State detection method and device of quick payment system, equipment, medium and product

Abstract

The invention provides a state detection method and device for a quick payment system, equipment, a medium and a product, and relates to the field of financial science and technology or other related fields. The method comprises the following steps: acquiring current operation parameters of the quick payment system in real time, wherein the current operation parameters comprise at least one of the following items: a current payment transaction rate, a current final state transaction rate, current average response time, a current system success rate, a current service success rate and a current system error code; the current operation parameters of the quick payment system are input into the long-short-term memory model obtained through pre-training, the current state of the quick payment system is obtained through prediction, and the current state comprises abnormal state or normal state. According to the method provided by the invention, the operation state of the quick payment system is monitored in real time through the long-short-term memory model obtained through pre-training, and the detection efficiency and accuracy are improved.

Description

Technical Field

[0001] The present application relates to the field of financial technology or other related fields, and in particular to a status detection method, device, equipment, medium and product for a quick payment system. Background Art

[0002] Testing the operating status of the quick payment system can promptly detect system failures or performance issues, which is crucial to ensuring the stability and security of the system, while also improving user experience and service quality.

[0003] In the prior art, technicians usually check various operating parameters of the quick payment system to determine whether the system is operating stably, that is, the operating status of the quick payment system is detected through manual detection.

[0004] However, this manual detection method has the disadvantages of low efficiency and poor accuracy, and usually cannot detect potential problems in the quick payment system in a timely manner. Summary of the Invention

[0005] The present application provides a status detection method, device, equipment, medium and product for a quick payment system, which is used to monitor the operating status of the quick payment system in real time through a long-short-term memory model obtained by pre-training, thereby improving the efficiency and accuracy of detection.

[0006] In a first aspect, the present application provides a method for detecting the status of a quick payment system, comprising:

[0007] Obtaining the current operating parameters of the quick payment system in real time, including at least one of the following: current payment transaction rate, current final transaction rate, current average response time, current system success rate, current business success rate, and current system error code;

[0008] The current operating parameters of the quick payment system are input into the pre-trained long short-term memory model to predict the current state of the quick payment system, which includes: abnormal or normal.

[0009] In a second aspect, the present application provides a status detection device for a quick payment system, comprising:

[0010] An acquisition module, configured to acquire, in real time, current operating parameters of the quick payment system, the current operating parameters including at least one of the following: current payment transaction rate, current final transaction rate, current average response time, current system success rate, current business success rate, and current system error code;

[0011] The prediction module is used to input the current operating parameters of the quick payment system into the pre-trained long-short-term memory model to predict the current state of the quick payment system, which includes: abnormal or normal.

[0012] In a third aspect, the present application provides an electronic device, comprising: a processor, and a memory communicatively connected to the processor;

[0013] Memory stores computer-executable instructions;

[0014] The processor executes the computer execution instructions stored in the memory to implement a status detection method for a quick payment system according to the first aspect of the invention.

[0015] In a fourth aspect, the present application provides a computer-readable storage medium, which stores computer-executable instructions. When the computer-executable instructions are executed by a processor, they are used to implement a status detection method for a quick payment system according to the invention content of the first aspect.

[0016] In a fifth aspect, the present application provides a computer program product, including a computer program, which, when executed by a processor, is used to implement a status detection method for a quick payment system according to the invention content of the first aspect.

[0017] The present application provides a method, apparatus, device, medium and product for detecting the status of a quick payment system, including: first, obtaining the current operating parameters of the quick payment system in real time, the current operating parameters including at least one of the following: current payment transaction rate, current final transaction rate, current average response time, current system success rate, current business success rate, and current system error code; then, inputting the current operating parameters of the quick payment system into a pre-trained long-short-term memory model to predict the current status of the quick payment system, the current status including: abnormal or normal. The following technical effects are achieved: by inputting the current operating parameters of the quick payment system obtained in real time into the pre-trained long-short-term memory model, an automated detection method is implemented to monitor the operating status of the quick payment system in real time according to the current operating parameters of the quick payment system, comprehensively evaluate the health status of the system, automatically predict whether the current operating status of the system is normal, and promptly discover system problems or failures, thereby ensuring that the quick payment system operates efficiently and reliably and provides services to users in a stable state; by utilizing the pre-trained long-short-term memory model, the accuracy and reliability of anomaly detection in the quick payment system are improved, thereby improving the user's payment experience and service quality; by reducing the frequency and intensity of manual intervention, the problems of low detection efficiency, insufficient accuracy and high cost investment caused by manual detection of the system status are avoided. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] 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.

[0019] Figure 1 A schematic diagram of an application scenario of a status detection method for a quick payment system provided in an embodiment of the present application.

[0020] Figure 2 A flow chart of a method for detecting the status of a quick payment system provided in an embodiment of the present application.

[0021] Figure 3 A schematic diagram of the structure of a status detection device for a quick payment system provided in an embodiment of the present application.

[0022] Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application.

