Verification method and device of business system, electronic equipment and storage medium

Abstract

The embodiment of the invention provides a verification method and device of a service system, electronic equipment and a storage medium. The method can be used in financial field. The method comprises the following steps: firstly, acquiring first production data within a first preset duration; then, inputting the first production data into a pre-trained verification switch model to obtain an output result corresponding to the first service system, the output result being used for indicating a first verification pass proportion of the first service system; the verification switch model is a model obtained by training second production data meeting a preset condition before a first preset time length, and the preset condition is a condition determined based on the queue depth; and finally, according to the first verification passing proportion, determining an on-off state of a verification switch of the first service system, the verification switch being used for opening or closing verification of the second incoming and outgoing message involved in the first service system within the next preset duration after the first preset duration. The method is used for achieving the effect of improving the message verification efficiency.

Description

Technical Field

[0001] The present application relates to the financial field, and in particular to a verification method, device, electronic device and storage medium for a business system. Background Art

[0002] When the banking business system sends and receives messages, the structure and fields of the messages will change due to the differences in the sending and receiving banks, user information, and the number of transit banks. If there are problems such as missing or repeated messages in the structure of the message, the business system will report an error when processing it. The format and content of the message need to be checked to ensure that the message can meet the processing requirements of the business system.

[0003] Existing message verification can usually use a document structure description (XML Schema Definition, XSD) file to verify the format of an extensible markup language document, or complete the verification of message fields and formats according to preset rules, such as checksum and field length verification.

[0004] However, due to the inconsistency between the service time provided by the current Society for Worldwide Interbank Financial Telecommunication network and the verification function, and the different types and qualities of messages sent by different messaging systems, the existing message verification has the problem of low processing efficiency. Summary of the invention

[0005] The embodiments of the present application provide a verification method, device, electronic device and storage medium of a business system, so as to achieve the effect of improving the efficiency of message verification.

[0006] In a first aspect, an embodiment of the present application provides a verification method for a business system, including:

[0007] Acquire first production data within a first preset time period, the first production data including: an identifier of a first business system involved in a first message, a first timestamp of the first message, a first type of the first message, a first identifier of the first message, and a first queue depth of the first message;

[0008] Inputting the first production data into a pre-trained verification switch model to obtain an output result corresponding to the first business system, wherein the output result is used to indicate a first verification pass ratio of the first business system, wherein the verification switch model is a model trained based on second production data meeting a preset condition before the first preset time, wherein the preset condition is a condition determined based on a queue depth;

[0009] The switch state of the check switch of the first business system is determined according to the first check pass ratio, and the check switch is used to turn on or off the check of the second incoming and outgoing messages of the first business system within the next preset time period after the first preset time period.

[0010] In one or more embodiments, determining the switch state of the verification switch of the first business system according to the first verification pass ratio includes:

[0011] If the first verification pass ratio is greater than a preset ratio, determining that the switch state of the verification switch is closed;

[0012] If the first verification pass ratio is less than or equal to the preset ratio, it is determined that the switch state of the verification switch is open.

[0013] In one or more embodiments, the preset conditions are: a preset time interval, and a queue depth greater than a preset depth.

[0014] In one or more embodiments, before inputting the first production data into a pre-trained verification switch model to obtain an output result corresponding to the first business system, the method further includes:

[0015] Acquire third production data of a preset time interval within a previous preset time period before the first preset time period;

[0016] In the third production data, production data having a queue depth greater than the preset depth is determined as the second production data, wherein the second production data includes: an identifier of a second business system involved in the second communication message, a second timestamp of the second communication message, a second type of the second communication message, a second identifier of the second communication message, a second queue depth of the second communication message, and a verification result of the second communication message;

[0017] The preset forest of trees model is trained according to the second production data to obtain the verification switch model.

[0018] In one or more embodiments, the method further comprises:

[0019] Obtaining a verification result of the first business system involving a second message within the next preset time period;

[0020] The verification switch model is modified according to the verification result of the first service system involving the second incoming and outgoing message within the next preset time period.

[0021] In one or more embodiments, the step of modifying the verification switch model according to the verification result of the first service system involving the second communication message within the next preset time period includes:

[0022] Determining a second verification pass ratio corresponding to the verification result of the second communication message according to the verification result of the first business system involving the second communication message within the next preset time period;

[0023] When the difference between the first verification pass ratio and the second verification pass ratio is greater than a preset difference, the verification switch model is modified according to the verification result of the first business system involving the second incoming and outgoing message within the next preset time period.

