embodiment, the service to be executed can be, but not limited to, a service in the financial field or a service in other fields, for example, a service executed on an application, etc.

[0038] In an exemplary embodiment, the execution device includes a controller and a data acquisition module. The controller is connected to the data acquisition module. The data acquisition module is used to connect to a data lake, and the data lake is used to store business information of a business to be executed. The target business information corresponding to the target business to be executed can be detected in the following ways, but is not limited thereto: The controller controls the data acquisition module to extract the initial business information corresponding to the target business from the data lake. The initial business information is used to indicate the initial authorization items corresponding to the target business and the initial authorization data of the target business under the initial authorization items. The target business information is determined according to the initial business information.

[0039] Optionally, in this embodiment, the controller can be used to control operation requests of various modules deployed in the execution device, such as a data acquisition module, a data preprocessing module, a feature selection module, etc., but is not limited thereto. For example, the controller can include, but is not limited to, a BMC (Baseboard Management Controller) and an FPGA (Field-Programmable Gate Array), etc.

[0040] Optionally, in this embodiment, the controller can be used to control the data acquisition module to extract the initial business information corresponding to the target business, including: generating an extraction request through the controller, where the extraction request is used to request the extraction of the initial business information; sending the extraction request to the data acquisition module, and extracting the initial business information extracted by the data acquisition module from the data lake in response to the extraction request. The data acquisition module is used to extract the initial business information corresponding to the target business from the business information stored in the data lake in response to the received extraction request.

[0041] Optionally, in this embodiment, the initial authorization items can include, but are not limited to, authorization items related to business transactions. For example, the initial authorization items can include, but are not limited to, business categories, business types, amounts, currencies, trading dates, settlement dates, buy / sell directions, etc.

[0042] Through the embodiments of the present application, the data acquisition module realizes the automatic extraction of the initial business information of the business to be executed from the data lake, ensures the timeliness and accuracy of the data, reduces errors that may be introduced by manual operations, and at the same time speeds up the business processing speed.

[0043] In an exemplary embodiment, a data preprocessing module is further deployed in the execution device. The controller is connected to the data preprocessing module. According to the initial service information, the target service information can be determined in, but not limited to, the following manner: generating a preprocessing request through the controller, where the preprocessing request is used to request to perform a preprocessing operation on the initial service information; sending the preprocessing request to the data preprocessing module and receiving the processing result returned by the data preprocessing module in response to the preprocessing request as the target service information, where the data preprocessing module is used to execute the preprocessing request.

[0044] Optionally, in this embodiment, a feature selection module is further deployed in the execution device. The controller is connected to the feature selection module. According to the initial service information, the target service information can be determined in, but not limited to, the following manner: generating a feature selection request through the controller, where the feature selection request is used to request to perform a feature selection operation on the initial service information after executing the preprocessing request; sending the feature selection request to the feature selection module and receiving the processing result returned by the feature selection module in response to the feature selection request as the target authorization item of the target service information, where the feature selection module is used to execute the feature selection request.

[0045] Optionally, in this embodiment, the feature selection request can include, but is not limited to: a request to perform a normalization operation on the initial service information; a request to perform a dimensionality reduction operation on the initial service information; a request to perform a partitioning operation on the initial service information; a request to perform a cross-validation operation on the initial service information.

[0046] Optionally, in this embodiment, the feature selection request can include, but is not limited to, a request to perform a normalization operation on the initial service information. The normalization operation can, but is not limited to, convert all numerical features to the same range through a normalization technique (such as min / max normalization, etc.). For example, all numerical features are converted to the interval [0, 1]. The feature selection request can include, but is not limited to, a request to perform a dimensionality reduction operation on the initial service information. The dimensionality reduction operation can, but is not limited to, include using a dimensionality reduction method, such as principal component analysis, etc., to reduce the number of feature items (equivalent to the target authorization item).

[0047] Optionally, in this embodiment, the feature selection request can include, but is not limited to, a request to perform a partitioning operation on the initial service information. The partitioning operation can, but is not limited to, randomly partition the data set into a training set, a validation set, and a test set according to a ratio of 6:2:2. The training set can be used, but is not limited to, for training the initial prediction model. The validation set can be used, but is not limited to, for hyperparameter tuning and preventing overfitting during the training process of the initial prediction model. The test set can be used, but is not limited to, for finally evaluating the performance of the target prediction model.

[0048] Through the embodiments of the present application, the data preprocessing module can process and optimize the original initial business information, improve the efficiency of data processing, and further ensure the reliability of business risk warning.

[0049] In an exemplary embodiment, after sending the preprocessing request to the data preprocessing module, it may but is not limited to: extracting the target authorization item from the initial authorization items, and screening the target authorization data from the initial authorization data; and / or, screening a set of authorization items from the initial authorization items, and screening the authorization data corresponding to each authorization item in the set of authorization items from the initial authorization data to obtain a set of authorization data; performing a target operation on the first authorization data corresponding to the first authorization item and the second authorization data corresponding to the second authorization item to obtain the third authorization data corresponding to the third authorization item, where the target authorization data includes the third authorization data, the set of authorization items includes the first authorization item and the second authorization item, and the performing a target operation on the first authorization data corresponding to the first authorization item and the second authorization data corresponding to the second authorization item includes: performing an addition operation on the first authorization data and the second authorization data, and / or, performing a subtraction operation on the first authorization data and the second authorization data, and / or, performing a multiplication operation on the first authorization data and the second authorization data, and / or, performing a division operation on the first authorization data and the second authorization data.