[0023] The above drawings illustrate specific embodiments of the present application, which will be described in more detail below. These drawings and the textual description are not intended to limit the scope of the present application in any way, but rather to illustrate the concepts of the present application to those skilled in the art by reference to specific embodiments. DETAILED DESCRIPTION

[0024] Exemplary embodiments will be described in detail herein, with examples illustrated in the accompanying drawings. In the following description, when referring to the drawings, identical numerals in different figures represent identical or similar elements, unless otherwise indicated. The embodiments described in the following exemplary embodiments are not intended to represent all embodiments consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present application, as detailed in the appended claims.

[0025] In the embodiments of the present application, words such as "first" and "second" are used to distinguish between identical or similar items with substantially the same functions and effects. Those skilled in the art will understand that words such as "first" and "second" do not limit the quantity and execution order, and words such as "first" and "second" do not necessarily limit differences. It should be noted that in the embodiments of the present application, words such as "exemplary" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described in this application as "exemplary" or "for example" should not be interpreted as being more preferred or advantageous than other embodiments or design schemes. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a concrete way. In the embodiments of the present application, "at least one" refers to one or more, and "more than one" refers to two or more.

[0026] It should be noted that the phrase "at the time of..." in the embodiments of this application can refer to the instantaneous occurrence of a certain event or a period of time after the occurrence of the certain event, and this is not specifically limited in this embodiment of the application. Furthermore, the method for detecting the status of a quick payment system provided in the embodiments of this application is merely an example, and a method for detecting the status of a quick payment system may include more or less content.

[0027] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of the relevant data comply with the relevant laws, regulations and standards of the relevant countries and regions, take necessary confidentiality measures, do not violate public order and good morals, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0028] In addition, this application involves conducting big data analysis of user information (including but not limited to personal biometrics, identity data, consumption data, asset data, electronic terminal operation data, etc.), and using artificial intelligence technology to make automated decisions, and making technical solutions that have a significant impact on personal rights and interests based on the results of automated decisions. The application provides users with corresponding operation entrances for them to choose to agree or reject the results of automated decisions; if the user chooses to reject, the expert decision-making process will be entered.

[0029] It should be noted that the status detection method, device, equipment, medium and product of the quick payment system provided in this application can be used in the field of financial technology or other related fields, and can also be used in any field other than the field of financial technology or other related fields. The application field of the status detection method, device, equipment, medium and product of the quick payment system in this application is not limited.

[0030] Quick Pay is a convenient and fast payment method that simply links a user's bank card to a third-party payment platform or e-commerce website account. Subsequently, when making a payment, the user simply enters the third-party platform's payment password or mobile phone verification code to complete the payment. This method eliminates the tedious steps of switching to the online banking page and entering the bank card password. The system used by banks to complete the quick payment process is called the Quick Pay system.

[0031] Continuously monitoring the operational status of the quick payment system is key to ensuring stable system operation and promptly identifying and resolving potential system failures or performance issues. This is crucial for maintaining system security and stability and improving user experience. In existing technology systems, technicians typically rely on manual testing, reviewing various operating parameters of the quick payment system to assess its operational status.

[0032] However, manual testing consumes significant time and human resources. Technicians cannot continuously monitor the operating parameters of the quick payment system at all times, and can only check during critical periods or when system issues arise, making real-time monitoring impossible. Furthermore, manual testing methods are susceptible to human influence. Manually testing the system's operating status to determine whether a problem exists and what the specific issue is requires a certain level of experience, which often takes time to accumulate. Even experienced technicians can make mistakes when diagnosing system issues, leading to misjudgments or missed detections.

[0033] Therefore, due to manpower limitations, manual testing of quick payment systems is usually difficult to detect system problems in a timely manner, and has the defects of low detection efficiency and insufficient accuracy, which in turn affects the stability and security of the system.

[0034] Based on this, the embodiments of the present application propose a state detection method, device, equipment, medium and product for a quick payment system, which can be used in the field of financial technology or other related fields, and is intended to solve the above technical problems of the prior art. By inputting the current operating parameters of the quick payment system obtained in real time into the long-short term memory model obtained in advance, the current operating state of the system is automatically predicted. Thus, through the method of automated detection, the operating state of the quick payment system can be monitored in real time, system problems or failures can be discovered in a timely manner, the frequency and intensity of manual intervention can be reduced, and the time and labor cost of manual intervention can be greatly reduced, thereby ensuring the stability and security of the system. And by utilizing deep learning models, the accuracy and reliability of anomaly detection can be improved, thereby improving the user payment experience and service quality.

[0035] The following specific embodiments describe in detail the technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems. 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.

[0036] In order to better understand the solution of the embodiment of the present application, an application scenario involved in the embodiment of the present application is first introduced below.

[0037] For specific application scenarios of this application, please refer to Figure 1 . Figure 1 This is a schematic diagram of an application scenario of a state detection method for a quick payment system provided in an embodiment of the present application. It should be noted that: Figure 1 What is shown are merely examples of application scenarios in which the embodiments of the present application can be applied, to help those skilled in the art understand the technical content of the present application, but it does not mean that the embodiments of the present application cannot be used in other devices, systems, environments or scenarios.

