Micro-service state prediction method, system and device based on time sequence weighted directed graph

Abstract

The invention provides a micro-service state prediction method, system and device based on a time sequence weighted directed graph. The method comprises the following steps: acquiring and preprocessing a call chain log, a micro-service log and monitoring index data in real time to generate preprocessed data; based on the preprocessed data, a time sequence weighted directed graph is generated, and the time sequence weighted directed graph is used for describing the overall operation state of the micro-service; and on the basis of a machine learning algorithm, the overall operation state of the micro-service is predicted, so that predictive treatment on the micro-service system is realized. According to the method, the micro-service state prediction and the prediction process of the time sequence weighted directed topological graph at the t + 1 moment are realized based on the time sequence weighted directed graph, and the process does not need human intervention, so that algorithm parameters can be obtained through data real-time training of t and before t, and the data at the t + 1 moment can be reasoned and predicted.

Description

Technical Field

[0001] The present application relates to the field of Internet microservice technology, and in particular to a microservice status prediction method, system and device based on a time-series weighted directed graph. Background Art

[0002] With the rapid development of Internet technology, microservice architecture has been widely used in various Internet systems. By adopting a loosely coupled approach, the business system can independently deploy different functional modules, which brings flexibility and convenience. However, with the continuous increase in business functions, the ever-expanding number of microservices, the increasingly complex call dependencies between microservices, and the scattered performance indicators and log records, the management and maintenance of the system has become more complicated. At present, the common microservice governance solutions basically use the microservice topology map to assist in troubleshooting, but the microservice topology map is not static, but changes over time. Therefore, there is an urgent need for a way to describe the dynamic changes of the microservice topology map, to be able to take a global snapshot record of the moment when the problem occurs, and to further predict the future state, so as to achieve predictive governance of the microservice system.

[0003] At present, microservice topology is mainly used to assist in fault location in microservice governance. Common methods include: (1) constructing a service topology diagram to assist in fault location after a fault occurs, but none of them involve time series indicator data. For example, Beijing Zitiao Network Technology Co., Ltd. proposed "Microservice Link Topology Processing Method, Device and Readable Storage Medium (CN202111101143.8)" and China Merchants Bank Co., Ltd. proposed "Microservice Governance Method, Device and Storage Medium (CN202310701184.3)". (2) Constructing a service topology diagram and storing time series indicators at the same time, but the time series indicator data is not integrated with the topology structure, but is simply used as an auxiliary annotation of graph nodes and edges. Specific fault location and analysis are still based on manual and previous experience. For example, Beijing Yiche Information Technology Co., Ltd. proposed "A Microservice Architecture System for Easy Management (CN202310290292.6)". (3) Constructing a topological relationship and storing time series indicators. The use of time series data is mainly to load time series indicator data after a fault occurs to assist in locating the problem. For example, China Shenhua International Engineering Co., Ltd. proposed a method for diagnosing microservice anomalies based on attribute relationship graphs (CN202111461547.8) and Hangzhou Dianzi University proposed a method for diagnosing microservice transient faults based on multimodal anomaly detection (CN202310469236.9).

[0004] Therefore, there is still a lack of a method that can deeply integrate microservice topology graphs and time series indicator data of microservice monitoring, and can simultaneously utilize the characteristics of graphs and time series data to reflect the overall status of microservices and predict their future status in both time and space dimensions, so as to achieve predictive governance of microservice systems. Summary of the invention

[0005] The present application shows a method, system and device for predicting microservice status based on a time-series weighted directed graph.

[0006] In a first aspect, the present application shows a microservice status prediction method based on a time-series weighted directed graph, the method comprising:

[0007] Collect and pre-process call chain logs, microservice logs, and monitoring indicator data in real time to generate pre-processed data;

[0008] Based on the pre-processed data, a time-series weighted directed graph is generated, where the time-series weighted directed graph is used to describe the overall operating status of the microservice;

[0009] Based on machine learning algorithms, the overall operating status of microservices is predicted to achieve predictive governance of microservice systems.

[0010] In an exemplary embodiment of the present disclosure, the method further includes:

[0011] Collect call chain logs, microservice logs, and monitoring indicator data in real time;

[0012] Pre-processing the real-time collected data;

[0013] Describe the preset events carried in the microservice business processing log;

[0014] Get microservice performance and operating system resource metrics based on preset probes.