[0024] In one or more embodiments, before training a preset forest of trees model according to the second production data to obtain the verification switch model, the method further includes:

[0025] In response to a modification operation performed by a user on the second production data, the second production data is modified.

[0026] In a second aspect, an embodiment of the present application provides a verification device for a business system, including:

[0027] an acquisition module, configured to acquire first production data within a first preset time period, wherein the first production data includes: an identifier of a first business system involved in a first communication message, a first timestamp of the first communication message, a first type of the first communication message, a first identifier of the first communication message, and a first queue depth of the first communication message;

[0028] a processing module, inputting the first production data into a pre-trained verification switch model to obtain an output result corresponding to the first business system, wherein the output result is used to indicate a first verification pass ratio of the first business system, wherein the verification switch model is a model trained based on second production data meeting a preset condition before the first preset time, wherein the preset condition is a condition determined based on a queue depth;

[0029] A determination module determines the switch state of the verification switch of the first business system according to the first verification pass ratio, and the verification switch is used to turn on or off the verification of the second incoming and outgoing messages involving the first business system within the next preset time period after the first preset time period.

[0030] In one or more embodiments, the determining module is specifically configured to:

[0031] If the first verification pass ratio is greater than a preset ratio, determining that the switch state of the verification switch is closed;

[0032] If the first verification pass ratio is less than or equal to the preset ratio, it is determined that the switch state of the verification switch is open.

[0033] In a possible implementation manner, the preset conditions are: a preset time interval, and a queue depth greater than a preset depth.

[0034] In one or more embodiments, before inputting the first production data into a pre-trained verification switch model to obtain an output result corresponding to the first business system, the processing module is further configured to:

[0035] Acquire third production data of a preset time interval within a previous preset time period before the first preset time period;

[0036] In the third production data, production data having a queue depth greater than the preset depth is determined as the second production data, wherein the second production data includes: an identifier of a second business system involved in the second communication message, a second timestamp of the second communication message, a second type of the second communication message, a second identifier of the second communication message, a second queue depth of the second communication message, and a verification result of the second communication message;

[0037] The preset forest of trees model is trained according to the second production data to obtain the verification switch model.

[0038] In one or more embodiments, the processing module is further configured to:

[0039] Obtaining a verification result of the first business system involving a second message within the next preset time period;

[0040] The verification switch model is modified according to the verification result of the first service system involving the second incoming and outgoing message within the next preset time period.

[0041] In one or more embodiments, the processing module modifies the verification switch model according to the verification result of the first service system involving the second communication message within the next preset time period, specifically for:

[0042] Determining a second verification pass ratio corresponding to the verification result of the second communication message according to the verification result of the first business system involving the second communication message within the next preset time period;

[0043] When the difference between the first verification pass ratio and the second verification pass ratio is greater than a preset difference, the verification switch model is modified according to the verification result of the first business system involving the second incoming and outgoing message within the next preset time period.

[0044] In one or more embodiments, before training a preset forest of trees model according to the second production data to obtain the verification switch model, the processing module is further configured to:

[0045] In response to a modification operation performed by a user on the second production data, the second production data is modified.

[0046] In a third aspect, an embodiment of the present application provides an electronic device, including:

[0047] a processor, and a memory communicatively connected to the processor;

[0048] The memory stores computer-executable instructions;

[0049] The processor executes the computer-executable instructions stored in the memory to implement the method described in the first aspect and any one of the embodiments above.

[0050] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, they are used to implement the method described in the first aspect and any one of the embodiments.

[0051] In a fifth aspect, an embodiment of the present application provides a computer program product, including a computer program, which, when executed by a processor, is used to implement a verification method for a business system as described in the first aspect and various possible implementations of the first aspect.