[0038] like Figure 1 As shown, this application scenario includes a payment terminal device 110, a backend server 120, and a data processing server 130. The payment terminal device 110 typically has a bank or payment institution application (APP) installed, or supports web payment functionality. It can receive payment instructions such as a payment password, mobile phone verification code, or payment password entered by the user to enable payment. In other words, the user can enter the payment password or mobile phone verification code from a third-party platform through the payment terminal device 110 to complete the payment. The specific form of the payment terminal device 110 may include, but is not limited to, a smartphone, tablet computer, PDA (Personal Digital Assistant), laptop, point-of-sale (POS) terminal, or self-service payment terminal.

[0039] The connection between the payment terminal device 110 and the backend server 120 can be wired or wireless. The backend server 120 can be responsible for key tasks such as processing payment instructions, verifying user identities, and managing account funds. It can also store the current operating parameters of the quick payment system corresponding to each bank transaction as it is processed. The backend server 120 can transmit data to the data processing server 130 via a wired or wireless connection. The data processing server 130 can be used to process the current operating parameters of the quick payment system stored in the backend server 120 to predict whether there are any anomalies in the current status of the quick payment system.

[0040] The backend server 120 and the data processing server 130 are usually deployed in a bank's data center for ease of maintenance and management.

[0041] In addition, in a possible implementation, the data processing server 130 may be the backend server 120, that is, there is no need to set up another data processing server 130. The current operating parameters of the quick payment system can be processed through the backend server 120, thereby predicting whether the current status of the quick payment system is normal.

[0042] Figure 2 This is a flow chart of a method for detecting the status of a quick payment system provided in an embodiment of the present application. Figure 2 As shown, the method includes:

[0043] S201. Obtain the current operating parameters of the quick payment system in real time.

[0044] In an embodiment of the present application, the execution entity of a status detection method for a quick payment system can be a server, which can be an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server, etc., and no specific restrictions are made here.

[0045] The current operating parameters include at least one of the following: current payment transaction rate, current final transaction rate, current average response time, current system success rate, current business success rate, and current system error code.

[0046] Specifically, the six operational parameters mentioned above can generally be used to monitor and evaluate the performance, stability, reliability, and transaction success rate of the quick payment system. The specific meaning of each operational parameter is as follows:

[0047] (1) Current payment transaction rate: This usually refers to the number of payment transactions processed by the quick payment system per unit time, usually measured in units of second, minute, or hour. It is used to reflect the system's transaction processing capacity and load.

[0048] (2) Current final state transaction rate: refers to the number of transactions that reach the final state of the quick payment system within a specific time period. The final state refers to a certain state reached after the transaction is completed, usually including success, failure, cancellation, etc. That is, the transaction is either successfully completed, failed, or canceled. This indicator measures the number of all transactions that enter the final state (whether successful or not) within a given time period, and can be used to understand the efficiency and stability of the quick payment system in processing transactions. In other words, obtaining this indicator helps the server understand the number of all transactions processed by the quick payment system, not just the successful ones.

[0049] (3) Current average response time: This refers to the average time it takes for a quick payment system to process a payment request, from the time it receives a user's request to the time it returns a response to the user. This time is usually measured in milliseconds or seconds. It is one of the important indicators for measuring the performance of a quick payment system, directly affecting the user experience and can be used to analyze the system's response speed.

[0050] (4) Current system success rate: refers to the ratio of the number of transactions successfully processed by the quick payment system to the total number of transactions within a specific time period. It is a key indicator for measuring the stability, reliability and service quality of the quick payment system.

[0051] (5) Current business success rate: refers to the ratio of the number of transactions successfully completed at the business level to the total number of transactions within a specific time period. This can include successful user verification, successful payment, etc. It can be used to analyze the effectiveness of business processes and user satisfaction. The current business success rate is similar to the system success rate, but the current business success rate focuses more on the success of specific business logic levels. For example, payment failures caused by network problems, insufficient user balance, incorrect payment passwords entered by users, or incorrect mobile phone verification codes, exclude failures caused by some technical errors. The current business success rate can help the server identify whether the business rules themselves caused certain transactions to fail.

[0052] (6) Current system error code: refers to the various types of error codes and their frequencies returned by the quick payment system during the transaction processing process within a specific time period. These error codes are usually used to identify specific failures or abnormal situations. Different error codes correspond to different failure causes, such as authentication failure, insufficient balance, communication timeout, etc. They can be used for troubleshooting and system optimization. By analyzing the error codes, problems in the system can be identified and resolved.

[0053] By obtaining these current operating parameters of the quick payment system in real time, the server can conduct a comprehensive assessment of the system's health status, thereby monitoring the system's health status in real time, ensuring that the quick payment system operates efficiently and reliably, and can provide services to users in a stable state.