[0015] In an exemplary embodiment of the present disclosure, in the method, real-time collection of call chain logs, microservice logs, and monitoring indicator data further includes:

[0016] The software development kit SDK of opentelemetry, an observability framework and toolkit integrated with each service in the microservice system, realizes the collection and reporting of logs of each microservice call chain.

[0017] In an exemplary embodiment of the present disclosure, in the method, pre-processing the real-time collected data further comprises:

[0018] The real-time collected data is pre-processed by deduplication and weight sorting.

[0019] In an exemplary embodiment of the present disclosure, the method further includes:

[0020] A time-series weighted directed graph is defined, weights of edges in the time-series weighted directed graph are determined, and a microservice time-series weighted directed topology graph is generated.

[0021] In an exemplary embodiment of the present disclosure, the method further includes:

[0022] Based on the autoregressive integrated moving average model ARIMA, the changes in the time series vector are modeled to predict the overall operating status of the microservice.

[0023] In a second aspect, the present application shows a microservice state prediction system based on a time-series weighted directed graph, the system comprising:

[0024] The data pre-processing module collects and pre-processes call chain logs, microservice logs, and monitoring indicator data in real time to generate pre-processed data;

[0025] A time-series weighted directed graph construction module generates a time-series weighted directed graph based on the pre-processed data, wherein the time-series weighted directed graph is used to describe the overall operation status of the microservice;

[0026] The microservice status prediction module predicts the overall operating status of microservices based on machine learning algorithms to achieve predictive governance of the microservice system.

[0027] In a third aspect, the present application shows a microservice state prediction device based on a time-series weighted directed graph, the device comprising:

[0028] The data pre-processing module is used to collect and pre-process call chain logs, microservice logs, and monitoring indicator data in real time to generate pre-processed data;

[0029] A time-series weighted directed graph construction module, used to generate a time-series weighted directed graph based on the pre-processed data, wherein the time-series weighted directed graph is used to describe the overall operation status of the microservice;

[0030] The microservice status prediction module is used to predict the overall operating status of microservices based on machine learning algorithms to achieve predictive governance of the microservice system.

[0031] In a fourth aspect, the present application illustrates an electronic device, comprising: a processor; a memory for storing processor-executable instructions; wherein the processor is configured to execute the method described in any of the above aspects.

[0032] In a fifth aspect, the present application illustrates a non-temporary computer-readable storage medium, which, when instructions in the storage medium are executed by a processor of an electronic device, enables the electronic device to execute a method as described in any of the above aspects.

[0033] In a sixth aspect, the present application illustrates a computer program product. When instructions in the computer program product are executed by a processor of an electronic device, the electronic device is enabled to execute the method described in any of the above aspects.

[0034] The technical solution provided by the present application may include: real-time collection and pre-processing of call chain logs, microservice logs, and monitoring indicator data to generate pre-processed data; based on the pre-processed data, generating a time-series weighted directed graph, the time-series weighted directed graph is used to describe the overall operating status of the microservice; based on a machine learning algorithm, the overall operating status of the microservice is predicted to achieve predictive governance of the microservice system. The present invention implements microservice status prediction based on a time-series weighted directed graph, and the prediction process of the time-series weighted directed topology graph at time t+1 may include the following beneficial effects: this process does not require human intervention, and is conducive to real-time training of data before and before t to obtain algorithm parameters to infer and predict data at time t+1. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 This is a flowchart of the steps of a microservice status prediction method based on a time-series weighted directed graph of the present application.

[0036] Figure 2 It is a step-by-step flowchart of a microservice state prediction method based on a time-series weighted directed graph of the present application.

[0037] Figure 3 It is a schematic diagram of the structure of a time-series weighted directed topology graph of a microservice state prediction method based on a time-series weighted directed graph of the present application.

[0038] Figure 4 This is a structural block diagram of a microservice state prediction system based on a time-series weighted directed graph in the present application.

[0039] Figure 5 It is a structural block diagram of a microservice state prediction device based on a time-series weighted directed graph of the present application.

[0040] Figure 6 It is a block diagram of an electronic device of the present application.

[0041] Figure 7 It is a block diagram of a computer-readable storage medium of the present application. DETAILED DESCRIPTION

[0042] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are 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 are within the scope of protection of this application.