[0050] Optionally, in this embodiment, performing a division operation on the first authorization data and the second authorization data may but is not limited to: dividing the first authorization data by the second authorization data, or dividing the second authorization data by the first authorization data; performing an addition operation on the first authorization data and the second authorization data may but is not limited to: adding the first authorization data and the second authorization data; performing a subtraction operation on the first authorization data and the second authorization data may but is not limited to: subtracting the second authorization data from the first authorization data, or subtracting the first authorization data from the second authorization data; performing a multiplication operation on the first authorization data and the second authorization data may but is not limited to: multiplying the first authorization data and the second authorization data.

[0051] Optionally, in this embodiment, it may but is not limited to performing only any one of the addition, subtraction, multiplication, and division operations on the first authorization data and the second authorization data. As an optional example, it may but is not limited to taking the first authorization item including the settlement date and the second authorization item including the trading date as an example, subtracting the trading date from the settlement date to obtain the trading cycle. Or, a combination of operations can be performed, making any combination of the addition, subtraction, multiplication, and division operations, and performing mathematical operations on the first authorization data and the second authorization data.

[0052] Through the embodiments of the present application, by screening and calculating the authorized items and authorized data, the integrity and pertinence of business information are ensured, interference from irrelevant information is avoided, and the accuracy and response speed of model prediction are improved.

[0053] In the technical solution provided in step S204 above, it is possible but not limited to regularly update and maintain the sample business information. For example, it is possible but not limited to record the newly executed business in the sample business information, or re-label the existing sample authorized information when factors affecting whether the authorization check passes, such as business rules or market conditions, change.

[0054] In an exemplary embodiment, the target business information may be input into the target prediction model in the following ways, but not limited to this, to obtain the target authorization information corresponding to the target business output by the target prediction model: detecting the first similarity between the target authorized item and the reference authorized item of the executed reference business, and detecting the second similarity between the target authorized data and the reference authorized data of the reference business under the reference authorized item, where the reference authorized item and the reference authorized data pass the authorization check; in the case where the first similarity is greater than or equal to the first similarity threshold and the second similarity is greater than or equal to the second similarity threshold, generating a first identifier corresponding to the target business, where the target authorization information includes the first identifier, and the first identifier is used to indicate that the target authorized item passes the authorization check.

[0055] Optionally, in this embodiment, in the case where the first similarity is less than or equal to the first similarity threshold and / or the second similarity is less than the second similarity threshold, a second identifier corresponding to the target business is generated, where the target authorization information includes the second identifier, and the second identifier is used to indicate that the target authorized item fails the authorization check.

[0056] Optionally, in this embodiment, the first similarity threshold and the second similarity threshold may be, but not limited to, preset in advance. The first similarity may be, but not limited to, used to detect the similarity degree between the target authorized item and the reference authorized item of the executed reference business, and the second similarity may be, but not limited to, used to detect the similarity degree between the target authorized data and the reference authorized data of the reference business under the reference authorized item.

[0057] Optionally, in this embodiment, the first similarity threshold and the second similarity threshold may be, but not limited to, dynamically adjusted. For example, the first similarity threshold may be increased, decreased, or kept unchanged, and / or the second similarity threshold may be increased, decreased, or kept unchanged.

[0058] Through the embodiments of the present application, through similarity detection, the adaptability and accuracy of the prediction model are improved, the risk of misjudgment is reduced, and the stability and security of business authorization inspection are enhanced.

[0059] In an exemplary embodiment, before inputting the target business information into the target prediction model to obtain the target authorization information corresponding to the target business output by the target prediction model, it may but is not limited to be done in the following manner: Input the sample business information into the initial prediction model to obtain the first candidate authorization information corresponding to the sample business information output by the initial prediction model, where the sample business information includes the sample authorization items passed by the executed sample business and the sample authorization data of the sample business under the sample authorization items; Perform a quotient operation on the first quantity of the first authorization information and the second quantity of the sample authorization information to obtain a first ratio, where the first authorization information is the authorization information in the first candidate authorization information that is the same as the sample authorization information; In the case where the first ratio is greater than or equal to the ratio threshold, determine the initial prediction model as the target prediction model.

[0060] Optionally, in this embodiment, a batch estimation module is also deployed in the execution device, and the controller is connected to the batch estimation module. After inputting the target business information into the target prediction model: It may but is not limited to be done by the controller calling the batch estimation module to perform parallel processing on at least one batch of target business information data sets, where the data set contains multiple target business information to be executed; The batch estimation module applies the target prediction model to generate a batch estimation result set containing target authorization information, where the batch estimation result set contains multiple target authorization information corresponding to multiple target businesses in the target business information data set.

[0061] Through the embodiments of the present application, by enabling the prediction model to be fully trained and verified, the performance of the prediction model can be continuously optimized, the accuracy of the prediction results is ensured, the business risk is reduced, and the intelligent level of the business process is improved.

