Performance failure risk prediction method and device and electronic equipment

Abstract

The invention discloses a performance fault risk prediction method and device and electronic equipment. The method relates to the field of big data, and comprises the following steps: acquiring a to-be-processed service processed on a service processing platform, and acquiring batch service processing data and online service processing data of the to-be-processed service; determining configuration information of the to-be-processed service according to the batch service processing data and the online service processing data; and inputting the batch service processing data, the online service processing data and the configuration information into the risk prediction model to obtain a prediction result, and determining a risk level when the service processing platform processes the to-be-processed service according to the prediction result. Through the method and the device, the problem of relatively low timeliness of determining whether the business processing platform has the performance fault based on the monitored operation data in the related technology is solved.

Description

Technical Field

[0001] The present application relates to the field of big data, and more specifically, to a method, device and electronic device for predicting performance failure risks. Background Art

[0002] As financial services of financial institutions continue to develop and increase, in order to ensure the normal operation of the business, it is necessary to transform the IT architecture simultaneously. At present, batch business systems and business processing have gradually changed from a design model centered on large data-centralized mainframes to a new processing architecture based on distributed platform batch processing and online services as the core, in order to improve system availability and system efficiency.

[0003] In order to ensure that the business processing platform can process business normally, it is necessary to monitor the business processing process to determine whether the business processing platform is operating normally, that is, whether there is a performance failure. At present, when monitoring the operating status of the business processing platform, the method usually adopted is to determine the operating status of the business processing platform based on the operating data obtained during the business processing, and determine whether an abnormality occurs in the process of processing the business based on the operating status. Then, in the case of an abnormality, the operating parameters of the business processing platform are adjusted in time to ensure the stable operation of the business processing platform.

[0004] However, the method of determining the operating status based on the operating data obtained during business processing and determining whether an abnormality occurs in the process of processing business based on the operating status can only be monitored in a timely manner after a performance failure occurs. It cannot guarantee the timeliness of discovering the performance failure phenomenon, thereby affecting the processing of the business by the business processing platform.

[0005] With regard to the problem in the related art that the timeliness of determining whether a business processing platform has a performance failure based on the operating data obtained through monitoring is low, no effective solution has been proposed so far. Summary of the invention

[0006] The main purpose of the present application is to provide a method, device and electronic device for predicting performance failure risk, so as to solve the problem of low timeliness in determining whether a business processing platform has a performance failure based on operating data obtained through monitoring in the related art.

[0007] In order to achieve the above-mentioned purpose, according to one aspect of the present application, a method for predicting performance failure risk is provided. The method comprises: obtaining pending business to be processed on a business processing platform, and obtaining batch business processing data and online business processing data of the pending business; determining configuration information of the pending business according to the batch business processing data and the online business processing data; inputting the batch business processing data, the online business processing data and the configuration information into a risk prediction model to obtain a prediction result, and determining the risk level of the business processing platform when processing the pending business according to the prediction result.

[0008] Optionally, batch business processing data, online business processing data and configuration information are input into a risk prediction model to obtain prediction results, including: grouping each feature data in the batch business processing data, online business processing data and configuration information according to the data type to obtain multiple groups of feature data, wherein the data type includes structured data and unstructured data; determining a processing strategy for data processing each group of feature data according to the data type, and using the processing strategy under the same data type to process the feature data to obtain multiple groups of processed feature data; inputting the multiple groups of processed feature data into the risk prediction model to obtain prediction results.

[0009] Optionally, a processing strategy for processing each group of feature data is determined according to the data type, and the feature data is processed using the processing strategy under the same data type to obtain multiple groups of processed feature data, including: when the data type is structured data, the feature data is normalized to obtain processed feature data; when the data type is unstructured data, the feature data located in a preset dictionary is obtained to obtain processed feature data, wherein the preset dictionary includes multiple preset words.

[0010] Optionally, the risk prediction model is trained in the following manner: obtaining business information of multiple historical businesses, and obtaining operating information of each historical business when it is processed, wherein the business information includes: historical batch business processing data, historical online business processing data and historical configuration information of the historical business, and the operating information includes the operating status of the data processing platform, and the identification value of each performance indicator of the data processing platform, and the identification value is used to characterize whether there is an abnormality in the performance indicator; determining the business information and the corresponding operating information as a set of sample data to obtain multiple sets of sample data, and using the multiple sets of sample data to train the neural network model to obtain a risk prediction model.

[0011] Optionally, determining the risk level of the business processing platform when processing the pending business based on the prediction results includes: when the prediction results indicate that the business processing platform can operate normally when processing the pending business, determining the risk level as no risk; when the prediction results indicate that the business processing platform cannot operate normally when processing the pending business, obtaining the abnormal probability of each performance indicator to obtain M abnormal probabilities; when there is an abnormal probability greater than a preset probability value among the M abnormal probabilities, determining the risk level as a first risk level; when all M abnormal probabilities are less than or equal to the abnormal probability of the preset probability value, determining the risk level as a second risk level, wherein the second risk level is lower than the first risk level.

[0012] Optionally, after determining the risk level of the business processing platform when processing the pending business based on the prediction results, the method also includes: when the risk level is a first risk level, recording the prediction results in the operation and maintenance log, and sending a prompt message to the operation and maintenance end, wherein the prompt information indicates that the equipment corresponding to the performance indicator to which the abnormal probability greater than the preset probability value belongs needs to be repaired; when the risk level is a second risk level, recording the prediction results in the operation and maintenance log, and processing the pending business through the business processing platform.

[0013] Optionally, obtaining batch business processing data and online business processing data of the business to be processed includes: obtaining the business content of the business to be processed, and determining the batch business processing data of the business to be processed based on the business content, wherein the batch business processing data includes at least one of the following: batch name, belonging application name, job step name, calling online service name, and calling concurrency number; determining the online business processing data of the business to be processed based on the business content, wherein the online business processing data includes at least one of the following: online service name, belonging application name, online method name, involved batch name, and batch concurrency number; determining the configuration information of the business to be processed based on the batch business processing data and the online business processing data includes: determining the number of servers and the configuration information of the servers required for processing the business to be processed based on the calling concurrency number and the batch concurrency number to obtain a first number; determining the configuration information of the servers and the first number as the configuration information of the business to be processed.