[0043] The microservice status prediction method based on a time-series weighted directed graph disclosed in the present invention specifically comprises the following steps:

[0044] Step S110, real-time collection and pre-processing of call chain logs, microservice logs, and monitoring indicator data to generate pre-processed data;

[0045] Step S120, generating a time-series weighted directed graph based on the pre-processed data, wherein the time-series weighted directed graph is used to describe the overall operating status of the microservice;

[0046] Step S130, based on the machine learning algorithm, predict the overall operating status of the microservice to achieve predictive governance of the microservice system.

[0047] The technical solution provided by the present application may include: real-time collection and pre-processing of call chain logs, microservice logs, and monitoring indicator data to generate pre-processed data; based on the pre-processed data, generating a time-series weighted directed graph, the time-series weighted directed graph is used to describe the overall operating status of the microservice; based on a machine learning algorithm, the overall operating status of the microservice is predicted to achieve predictive governance of the microservice system. The present invention implements microservice status prediction based on a time-series weighted directed graph, and the prediction process of the time-series weighted directed topology graph at time t+1 may include the following beneficial effects: this process does not require human intervention, and is conducive to real-time training of data before and before t to obtain algorithm parameters to infer and predict data at time t+1.

[0048] In the embodiment of this example, a temporal weighted directed acyclic graph is a graph structure used to represent and analyze temporal data. Nodes represent entities in the system, directed edges represent relationships between entities, and the weights on the edges are temporal data that changes over time.

[0049] ARIMA model (AutoRegressive Integrated Moving Average): is a classic time series analysis and forecasting model used to describe and predict changes in time series data.

[0050] Embodiment 1:

[0051] Reference Figure 1 , shows a flowchart of a method for predicting microservice status based on a time-series weighted directed graph of the present application, which can be applied to electronic devices, wherein the method can specifically include the following steps:

[0052] In step S110, the call chain log, microservice log, and monitoring indicator data may be collected and pre-processed in real time to generate pre-processed data.

[0053] In the embodiment of this example, the method further includes:

[0054] Collect call chain logs, microservice logs, and monitoring indicator data in real time;

[0055] Pre-processing the real-time collected data;

[0056] Describe the preset events carried in the microservice business processing log;

[0057] Get microservice performance and operating system resource metrics based on preset probes.

[0058] In the embodiment of this example, in the method, real-time collection of call chain logs, microservice logs, and monitoring indicator data also includes:

[0059] The software development kit SDK of opentelemetry, an observability framework and toolkit integrated with each service in the microservice system, realizes the collection and reporting of logs of each microservice call chain.

[0060] In the embodiment of this example, in the method, pre-processing the real-time collected data further includes:

[0061] The real-time collected data is pre-processed by deduplication and weight sorting.

[0062] In step S120, a time-series weighted directed graph may be generated based on the pre-processed data, and the time-series weighted directed graph is used to describe the overall operating status of the microservice.

[0063] In the embodiment of this example, the method further includes:

[0064] A time-series weighted directed graph is defined, weights of edges in the time-series weighted directed graph are determined, and a microservice time-series weighted directed topology graph is generated.

[0065] In step S130, the overall operating status of the microservice can be predicted based on the machine learning algorithm to achieve predictive governance of the microservice system.

[0066] In the embodiment of this example, the method further includes:

[0067] Based on the autoregressive integrated moving average model ARIMA, the changes in the time series vector are modeled to predict the overall operating status of the microservice.

[0068] Embodiment 2:

[0069] like Figure 2 As shown, in the embodiment of this example, data such as call chain logs, microservice logs, and monitoring indicators are collected and pre-processed in real time.

[0070] 1.1.1) Integrate the SDK of opentelemetry into each service in the microservice system to collect and report the call chain logs of each microservice. The call chain log adopts the opentelemetry specification, and the call chain log contains time, serviceID, traceID, spanID, parentSpanID and attribute. The serviceID is used to mark the current service; the traceId is used to mark the entire processing process of the current business; the spanID is used to mark the corresponding processing node in the current business processing process; the parentSpanID is used to mark the upstream processing node of the corresponding processing node in the current business processing process; the attribute is in the key:value format, carrying additional information about the current service and the current business processing process, such as the service name, deployment location, the currently executed function and function parameters, etc.