[0054] S202: Input the current operating parameters of the quick payment system into a pre-trained long short-term memory model to predict the current state of the quick payment system.

[0055] In the embodiment of the present application, the current state includes: abnormal or normal.

[0056] Specifically, the server stores a pre-trained deep learning model, such as a long-short-term memory (LSTM) model. The server can input the current operating parameters of the quick payment system into this LSTM model to further predict whether the current status of the quick payment system is abnormal. This allows the server to autonomously detect the current operating status of the quick payment system, avoiding the low accuracy and high cost of manual detection.

[0057] This embodiment provides a method for detecting the status of a quick payment system, comprising: first, obtaining current operating parameters of the quick payment system in real time, where the current operating parameters include at least one of the following: a current payment transaction rate, a current final transaction rate, a current average response time, a current system success rate, a current business success rate, and a current system error code; then, inputting the current operating parameters of the quick payment system into a pre-trained long-short-term memory model to predict the current status of the quick payment system, where the current status includes abnormal or normal.

[0058] The following technical effects are achieved: by inputting the current operating parameters of the quick payment system obtained in real time into the pre-trained long-short-term memory model, an automated detection method is implemented to monitor the operating status of the quick payment system in real time according to the current operating parameters of the quick payment system, comprehensively evaluate the health status of the system, automatically predict whether the current operating status of the system is normal, and promptly discover system problems or failures, thereby ensuring that the quick payment system operates efficiently and reliably and provides services to users in a stable state; by utilizing the pre-trained long-short-term memory model, the accuracy and reliability of anomaly detection in the quick payment system are improved, thereby improving the user's payment experience and service quality; by reducing the frequency and intensity of manual intervention, the problems of low detection efficiency, insufficient accuracy and high cost investment caused by manual detection of the system status are avoided.

[0059] In one possible implementation, in step S202, the current operating parameters of the quick payment system are input into a pre-trained long-short-term memory model to predict the current state of the quick payment system, including:

[0060] S301: Calculate a first matching degree between current operating parameters and historical operating parameters.

[0061] Specifically, the server may further obtain historical operating parameters corresponding to multiple historical states of the quick payment system within a preset time period, and calculate a first degree of match between the current operating parameters corresponding to the current state of the quick payment system and the historical operating parameters corresponding to the historical states. The preset time period generally refers to a period of time before the current moment, which may be one week, one month, three months, or six months, etc. There is no specific limitation here, and the server may set the parameters based on actual circumstances. However, historical operating parameters corresponding to historical states that are too far away from the current moment and therefore lack reference significance are generally not obtained as historical operating parameters in the embodiments of this application.

[0062] S302: When the first matching degree is less than a preset first matching degree threshold, the current operating parameters are input into the long short-term memory model to predict the current state.

[0063] Specifically, if the first degree of match between the current operating parameters and the historical operating parameters is less than a preset first matching threshold, this indicates that none of the multiple historical states within the preset time period is relatively consistent with the current state, that is, none of the multiple historical states can match the current state. The server can then input the current operating parameters corresponding to the current state into the long-short-term memory model to predict the current state of the quick payment system.

[0064] An embodiment of the present application provides a method for detecting the status of a quick payment system. The method obtains historical operating parameters corresponding to multiple historical states of the quick payment system within a preset time period, calculates a first degree of match between the current operating parameters corresponding to the current state of the quick payment system and the historical operating parameters corresponding to the historical states, and then, when the first degree of match is less than a preset first degree of match threshold, inputs the current operating parameters into a long-short-term memory model to predict the current state of the quick payment system. This method allows the server to re-predict the current state of the quick payment system using the long-short-term memory model only when there is a significant difference between the current operating parameters and the acquired historical operating parameters. Otherwise, re-prediction is unnecessary. This minimizes the number of calculations performed by the server, reduces computational complexity, and thereby increases the server's computational speed, thereby improving the server's efficiency in detecting the current operating state of the quick payment system.

[0065] In a possible implementation, after step S301, the method further includes:

[0066] S401: Take a historical state corresponding to a historical operating parameter with a first matching degree greater than or equal to a first matching degree threshold as the current state.

[0067] Specifically, if the first degree of match between the current operating parameters and the historical operating parameters is greater than or equal to a preset first matching threshold, it indicates that the current state is relatively consistent with the historical state and can be matched with the historical state. The server can then directly use the historical state corresponding to the historical operating parameters with a first matching degree greater than or equal to the first matching threshold as the current state corresponding to the current moment, without having to predict the current operating state of the quick payment system.

[0068] An embodiment of the present application provides a state detection method for a quick payment system. When a first matching degree between current operating parameters and historical operating parameters is greater than or equal to a preset first matching degree threshold, the historical state corresponding to the historical operating parameters with a first matching degree greater than or equal to the first matching degree threshold is directly used as the current state corresponding to the current moment, thereby reducing the number of calculations used to predict the current state of the quick payment system through a long-short-term memory model, thereby saving the server's computing power resources, avoiding waste of the server's computing power resources, and further improving the server's detection efficiency of the current operating state of the quick payment system.