[0062] In an exemplary embodiment, when the first ratio is less than the ratio threshold, it is possible but not limited to adjust the model parameters of the initial prediction model to obtain a candidate prediction model; input the candidate service information into the candidate prediction model to obtain the second candidate authorization information corresponding to the candidate service output by the candidate prediction model, where the candidate service information is the service information corresponding to the executed candidate service, and the candidate service information includes the candidate authorization items passed by the candidate service and the candidate authorization data of the candidate service under the candidate authorization items; perform a quotient operation on the third quantity of the second authorization information and the fourth quantity of the candidate authorization information to obtain a second ratio, where the second authorization information is the authorization information in the second candidate authorization information that is the same as the candidate authorization information; when the second ratio is greater than or equal to the ratio threshold, end the training and determine the candidate prediction model as the target prediction model.

[0063] Optionally, in this embodiment, it is possible but not limited to first determine the model parameters to be adjusted, then determine the adjustment direction of the model parameters, and then determine the adjustment granularity. For example, starting from the maximum value of the model parameters, first reduce the model parameters by 0.1, detect the accuracy of the model prediction after adjustment. If the accuracy of the model prediction after adjustment is improved, it is determined that the adjustment direction of the model parameters is to reduce the model parameters. In such a case, continue to decrease the model parameters while gradually reducing the adjustment granularity. For example, adjust the granularity from 0.1 to 0.01 until the second ratio is greater than or equal to the ratio threshold, and then end the training.

[0064] Through the embodiments of the present application, by dynamically adjusting the model parameters, the accuracy and effectiveness of the prediction model are improved, ensuring that the prediction model can operate stably in the actual environment.

[0065] In the technical solution provided in step S206 above, when the target authorization information is used to indicate that any one of the authorization checks for the target authorization item fails, it is determined that the target service is not allowed to be executed, and a warning message is generated.

[0066] Optionally, in this embodiment, Figure 3 is a structural block diagram of an optional execution device according to an embodiment of the present application, as Figure 3As shown, the execution device may but is not limited to include a controller, a data acquisition module, a data preprocessing module, a feature selection module, a prediction model, and a batch estimation module. The controller may but is not limited to be connected to the data acquisition module, the data preprocessing module, the feature selection module, the prediction model, and the batch estimation module. The data acquisition module may but is not limited to be connected to the data preprocessing module. The data preprocessing module may but is not limited to be connected to the feature selection module. The feature selection module may but is not limited to be connected to the prediction model. The prediction model may but is not limited to be connected to the batch estimation module.

[0067] Through the embodiments of the present application, in view of the disadvantages of the existing authorization check item monitoring provided based on business experience, to solve the problem that the traditional method cannot solve the numerous pre-trade inspections before the transaction inflow, a financial market transaction risk early warning model (equivalent to the target prediction model) based on the particle swarm optimization algorithm is provided, which improves the timeliness of the transaction inflow and effectively reduces the operation and maintenance cost of the business, and avoids the possible high-definition calculation risk.

[0068] To better understand the working process of the business execution method in the embodiments of the present application, the following will explain and illustrate the working process of the business execution method in the embodiments of the present application in combination with optional embodiments, which may but is not limited to be applicable to the embodiments of the present application.

[0069] The financial market transaction is transmitted from the first system to the second system for post-transaction processing. Among them, the first system is used for the front-end management and business process control of the financial market transaction, and the second system is used for the back-end processing of the transaction order and market operation. The main process is as follows: After checking the integrity of the transaction, it is connected for processing. The transaction that fails the check enters the 'to-do task list', and the exception event is redone or ignored; after accessing the financial market transaction, according to the setting of the 'authorization check parameter', the financial market transaction is subjected to authorization check, and the transaction that passes the authorization check is subjected to manual or automatic authorization processing according to the 'workflow review number configuration rule'; after the transaction is authorized, the system generates accounting entries and cash / bond flows according to the 'accounting parameter' and 'payment and receipt flow generation rule', and sends a transaction confirmation for transaction confirmation matching; the system confirms the transaction cash / bond flow according to the transaction confirmation matching result, 'clearing flow confirmation rule', 'workflow review number', etc., updates the position information, and generates a transaction clearing and settlement message according to the 'clearing routing rule' to complete the clearing and settlement processing; at the end of the day, the accounting situation of the financial market transaction is accounted and managed. Among them, according to the setting of the 'authorization check parameter', the specific process of subjecting the financial market transaction to authorization check and subjecting the transaction that passes the authorization check to automatic authorization processing according to the 'workflow review number configuration rule' is as follows:

[0070] Figure 4It is a specific flowchart of an execution method for an optional service according to an embodiment of the present application. As Figure 4 shown, the process of automatically authorizing a transaction may but is not limited to include:

[0071] Step 1: The data acquisition module forms an original transaction data file (equivalent to business information) from the transaction data in the data lake (business category, business type, amount, currency, transaction date, settlement date, transaction cycle, buy / sell direction, whether authorization check passes flag, etc.). Through a query statement, the transaction data in the data lake (such as data on business category, business type, amount, currency, transaction date, settlement date, buy / sell direction, etc.) is cleaned, and then the cleaned transaction data file is passed to the data preprocessing module in the server-side (equivalent to the execution device) for the next data preprocessing. It should be noted that Figure 4 it can be but is not limited to taking the transaction data including amount, currency, business category, and settlement date as an example for explanation and illustration.