[0071] 1.1.2 Perform pre-processing based on the data collected in 1.1.1. Let the service set be S. Extract the serviceID in the call chain log, remove duplicates, and obtain a set of serviceIDs:

[0072] S serviceID ={s i ∣serviceID∣s i ∈S}

[0073] According to the fixed key, extract the service-related attributes in the attribute corresponding to the serviceID and remove the duplicates, and define set A s For each service s i ∈S, then A s_i Services included i All service-level attributes, namely:

[0074] A si ={s j .attribute|s j ∈S and s j.serviceID=s i. serviceID}

[0075] Combining the above two sets, we get a service set that contains the service identifier of a specific service attribute condition:

[0076] S={s i ∣s i .serviceID∈S serviceID And A si Included Services i All service-level attributes of

[0077] 1.1.3 Pre-process the data collected in 1.1.1. Suppose the original call chain log data sequence is E. Each node e i Contains time, serviceID, traceID, spanID, parentSpanID and attribute, and defines the starting node e0, then e satisfies:

[0078] e0.parentSpanId = NULL

[0079] e i .spanId=e i+1 .parentSpanId

[0080] e i .serviceID∈S serviceID

[0081] Define the call chain sequence set P, p i ∈P,p i is an ordered sequence, then:

[0082] e i .traceID=p i .traceID

[0083] p i =[e0,e1,e2,...,e k ]

[0084] p i. serviceID=[e0.serviceID,e1.serviceID,...,e k .serviceID]

[0085] Define Ps as the set of service calling sequences. i .serviceID is used to deduplicate adjacent nodes, and combined with P and S, we can get:

[0086] P si ∈P s

[0087] P si ={s0,s1,s2,…,s k}

[0088] 1.1.4) Extract the call chain related attributes in the attribute corresponding to spanID according to the fixed key and define set A E , for each call chain node e i ∈E, then AEi contains the call chain node e i All call chain level attributes, namely:

[0089] A Ei ={e i .attribute|e i ∈E}

[0090] Combined with ei.time, we get a set of weighted event sequences W related to the call chain P :

[0091] W Pi ∈W P

[0092] W Pi ={(t1,A E1 ),(t2,A E1 ),…}

[0093] 1.2) Integrate the SDK of opentelemetry into each service in the microservice system. The microservice business processing log carries time, serviceID, traceID, spanID and corresponding event description. De-noise the microservice log to obtain the log set L. Then for any l i ∈L,l i satisfy:

[0094] l i .serviceID∈S serviceID

[0095] For any l i There exists p i and:

[0096] p i ∈P

[0097] l i .traceID=p i .traceID

[0098] li .spanID=e i .spanID

[0099] For any l i Existence i and:

[0100] e i ∈E

[0101] l i .traceID=e i .traceID

[0102] Combined i .time gets a set of weighted time series W related to microservice logs Li :

[0103] W Li ∈W L

[0104] W Li ={(t1,l1),(t2,…)}

[0105] 1.3) Use Prometheus probes to obtain service-related performance and operating system resource indicators.

[0106] Let the set of indicators be M, then for any m i ∈M,m i is an ordered sequence of monitoring indicators, and v is the monitoring dimension coefficient:

[0107] m i ={m i1 ,m i2 ,…,m iu}

[0108] m i satisfy:

[0109] m i .serviceID∈S serviceID

[0110] That is, for any mi there exists s i And satisfy:

[0111] s i ∈S

[0112] m i .serviceID=s i .serviceID

[0113] Define microservice node weight W s , combined with m i.time, for any W si ∈W s ,have:

[0114] W si ={(t1,m i ),(t2,…)}

[0115] In the embodiment of this example, a microservice time-series weighted directed topology graph is constructed based on the pre-processed data in the previous step.

[0116] 2.1) Define a time-series weighted directed graph G. The vertex set S of G is obtained from 1.1.2. The edge set E of G can be obtained from Ps in 1.1.3. The node weight Ws is obtained from 1.3.

[0117] 2.2) From 1.1.4 and 1.2, we can see that W P and W L are the weights of the edges, and define W E is the weight of the edge in graph G, then:

[0118] W E =W P ∩W L

[0119] 2.3) From 2.1 and 2.2, we can get the microservice timing weighted directed topology graph:

[0120] G=(S,W s ,E,W E )

[0121] In this example, the ARIMA model (AutoRegressive Integrated Moving Average) is a classic model for time series data analysis and prediction. It combines the autoregressive (AR) and moving average (MA) methods and includes the concept of integration to process non-stationary time series data. Use the ARIMA model to predict the future state of G:

[0122] 3.1) Define a set of time series vectors:

[0123] W=(W s ,W E )

[0124] Then G can be expressed as:

[0125] G=(S,E,W)

[0126] W is a time series vector, which can be expressed as:

[0127] W=[W1,W2,…,W t ]

[0128] Each W t A time series vector representing the time t.