[0014] In order to achieve the above-mentioned purpose, according to another aspect of the present application, a prediction device for performance failure risk is provided. The device comprises: a first acquisition unit, used to acquire pending business to be processed on a business processing platform, and to acquire batch business processing data and online business processing data of the pending business; a first determination unit, used to determine the configuration information of the pending business according to the batch business processing data and the online business processing data; a prediction unit, used to input the batch business processing data, the online business processing data and the configuration information into a risk prediction model, obtain a prediction result, and determine the risk level of the business processing platform when processing the pending business according to the prediction result.

[0015] Optionally, the prediction unit includes: a grouping module, which is used to group each feature data in batch business processing data, online business processing data and configuration information according to the data type to obtain multiple groups of feature data, wherein the data type includes structured data and unstructured data; a processing module, which is used to determine a processing strategy for data processing on each group of feature data according to the data type, and use the processing strategy under the same data type to process the feature data to obtain multiple groups of processed feature data; an input module, which is used to input the multiple groups of processed feature data into the risk prediction model to obtain prediction results.

[0016] Optionally, the processing module includes: a normalization submodule, which is used to normalize the feature data when the data type is structured data to obtain processed feature data; and an acquisition submodule, which is used to acquire the feature data located in a preset dictionary when the data type is unstructured data to obtain processed feature data, wherein the preset dictionary includes multiple preset words.

[0017] Optionally, the risk prediction model is trained in the following manner: a second acquisition unit is used to obtain business information of multiple historical businesses, and obtain operation information of each historical business when it is processed, wherein the business information includes: historical batch business processing data, historical online business processing data and historical configuration information of historical businesses, and the operation information includes the operation status of the data processing platform and the identification value of each performance indicator of the data processing platform, and the identification value is used to characterize whether there is an abnormality in the performance indicator; a second determination unit is used to determine the business information and the corresponding operation information as a group of sample data, obtain multiple groups of sample data, and use the multiple groups of sample data to train the neural network model to obtain a risk prediction model.

[0018] Optionally, the prediction unit includes: a first determination module, which is used to determine the risk level as no risk when the prediction result indicates that the business processing platform can operate normally when processing the pending business; a first acquisition module, which is used to obtain the abnormal probability of each performance indicator and obtain M abnormal probabilities when the prediction result indicates that the business processing platform cannot operate normally when processing the pending business; a second determination module, which is used to determine the risk level as the first risk level when there is an abnormal probability greater than a preset probability value among the M abnormal probabilities; and a third determination module, which is used to determine the risk level as the second risk level when all the M abnormal probabilities are less than or equal to the abnormal probability of the preset probability value, wherein the second risk level is lower than the first risk level.

[0019] Optionally, after determining the risk level of the business processing platform when processing the pending business based on the prediction results, the device also includes: a recording unit, which is used to record the prediction results in the operation and maintenance log when the risk level is a first risk level, and send a prompt message to the operation and maintenance end, wherein the prompt information indicates that the equipment corresponding to the performance indicator to which the abnormal probability greater than the preset probability value belongs needs to be repaired; a processing unit, which is used to record the prediction results in the operation and maintenance log when the risk level is a second risk level, and process the pending business through the business processing platform.

[0020] Optionally, the first acquisition unit includes: a second acquisition module, used to acquire the business content of the business to be processed, and determine the batch business processing data of the business to be processed based on the business content, wherein the batch business processing data includes at least one of the following: batch name, application name, job step name, online service name, and concurrent number of calls; a fourth determination module, used to determine the online business processing data of the business to be processed based on the business content, wherein the online business processing data includes at least one of the following: online service name, application name, online method name, batch name involved, and batch concurrent number; the first determination unit includes: a fifth determination module, used to determine the number of servers and the configuration information of the servers required to process the business to be processed based on the concurrent number of calls and the batch concurrent number, and obtain a first number; a sixth determination module, used to determine the configuration information of the server and the first number as the configuration information of the business to be processed.

[0021] In an embodiment of the present application, the method of obtaining pending business to be processed on a business processing platform, and obtaining batch business processing data and online business processing data of the pending business; determining configuration information of the pending business based on the batch business processing data and the online business processing data; inputting the batch business processing data, the online business processing data and the configuration information into a risk prediction model to obtain a prediction result, and determining the risk level of the business processing platform when processing the pending business based on the prediction result, by obtaining the batch business processing data, the online business processing data and the configuration information configured when processing the pending business, and predicting the risk of running the pending business based on the batch business processing data, the online business processing data and the configuration information, thereby judging whether the business processing platform can operate normally when running the pending business based on the prediction result, and achieving the purpose of adjusting the operating data of the business processing platform running the pending business in advance based on the prediction result before the pending business is processed, thereby achieving the technical effect of ensuring that the business processing platform can process the pending business normally, thereby solving the technical problem of low timeliness in determining whether there is an abnormality in the business processing platform based on the operating data obtained by monitoring in the related technology. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The drawings constituting a part of the present application are used to provide a further understanding of the present application. The illustrative embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0023] Figure 1 A hardware structure block diagram of a computer terminal for implementing a method for predicting performance failure risk is shown;

[0024] Figure 2 is a flow chart of a method for predicting performance failure risk provided in Example 1 of the present application;

[0025] Figure 3 is a schematic diagram of a device for predicting performance failure risk provided in Example 2 of the present application;

[0026] Figure 4 It is a structural block diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0027] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0028] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0029] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0030] It should be noted that the performance failure risk prediction method, device and electronic device determined in the present disclosure can be used in the big data field, and can also be used in any field other than the big data field. The application field of the performance failure risk prediction method, device and electronic device determined in the present disclosure is not limited.

[0031] It should be noted that the collected information, 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.) used 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 relevant data are in compliance with the relevant laws, regulations and standards of the relevant regions, necessary confidentiality measures are taken, and public order and good customs are not violated. Corresponding operation entrances are provided for users to choose to authorize use or refuse use. If the user chooses to refuse, the expert decision-making process is entered. For example, an interface is set between this system and relevant users or institutions. Before obtaining relevant information, it is necessary to send an acquisition request to the aforementioned user or institution through the interface, and obtain relevant information after receiving the consent information fed back by the aforementioned user or institution.