[0072] Step 2: Data preprocessing and marking (equivalent to the data preprocessing module) further performs combination and discretization processing on the transaction data file obtained through the data acquisition module. Specifically, in different transaction data items (equivalent to initial authorization items), one or more key index items are selected or fitted, and distinguished according to business-related knowledge: according to the business category, the data is classified into types such as bonds, financing, foreign exchange, derivatives, etc.; according to the date range, the settlement date of the data minus the transaction date to obtain the transaction cycle; according to the buy / sell direction, items such as borrowing, lending, buying, and selling are unified, etc.; encoded through a dictionary or one-hot (one-hot encoding) method, and the labels are marked, thereby forming an initial data set, including feature items (such as feature items such as business category, business type, amount, currency, transaction cycle, and buy / sell direction, equivalent to target authorization items), category items (whether authorization check passes flag), so as to further form an initial data set and obtain a training data set that can be used for machine learning.

[0073] Step 3: The feature selection module normalizes and reduces the dimension of the training data set that has been formed in Step 2, and discretizes it into a training set, a test set, and a validation set according to a ratio of 6:2:2, and performs cross-validation.

[0074] Step 4: Use the training set and the validation set to train a prediction model according to the pre-selected particle swarm algorithm. The specific operations include: after configuring the relevant algorithm on the big data platform, obtaining data from the test environment, inputting the historical data training set obtained through preprocessing into the early warning algorithm model, and performing model debugging, adjusting the inertia weight, starting from w = 1, linearly decreasing, and at the same time, it can be but is not limited to fine-tuning the learning factor c by an amplitude of 0.1 1 = c 2= 2, thereby updating the model and training an estimation model with specific adaptation parameters.

[0075] As an optional embodiment, the particle swarm optimization algorithm is inspired by the activities of bird flocks. By sharing information among individuals in the group, the movement of the entire group evolves from disorder to order in the problem-solving space, thereby obtaining the optimal solution. The particle swarm optimization algorithm is an iterative optimization algorithm. The system is initialized with a set of random solutions and searches for the optimal value through iteration. The particle swarm optimization algorithm is initialized with a group of random particles (random solutions), and then the optimal solution is found through iteration. In each iteration, the particles update themselves by tracking two "extremes" (pbest, gbest). After finding these two optimal values, the particles update their velocities and positions using the following formulas (1) and (2).

[0076]

[0077] Among them, w is the inertia weight factor, V i k is the velocity of the i-th particle in the k-th iteration, V i k+1 is the velocity of the i-th particle in the (k + 1)-th iteration, is the position of the i-th particle in the k-th iteration, is the position of the i-th particle in the (k + 1)-th iteration, c 1 and c 2 are learning factors, usually taking c 1 = c 2 = 2, is the individual historical optimal position of the i-th particle in the k-th iteration, is the group historical optimal position of the entire particle swarm in the k-th iteration, r 1 and r 2 are random factors, usually random numbers between 0 and 1. The essence of the particle swarm optimization algorithm is to use these three pieces of information: the current position, the global extreme value, and the individual extreme value, to guide the particles to find the next iterative position. The key to the excellent characteristics of the particle swarm optimization algorithm is that individuals make full use of their own experience and group experience to adjust their own states.

[0078] Step 5: Use the test set to evaluate the trained prediction model (equivalent to the target prediction model) to verify the model accuracy. And subsequently, through configuring unified batch scheduling (equivalent to the batch estimation module), real-time estimate transaction data, obtain classification through feature item estimation. If the estimated classification item is an identifier indicating that the authorization check fails (equivalent to the second identifier), then form a warning to prompt that the business has a liquidation risk and assist the business in better concluding transactions.

[0079] Through the embodiments of the present application, a financial market trading risk warning model (equivalent to the target prediction model) based on the particle swarm optimization algorithm is provided. By independently developing multiple functional modules such as data collection, data preprocessing and marking (equivalent to the data preprocessing module), feature selection, particle swarm algorithm, and batch estimation, after basic cleaning of historical data, a series of processing actions such as historical data marking, data preprocessing, feature selection, particle swarm algorithm, and batch estimation are carried out, and finally the risk identification of transactions is realized. It well solves the problems of false alarms or excessive alarms caused by excessive authorization item checks before transaction inflow, as well as the lack of monitoring after inflow, reduces the labor cost of the business, improves the accuracy and effectiveness of system alarms, and reduces the possible high-precision calculation risks.

[0080] The method for executing the service provided by the embodiments of the present application, in order to quickly determine whether the authorization check of the target service passes, by inputting the target service information into the target prediction model, obtaining the target authorization information corresponding to the target service output by the target prediction model, realizes the automatic determination of whether the authorization check passes, thereby realizes the efficient automation of the service execution process, significantly improves the speed of service processing, and at the same time improves the efficiency of the authorization check for the authorization items required for executing the service, the accuracy of business transaction risk warning, and the warning efficiency of business transaction risks, and further solves the technical problem of the low efficiency of the authorization check for the authorization items required for executing the service.