[0052] The verification method, device, electronic device and storage medium of the business system provided in the embodiment of the present application obtain the first production data within the first preset time length, and input these data into a pre-trained verification switch model to obtain the output result of the first business system. Finally, according to the proportion of verification passed in the output result of the model, the verification switch state of the first business system is determined. In the above method, a verification switch is set for the first business system, and a corresponding verification switch model is constructed, and then the model is pre-trained. Message verification is performed based on the trained model, thereby significantly improving the accuracy and efficiency of the verification. By inputting the first production data within the first preset time length into the trained model, the proportion of verification passed is obtained according to the output result of the model, and then the verification switch state of the first business system is adjusted, which effectively optimizes the message verification process and improves the overall verification efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0054] Figure 1 Schematic diagram of the process of the verification method of the business system provided in the embodiment of the present application Figure 1 ;

[0055] Figure 2 Schematic diagram of the process of the verification method of the business system provided in the embodiment of the present application Figure 2 ;

[0056] Figure 3 Schematic diagram of the process of the verification method of the business system provided in the embodiment of the present application Figure 3 ;

[0057] Figure 4 A schematic diagram of the structure of a verification device for a business system provided in an embodiment of the present application;

[0058] Figure 5 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application.

[0059] The above drawings have shown clear embodiments of the present application, which will be described in more detail later. These drawings and text descriptions are not intended to limit the scope of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0060] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0061] When the banking business system sends and receives messages, it will verify the format and content of the message according to business needs before receiving the message from the external system and sending the message to the external system to ensure that the message can meet the system processing requirements. After the message passes the verification, the subsequent business process will be carried out. In the case of large message traffic, abnormal verification system, high message accuracy, etc., the system needs to turn off the message verification function and directly interact with the external system for messages.

[0062] However, due to the different types of interactive messages and specific business requirements, problems such as missing and duplication of message structures may occur, causing errors in the business system during processing. Existing message verification can usually use XSD files to verify the format of eXtensible Markup Language (XML) documents, or complete the verification of message fields and formats according to preset rules, such as checksum and field length verification.

[0063] However, due to the inconsistency between the service time provided by the current Society for Worldwide Interbank Financial Telecommunication (SWIFT) network and the verification function, and the different types and qualities of messages sent by different messaging systems, the existing message verification has the problem of low processing efficiency.

[0064] The verification method, device and storage medium of the business system provided by the present application are intended to solve the above technical problems of the prior art. The inventive concept of the present application is as follows: First, a verification switch is set for the first business system, and a verification switch model is constructed. After that, the model is pre-trained, and message verification is performed based on the trained verification switch model, thereby effectively improving the accuracy and efficiency of message verification. At the same time, by obtaining the first production data within the first preset time length, and inputting these data into the trained verification switch model, the verification pass ratio corresponding to the first business system is obtained according to the output result of the model, and the verification switch state of the first business system is further adjusted. By using the verification switch control, the message verification process is optimized and the overall verification efficiency is improved.

[0065] It should be noted that the verification method, device, electronic device and storage medium of the business system provided in this application can be used in the financial field, and can also be used in any field other than the financial field. The application field of the verification method, device, electronic device and storage medium of the business system provided in this application is not limited.

[0066] The technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems are described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0067] Figure 1 Schematic diagram of the verification method of the business system provided in this application Figure 1 ,like Figure 1 As shown, the method includes:

[0068] S110, obtaining first production data within a first preset time period;

[0069] The first production data includes: an identifier of a first business system involved in the first message, a first timestamp of the first message, a first type of the first message, a first identifier of the first message, and a first queue depth of the first message.

[0070] In this step, it is first necessary to obtain a first preset time period according to the business situation, and then obtain the first production data generated within the first preset time period.

[0071] Among them, the first preset duration refers to the duration corresponding to obtaining the first production data, the first production data refers to the specific information of the incoming and outgoing messages, the identifier of the first business system refers to the identifier that can uniquely mark the business system, the first type of message refers to the message exchange category representing a specific type in the first business system, the first identifier of the message refers to the key information that can uniquely mark the message, and the first queue depth of the message refers to the maximum number of messages that can be stored in a message queue.

[0072] In a possible implementation, the message queue is used to transfer data or messages between different business systems, and the messages are temporarily stored in the queue, waiting for the receiver to process. The message queue can be RabbitMQ, Kafka, ActiveMQ, etc., and the message interaction with the business system is carried out through different message queues, and the first production data record in the message interaction process is collected.