[0032] The embodiments or examples of the present disclosure are not exhaustive, but are only illustrative of some embodiments or examples, and are not intended to be specific limitations on the scope of protection of the present disclosure. In the absence of contradiction, each step in a certain embodiment or example can be implemented as an independent example, and the steps can be combined arbitrarily. For example, the scheme after removing some steps in a certain embodiment or example can also be implemented as an independent example, and the order of the steps in a certain embodiment or example can be arbitrarily exchanged. In addition, the optional methods or optional examples in a certain embodiment or example can be combined arbitrarily; in addition, the various embodiments or examples can be combined arbitrarily, for example, some or all steps of different embodiments or examples can be combined arbitrarily, and a certain embodiment or example can be combined arbitrarily with the optional methods or optional examples of other embodiments or examples.

[0033] For the convenience of description, some nouns or terms involved in the embodiments of the present application are explained below:

[0034] Batch business: refers to a business model in which banks centrally process non-real-time, large amounts of accumulated business data at a specific time. It is usually used to process periodic, batch financial businesses such as payroll and loan repayment.

[0035] Online business: refers to a business model in which banks use real-time online systems to process immediate financial business requests initiated by customers, such as customers making deposits and withdrawals at ATMs or making online banking transfers.

[0036] Example 1

[0037] According to an embodiment of the present application, an embodiment of a method for predicting performance failure risk is also provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0038] The method embodiment provided in the first embodiment of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Figure 1 FIG. 1 shows a hardware structure block diagram of a computer terminal for implementing a method for predicting performance failure risk. Figure 1As shown, the computer terminal 10 (or mobile device) may include one or more (102a, 102b, ..., 102n are used to illustrate) processors 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory 104 for storing data, and a transmission device 106 for communication functions. In addition, it may also include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of the BUS bus), a network interface, a power supply and / or a camera. It can be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the above electronic device. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations are shown.

[0039] It should be noted that the one or more processors 102 and / or other data processing circuits described above may generally be referred to herein as "data processing circuits". The data processing circuits may be embodied in whole or in part as software, hardware, firmware, or any other combination thereof. In addition, the data processing circuit may be a single independent processing module, or may be incorporated in whole or in part into any of the other components in the computer terminal 10 (or mobile device). As described in the embodiments of the present application, the data processing circuit acts as a processor control (e.g., selection of a variable resistor terminal path connected to an interface).

[0040] The memory 104 can be used to store software programs and modules of application software, such as program instructions / data storage devices corresponding to the performance failure risk prediction method in the embodiment of the present application. The processor 102 executes various functional applications and data processing by running the software programs and modules stored in the memory 104, that is, the above-mentioned performance failure risk prediction method is realized. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories may be connected to the computer terminal 10 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0041] The transmission device 106 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of the computer terminal 10. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0042] The display may be, for example, a touch screen liquid crystal display (LCD) that enables a user to interact with a user interface of the computer terminal 10 (or mobile device).

[0043] Under the above operating environment, this application provides Figure 2 The prediction method of performance failure risk is shown. Figure 2 is a flow chart of a method for predicting performance failure risk according to Example 1 of the present application, such as Figure 2 As shown, the method includes:

[0044] Step S201, obtaining pending business to be processed on the business processing platform, and obtaining batch business processing data and online business processing data of the pending business.

[0045] It should be noted that as the complexity of executing business gradually increases, the business currently processed usually has two business modes: batch business and online business, and in some scenarios, the two business modes will be carried out at the same time. For example, the business to be processed may be a public transfer business, which may include batch transfer operations to several companies, and also include timely transfer operations to a company in an online manner upon receiving a request from a company. In this case, since the amount of business that needs to be processed at different times is different, the business data that needs to be configured by the business processing platform is also different. Therefore, in order to ensure that the business can be processed normally at any time, it is necessary to predict the processing results of the business based on the business configuration data after completing the configuration of the business data, and adjust the business configuration data in time according to the processing results, so as to ensure the normal progress of the business.

[0046] Specifically, after obtaining the pending business that the business platform needs to execute, the batch business processing data and online business processing data configured in the business processing platform for processing the business can be obtained, wherein the batch business processing data and the online business processing data are respectively the batch business indicator system data configured when processing batch business and the online service indicator system data configured when processing online business.

[0047] It should be noted that the batch service indicator system data and the online service indicator system data can be shown in Table 1:

[0048] Table 1

[0049]

[0050] Among them, batch business data may include but is not limited to batch name, application, batch job step, called online service name, called online method name, calling concurrency number, time window, etc.; online service negligence may include but is not limited to online service name, application, online method name, involved batch name, total concurrency number, batch concurrency number, etc.

[0051] Step S202: determining configuration information of the service to be processed according to the batch service processing data and the online service processing data.

[0052] Specifically, after obtaining the batch business processing data and the online business processing data, since the indicator values ​​required for executing batch business and online business are determined, the configuration information of the server that the business processing platform needs to allocate to the business when executing the business can be calculated based on the indicator values, so that the business to be processed can be run through the server allocated by the business processing platform.

[0053] It should be noted that when calculating the configuration information based on the batch business processing data and the online business processing data, the configuration information shown in Table 2 may be calculated:

[0054] Table 2

[0055]

[0056] Among them, the configuration information may include but is not limited to server resource information (server CPU, memory, I / O), transaction log information generated during the test (real-time usage of server resources), database resource information (database CPU, memory, number of connections, etc.), data processing information generated during the test (real-time usage of database resources), etc.

[0057] For example, the number of servers and related configuration information such as the CPU of the server can be determined according to the batch concurrency number and the call concurrency number, so as to ensure that the business processing platform can run the business to be processed normally.

[0058] Step S203, inputting batch business processing data, online business processing data and configuration information into the risk prediction model to obtain prediction results, and determining the risk level of the business processing platform when processing the pending business according to the prediction results.