[0081] It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a different order than here.

[0082] Embodiment 2

[0083] The embodiments of the present application also provide an execution device for a service. It should be noted that the execution device for the service in the embodiments of the present application can be used to execute the method for executing the service provided by the embodiments of the present application. The following introduces the execution device for the service provided by the embodiments of the present application.

[0084] According to the embodiments of the present application, there is also provided a device for implementing the above-mentioned method for executing a service, as Figure 5 shown, applied to an execution device, the device includes:

[0085] A detection module 502, configured to detect target service information corresponding to a target service to be executed, where the target service information includes target authorization items required for executing the target service and target authorization data of the target service under the target authorization items;

[0086] A first input module 504 is configured to input the target service information into a target prediction model, and obtain target authorization information corresponding to the target service output by the target prediction model. The target authorization information is used to indicate whether the target authorization item passes an authorization check. The target prediction model is obtained by training an initial prediction model using sample service information annotated with sample authorization information.

[0087] A first processing module 506 is configured to, when the target authorization information is used to indicate that all target authorization items pass the authorization check, determine that the execution of the target service is allowed, and execute the target service.

[0088] For the service execution device provided in the embodiments of the present application, in order to quickly determine whether the authorization check of the target service passes, by inputting the target service information into the target prediction model and obtaining the target authorization information corresponding to the target service output by the target prediction model, it realizes the automatic determination of whether the authorization check passes, thereby realizing the efficient automation of the service execution process, significantly improving the speed of service processing, and at the same time improving the efficiency of the authorization check for the authorization items required for executing the service, the accuracy of business transaction risk warning, and the warning efficiency of business transaction risks, and further solving the technical problem of low efficiency of the authorization check for the authorization items required for executing the service.

[0089] In an exemplary embodiment, the execution device includes a controller and a data acquisition module. The controller is connected to the data acquisition module. The data acquisition module is configured to connect to a data lake, and the data lake is used to store service information of services to be executed. The detection module includes:

[0090] An extraction unit is configured to control, through the controller, the data acquisition module to extract initial service information corresponding to the target service from the data lake. The initial service information is used to indicate initial authorization items corresponding to the target service and initial authorization data of the target service under the initial authorization items.

[0091] A determination unit is configured to determine the target service information according to the initial service information.

[0092] In an exemplary embodiment, a data preprocessing module is further deployed in the execution device. The controller and the data preprocessing module, the determination unit is configured to:

[0093] Generate a preprocessing request through the controller, where the preprocessing request is used to request to perform a preprocessing operation on the initial service information.

[0094] Send the preprocessing request to the data preprocessing module, and receive the processing result returned by the data preprocessing module in response to the preprocessing request as the target service information, where the data preprocessing module is used to execute the preprocessing request.

[0095] In an exemplary embodiment, the apparatus further includes:

[0096] A second processing module, configured to extract the target authorization item from the initial authorization items and screen the target authorization data from the initial authorization data after sending the preprocessing request to the data preprocessing module;

[0097] And / or, a screening module, configured to screen a set of authorization items from the initial authorization items, and screen the authorization data corresponding to each authorization item in the set of authorization items from the initial authorization data to obtain a set of authorization data; perform a target operation on the first authorization data corresponding to the first authorization item and the second authorization data corresponding to the second authorization item to obtain the third authorization data corresponding to the third authorization item, where the target authorization data includes the third authorization data, the set of authorization items includes the first authorization item and the second authorization item, and the performing the target operation on the first authorization data corresponding to the first authorization item and the second authorization data corresponding to the second authorization item includes: performing a sum operation on the first authorization data and the second authorization data, and / or, performing a difference operation on the first authorization data and the second authorization data, and / or, performing a product operation on the first authorization data and the second authorization data, and / or, performing a quotient operation on the first authorization data and the second authorization data.

[0098] In an exemplary embodiment, the first input module includes:

[0099] A detection unit, configured to detect a first similarity between the target authorization item and the reference authorization item of the executed reference service, and detect a second similarity between the target authorization data and the reference authorization data of the reference service under the reference authorization item, where the reference authorization item and the reference authorization data pass the authorization check;

[0100] A generation unit, configured to generate a first identifier corresponding to the target service when the first similarity is greater than or equal to a first similarity threshold and the second similarity is greater than or equal to a second similarity threshold, where the target authorization information includes the first identifier, and the first identifier is used to indicate that the target authorization item passes the authorization check.

[0101] In an exemplary embodiment, the apparatus further includes:

[0102] A second input module, configured to input the sample service information into the initial prediction model before inputting the target service information into the target prediction model to obtain the target authorization information corresponding to the target service output by the target prediction model, where the sample service information includes the sample authorization items passed by the executed sample service and the sample authorization data of the sample service under the sample authorization items;

[0103] A first execution module, configured to perform a quotient operation on a first quantity of the first authorization information and a second quantity of the sample authorization information to obtain a first ratio, where the first authorization information is the authorization information that is the same as the sample authorization information in the first candidate authorization information;

[0104] A determination module, configured to determine the initial prediction model as the target prediction model when the first ratio is greater than or equal to a ratio threshold.