[0069] In a possible implementation, in step S401, taking the historical state corresponding to the historical operating parameter with the first matching degree greater than or equal to the first matching degree threshold as the current state includes:

[0070] S501: Determine, from one or more historical operating parameters having a first matching degree greater than or equal to a first matching degree threshold, a historical operating parameter having a historical time closest to the current time as a target historical operating parameter.

[0071] S502: The historical state corresponding to the target historical operating parameter is used as the current state.

[0072] In the embodiment of the present application, historical time refers to the time corresponding to the historical operating parameters, and current time refers to the current moment.

[0073] Specifically, when the first matching degree is greater than or equal to the first matching degree threshold, the server can select the historical operating parameter closest to the current time from the corresponding one or more historical operating parameters as the target historical operating parameter, so as to use the historical state corresponding to the target historical operating parameter as the current state.

[0074] An embodiment of the present application provides a method for detecting the status of a quick payment system. This method selects, from one or more historical operating parameters with a first matching degree greater than or equal to a first matching degree threshold, the historical operating parameter with the closest historical time to the current time as the target historical operating parameter, and then uses the historical state corresponding to the target historical operating parameter as the current state. The method for determining the current state is further refined. Because historical states closer to the current time are more reflective of the current state of the quick payment system, selecting the historical state closest to the current time as the current state makes the current state of the quick payment system ultimately output by the server more accurate, thereby further improving the accuracy and reliability of the server's detection of anomalies in the quick payment system.

[0075] In a possible implementation, in step S301, calculating a first matching degree between current operating parameters and historical operating parameters includes:

[0076] S601. Obtain the last update time of the quick payment system.

[0077] Specifically, the server can determine the date and time of the last system update by obtaining the quick payment system's log files, database records, system update records, version history, or system maintenance records. Alternatively, the server can obtain the time of the quick payment system's last update by calling the corresponding Application Programming Interface (API). In other words, the server can obtain the time of the quick payment system's last update through a variety of channels, and the specific methods for obtaining the information are not limited here.

[0078] S602: Calculate a first matching degree between the current operating parameters and the historical operating parameters after the last update time.

[0079] Specifically, each time the quick payment system is updated, the operating parameters of the system after the update may be completely different from those before the update.

[0080] Therefore, in order to improve the server's accuracy in identifying the operating status of the quick payment system and minimize the amount of computation required to calculate the first matching degree, thereby improving the server's prediction efficiency, the server can simply calculate the first matching degree between the current operating parameters and the historical operating parameters after the last update time, rather than between the current operating parameters and the historical operating parameters of different versions. This reduces the server's computational workload and improves the server's calculation speed.

[0081] In addition, the calculation of the first matching degree between the current operating parameters and the historical operating parameters can use a simple comparison algorithm (such as string comparison, numerical comparison) or a complex algorithm (such as a machine learning model, a similarity measurement algorithm) to calculate the first matching degree, and no specific restrictions are made here.

[0082] An embodiment of the present application provides a method for detecting the status of a quick payment system. This method takes into account the significant differences in operating parameters between different versions of the quick payment system after each version update. The method obtains the last update time of the quick payment system and only calculates a first matching degree between the current operating parameters and the historical operating parameters after the last update time. By only calculating the first matching degree between the current operating parameters and the historical operating parameters of the same version, the server's computational load for calculating the first matching degree is minimized, thereby increasing the server's computational speed and, in turn, improving the server's prediction efficiency and accuracy.

[0083] In a possible implementation, before step S201, the method further includes the server pre-training the long short-term memory model. The specific training process includes:

[0084] S701. Obtain a sample set of the quick payment system.

[0085] The sample set includes multiple samples, each sample includes sample operation parameters and corresponding sample status, and the sample operation parameters include at least one of the following: sample payment transaction rate, sample final transaction rate, sample average response time, sample system success rate, sample business success rate, and sample system error code.

[0086] Specifically, to pre-train the LSTM model, the server can first obtain a sample set consisting of multiple samples of operating parameters and corresponding statuses from the quick payment system's log files. A first predetermined proportion (e.g., 80%) of the samples in the sample set can be used as a training set for pre-training the LSTM model; a second predetermined proportion (e.g., 20%) of the samples can be used as a test set for testing the pre-trained LSTM model to verify whether the pre-trained LSTM model can accurately predict the operating status of the quick payment system. The sample operating parameters included in each sample in the sample set are similar to the current operating parameters in step S201 and are not further described here.

[0087] S702: Obtain relationship information between running parameters of each sample in the sample set.

[0088] Specifically, the server can further obtain information about the relationships between the operating parameters of each sample in the sample set. For example, by calculating the Pearson correlation coefficient between different operating parameters in the same sample to determine the degree of linear correlation between different operating parameters; or by using visualization tools such as scatter plots and heat maps to intuitively obtain information about the relationships between different operating parameters.