[0129] 3.2) Use the ARIMA(p,d,q) model to model the changes in the time series vector. This can be expressed as:

[0130] W t =f(W t-1 ,W t-2 ,…,W t-p ,ε t ,d,q)

[0131] Among them, f is the function of the ARIMA model, p is the order of the autoregressive term, d is the difference order, is the order of the moving average term, and ε t is the error term. Use the historical time series vector set [W1, W2, …] to train the ARIMA model to determine the parameters of the model. Using the trained ARIMA model, given the time series vector W at time t t , predict the time series vector W at time t+1 t +1:

[0132] W t +1=f(W t ,W t-1 ,…,W t-p+1 ,ε t+1 ,d,q)

[0133] Use the predicted time series vector W t +1Construct the time-series weighted directed graph G at the future time t+1 t+ 1:

[0134] G t +1=(S,f(W t ,W t-1 ,…,W t-p+1 ,ε t+1 ,d,q),E)

[0135] 3.1), that is:

[0136] G t+1 =(S,f(W St ,W St-1 ,…,W St-p+1 ,ε t+1 ,d,q),E,f(W Et ,W Et-1 ,…,W Et-p+1 ,ε t+1 ,d,q))

[0137] Embodiment three:

[0138] In the embodiment of this example, take the actual implementation project as an example:

[0139] 1. The opentelemetry SDK is integrated into the application service code to collect various indicators of the business system, including standard K8s / Docker container environment variables, parameters, application names, user-defined tags, etc. The SDK supports the collection of call chains of common basic components, covering but not limited to various network protocols such as HTTP and gRPC, various database drivers such as MySQL, Mongo, Redis, ClickHouse, etc., and is applicable to multiple programming languages, such as Go, Java, C++, Python, JavaScript, etc.

[0140] By integrating SDK, call chain logs can be collected in near real time, such as:

[0141]

[0142]

[0143]

[0144]

[0145] Use business log collection tools to collect microservice logs in near real time, such as:

[0146]

[0147]

[0148] Prometheus is used to collect system resource indicator data in near real time.

[0149] 2. The call chain log data and microservice log data are processed in real time using Flink stream computing. The system resource indicator data collected by Prometheus is set to a 5s time slice and processed in batches using Flink.

[0150] 3. Using the preprocessed data in step 2, construct a topology map in real time and record the changes in the topology map weights on the timeline.

[0151] 4. Such as Figure 3 As shown in the figure, the topology data obtained in step 3 is saved in two graph databases, Neo4J and redis-graph. Neo4J is used to store the full data for a long time, and redis-graph is used as a memory database to store data for a period of time to speed up the execution of subsequent steps.

[0152] 5. Use the data saved in redis-graph, the data before time t as training data, the data at time t as labeled data, and perform real-time training to obtain the parameters p, d, and q of the ARIMA model.

[0153] 6. Use the data saved in redis-graph and the p, d, and q parameters of the ARIMA model obtained through training in step 5 as input to predict the topology data at time t+1s, and then write it to another redis-graph instance as the data foundation for microservice governance functions.

[0154] In the embodiment of this example, the present disclosure preprocesses the call chain log, microservice log, and system resource indicator data. The construction process of the time series weighted directed topology graph. The prediction process of the time series weighted directed topology graph at time t+1. This process does not require human intervention, and is conducive to real-time training of data before t and obtaining algorithm parameters to infer and predict the data at time t+1.

[0155] It should be noted that, for the method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the order of the actions described, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all optional embodiments, and the actions involved are not necessarily required by the present application.

[0156] Reference Figure 4 , shows a structural block diagram of a microservice state prediction system based on a time-series weighted directed graph of the present application, the system comprising:

[0157] The data pre-processing module 210 collects and pre-processes the call chain log, microservice log, and monitoring indicator data in real time to generate pre-processed data;

[0158] A time-series weighted directed graph construction module 220 generates a time-series weighted directed graph based on the pre-processed data, wherein the time-series weighted directed graph is used to describe the overall operation status of the microservice;

[0159] The microservice status prediction module 230 predicts the overall operating status of the microservice based on a machine learning algorithm to achieve predictive governance of the microservice system.