[0059] It should be noted that the risk level may be the risk level of the performance failure risk of the business processing platform, wherein the performance failure risk may be the risk of performance failure or performance abnormality occurring when the business processing platform is running the business. By predicting the risk level, the probability of the performance failure risk of the business processing platform can be predicted, and then, in the event that there may be a performance failure risk, the business processing platform can be operated and maintained in a timely manner to ensure that the business processing platform can operate normally when processing the business and avoid performance failures when processing the business.

[0060] Specifically, when batch business processing data, online business processing data and configuration information are obtained, all indicator data configured by the data processing platform for executing the business to be processed, as well as relevant information of the business to be processed, can be determined. When the business processing system constructed by the above indicator data processes the business to be processed, the batch business processing data, online business processing data and configuration information can be analyzed through a risk prediction model to determine whether the business processing system constructed by the above indicator data can process the business to be processed normally, and the risk level of the risk of operating performance failure can be determined based on the prediction results. Then, it can be determined whether the business processing platform needs to be maintained or whether the above indicator data needs to be adjusted based on the risk level, thereby ensuring the normal operation of the business to be processed.

[0061] The performance failure risk prediction method provided in the embodiment of the present application obtains pending business to be processed on the business processing platform, and obtains batch business processing data and online business processing data of the pending business; determines the configuration information of the pending business according to the batch business processing data and the online business processing data; inputs the batch business processing data, the online business processing data and the configuration information into the risk prediction model to obtain the prediction result, and determines the risk level of the business processing platform when processing the pending business according to the prediction result. By obtaining the batch business processing data, the online business processing data and the configuration information configured when processing the pending business, and predicting the risk of running the pending business according to the batch business processing data, the online business processing data and the configuration information, it is judged whether the business processing platform can operate normally when running the pending business according to the prediction result, so as to achieve the purpose of adjusting the operation data of the business processing platform running the pending business in advance according to the prediction result before the pending business is processed, thereby achieving the technical effect of ensuring that the business processing platform can normally process the pending business, thereby solving the technical problem of low timeliness in determining whether there is an abnormality in the business processing platform based on the operation data obtained by monitoring in the related technology.

[0062] Optionally, in the performance failure risk prediction method provided in an embodiment of the present application, batch business processing data, online business processing data and configuration information are input into a risk prediction model to obtain a prediction result, including: grouping each feature data in the batch business processing data, online business processing data and configuration information according to the data type to obtain multiple groups of feature data, wherein the data type includes structured data and unstructured data; determining a processing strategy for data processing each group of feature data according to the data type, and processing the feature data using the processing strategy under the same data type to obtain multiple groups of processed feature data; inputting the multiple groups of processed feature data into the risk prediction model to obtain a prediction result.

[0063] It should be noted that when inputting batch business processing data, online business processing data and configuration information into the risk prediction model, due to the inconsistency of the data styles in the batch business processing data, online business processing data and configuration information, the model may not be able to accurately identify and read the data. Therefore, it is necessary to process the batch business processing data, online business processing data and configuration information first, and input the processed data into the risk prediction model to obtain more accurate prediction results.

[0064] Specifically, when processing data, since the data types of different data are different, the data can be grouped according to the data types of structured data and unstructured data, thereby obtaining two sets of feature data, wherein the data in each set of feature data is stored according to the correspondence between feature name and feature value.

[0065] Furthermore, since structured data is data with a clear format and is represented in the form of numerical values, while the format of unstructured data is not fixed, different types of data require different data processing strategies based on the data type to perform data processing operations, thereby obtaining data that can be accurately identified and processed by the risk prediction model, thereby ensuring that the risk prediction model can accurately identify indicator data in batch business processing data, online business processing data, and configuration information, and accurately predict the risk level based on the indicator data, thereby ensuring the accuracy of the prediction.

[0066] This embodiment classifies batch business processing data, online business processing data and indicator data in configuration information according to data type, thereby ensuring that the risk prediction model can accurately identify the indicator data input into the model, further ensuring the prediction accuracy of the risk prediction model.

[0067] Optionally, in the performance failure risk prediction method provided in the embodiment of the present application, a processing strategy for processing each group of feature data is determined according to the data type, and the feature data is processed using the processing strategy under the same data type to obtain multiple groups of processed feature data, including: when the data type is structured data, normalizing the feature data to obtain processed feature data; when the data type is unstructured data, obtaining feature data located in a preset dictionary to obtain processed feature data, wherein the preset dictionary includes multiple preset words.

[0068] Specifically, when the processing strategy is used to process the data, for the indicator data whose data type is structured data, since the indicator data is already a numerical value, the indicator data can be directly normalized to obtain the processed feature data.

[0069] For example, for timestamp data, data normalization can be performed according to the smallest unit of seconds; for resource usage data, normalization can be used to eliminate the impact of the dimension on the weight of subsequent model training.

[0070] Furthermore, for data types that are unstructured data, it is necessary to first filter the unstructured data through a preset dictionary and delete the unstructured data that cannot be used as indicator data for predictive operations. The unstructured data that cannot be used as indicator data for predictive operations may be data that cannot be converted into numerical values ​​or cannot be recognized by the model.

[0071] After being filtered through the preset dictionary, the remaining indicator data are all feature data that can be recognized by the model, so the feature data is determined as the filtered feature data, thereby ensuring that the model can accurately read the indicator data and determine the risk level based on the indicator data.

[0072] This embodiment processes different types of indicator data in different ways, thereby ensuring that the model can accurately read the indicator data and improving the accuracy of model prediction.

[0073] Optionally, in the performance failure risk prediction method provided in the embodiment of the present application, the risk prediction model is trained in the following manner: obtaining business information of multiple historical businesses, and obtaining operation information of each historical business when being processed, wherein the business information includes: historical batch business processing data, historical online business processing data and historical configuration information of the historical business, and the operation information includes the operation status of the data processing platform, the identification value of each performance indicator of the data processing platform, and the identification value is used to characterize whether there is an abnormality in the performance indicator; determining the business information and the corresponding operation information as a set of sample data to obtain multiple sets of sample data, and using the multiple sets of sample data to train the neural network model to obtain a risk prediction model.