[0073] For example, when data is transmitted between business system A and business system B, business system A sends a message to business system B, and business system A also receives a message returned by business system B. ActiveMQ message queues can be used to interact with business systems A and B through messages. The first production data is generated during the message interaction, and the production data carries the identifiers of business system A and business system B involved in the messages, and generates specific timestamp information for the messages. The type of the messages is determined based on the content of the message interaction between the business systems, such as customer financial transaction type messages, securities transaction type messages, or bank report type messages. At the same time, the first production data generated also includes the unique identifier of the message and the depth of the message queue.

[0074] S120, inputting the first production data into a pre-trained verification switch model to obtain an output result corresponding to the first business system;

[0075] Among them, the output result is used to indicate the first verification pass ratio of the first business system. The verification switch model is a model trained based on the second production data that meets the preset conditions before the first preset time, and the preset conditions are conditions determined based on the queue depth.

[0076] In this step, a verification switch model is first pre-constructed and trained to obtain a trained verification switch model. The first production data obtained above is then used as input of the verification switch model, and the verification switch model then outputs an output result corresponding to the first business system.

[0077] Among them, the verification switch model refers to a model that can set the switch state of the business system verification switch, the output result of the business system refers to the proportion of message verification results that pass the verification, and the preset condition refers to the pre-set rules for restricting the first production data.

[0078] In a possible implementation, the verification switch model can be obtained by training a random forest model based on the first production data, and by constructing multiple decision trees, the results output by each decision tree are classified or regressed to make a final decision. Each type in the acquired first production data is used as a feature type selected by the model, and the model calculates based on these features and the specific content corresponding to the features. The output result is the verification result of the message, and the proportion of the verification passed in the verification result is the output result corresponding to the first business system.

[0079] In a possible implementation manner, the preset conditions are: a preset time interval, and a queue depth greater than a preset depth.

[0080] The preset time interval refers to a time period divided within the first preset time length, and the preset depth refers to a threshold of the queue depth preset before the business system or business process starts.

[0081] In a possible implementation, the corresponding second production data can be obtained according to a preset condition, that is, before a first preset time length and within a preset time interval, when the queue depth is greater than a preset depth. For example, the preset condition can be set to be before a first preset time length 1 and within a preset time interval of 1 hour, when the queue depth is greater than a preset depth H.

[0082] S130, determining a switch state of a check switch of the first business system according to the first check pass ratio;

[0083] The verification switch is used to turn on or off the verification of the second communication message involving the first business system within the next preset time period after the first preset time period.

[0084] In this step, the proportion of message verification passes in the verification results is first determined, and then the specific setting of the switch state of the verification switch of the first business system is determined based on the verification pass proportion.

[0085] The verification passing means that the message being verified has no format or content errors.

[0086] In a possible implementation, the above determination of the proportion of message verification results that pass the verification may be performed by dividing the verification results that pass the verification by the total number of all verification results to obtain the percentage of the verification results that pass the verification.

[0087] In a possible implementation, step S130 may also include the following implementation: if the first verification pass ratio is greater than a preset ratio, determining that the switch state of the verification switch is closed; if the first verification pass ratio is less than or equal to the preset ratio, determining that the switch state of the verification switch is open.

[0088] The preset ratio refers to a preset threshold value of the verification pass ratio.

[0089] For example, the pre-set verification pass ratio is 70%. When the first verification pass ratio is 90%, it can be explained that the proportion of errors in the message format or content is small, which can meet the business needs. At this time, the switch state of the verification switch can be determined to be closed, that is, the message does not need to be verified and the message can be directly sent and received; when the first verification pass ratio is 60%, it can be explained that the proportion of errors in the message format or content is large, which cannot meet the business needs. At this time, the switch state of the verification switch can be determined to be open, that is, the message needs to be verified before sending and receiving the message.

[0090] The verification method of the business system provided in the embodiment of the present application obtains the first production data within the first preset time length, and then inputs the obtained first production data into the pre-trained verification switch model to obtain the output result corresponding to the first business system, and finally determines the switch state of the verification switch of the first business system according to the verification pass ratio in the output result. In this embodiment, the verification switch is first set for the first business system, and the verification switch model is constructed, and then the model is pre-trained, and the message verification is performed based on the trained verification switch model, which can effectively improve the accuracy and verification efficiency of the message verification, and by inputting the first production data obtained within the first preset time length into the trained verification switch model, the verification pass ratio corresponding to the first business system is obtained according to the model output result, and the verification switch state of the first business system is set accordingly, and the verification switch is used to determine whether the message verification is required, thereby improving the efficiency of the message verification.