[0105] In an exemplary embodiment, when the first ratio is less than the ratio threshold, the apparatus further includes:

[0106] An adjustment module, configured to adjust model parameters of the initial prediction model to obtain a candidate prediction model;

[0107] A third input module, configured to input candidate service information into the candidate prediction model to obtain second candidate authorization information corresponding to the candidate service output by the candidate prediction model, where the candidate service information is service information corresponding to an executed candidate service, and the candidate service information includes candidate authorization items passed by the candidate service and candidate authorization data of the candidate service under the candidate authorization items;

[0108] A second execution module, configured to perform a quotient operation on a third quantity of the second authorization information and a fourth quantity of the candidate authorization information to obtain a second ratio, where the second authorization information is the authorization information that is the same as the candidate authorization information in the second candidate authorization information; when the second ratio is greater than or equal to the ratio threshold, end the training and determine the candidate prediction model as the target prediction model.

[0109] It should be noted here that the above detection module 502, first input module 504, and first processing module 506 correspond to steps S202 to S206 in Embodiment 1. The functions of the two modules are the same as those of the corresponding steps in terms of the implemented examples and application scenarios, but are not limited to the content disclosed in Embodiment 1 above. It should be noted that the above modules or units can be hardware components or software components stored in a memory (for example, memory 104) and processed by one or more processors (for example, processors 102a, 102b,..., 102n). The above modules can also be part of a device and can run on the computer terminal 10 provided in Embodiment 1.

[0110] Embodiment 3

[0111] An embodiment of the present application may provide an electronic device. Figure 6 It is a structural block diagram of an electronic device according to an embodiment of the present application. As Figure 6 shown, the electronic device may include: one or more ( Figure 6 only one is shown in the figure) processors 602, a memory 604, a storage controller, and a peripheral interface, where the peripheral interface is connected to a radio frequency module, an audio module, and a display.

[0112] Among them, the memory can be used to store software programs and modules, such as the program instructions / modules corresponding to the methods and devices in the embodiments of the present application. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory, that is, implements the above methods. The memory may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memories, or other non-volatile solid-state memories. In some instances, the memory may further include a memory remotely disposed relative to the processor, and these remote memories may be connected to the terminal through a network. Examples of the above network include but are not limited to the Internet, an enterprise intranet, a local area network, a mobile communication network, and combinations thereof.

[0113] The processor can call the information and application programs stored in the memory through the transmission device to perform the following steps: detecting target service information corresponding to a target service to be executed, where the target service information includes a target authorization item required to execute the target service and target authorization data of the target service under the target authorization item; inputting the target service information into a target prediction model to obtain target authorization information corresponding to the target service output by the target prediction model, where the target authorization information is used to indicate whether the target authorization item passes an authorization check, and the target prediction model is obtained by training an initial prediction model using sample service information annotated with sample authorization information; and determining to allow execution of the target service and executing the target service when the target authorization information is used to indicate that all target authorization items pass the authorization check.

[0114] The processor can also call the information and application programs stored in the memory through the transmission device to perform the following steps: controlling, through the controller, the data acquisition module to extract initial service information corresponding to the target service from the data lake, where the initial service information is used to indicate an initial authorization item corresponding to the target service and initial authorization data of the target service under the initial authorization item; and determining the target service information according to the initial service information.

[0115] The processor can also call the information and application programs stored in the memory through the transmission device to perform the following steps: generating, through the controller, a preprocessing request, where the preprocessing request is used to request a preprocessing operation to be performed on the initial service information; sending the preprocessing request to the data preprocessing module and receiving, as the target service information, a processing result returned by the data preprocessing module in response to the preprocessing request, where the data preprocessing module is used to execute the preprocessing request.

[0116] The processor can also call the information and application programs stored in the memory through the transmission device to perform the following steps: extract the target authorization item from the initial authorization items, and filter the target authorization data from the initial authorization data; and / or, filter a set of authorization items from the initial authorization items, and filter the authorization data corresponding to each authorization item in the set of authorization items from the initial authorization data to obtain a set of authorization data; perform a target operation on the first authorization data corresponding to the first authorization item and the second authorization data corresponding to the second authorization item to obtain the third authorization data corresponding to the third authorization item, where the target authorization data includes the third authorization data, the set of authorization items includes the first authorization item and the second authorization item, and the performing a target operation on the first authorization data corresponding to the first authorization item and the second authorization data corresponding to the second authorization item includes: performing a sum operation on the first authorization data and the second authorization data, and / or, performing a difference operation on the first authorization data and the second authorization data, and / or, performing a product operation on the first authorization data and the second authorization data, and / or, performing a quotient operation on the first authorization data and the second authorization data.

[0117] The processor can also call the information and application programs stored in the memory through the transmission device to perform the following steps: detect a first similarity between the target authorization item and the reference authorization item of the executed reference service, and detect a second similarity between the target authorization data and the reference authorization data of the reference service under the reference authorization item, where the reference authorization item and the reference authorization data pass the authorization check; in the case where the first similarity is greater than or equal to a first similarity threshold and the second similarity is greater than or equal to a second similarity threshold, generate a first identifier corresponding to the target service, where the target authorization information includes the first identifier, and the first identifier is used to indicate that the target authorization item passes the authorization check.