[0089] S703: Generate an extended sample set based on the sample set under the constraint of the relationship information.

[0090] Specifically, after obtaining the relationship information between the various sample operating parameters, the server can further generate extended sample sets based on the sample set, subject to the constraints of this relationship information. For example, with respect to the sample payment transaction rate and sample average response time, if the sample average response time is very long, payment transactions in the quick payment system typically fail. Therefore, there is a negative correlation between the sample payment transaction rate and the sample average response time. Therefore, subject to this negative correlation, the server can generate multiple corresponding extended sample sets based on the sample set.

[0091] Optionally, the server can perform automatic feature engineering on the sample operating parameters contained in multiple samples in the sample set. Specifically, the server can use the open source library of feature engineering tools (Featuretools) to perform automatic feature engineering. Use the prepared multiple samples as feature engineering input data, use the time node as the unique identifier feature, and then create a feature entity set containing multiple sample operating parameters and the relationship information between them. Then, use the Deep Feature Synthesis (DFS) method to perform deformation calculations on the multiple sample operating parameters in the feature entity set. For example, summing, averaging, weighted average, maximum or minimum values, etc. More complex deformation calculations can also be performed, such as calculating the standard deviation of the average response time of the samples based on the average response time of multiple samples. Thus, the corresponding extended sample set is obtained according to the feature entity set.

[0092] S704: Train the long short-term memory model using the sample set and the extended sample set.

[0093] Specifically, the server can further train the long short-term memory model through the sample set and the generated extended sample set, and train the long short-term memory model through further enriched data, thereby improving the prediction accuracy of the model.

[0094] An embodiment of the present application provides a state detection method for a quick payment system, which obtains a sample set of the quick payment system and the relationship information between the operating parameters of each sample in the sample set, and generates an extended sample set based on the sample set under the constraint of the relationship information, and then trains the long-short-term memory model with the sample set and the extended sample set. By further enriching the data for model training, the prediction accuracy of the model is improved, thereby achieving the effect of further improving the prediction accuracy of the server.

[0095] In a possible implementation, before step S703, the method further includes:

[0096] S801. For a target sample in a sample set with missing sample operation parameters, calculate a second matching degree between the target sample and the complete sample.

[0097] Specifically, after the server obtains the sample set of the quick payment system, it can check whether there is a target sample with missing sample operation parameters in the sample set. For target samples with missing sample operation parameters in the sample set, the server can further calculate the second matching degree between the target sample and the complete sample.

[0098] S802: Supplement the missing sample operation parameters in the target sample based on the complete sample whose second matching degree is greater than or equal to the preset second matching degree threshold.

[0099] Specifically, the server can use the K-Nearest Neighbor (KNN) interpolation method to supplement the missing sample operating parameters in the target sample based on the complete sample whose second matching degree is greater than or equal to the preset second matching degree threshold, that is, the corresponding sample operating parameters in the complete sample are used as the missing sample operating parameters in the target sample, thereby obtaining a sample set with complete sample operating parameters.

[0100] An embodiment of the present application provides a state detection method for a quick payment system, which calculates the second matching degree between a target sample with missing sample operating parameters and a complete sample, and uses the KNN interpolation method to supplement the missing sample operating parameters in the target sample based on complete samples with a second matching degree greater than or equal to a preset second matching degree threshold, thereby obtaining a sample set with complete sample operating parameters, realizing preprocessing of the acquired sample set, and further improving the prediction accuracy of the server.

[0101] In a possible implementation, after step S703, the method further includes:

[0102] S901. For each extended sample in the extended sample set, generate a description text of the extended sample according to the samples in the sample set corresponding to the extended sample and the relationship between the extended sample and the samples. The description text includes the relationship between the extended sample and the samples and the meaning of the extended sample.

[0103] Specifically, the server can first clarify the relationship between the extended sample and the corresponding sample in the sample set. For example, if the extended sample is generated by finding the corresponding sample in the sample set that is most similar to it, the server can describe how this similarity is calculated (for example, based on which sample operation parameters). For each extended sample, the server should record in detail how it is generated based on the sample in the corresponding sample set and its meaning.

[0104] An embodiment of the present application provides a state detection method for a quick payment system. By generating explanatory text for extended samples, clear and detailed explanatory text can be provided for each extended sample, ensuring that these texts are both accurate and explanatory, thereby facilitating subsequent training of the long-short-term memory model based on the extended sample set.

[0105] Figure 3 This is a schematic diagram of the structure of a status detection device for a quick payment system provided in an embodiment of the present application. Figure 3As shown, the status detection device of the quick payment system includes: an acquisition module 310, a prediction module 320;

[0106] Acquisition module 310, for acquiring in real time current operating parameters of the quick payment system, the current operating parameters including at least one of the following: current payment transaction rate, current final transaction rate, current average response time, current system success rate, current business success rate, and current system error code;

[0107] The prediction module 320 is used to input the current operating parameters of the quick payment system into the pre-trained long short-term memory model to predict the current state of the quick payment system, which includes: abnormal or normal.