[0091] Based on the above embodiments, Figure 2 Schematic diagram of the process of the verification method of the business system provided in the embodiment of the present application Figure 2 ,like Figure 2 As shown, before the above step S120, a possible implementation of the method further includes the following steps:

[0092] S210: Acquire third production data of a preset time interval within a previous preset time period before the first preset time period.

[0093] In this step, the specific values ​​of the first preset time length and the previous preset time length are first determined, and then, within the previous preset time length before the first preset time length, according to the preset time interval, the production data within the time interval is obtained as the third production data.

[0094] For example, the first preset duration is T1, the previous preset duration before the first preset duration is T2, and the preset time interval is T3. Then, according to the specific value of the first preset duration T1, work back in time to find the previous preset duration T2. ​​Within the previous preset duration T2, obtain the production data of the time interval T3, which is the third production data.

[0095] S220, determining, within the third production data, production data whose queue depth is greater than a preset depth as second production data;

[0096] Among them, the second production data includes: an identifier of a second business system involved in the second message, a second timestamp of the second message, a second type of the second message, a second identifier of the second message, a second queue depth of the second message, and a verification result of the second message.

[0097] In a possible implementation, the above-mentioned determination of the second production data can be to extract the production data whose queue depth is greater than a preset depth in the third production data, and finally determine the second production data and its specific content based on the second business system identifier, second timestamp, message type, message identifier, and queue depth and verification results of the incoming and outgoing messages involved in the incoming and outgoing messages.

[0098] S230: According to the second production data, a preset forest of trees model is trained to obtain a verification switch model.

[0099] In this step, the forest of trees model is first pre-set, and then the obtained second production data is used as the input of the model to train the preset forest of trees model. The output result of the model can be used to indicate the switch state of the verification switch, and the trained preset forest of trees model is used as the verification switch model.

[0100] In a possible implementation manner, before the above step S230, the method further includes: in response to a modification operation performed by a user on the second production data, modifying the second production data.

[0101] In this step, the user first performs a correction operation on the second production data, and then responds to the user's correction operation and performs specific corrections on the second production data according to the specific content of the correction operation.

[0102] Among them, the correction operation refers to the screening or modification operation of production data according to certain rules.

[0103] In one possible implementation, the above-mentioned correction of the second production data may be to delete duplicate data in the second production data, or to clear abnormal data in the second production data. The correction of the second production data may also be to delete unrepresentative data in the second production data based on the business personnel's suggestions for message verification, and only retain representative data related to the business.

[0104] The verification method of the business system provided in the embodiment of the present application first obtains the third production data of the preset time interval within the previous preset time before the first preset time, and then trains the preset forest tree model according to the second production data with a queue depth greater than the preset depth in the obtained third production data, and finally obtains the verification switch model. In this embodiment, firstly, according to the first preset time and the preset time interval, the third production data is divided and restricted in the time dimension, the third production data of the preset time interval within the previous preset time before the first preset time is obtained, and the queue depth is pre-set, and the second production data with a queue depth greater than the preset depth in the third production data is extracted, and the actual production data within the time of large message interaction volume can be analyzed in a targeted manner, and then these representative data are input into the preset forest tree model for training, and finally the verification switch model is obtained, which can effectively improve the accuracy of the message verification switch state setting, and at the same time improve the message verification efficiency.

[0105] Based on the above embodiments, Figure 3 Schematic diagram of the process of the verification method of the business system provided in the embodiment of the present application Figure 3 ,like Figure 3 As shown, the verification method of the business system also includes the following steps:

[0106] S310: Obtain verification results of the first service system involving the second message within the next preset time period.

[0107] In this step, the next preset time length is first determined, and then the second incoming and outgoing message is matched according to the identifier of the first service system within the next preset time length, thereby obtaining a verification result involving the second incoming and outgoing message.

[0108] In one possible implementation, the verification result of the second message may be included in the second message production data, and the identifier of the first business system may also be included in the second message production data. Then, in the second message production data, the first business system is matched according to the identifier of the first business system, and then the verification result of the second message in the second message production data related to the first business system is obtained.

[0109] S320: Modify the verification switch model according to the verification result of the first service system involving the second incoming and outgoing message within the next preset time period.