[0118] The processor can also call the information and application programs stored in the memory through the transmission device to perform the following steps: input the sample service information into the initial prediction model to obtain a first candidate authorization information corresponding to the sample service information output by the initial prediction model, where the sample service information includes the sample authorization item passed by the executed sample service and the sample authorization data of the sample service under the sample authorization item; perform a quotient operation on the first quantity of the first authorization information and the second quantity of the sample authorization information to obtain a first ratio, where the first authorization information is the authorization information in the first candidate authorization information that is the same as the sample authorization information; in the case where the first ratio is greater than or equal to a ratio threshold, determine the initial prediction model as the target prediction model.

[0119] The processor can also call the information and application programs stored in the memory through the transmission device to perform the following steps: adjusting the model parameters of the initial prediction model to obtain a candidate prediction model; inputting the candidate service information into the candidate prediction model to obtain the second candidate authorization information corresponding to the candidate service output by the candidate prediction model, where the candidate service information is the service information corresponding to the executed candidate service, and the candidate service information includes the candidate authorization items passed by the candidate service and the candidate authorization data of the candidate service under the candidate authorization items; performing a quotient operation on the third quantity of the second authorization information and the fourth quantity of the candidate authorization information to obtain a second ratio, where the second authorization information is the authorization information in the second candidate authorization information that is the same as the candidate authorization information; and ending the training and determining the candidate prediction model as the target prediction model when the second ratio is greater than or equal to the ratio threshold.

[0120] By adopting the embodiments of the present application, an execution solution for services is provided. In order to quickly determine whether the authorization check for the target service passes, by inputting the target service information into the target prediction model to obtain the target authorization information corresponding to the target service output by the target prediction model, it is realized to automatically determine whether the authorization check passes, thereby realizing the efficient automation of the service execution process, significantly improving the speed of service processing, and at the same time improving the efficiency of the authorization check for the authorization items required for executing the service, the accuracy of the business transaction risk warning, and the warning efficiency of the business transaction risk, and further solving the technical problem of the low efficiency of the authorization check for the authorization items required for executing the service.

[0121] Those of ordinary skill in the art can understand that Figure 6 The structure shown is only for illustration, and the electronic device can also be a smart phone (such as an Android phone, an iOS phone, etc.), a tablet computer, a handheld computer, and terminal devices such as Mobile Internet Devices (MID), PAD, etc. Figure 6 It does not limit the structure of the above electronic device. For example, the electronic device may further include more or fewer components (such as a network interface, a display device, etc.) than those shown Figure 6 in the figure, or have a different configuration from that shown Figure 6 in the figure.

[0122] Those of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing the relevant hardware of the terminal device through a program, and the program can be stored in a computer-readable storage medium. The storage medium may include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disc, etc.

[0123] Example 4

[0124] An embodiment of the present application further provides a storage medium. Optionally, in this embodiment, the above storage medium may be used to store the program code executed by the method for executing the service provided in the first embodiment above.

[0125] Optionally, in this embodiment, the above storage medium may be located in any one of the computer terminals in the computer terminal group in the computer network, or in any one of the mobile terminals in the mobile terminal group.

[0126] The present application also provides a computer program product, which is suitable for executing a program for the steps of the method for executing a service when executed on a data processing device.

[0127] The serial numbers of the embodiments of the present application above are only for description and do not represent the advantages or disadvantages of the embodiments.

[0128] In the above embodiments of the present application, the descriptions of the respective embodiments have their own emphases. For the parts not detailed in a certain embodiment, reference may be made to the relevant descriptions of other embodiments.

[0129] In the several embodiments provided by the present application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the couplings or direct couplings or communication connections shown or discussed with each other can be through some interfaces. The indirect couplings or communication connections of the units or modules can be in electrical or other forms.

[0130] The units described as separate components may or may not be physically separated. The components shown as units may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0131] In addition, the functional units in the respective embodiments of the present application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The above integrated units can be implemented in the form of hardware or in the form of software functional units.

[0132] When the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of this application. The aforementioned storage medium includes: various media such as USB flash drives, read-only memories (ROMs), random access memories (RAMs), mobile hard disks, magnetic disks, or optical discs that can store program codes.

[0133] The above are only the preferred embodiments of this application. It should be noted that for those of ordinary skill in the art of this technology, without departing from the principle of this application, several improvements and refinements can be made, and these improvements and refinements should also be regarded as the protection scope of this application.

Claims

1. A method for executing a service, characterized in that: Applied to an execution device, the method comprises: Detecting target service information corresponding to the target service to be executed, wherein the target service information includes a target authorization item required to execute the target service and target authorization data of the target service under the target authorization item; Input the target service information into a target prediction model to obtain target authorization information corresponding to the target service output by the target prediction model, wherein the target authorization information is used to indicate whether the target authorization item has passed the authorization check, and the target prediction model is obtained by training an initial prediction model using sample service information annotated with sample authorization information; In a case where the target authorization information is used to indicate that all the target authorization items have passed the authorization check, it is determined that the target service is allowed to be executed, and the target service is executed.