[0108] In one possible design, the prediction module 320 includes: a first matching module and an input module;

[0109] A first matching degree module, configured to calculate a first matching degree between current operating parameters and historical operating parameters;

[0110] The input module is used to input the current operating parameters into the long short-term memory model when the first matching degree is less than a preset first matching degree threshold, and predict the current state.

[0111] In one possible design, the apparatus further includes: a comparison module;

[0112] The comparison module is configured to use a historical state corresponding to a historical operating parameter with a first matching degree greater than or equal to a first matching degree threshold as a current state.

[0113] In one possible design, the comparison module includes: a time comparison module and a determination module;

[0114] a time comparison module, configured to determine, from one or more historical operating parameters having a first matching degree greater than or equal to a first matching degree threshold, a historical operating parameter whose historical time is closest to the current time, as a target historical operating parameter, where the historical time is a time corresponding to the historical operating parameter;

[0115] The determination module is used to take the historical state corresponding to the target historical operating parameters as the current state.

[0116] In one possible design, the first matching degree module includes: an update time acquisition module and a calculation module;

[0117] Update time acquisition module, used to obtain the last update time of the quick payment system;

[0118] The calculation module is used to calculate a first matching degree between the current operating parameters and the historical operating parameters after the last update time.

[0119] In one possible design, the device further includes a model pre-training module, which includes: a sample set acquisition module, a relationship information acquisition module, an extended sample set generation module, and a training module;

[0120] A sample set acquisition module is used to acquire a sample set of the quick payment system. The sample set includes multiple samples, each sample includes sample operation parameters and a corresponding sample status, and the sample operation parameters include at least one of the following: sample payment transaction rate, sample final transaction rate, sample average response time, sample system success rate, sample business success rate, and sample system error code;

[0121] A relationship information acquisition module is used to obtain relationship information between the operating parameters of each sample in the sample set;

[0122] An extended sample set generation module, used to generate an extended sample set based on the sample set under the constraint of the relationship information;

[0123] The training module is used to train the long short-term memory model using sample sets and extended sample sets.

[0124] In one possible design, the apparatus further includes: a second matching module and a supplementing module;

[0125] A second matching degree module is configured to calculate a second matching degree between a target sample in the sample set having missing sample operation parameters and a complete sample, where the complete sample includes a sample having no missing sample operation parameters;

[0126] The supplementing module is used to supplement the missing sample operation parameters in the target sample based on the complete sample whose second matching degree is greater than or equal to the preset second matching degree threshold.

[0127] In one possible design, the apparatus further includes: an extended text generation module;

[0128] The extended text generation module is used to generate an explanatory text for each extended sample in the extended sample set based on the samples in the sample set corresponding to the extended sample and the relationship between the extended sample and the samples. The explanatory text includes the relationship between the extended sample and the sample and the meaning of the extended sample.

[0129] The state detection device of a quick payment system provided in this embodiment can execute the state detection method of a quick payment system in the above embodiment. Its implementation principle and technical effects are similar and will not be described in detail in this embodiment.

[0130] In the specific implementation of the aforementioned status detection device of a quick payment system, each module can be implemented as a processor, and the processor can execute computer-executable instructions stored in the memory, so that the processor executes the aforementioned status detection method of a quick payment system.

[0131] Figure 4 This is a schematic diagram of the structure of the electronic device provided in the embodiment of the present application. Figure 4 As shown, the electronic device includes: at least one processor 410 and a memory 420. The electronic device also includes a communication component 430. The processor 410, the memory 420 and the communication component 430 are connected via a bus 440.

[0132] During the specific implementation process, at least one processor 410 executes the computer execution instructions stored in the memory 420, so that at least one processor 410 executes the status detection method of a quick payment system executed on the electronic device side as described above.

[0133] The specific implementation process of the processor 410 can be found in the above method embodiment. Its implementation principle and technical effects are similar and will not be repeated here in this embodiment.

[0134] In the above embodiments, it should be understood that the processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASICs), etc. A general-purpose processor may be a microprocessor or any conventional processor. The steps of the method disclosed in the present invention may be directly executed by a hardware processor or by a combination of hardware and software modules within the processor.

[0135] The memory may include a high-speed RAM memory, and may also include a non-volatile storage NVM, such as at least one disk storage.

[0136] A bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus. Buses can be categorized as address buses, data buses, and control buses. For ease of illustration, the buses in the drawings of this application are not limited to just one bus or just one type of bus.

[0137] The above-mentioned functions implemented by the electronic device and the main control device have introduced the solutions provided by the embodiments of the present invention. It can be understood that in order to implement the above-mentioned functions, the electronic device or the main control device includes hardware structures and / or software modules corresponding to the execution of each function. In combination with the units and algorithm steps of the various examples described in the embodiments disclosed in the embodiments of the present invention, the embodiments of the present invention can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the technical solution of the embodiments of the present invention.