[0110] In this step, the verification result of the first service system involving the second incoming and outgoing message within the next preset time period is analyzed, and the verification switch model is adjusted according to the analysis result.

[0111] In a possible implementation, the above-mentioned correction of the verification switch model can be to train the verification switch model according to the verification result of the first business system involving the second communication message within the next preset time period, adjust the switch state of the verification switch during the training, and when the verification result accuracy of the verification switch model after training is greater than that of the verification switch model before training, replace the verification switch model before training with the verification switch model after training.

[0112] In a possible implementation manner, a possible implementation of the above step S320 includes the following steps:

[0113] S321: Determine a second verification pass ratio corresponding to the verification result of the second message according to the verification result of the first business system involving the second message within the next preset time period.

[0114] In this step, the verification results of the second incoming messages involving the first business system within the next preset time period are first analyzed to identify the second incoming message records that pass and fail the verification in the verification results, and determine the second verification pass ratio corresponding to the verification results of the second incoming messages based on the proportion of the records that pass the verification in the verification results of the second incoming messages.

[0115] For example, in the verification results of the second inter-communication message, there are 90 second inter-communication message records that passed the message verification, and there are 30 second inter-communication message records that failed the message verification. Then, the proportion of the records that passed the message verification in the verification results of the second inter-communication message is 75%, that is, the second verification pass ratio is 75%.

[0116] S322: when the difference between the first verification pass ratio and the second verification pass ratio is greater than a preset difference, the verification switch model is modified according to the verification result of the first service system involving the second incoming and outgoing message within the next preset time period.

[0117] In this step, a difference threshold between the first verification pass ratio and the second verification pass ratio, that is, a preset difference, is pre-set, and the obtained first verification pass ratio is subtracted from the second verification pass ratio to obtain a ratio difference. When the ratio difference is greater than the preset difference, the verification result of the first business system involving the second incoming and outgoing message within the next preset time period is analyzed, and then the verification switch model is corrected according to the analysis result.

[0118] For example, taking the above example for further explanation, the preset difference is set to 5%, the second verification pass ratio is 75%, when the first verification pass ratio is 69%, the difference between the first verification pass ratio and the second verification pass ratio is 6%, which is greater than the preset difference, then according to the verification result of the second incoming message of the first business system within the next preset time period, the verification switch model is corrected; when the first verification pass ratio is 83%, the difference between the first verification pass ratio and the second verification pass ratio is 8%, which is greater than the preset difference, then according to the verification result of the second incoming message of the first business system within the next preset time period, the verification switch model is corrected; when the first verification pass ratio is 72%, the difference between the first verification pass ratio and the second verification pass ratio is 3%, which is less than the preset difference, then there is no need to correct the verification switch model.

[0119] The verification method of the business system provided in the embodiment of the present application obtains the verification result of the second message to and from the first business system within the next preset time period, and modifies the verification switch model according to the verification result. In this embodiment, by obtaining the verification result of the second message to and from the first business system, analyzing these verification results to achieve the correction of the verification switch model, the accuracy of the verification switch state setting of the first business system by the verification switch model can be improved, and the efficiency of message verification can be further improved.

[0120] Based on the above embodiments, the following are device embodiments involved in this application:

[0121] Figure 4 A schematic diagram of the structure of a verification device for a business system provided in an embodiment of the present application, such as Figure 4 As shown, the verification device 400 of the business system provided in this embodiment includes:

[0122] The acquisition module 410 is used to acquire first production data within a first preset time period, where the first production data includes: an identifier of a first business system involved in the first communication message, a first timestamp of the first communication message, a first type of the first communication message, a first identifier of the first communication message, and a first queue depth of the first communication message;

[0123] The processing module 420 inputs the first production data into a pre-trained verification switch model to obtain an output result corresponding to the first business system, where the output result is used to indicate a first verification pass ratio of the first business system, where the verification switch model is a model trained based on second production data that meets a preset condition before a first preset time, where the preset condition is a condition determined based on a queue depth;

[0124] The determination module 430 determines the switch state of the check switch of the first business system according to the first check pass ratio, and the check switch is used to turn on or off the check of the second incoming and outgoing messages of the first business system within the next preset time period after the first preset time period.