2. The method according to claim 1, characterized in that: The execution device includes a controller and a data acquisition module, the controller is connected to the data acquisition module, the data acquisition module is used to connect to a data lake, the data lake is used to store business information of the business to be executed, and the target business information corresponding to the target business to be executed is detected, including: Controlling the data acquisition module by the controller to extract initial business information corresponding to the target business from the data lake, wherein the initial business information is used to indicate an initial authorization item corresponding to the target business and initial authorization data of the target business under the initial authorization item; The target service information is determined according to the initial service information.

3. The method according to claim 2, characterized in that The execution device further deploys a data preprocessing module, the controller is connected to the data preprocessing module, and the target business information is determined according to the initial business information, including: Generate a preprocessing request by the controller, wherein the preprocessing request is used to request to perform a preprocessing operation on the initial service information; The preprocessing request is sent to the data preprocessing module, and a processing result returned by the data preprocessing module in response to the preprocessing request is received as the target service information, wherein the data preprocessing module is used to execute the preprocessing request.

4. The method according to claim 3, characterized in that: After sending the preprocessing request to the data preprocessing module, the method further includes: extracting the target authorization item from the initial authorization item, and filtering the target authorization data from the initial authorization data; and / or, A set of authorization items is screened from the initial authorization items, and authorization data corresponding to each authorization item in the set of authorization items is screened from the initial authorization data to obtain a set of authorization data; a target operation is performed on first authorization data corresponding to a first authorization item and second authorization data corresponding to a second authorization item to obtain third authorization data corresponding to a third authorization item, wherein the target authorization data includes the third authorization data, the set of authorization items includes the first authorization item and the second authorization item, and the target operation is performed on the first authorization data corresponding to the first authorization item and the second authorization data corresponding to the second authorization item, including: performing a sum operation on the first authorization data and the second authorization data, and / or performing a difference operation on the first authorization data and the second authorization data, and / or performing a product operation on the first authorization data and the second authorization data, and / or performing a quotient operation on the first authorization data and the second authorization data.

5. The method according to claim 1, characterized in that The step of inputting the target service information into a target prediction model to obtain target authorization information corresponding to the target service output by the target prediction model includes: Detecting a first similarity between a target authorization item and a reference authorization item of an executed reference service, and detecting a second similarity between target authorization data and reference authorization data of the reference service under the reference authorization item, wherein the reference authorization item and the reference authorization data pass the authorization check; When the first similarity is greater than or equal to a first similarity threshold and the second similarity is greater than or equal to a second similarity threshold, a first identifier corresponding to the target service is generated, wherein the target authorization information includes the first identifier, and the first identifier is used to indicate that the target authorization item passes the authorization check.

6. The method according to claim 1, characterized in that Before inputting the target service information into a target prediction model to obtain target authorization information corresponding to the target service output by the target prediction model, the method further includes: Inputting the sample service information into the initial prediction model to obtain first candidate authorization information corresponding to the sample service information output by the initial prediction model, wherein the sample service information includes a sample authorization item passed by the executed sample service and sample authorization data of the sample service under the sample authorization item; Performing a quotient operation on a first quantity of first authorization information and a second quantity of sample authorization information to obtain a first ratio, wherein the first authorization information is the same authorization information as the sample authorization information in the first candidate authorization information; When the first ratio is greater than or equal to a ratio threshold, the initial prediction model is determined as the target prediction model.

7. The method according to claim 6, characterized in that In a case where the first ratio is less than the ratio threshold, the method further includes: Adjusting the model parameters of the initial prediction model to obtain a candidate prediction model; Inputting candidate service information into the candidate prediction model to obtain second candidate authorization information corresponding to the candidate service output by the candidate prediction model, wherein the candidate service information is service information corresponding to the executed candidate service, and the candidate service information includes the candidate authorization item passed by the candidate service and the candidate authorization data of the candidate service under the candidate authorization item; Performing a quotient operation on a third quantity of second authorization information and a fourth quantity of the candidate authorization information to obtain a second ratio, wherein the second authorization information is the same as the candidate authorization information in the second candidate authorization information; When the second ratio is greater than or equal to the ratio threshold, the training is terminated and the candidate prediction model is determined as the target prediction model.

8. A service execution device, characterized in that: Applied to an execution device, the device comprises: A detection module, used to detect target service information corresponding to the target service to be executed, wherein the target service information includes a target authorization item required to execute the target service and target authorization data of the target service under the target authorization item; A first input module is used to input the target service information into a target prediction model to obtain target authorization information corresponding to the target service output by the target prediction model, wherein the target authorization information is used to indicate whether the target authorization item has passed the authorization check, and the target prediction model is obtained by training an initial prediction model using sample service information annotated with sample authorization information; The first processing module is used to determine that the target service is allowed to be executed and execute the target service when the target authorization information is used to indicate that the target authorization items have passed the authorization check.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored executable program, wherein when the executable program is run, the device where the computer-readable storage medium is located is controlled to execute the service execution method according to any one of claims 1 to 7.

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

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

Images