[0074] Specifically, when training the risk prediction model, historical batch business processing data, historical online business processing data and historical configuration information of different businesses at different historical moments can be obtained. For example, the historical batch business processing data, historical online business processing data and historical configuration information of the business processing platform processing business A at moment A are obtained, and the operation information when processing business A through the above-mentioned historical indicator data is obtained, wherein the operation information is used to determine whether the operation status of the business processing platform when processing business A is normal, that is, whether the business processing platform is operating normally. When operating normally, it indicates that the performance of the business processing platform is normal. At this time, the identification value can be 1. When operating abnormally, it indicates that the performance of the business processing platform is abnormal. At this time, the identification value can be 0, thereby using the identification value to indicate whether the operation status of the business processing platform when processing business A at moment A is normal.

[0075] Furthermore, after obtaining the historical batch business processing data, historical online business processing data, historical configuration information and corresponding operation information of different businesses at different historical moments, the above-mentioned business information, that is, the historical indicator information and the corresponding operation information, can be used as a set of sample data, so that by obtaining the business information and operation information of different businesses at different moments, multiple sets of sample data can be obtained, and then the risk prediction model can be trained with multiple sets of sample data, thereby ensuring the accuracy of the training of the risk prediction model, and at the same time ensuring that the risk prediction model can determine whether the business processing platform can operate normally when processing the pending business based on the batch business processing data, online business processing data and configuration information, thereby achieving the effect of early prediction and monitoring of the business processing process.

[0076] It should be noted that when determining whether the business processing platform is operating normally based on operating information, it is possible to determine whether the operating status of the business processing platform is abnormal by comparing data such as batch time consumed, average service time consumed, server resource utilization rate, database resource utilization rate, etc. with the thresholds corresponding to each data.

[0077] This embodiment trains the risk identification model by acquiring sample data, thereby achieving the technical effect of improving the accuracy of model identification.

[0078] Optionally, in the performance failure risk prediction method provided in the embodiment of the present application, determining the risk level of the business processing platform when processing the pending business based on the prediction results includes: when the prediction results indicate that the business processing platform can operate normally when processing the pending business, determining the risk level as no risk; when the prediction results indicate that the business processing platform cannot operate normally when processing the pending business, obtaining the abnormal probability of each performance indicator to obtain M abnormal probabilities; when there is an abnormal probability greater than a preset probability value among the M abnormal probabilities, determining the risk level as a first risk level; when all M abnormal probabilities are less than or equal to the abnormal probability of the preset probability value, determining the risk level as a second risk level, wherein the second risk level is lower than the first risk level.

[0079] It should be noted that the prediction results include the probability of abnormal operation of the business processing platform when processing the pending business, and which indicator values ​​are abnormal in the case of abnormal operation. For example, the prediction results can be: the probability of normal operation of business A is 90%, and the probability of abnormal operation of business A is 10%, among which the probability of average time consumption not meeting the requirements is 90%, and the probability of abnormal database resource utilization is 10%. Therefore, the performance failure risk of running the pending business can be accurately determined based on the prediction results.

[0080] Specifically, when the prediction result is obtained, when the probability of normal operation of the pending business is 100%, or when the probability of normal operation of the pending business is greater than a preset value, the risk level indicating that the business platform has a performance failure risk is no risk.

[0081] When the prediction result indicates that the business processing platform cannot operate normally when processing pending business, that is, when the probability of abnormal operation of pending data is greater than the preset threshold, it is necessary to determine the level of risk occurrence based on the abnormal probability of each performance indicator. When the probability of each performance indicator is less than or equal to the preset probability value, for example, the probability of abnormal operation of business A is 10%, among which the probability of average time consumption not meeting the requirements is 4%, and the probability of abnormal database resource usage is 5%, it can be determined that the probability of each abnormal risk is less than the preset value of 10%, and the risk level of the current performance failure risk can be determined to be low risk, that is, the second risk level.

[0082] When there is an abnormal probability that the probability of a certain performance indicator is greater than the preset probability value, for example, the probability that the average time consumption does not meet the requirements is 40%, the risk level can be determined as high risk, that is, the second risk level, so as to accurately determine the performance failure risk of the business processing platform when processing the pending business based on the prediction results, thereby ensuring the stable operation of the business processing platform.

[0083] This embodiment accurately determines the performance failure risk of the business processing platform when processing the pending business based on the prediction results, so that the operating indicator data of the business data platform can be adjusted according to the performance failure risk, thereby ensuring the stable processing of the pending business and ensuring the stable operation of the business processing platform.

[0084] Optionally, in the performance failure risk prediction method provided in the embodiment of the present application, after determining the risk level of the business processing platform when processing the pending business based on the prediction results, the method also includes: when the risk level is a first risk level, recording the prediction result in an operation and maintenance log, and sending a prompt message to the operation and maintenance end, wherein the prompt information indicates that the equipment corresponding to the performance indicator to which the abnormal probability greater than the preset probability value belongs needs to be repaired; when the risk level is a second risk level, recording the prediction result in the operation and maintenance log, and processing the pending business through the business processing platform.

[0085] Specifically, when the risk level is the first risk level, it indicates that the current risk is high, and the current prediction results need to be recorded in the operation and maintenance log for storage, and a prompt message is sent to the operation and maintenance end, so that the operation and maintenance section can process the indicator data of the business processing platform after receiving the prompt message, thereby ensuring that the business processing platform can operate normally when processing the business to be processed.

[0086] Furthermore, when the risk level is the second risk level, it indicates that the current risk is low. The prediction results need to be recorded in the operation and maintenance log, and the pending business needs to be processed through the business processing platform. The actual processing results are compared with the prediction results to determine whether the prediction results are accurate. At the same time, due to the low risk situation, the business processing platform can still process the pending business normally. Therefore, the sample data can be updated by processing the pending business normally, thereby improving the prediction accuracy of the model.

[0087] This embodiment performs different processing on pending businesses with different predicted risks, thereby ensuring that pending businesses can be processed normally and that frequent maintenance of the business processing platform does not occur.