[0125] In an optional embodiment, the determination module 430 is specifically configured to:

[0126] If the first verification pass ratio is greater than a preset ratio, determining that the switch state of the verification switch is closed;

[0127] If the first verification pass ratio is less than or equal to the preset ratio, it is determined that the switch state of the verification switch is open.

[0128] In a possible implementation manner, the preset conditions are: a preset time interval, and a queue depth greater than a preset depth.

[0129] In an optional embodiment, before inputting the first production data into a pre-trained verification switch model to obtain an output result corresponding to the first business system, the processing module 420 is further used to:

[0130] Acquire third production data of a preset time interval within a previous preset time length before the first preset time length;

[0131] In the third production data, the production data with a queue depth greater than a preset depth is determined as the second production data, and the second production data includes: an identifier of a second business system involved in the second communication message, a second timestamp of the second communication message, a second type of the second communication message, a second identifier of the second communication message, a second queue depth of the second communication message, and a verification result of the second communication message;

[0132] The preset forest of trees model is trained according to the second production data to obtain a verification switch model.

[0133] In an optional embodiment, the processing module 420 is further configured to:

[0134] Obtaining a verification result of the first business system involving the second communication message within a next preset time period;

[0135] The verification switch model is modified according to the verification result of the first service system involving the second incoming and outgoing message within the next preset time period.

[0136] In an optional embodiment, the processing module 420 modifies the verification switch model according to the verification result of the first service system involving the second communication message within the next preset time period, specifically for:

[0137] Determine, according to the verification result of the first business system involving the second message within the next preset time period, a second verification pass ratio corresponding to the verification result of the second message;

[0138] When the difference between the first verification pass ratio and the second verification pass ratio is greater than a preset difference, the verification switch model is modified according to the verification result of the first service system involving the second incoming and outgoing message within the next preset time period.

[0139] In an optional embodiment, before training the preset forest of trees model according to the second production data to obtain the verification switch model, the processing module 420 is further used to:

[0140] In response to a correction operation performed by the user on the second production data, the second production data is corrected.

[0141] The verification device of the business system provided in this embodiment can execute the method provided in the above method embodiment. Its implementation principle and technical effect are similar, and this embodiment will not be described in detail here.

[0142] Based on the above embodiments, Figure 5 This is a schematic diagram of the structure of the electronic device provided in this application. Figure 5 As shown, the electronic device 500 provided in this embodiment includes: at least one processor 510 and a memory 520. Optionally, the device 500 also includes a communication component 530. The processor 501, the memory 520 and the communication component 530 are connected via a bus 540.

[0143] In a specific implementation process, at least one processor 510 executes the computer-executable instructions stored in the memory 520, so that at least one processor 510 executes the above method.

[0144] The specific implementation process of the processor 510 can be found in the above method embodiment, and its implementation principle and technical effect are similar, so this embodiment will not be repeated here.

[0145] In the above embodiments, it should be understood that the processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), etc. The general-purpose processor may be a microprocessor or the processor may be any conventional processor, etc. The steps of the method disclosed in the invention may be directly embodied as being executed by a hardware processor, or may be executed by a combination of hardware and software modules in the processor.

[0146] The memory may include a high-speed memory (Random Access Memory, RAM), and may also include a non-volatile memory (Non-volatile Memory, NVM), such as at least one disk memory.

[0147] The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, the bus in the drawings of the present application is not limited to only one bus or one type of bus.

[0148] The present application also provides a computer program product, including a computer program, which implements the above method when executed by a processor.

[0149] The present application also provides a computer-readable storage medium, in which computer-executable instructions are stored. When a processor executes the computer-executable instructions, the above method is implemented.

[0150] The above-mentioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk or optical disk. The readable storage medium can be any available medium that can be accessed by a general or special-purpose computer.

[0151] An exemplary readable storage medium is coupled to a processor so that the processor can read information from the readable storage medium and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can be located in an application specific integrated circuit (Application Specific Integrated Circuits, referred to as: ASIC). Of course, the processor and the readable storage medium can also exist in the device as discrete components.

[0152] The division of units is only a logical function division, and there may be other divisions in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interface, device or unit, which can be electrical, mechanical or other forms.

[0153] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0154] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0155] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0156] Those skilled in the art can understand that all or part of the steps of implementing the above-mentioned method embodiments can be completed by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, the steps of the above-mentioned method embodiments are executed; and the aforementioned storage medium includes: ROM, RAM, disk or optical disk and other media that can store program codes.