[0160] Reference Figure 5 , shows a structural block diagram of a microservice state prediction device based on a time-series weighted directed graph of the present application, the device comprising:

[0161] The data pre-processing module 310 is used to collect and pre-process the call chain log, microservice log and monitoring indicator data in real time to generate pre-processed data;

[0162] A time-series weighted directed graph construction module 320, for generating a time-series weighted directed graph based on the pre-processed data, wherein the time-series weighted directed graph is used to describe the overall operation status of the microservice;

[0163] The microservice status prediction module 330 is used to predict the overall operating status of the microservice based on a machine learning algorithm to achieve predictive governance of the microservice system.

[0164] As for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0165] Optionally, an embodiment of the present application further provides an electronic device, comprising: a processor, a memory, and a computer program stored in the memory and executable on the processor. When the computer program is executed by the processor, the various processes of the above-mentioned method embodiment are implemented, and the same technical effect can be achieved. To avoid repetition, it will not be described here.

[0166] The embodiment of the present application also provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, each process of the above method embodiment is implemented, and the same technical effect can be achieved. To avoid repetition, it is not repeated here. The computer-readable storage medium is, for example, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0167] Figure 6 800 is a block diagram of an electronic device 800 shown in the present application. For example, the electronic device 800 may be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, etc.

[0168] Reference Figure 6 , the electronic device 800 may include one or more of the following components: a processing component 802 , a memory 804 , a power component 806 , a multimedia component 808 , an audio component 810 , an input / output (I / O) interface 812 , a sensor component 814 , and a communication component 816 .

[0169] The processing component 802 generally controls the overall operation of the electronic device 800, such as operations associated with display, phone calls, data communications, camera operations, and recording operations. The processing component 802 may include one or more processors 820 to execute instructions to complete all or part of the steps of the above method. In addition, the processing component 802 may include one or more modules to facilitate the interaction between the processing component 802 and other components. For example, the processing component 802 may include a multimedia module to facilitate the interaction between the multimedia component 808 and the processing component 802.

[0170] The memory 804 is configured to store various types of data to support operations on the device 800. Examples of such data include instructions for any application or method operating on the electronic device 800, contact data, phone book data, messages, images, videos, etc. The memory 804 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0171] The power supply component 806 provides power to the various components of the electronic device 800. The power supply component 806 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to the electronic device 800.

[0172] The multimedia component 808 includes a screen that provides an output interface between the electronic device 800 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundaries of the touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 808 includes a front camera and / or a rear camera. When the device 800 is in an operating mode, such as a shooting mode or a video mode, the front camera and / or the rear camera may receive external multimedia data. Each front camera and the rear camera may be a fixed optical lens system or have a focal length and optical zoom capability.

[0173] The audio component 810 is configured to output and / or input audio signals. For example, the audio component 810 includes a microphone (MIC), and when the electronic device 800 is in an operating mode, such as a call mode, a recording mode, and a voice recognition mode, the microphone is configured to receive an external audio signal. The received audio signal can be further stored in the memory 804 or sent via the communication component 816. In some embodiments, the audio component 810 also includes a speaker for outputting audio signals.

[0174] I / O interface 812 provides an interface between processing component 802 and peripheral interface modules, such as keyboards, click wheels, buttons, etc. These buttons may include but are not limited to: home button, volume button, start button, and lock button.

[0175] The sensor assembly 814 includes one or more sensors for providing various aspects of status assessment for the electronic device 800. For example, the sensor assembly 814 can detect the open / closed state of the device 800, the relative positioning of components, such as the display and keypad of the electronic device 800, and the sensor assembly 814 can also detect the position change of the electronic device 800 or a component of the electronic device 800, the presence or absence of contact between the user and the electronic device 800, the orientation or acceleration / deceleration of the electronic device 800, and the temperature change of the electronic device 800. The sensor assembly 814 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. The sensor assembly 814 may also include an optical sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 814 may also include an accelerometer, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

[0176] The communication component 816 is configured to facilitate wired or wireless communication between the electronic device 800 and other devices. The electronic device 800 can access a wireless network based on a communication standard, such as WiFi, a carrier network (such as 2G, 3G, 4G or 5G), or a combination thereof. In an exemplary embodiment, the communication component 816 receives a broadcast signal or broadcast operation information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 816 also includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.