[0088] Optionally, in the performance failure risk prediction method provided in the embodiment of the present application, obtaining batch business processing data and online business processing data of the pending business includes: obtaining the business content of the pending business, and determining the batch business processing data of the pending business based on the business content, wherein the batch business processing data includes at least one of the following: batch name, application name, job step name, online service name, and concurrent number of calls; determining the online business processing data of the pending business based on the business content, wherein the online business processing data includes at least one of the following: online service name, application name, online method name, batch name involved, and batch concurrent number; determining the configuration information of the pending business based on the batch business processing data and the online business processing data includes: determining the number of servers and the configuration information of the servers required for processing the pending business based on the concurrent number of calls and the batch concurrent number, and obtaining a first number; determining the configuration information of the servers and the first number as the configuration information of the pending business.

[0089] Specifically, when acquiring batch business processing data, online business processing data and configuration information, the above data acquisition operation can be performed according to the instruction data shown in Table 3, so as to obtain relevant configuration information that can be used to characterize this business processing operation, and then determine the performance failure risk of the business processing platform when processing the pending business based on the configuration information.

[0090] Table 3

[0091]

[0092]

[0093] This embodiment ensures the accuracy of model prediction by explaining the indicator data that needs to be obtained.

[0094] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0095] Example 2

[0096] The embodiment of the present application also provides a performance failure risk prediction device. It should be noted that the performance failure risk prediction device of the embodiment of the present application can be used to execute the performance failure risk prediction method provided in the above embodiment. The performance failure risk prediction device provided in the embodiment of the present application is introduced below.

[0097] Figure 3 is a schematic diagram of a performance failure risk prediction device provided in Example 2 of the present application, such as Figure 3As shown, the device comprises:

[0098] The first acquisition unit 31 is used to acquire the pending business to be processed on the business processing platform, and acquire batch business processing data and online business processing data of the pending business.

[0099] The first determining unit 32 is used to determine the configuration information of the to-be-processed service according to the batch service processing data and the online service processing data.

[0100] The prediction unit 33 is used to input batch business processing data, online business processing data and configuration information into the risk prediction model to obtain a prediction result, and determine the risk level of the business processing platform when processing the pending business based on the prediction result.

[0101] The performance failure risk prediction device provided in the embodiment of the present application obtains the pending business to be processed on the business processing platform through the first acquisition unit 31, and obtains the batch business processing data and online business processing data of the pending business; the first determination unit 32 determines the configuration information of the pending business according to the batch business processing data and the online business processing data; the prediction unit 33 inputs the batch business processing data, the online business processing data and the configuration information into the risk prediction model to obtain the prediction result, and determines the risk level of the business processing platform when processing the pending business according to the prediction result. By acquiring the batch business processing data, online business processing data and configuration information configured when processing the pending business, and predicting the risks of running the pending business based on the batch business processing data, online business processing data and configuration information, it is possible to judge whether the business processing platform can operate normally when running the pending business based on the prediction results. This achieves the purpose of adjusting the operating data of the business processing platform for running the pending business in advance based on the prediction results before the pending business is processed, thereby achieving the technical effect of ensuring that the business processing platform can process the pending business normally, and further solving the technical problem of low timeliness in determining whether there is an abnormality in the business processing platform based on the operating data obtained through monitoring in the related technology.

[0102] Optionally, in the performance failure risk prediction device provided in the embodiment of the present application, the prediction unit 33 includes: a grouping module, which is used to group each feature data in batch business processing data, online business processing data and configuration information according to the data type to obtain multiple groups of feature data, wherein the data type includes structured data and unstructured data; a processing module, which is used to determine a processing strategy for data processing on each group of feature data according to the data type, and use the processing strategy under the same data type to process the feature data to obtain multiple groups of processed feature data; an input module, which is used to input the multiple groups of processed feature data into a risk prediction model to obtain a prediction result.

[0103] Optionally, in the performance failure risk prediction device provided in the embodiment of the present application, the processing module includes: a normalization sub-module, which is used to normalize the feature data when the data type is structured data to obtain processed feature data; and an acquisition sub-module, which is used to acquire the feature data located in a preset dictionary when the data type is unstructured data to obtain processed feature data, wherein the preset dictionary includes multiple preset words.

[0104] Optionally, in the performance failure risk prediction device provided in the embodiment of the present application, the risk prediction model is trained in the following manner: a second acquisition unit is used to obtain business information of multiple historical businesses, and obtain the operation information of each historical business when it is processed, wherein the business information includes: historical batch business processing data, historical online business processing data and historical configuration information of historical businesses, and the operation information includes the operating status of the data processing platform and the identification value of each performance indicator of the data processing platform, and the identification value is used to characterize whether there is an abnormality in the performance indicator; a second determination unit is used to determine the business information and the corresponding operation information as a set of sample data, obtain multiple sets of sample data, and use the multiple sets of sample data to train the neural network model to obtain a risk prediction model.

[0105] Optionally, in the performance failure risk prediction device provided in the embodiment of the present application, the prediction unit 33 includes: a first determination module, which is used to determine the risk level as no risk when the prediction result indicates that the business processing platform can operate normally when processing the pending business; a first acquisition module, which is used to obtain the abnormal probability of each performance indicator and obtain M abnormal probabilities when the prediction result indicates that the business processing platform cannot operate normally when processing the pending business; a second determination module, which is used to determine the risk level as the first risk level when there is an abnormal probability greater than a preset probability value among the M abnormal probabilities; and a third determination module, which is used to determine the risk level as the second risk level when all the M abnormal probabilities are less than or equal to the abnormal probability of the preset probability value, wherein the second risk level is lower than the first risk level.

[0106] Optionally, in the performance failure risk prediction device provided in the embodiment of the present application, after determining the risk level of the business processing platform when processing the pending business based on the prediction results, the device also includes: a recording unit, which is used to record the prediction results in the operation and maintenance log when the risk level is a first risk level, and send a prompt message to the operation and maintenance end, wherein the prompt information indicates that the equipment corresponding to the performance indicator to which the abnormal probability greater than the preset probability value belongs needs to be repaired; a processing unit, which is used to record the prediction results in the operation and maintenance log when the risk level is a second risk level, and process the pending business through the business processing platform.