[0157] Finally, it should be noted that those skilled in the art will readily conceive of other embodiments of the present invention after considering the specification and practicing the invention disclosed herein. The present invention is intended to cover any variations, uses or adaptations of the present invention, which follow the general principles of the present invention and include common knowledge or customary technical means in the art not disclosed by the present invention, are not limited to the precise structure described above and shown in the drawings, and may be modified and changed in various ways without departing from the scope thereof. The scope of the present invention is limited only by the appended claims.

Claims

1. A verification method for a business system, characterized in that: include: Acquire first production data within a first preset time period, the first production data including: an identifier of a first business system involved in a first message, a first timestamp of the first message, a first type of the first message, a first identifier of the first message, and a first queue depth of the first message; Inputting the first production data into a pre-trained verification switch model to obtain an output result corresponding to the first business system, wherein the output result is used to indicate a first verification pass ratio of the first business system, wherein the verification switch model is a model trained based on second production data meeting a preset condition before the first preset time, wherein the preset condition is a condition determined based on a queue depth; The switch state of the check switch of the first business system is determined according to the first check pass ratio, and the check switch is used to turn on or off the check of the second incoming and outgoing messages of the first business system within the next preset time period after the first preset time period.

2. The method according to claim 1, characterized in that The determining the switch state of the check switch of the first business system according to the first check pass ratio includes: If the first verification pass ratio is greater than a preset ratio, determining that the switch state of the verification switch is closed; If the first verification pass ratio is less than or equal to the preset ratio, it is determined that the switch state of the verification switch is open.

3. The method according to claim 1 or 2, characterized in that: The preset conditions are: a preset time interval, and a queue depth greater than a preset depth.

4. The method according to claim 3, characterized in that Before inputting the first production data into a pre-trained verification switch model to obtain an output result corresponding to the first business system, the method further includes: Acquire third production data of a preset time interval within a previous preset time period before the first preset time period; In the third production data, production data having a queue depth greater than the preset depth is determined as the second production data, wherein the second production data includes: an identifier of a second business system involved in the second communication message, a second timestamp of the second communication message, a second type of the second communication message, a second identifier of the second communication message, a second queue depth of the second communication message, and a verification result of the second communication message; The preset forest of trees model is trained according to the second production data to obtain the verification switch model.

5. The method according to claim 1 or 2, characterized in that: The method further comprises: Obtaining a verification result of the first business system involving a second message within the next preset time period; The verification switch model is modified according to the verification result of the first service system involving the second incoming and outgoing message within the next preset time period.

6. The method according to claim 5, characterized in that The step of modifying the verification switch model according to the verification result of the first service system involving the second message within the next preset time period includes: Determining a second verification pass ratio corresponding to the verification result of the second communication message according to the verification result of the first business system involving the second communication message within the next preset time period; When the difference between the first verification pass ratio and the second verification pass ratio is greater than a preset difference, the verification switch model is modified according to the verification result of the first business system involving the second incoming and outgoing message within the next preset time period.

7. The method according to claim 4, characterized in that Before training the preset forest of trees model according to the second production data to obtain the verification switch model, the method further includes: In response to a modification operation performed by a user on the second production data, the second production data is modified.

8. A verification device for a business system, characterized in that: include: an acquisition module, configured to acquire first production data within a first preset time period, wherein the first production data includes: an identifier of a first business system involved in a first communication message, a first timestamp of the first communication message, a first type of the first communication message, a first identifier of the first communication message, and a first queue depth of the first communication message; a processing module, inputting the first production data into a pre-trained verification switch model to obtain an output result corresponding to the first business system, wherein the output result is used to indicate a first verification pass ratio of the first business system, wherein the verification switch model is a model trained based on second production data meeting a preset condition before the first preset time, wherein the preset condition is a condition determined based on a queue depth; A determination module determines the switch state of the verification switch of the first business system according to the first verification pass ratio, and the verification switch is used to turn on or off the verification of the second incoming and outgoing messages involving the first business system within the next preset time period after the first preset time period.

9. An electronic device, characterized in that: include: a processor, and a memory communicatively connected to the processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory to implement the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 7 when executed by a processor.

Images