[0138] The present application also provides a computer-readable storage medium, which stores computer-executable instructions. When a processor executes the computer-executable instructions, it is used to implement the status detection method of the above-mentioned quick payment system.

[0139] The readable storage medium may be implemented by any type of volatile or non-volatile memory 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 may be any available medium that can be accessed by a general-purpose or special-purpose computer.

[0140] 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 an integral part of the processor. The processor and the readable storage medium can be located in an application specific integrated circuit (ASIC). Of course, the processor and the readable storage medium can also exist as discrete components in an electronic device or a main control device.

[0141] The present application also provides a computer program product, which includes a computer program. The computer program is stored in a readable storage medium. At least one processor of an electronic device can read the computer program from the readable storage medium. At least one processor executes the computer program so that the electronic device executes the solution provided by the above embodiment.

[0142] Those skilled in the art will appreciate that all or part of the steps in the above-described method embodiments can be implemented using hardware associated with program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0143] So far, the technical solution of the present application has been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the scope of protection of the present application is obviously not limited to these specific embodiments. The above embodiments are only used to illustrate the technical solution of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, ordinary technicians in this field should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some or all of the technical features therein. However, these modifications or replacements do not cause the essence of the corresponding technical solution to deviate from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for detecting the status of a quick payment system, characterized in that: include: obtaining, in real time, current operating parameters of the quick payment system, the current operating parameters including at least one of the following: current payment transaction rate, current final transaction rate, current average response time, current system success rate, current business success rate, and current system error code; The current operating parameters of the quick payment system are input into a pre-trained long short-term memory model to predict the current state of the quick payment system, where the current state includes abnormality or normality.

2. The method according to claim 1, characterized in that Inputting the current operating parameters of the quick payment system into a pre-trained long short-term memory model to predict the current state of the quick payment system includes: Calculating a first matching degree between the current operating parameters and the historical operating parameters; When the first matching degree is less than a preset first matching degree threshold, the current operating parameters are input into the long short-term memory model to predict the current state.

3. The method according to claim 2, characterized in that The method further comprises: The historical state corresponding to the historical operating parameter in which the first matching degree is greater than or equal to the first matching degree threshold is used as the current state.

4. The method according to claim 3, characterized in that The taking the historical state corresponding to the historical operating parameter whose first matching degree is greater than or equal to the first matching degree threshold as the current state includes: Determine, from one or more historical operating parameters whose first matching degree is greater than or equal to the first matching degree threshold, a historical operating parameter whose historical time is closest to the current time as a target historical operating parameter, where the historical time is the time corresponding to the historical operating parameter; The historical state corresponding to the target historical operating parameter is used as the current state.

5. The method according to any one of claims 2 to 4, characterized in that The calculating a first matching degree between the current operating parameter and the historical operating parameter includes: Obtain the last update time of the quick payment system; A first matching degree between the current operating parameter and the historical operating parameter after the last update time is calculated.

6. The method according to any one of claims 1 to 4, characterized in that The training process of the long short-term memory model includes: Obtaining a sample set of the quick payment system, the sample set comprising a plurality of samples, each sample comprising a sample operating parameter and a corresponding sample status, the sample operating parameter comprising at least one of the following: a sample payment transaction rate, a sample final transaction rate, a sample average response time, a sample system success rate, a sample business success rate, and a sample system error code; Obtaining relationship information between operating parameters of each sample in the sample set; generating an extended sample set according to the sample set under the constraint of the relationship information; The long short-term memory model is trained using the sample set and the extended sample set.

7. The method according to claim 6, characterized in that Under the constraint of the relationship information, before generating the extended sample set according to the sample set, the method further includes: For a target sample in the sample set that has a missing sample operation parameter, calculating a second matching degree between the target sample and a complete sample, where the complete sample includes a sample that does not have the missing sample operation parameter; The sample operation parameters missing in the target sample are supplemented according to the complete sample whose second matching degree is greater than or equal to a preset second matching degree threshold.

8. The method according to claim 6, characterized in that After generating an extended sample set according to the sample set under the constraint of the relationship information, the method further includes: For each extended sample in the extended sample set, an explanatory text of the extended sample is generated according to the sample in the sample set corresponding to the extended sample and the relationship between the extended sample and the sample, wherein the explanatory text includes the relationship between the extended sample and the sample and the meaning of the extended sample.

9. A status detection device for a quick payment system, characterized in that: include: an acquisition module, configured to acquire, in real time, current operating parameters of the quick payment system, wherein the current operating parameters include at least one of the following: a current payment transaction rate, a current final transaction rate, a current average response time, a current system success rate, a current business success rate, and a current system error code; The prediction module is used to input the current operating parameters of the quick payment system into a pre-trained long short-term memory model to predict the current state of the quick payment system, where the current state includes: abnormal or normal.

10. 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 8.

11. 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 8 when executed by a processor.

12. A computer program product, characterized in that The invention comprises a computer program, which implements the method according to any one of claims 1 to 8 when the computer program is executed by a processor.

Images