[0107] Optionally, in the performance failure risk prediction device provided in the embodiment of the present application, the first acquisition unit 31 includes: a second acquisition module, used to acquire the business content of the business to be processed, and determine the batch business processing data of the business to be processed based on the business content, wherein the batch business processing data includes at least one of the following: batch name, application name, job step name, call online service name, and call concurrency number; a fourth determination module, used to determine the online business processing data of the business to be processed based on the business content, wherein the online business processing data includes at least one of the following: online service name, application name, online method name, involved batch name, and batch concurrency number; the first determination unit 32 includes: a fifth determination module, used to determine the number of servers and the configuration information of the servers required to process the business to be processed based on the call concurrency number and the batch concurrency number, and obtain a first number; a sixth determination module, used to determine the configuration information of the server and the first number as the configuration information of the business to be processed.

[0108] It should be noted that the first acquisition unit 31, the first determination unit 32, and the prediction unit 33 correspond to steps S201 to S203 in Embodiment 1, and the two modules and the corresponding steps implement the same examples and application scenarios, but are not limited to the contents disclosed in Embodiment 1. It should be noted that the above modules or units may be hardware components or software components stored in a memory (e.g., memory 104) and processed by one or more processors (e.g., processors 102a, 102b, ..., 102n), and the above modules may also be part of a device and run in the computer terminal 10 provided in Embodiment 1.

[0109] Example 3

[0110] An embodiment of the present application may provide an electronic device, Figure 4 is a structural block diagram of an electronic device according to an embodiment of the present application. Figure 4 As shown, the electronic device may include: one or more ( Figure 4 (only one is shown) processor 1002, memory 1004, storage controller, and peripheral interface, wherein the peripheral interface is connected to the radio frequency module, audio module and display.

[0111] Among them, the memory can be used to store software programs and modules, such as program instructions / modules corresponding to the methods and devices in the embodiments of the present application, and the processor executes various functional applications and data processing by running the software programs and modules stored in the memory, that is, realizing the above-mentioned method. The memory may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory may further include a memory remotely arranged relative to the processor, and these remote memories may be connected to the terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0112] The processor can call the information and application programs stored in the memory through the transmission device to perform the following steps: obtain the pending business to be processed on the business processing platform, and obtain the batch business processing data and online business processing data of the pending business; determine the configuration information of the pending business based on the batch business processing data and the online business processing data; input the batch business processing data, the online business processing data and the configuration information into the risk prediction model to obtain the prediction results, and determine the risk level of the business processing platform when processing the pending business based on the prediction results.

[0113] The processor can also call the information and application programs stored in the memory through the transmission device to perform the following steps: input batch business processing data, online business processing data and configuration information into the risk prediction model to obtain prediction results including: grouping the various feature data in the batch business processing data, online business processing data and configuration information according to the data type to obtain multiple groups of feature data, wherein the data type includes structured data and unstructured data; determining a processing strategy for data processing each group of feature data according to the data type, and using the processing strategy under the same data type to process the feature data to obtain multiple groups of processed feature data; inputting the multiple groups of processed feature data into the risk prediction model to obtain prediction results.

[0114] The processor can also call the information and application programs stored in the memory through the transmission device to perform the following steps: determine the processing strategy for data processing of each group of feature data according to the data type, and use the processing strategy under the same data type to process the feature data to obtain multiple groups of processed feature data, including: when the data type is structured data, normalize the feature data to obtain processed feature data; when the data type is unstructured data, obtain the feature data located in a preset dictionary to obtain processed feature data, wherein the preset dictionary includes multiple preset words.

[0115] The processor can also call the information and application programs stored in the memory through the transmission device to perform the following steps: The risk prediction model is trained in the following manner: the business information of multiple historical businesses is obtained, and the operation information of each historical business when it is processed is obtained, wherein the business information includes: historical batch business processing data, historical online business processing data and historical configuration information of historical businesses, and the operation information includes the operation status of the data processing platform and the identification value of each performance indicator of the data processing platform, and the identification value is used to characterize whether there is an abnormality in the performance indicator; the business information and the corresponding operation information are determined as a set of sample data to obtain multiple sets of sample data, and the multiple sets of sample data are used to train the neural network model to obtain a risk prediction model.

[0116] The processor can also call the information and application programs stored in the memory through the transmission device to perform the following steps: determining the risk level of the business processing platform when processing the pending business based on the prediction results, including: when the prediction results indicate that the business processing platform can operate normally when processing the pending business, the risk level is determined to be no risk; when the prediction results indicate that the business processing platform cannot operate normally when processing the pending business, the abnormal probability of each performance indicator is obtained to obtain M abnormal probabilities; when there is an abnormal probability greater than a preset probability value among the M abnormal probabilities, the risk level is determined to be a first risk level; when the M abnormal probabilities are all less than or equal to the abnormal probability of the preset probability value, the risk level is determined to be a second risk level, wherein the second risk level is lower than the first risk level.

[0117] The processor can also call the information and application programs stored in the memory through the transmission device to perform the following steps: After determining the risk level of the business processing platform when processing the pending business based on the prediction results, the method also includes: when the risk level is the first risk level, recording the prediction results in the operation and maintenance log, and sending a prompt message to the operation and maintenance end, wherein the prompt information indicates that the equipment corresponding to the performance indicator to which the abnormal probability greater than the preset probability value belongs needs to be repaired; when the risk level is the second risk level, recording the prediction results in the operation and maintenance log, and processing the pending business through the business processing platform.

[0118] The processor can also call the information and application programs stored in the memory through the transmission device to perform the following steps: obtaining the batch business processing data and online business processing data of the business to be processed includes: obtaining the business content of the business to be processed, and determining the batch business processing data of the business to be processed according to the business content, wherein the batch business processing data includes at least one of the following: batch name, belonging application name, job step name, calling online service name, and calling concurrent number; determining the online business processing data of the business to be processed according to the business content, wherein the online business processing data includes at least one of the following: online service name, belonging application name, online method name, involved batch name, and batch concurrent number; determining the configuration information of the business to be processed according to the batch business processing data and the online business processing data includes: determining the number of servers and the configuration information of the servers required for processing the business to be processed according to the calling concurrent number and the batch concurrent number, and obtaining a first number; determining the configuration information of the servers and the first number as the configuration information of the business to be processed.