[0177] In an exemplary embodiment, the electronic device 800 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the above methods.

[0178] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 804 including instructions, and the instructions can be executed by a processor 820 of an electronic device 800 to perform the above method. For example, the non-transitory computer-readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0179] Figure 7 19 is a block diagram of a computer-readable storage medium 1900 shown in the present application. For example, the computer-readable storage medium 1900 may be provided as a server.

[0180] Reference Figure 7 , the computer-readable storage medium 1900 includes a processing component 1922, which further includes one or more processors, and a memory resource represented by a memory 1932 for storing instructions, such as an application, that can be executed by the processing component 1922. The application stored in the memory 1932 may include one or more modules, each corresponding to a set of instructions. In addition, the processing component 1922 is configured to execute instructions to perform the above method.

[0181] The computer readable storage medium 1900 may also include a power supply component 1926 configured to perform power management of the computer readable storage medium 1900, a wired or wireless network interface 1950 configured to connect the computer readable storage medium 1900 to a network, and an input / output (I / O) interface 1958. The computer readable storage medium 1900 may operate based on an operating system stored in the memory 1932, such as Windows Server™, Mac OS X™, Unix™, Linux™, FreeBSD™ or the like.

[0182] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.

[0183] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for a terminal (which can be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to execute the methods described in each embodiment of the present application.

[0184] The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present application, ordinary technicians in this field can also make many forms without departing from the purpose of the present application and the scope of protection of the claims, all of which are within the protection of the present application.

[0185] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed in the present application can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0186] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0187] In the embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, 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, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0188] 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.

[0189] 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.

[0190] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard drives, ROM, RAM, magnetic disks, or optical disks.

[0191] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A microservice status prediction method based on a time-series weighted directed graph, characterized in that: The method comprises: Collect and pre-process call chain logs, microservice logs, and monitoring indicator data in real time to generate pre-processed data; Based on the pre-processed data, a time-series weighted directed graph is generated, where the time-series weighted directed graph is used to describe the overall operating status of the microservice; Based on machine learning algorithms, the overall operating status of microservices is predicted to achieve predictive governance of microservice systems.

2. The method according to claim 1, characterized in that The method further comprises: Collect call chain logs, microservice logs, and monitoring indicator data in real time; Pre-processing the real-time collected data; Describe the preset events carried in the microservice business processing log; Get microservice performance and operating system resource metrics based on preset probes.

3. The method according to claim 2, characterized in that In the method, real-time collection of call chain logs, microservice logs, and monitoring indicator data also includes: The software development kit SDK of opentelemetry, an observability framework and toolkit integrated with each service in the microservice system, realizes the collection and reporting of logs of each microservice call chain.

4. The method according to claim 1, characterized in that In the method, pre-processing the real-time collected data further comprises: The real-time collected data is pre-processed by deduplication and weight sorting.

5. The method according to claim 1, characterized in that The method further comprises: A time-series weighted directed graph is defined, weights of edges in the time-series weighted directed graph are determined, and a microservice time-series weighted directed topology graph is generated.

6. The method according to claim 1, characterized in that The method further comprises: Based on the autoregressive integrated moving average model ARIMA, the changes in the time series vector are modeled to predict the overall operating status of the microservice.

7. A microservice status prediction system based on a time-series weighted directed graph, characterized in that: The system comprises: The data pre-processing module collects and pre-processes call chain logs, microservice logs, and monitoring indicator data in real time to generate pre-processed data; A time-series weighted directed graph construction module generates a time-series weighted directed graph based on the pre-processed data, wherein the time-series weighted directed graph is used to describe the overall operation status of the microservice; The microservice status prediction module predicts the overall operating status of microservices based on machine learning algorithms to achieve predictive governance of the microservice system.

8. A microservice status prediction device based on a time-series weighted directed graph, characterized in that: The device comprises: The data pre-processing module is used to collect and pre-process call chain logs, microservice logs, and monitoring indicator data in real time to generate pre-processed data; A time-series weighted directed graph construction module, used to generate a time-series weighted directed graph based on the pre-processed data, wherein the time-series weighted directed graph is used to describe the overall operation status of the microservice; The microservice status prediction module is used to predict the overall operating status of microservices based on machine learning algorithms to achieve predictive governance of the microservice system.

9. An electronic device, characterized in that: include: A processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the computer program implements the method according to any one of claims 1 to 6 when executed by the processor.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images