[0119] It can be understood by those skilled in the art that Figure 4 The structure shown is for illustration only, and the electronic device may also be a smart phone (such as an Android phone, an iOS phone, etc.), a tablet computer, a PDA, a mobile Internet device (Mobile Internet Devices, MID), a PAD, and other terminal devices. Figure 4 The structure of the electronic device is not limited. Figure 4 More or fewer components (such as network interfaces, display devices, etc.) shown in, or having Figure 4 Different configurations are shown.

[0120] A person of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing the hardware related to the terminal device through a program, and the program can be stored in a computer-readable storage medium, and the storage medium may include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0121] Example 4

[0122] The embodiment of the present application further provides a storage medium. Optionally, in this embodiment, the storage medium can be used to store the program code executed by the performance failure risk prediction method provided in the first embodiment.

[0123] Optionally, in this embodiment, the above storage medium may be located in any computer terminal in a computer terminal group in a computer network, or in any mobile terminal in a mobile terminal group.

[0124] The present application also provides a computer program product, which, when executed on a data processing device, is suitable for executing the steps of the method for predicting performance failure risk.

[0125] The present application also provides a computer-readable storage medium, which includes a stored executable program, wherein when the executable program is running, the program controls the device where the computer-readable storage medium is located to execute the steps of the method for predicting performance failure risks.

[0126] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0127] In the above embodiments of the present application, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0128] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0129] 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.

[0130] In addition, each functional unit in each embodiment of the present application 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. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0131] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or optical disk and other media that can store program codes.

[0132] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A method for predicting performance failure risk, characterized in that: include: Acquire pending business to be processed on the business processing platform, and acquire batch business processing data and online business processing data of the pending business; Determining configuration information of the to-be-processed service according to the batch service processing data and the online service processing data; The batch business processing data, the online business processing data and the configuration information are input into a risk prediction model to obtain a prediction result, and the risk level of the business processing platform when processing the pending business is determined based on the prediction result.

2. The method according to claim 1, characterized in that Inputting the batch business processing data, the online business processing data and the configuration information into a risk prediction model to obtain a prediction result includes: Grouping the batch business processing data, the online business processing data and each feature data in the configuration information according to data type to obtain multiple groups of feature data, wherein the data type includes structured data and unstructured data; Determine a processing strategy for processing each set of feature data according to the data type, and process the feature data using the processing strategy under the same data type to obtain multiple sets of processed feature data; The multiple groups of processed feature data are input into the risk prediction model to obtain the prediction result.

3. The method according to claim 2, characterized in that Determine a processing strategy for processing each set of feature data according to the data type, and use the processing strategy under the same data type to process the feature data, and obtain multiple sets of processed feature data including: In the case where the data type is structured data, normalizing the feature data to obtain the processed feature data; In the case where the data type is unstructured data, feature data in a preset dictionary is acquired to obtain the processed feature data, wherein the preset dictionary includes a plurality of preset words.

4. The method according to claim 1, characterized in that: The risk prediction model is trained in the following way: Acquire business information of multiple historical businesses, and acquire operation information of each historical business when it is processed, wherein the business information includes: historical batch business processing data, historical online business processing data and historical configuration information of the historical business, and the operation information includes the operation status of the data processing platform and the identification value of each performance indicator of the data processing platform, and the identification value is used to indicate whether the performance indicator is abnormal; The business information and the corresponding operation information are determined as a group of sample data to obtain multiple groups of sample data, and the neural network model is trained using the multiple groups of sample data to obtain the risk prediction model.

5. The method according to claim 1, characterized in that Determining the risk level of the business processing platform when processing the pending business according to the prediction result includes: If the prediction result indicates that the business processing platform can operate normally when processing the pending business, the risk level is determined to be no risk; When the prediction result indicates that the business processing platform cannot operate normally when processing the to-be-processed business, obtaining the abnormal probability of each performance indicator to obtain M abnormal probabilities; When there is an abnormal probability greater than a preset probability value among the M abnormal probabilities, determining the risk level as a first risk level; In a case where the M abnormal probabilities are all less than or equal to the abnormal probability of the preset probability value, the risk level is determined as a second risk level, wherein the second risk level is lower than the first risk level.

6. The method according to claim 5, characterized in that After determining the risk level of the business processing platform when processing the to-be-processed business according to the prediction result, the method further includes: When the risk level is the first risk level, the prediction result is recorded in the operation and maintenance log, and a prompt message is sent to the operation and maintenance end, wherein the prompt message indicates that the equipment corresponding to the performance indicator to which the abnormal probability greater than the preset probability value belongs needs to be repaired; When the risk level is the second risk level, the prediction result is recorded in the operation and maintenance log, and the pending business is processed through the business processing platform.

7. The method according to claim 1, characterized in that Acquiring batch business processing data and online business processing data of the business to be processed includes: Acquire the business content of the business to be processed, and determine the batch business processing data of the business to be processed according to the business content, wherein the batch business processing data includes at least one of the following: batch name, application name, job step name, online service name, and concurrent number of calls; Determine the online business processing data of the to-be-processed business according to the business content, wherein the online business processing data includes at least one of the following: online service name, application name, online method name, batch name involved, and batch concurrency number; Determining the configuration information of the to-be-processed service according to the batch service processing data and the online service processing data includes: Determine the number of servers and configuration information of the servers required for processing the pending business according to the concurrent number of calls and the concurrent number of batches, to obtain a first number; The configuration information of the server and the first quantity are determined as the configuration information of the service to be processed.

8. A device for predicting performance failure risk, characterized in that: include: A first acquisition unit is used to acquire pending business to be processed on the business processing platform, and to acquire batch business processing data and online business processing data of the pending business; A first determining unit, configured to determine configuration information of the to-be-processed service according to the batch service processing data and the online service processing data; The prediction unit is used to input the batch business processing data, the online business processing data and the configuration information into the risk prediction model to obtain a prediction result, and determine the risk level of the business processing platform when processing the pending business according to the prediction result.

9. A computer program product comprising computer instructions, characterized in that When the computer instructions are executed by a processor, the steps of the method for predicting performance failure risk described in any one of claims 1 to 7 are implemented.

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

Images