CN113141273A

CN113141273A - Self-repairing method, device and equipment based on early warning information and storage medium

Info

Publication number: CN113141273A
Application number: CN202110433757.XA
Authority: CN
Inventors: 晏彬; 赵贵斌
Original assignee: Kangjian Information Technology Shenzhen Co Ltd
Current assignee: Kangjian Information Technology Shenzhen Co Ltd
Priority date: 2021-04-22
Filing date: 2021-04-22
Publication date: 2021-07-20

Abstract

The invention relates to the field of cloud services, is applied to the field of intelligent medical treatment, and provides a self-repairing method, device, equipment and storage medium based on early warning information, which are used for improving the reliability of identification and self-repairing of the early warning information. The self-repairing method based on the early warning information comprises the following steps: extracting early warning information from the monitoring data of a preset monitoring system to obtain early warning information to be processed; analyzing and verifying the early warning information to be processed in sequence to obtain information to be matched; extracting target early warning characteristics of information to be matched; matching and splicing the repair script module library to obtain a target repair script through the target early warning feature and the host internet interconnection protocol information and the monitoring item information in the early warning information to be processed; and calling a target repair script to execute repair, detecting detection information, and triggering a repair ending instruction based on the detection information. In addition, the invention also relates to a block chain technology, and the monitoring data can be stored in the block chain.

Description

Self-repairing method, device and equipment based on early warning information and storage medium

Technical Field

The invention relates to the field of abnormity monitoring, in particular to a self-repairing method, a self-repairing device, self-repairing equipment and a self-repairing storage medium based on early warning information.

Background

With the development of computer technology and big data information industry, network structures are more and more complex, and with the great increase of various server resources and backend services, the repair of the early warning information of the network structures also becomes a problem which needs to be solved urgently. At present, fault self-repairing is generally performed by acquiring early warning information and matching a repairing strategy according to the early warning information.

However, the inspection logic is simple, and the issuing operation of the repair strategy is not convenient, so that the accuracy of the identification of the early warning information is low, and the accuracy and the efficiency of the self-repair of the early warning information are low, thereby the reliability of the identification and the self-repair of the early warning information is low.

Disclosure of Invention

The invention provides a self-repairing method, device, equipment and storage medium based on early warning information, which are used for improving the reliability of identification and self-repairing of the early warning information.

The invention provides a self-repairing method based on early warning information in a first aspect, which comprises the following steps:

acquiring monitoring data of a preset monitoring system, and extracting early warning information of the monitoring data through a preset early warning analysis model to obtain to-be-processed early warning information, wherein the to-be-processed early warning information comprises host internet interconnection protocol information and monitoring item information;

sequentially performing state analysis, configuration analysis, white list library analysis and verification processing on the early warning information to be processed to obtain information to be matched;

calling a preset feature extraction model, and performing early warning feature extraction and early warning feature matching based on an early warning feature library on the information to be matched to obtain target early warning features;

matching and splicing a preset repair script module library through the target early warning feature, the host internet interconnection protocol information and the monitoring item information to obtain a target repair script;

and calling the target repair script to execute repair and detect to obtain detection information, and triggering a repair ending instruction based on the detection information.

Optionally, in a first implementation manner of the first aspect of the present invention, the obtaining monitoring data of a preset monitoring system, and performing early warning information extraction on the monitoring data through a preset early warning analysis model to obtain to-be-processed early warning information includes:

acquiring monitoring data of a preset monitoring system, and extracting and fusing fault characteristics of the monitoring data through a preset early warning analysis model based on a preset attention mechanism to obtain fault information;

deleting the fault information in the monitoring data to obtain filtering information, and performing fault prediction on the filtering information through the early warning analysis model to obtain potential early warning information;

matching the monitoring data with a preset early warning information template to obtain initial early warning information;

and merging the fault information, the potential early warning information and the initial early warning information to obtain early warning information to be processed.

Optionally, in a second implementation manner of the first aspect of the present invention, the performing state analysis, configuration analysis, white list library analysis and verification processing on the to-be-processed early warning information in sequence to obtain to-be-matched information includes:

acquiring corresponding state information from a preset configuration management database through the host internet interconnection protocol information in the to-be-processed early warning information, and judging whether the state information is preset non-processing state information or not;

if the state information is not preset non-processing state information, self-repairing configuration information is obtained, and whether the self-repairing configuration information exists in the monitoring item information or not is judged;

if the monitoring item information has the self-repairing configuration information, judging whether the host Internet interconnection protocol information and the monitoring item information exist in a preset self-repairing white list library or not;

and if the host internet interconnection protocol information and the monitoring item information exist in the self-repairing white list library, performing information verification processing on the to-be-processed early warning information to obtain to-be-matched information.

Optionally, in a third implementation manner of the first aspect of the present invention, if the host internet protocol information and the monitoring item information exist in the self-repair white list library, performing information verification processing on the to-be-processed warning information to obtain to-be-matched information, where the information verification processing includes:

if the host internet interconnection protocol information and the monitoring item information exist in the self-repairing white list library, traversing a preset historical early warning information knowledge graph through the monitoring item information to obtain comparison information;

calculating the information similarity of the to-be-processed early warning information and the comparison information, and judging whether the information similarity is greater than a preset contrast threshold value or not;

and if the information similarity is greater than the preset contrast threshold, determining the to-be-processed early warning information as to-be-matched information.

Optionally, in a fourth implementation manner of the first aspect of the present invention, the matching and splicing a preset repair script module library through the target early warning feature, the host internet interconnection protocol information, and the monitoring item information to obtain a target repair script includes:

calculating the feature similarity between the information to be matched and a repair script module in a preset repair script module library through the target early warning feature, the host internet interconnection protocol information and the monitoring item information, and judging whether the feature similarity is a preset target value;

if the feature similarity is the preset target value, splicing the repair script modules corresponding to the feature similarity according to a preset merging strategy to obtain a target repair script;

if the feature similarity is not the preset target value, judging whether the feature similarity is larger than a preset similarity threshold value;

and if the feature similarity is greater than the preset similarity threshold, filtering and splicing the repair script modules corresponding to the feature similarity to obtain a target repair script.

Optionally, in a fifth implementation manner of the first aspect of the present invention, if the feature similarity is greater than the preset similarity threshold, filtering and splicing the repair script modules corresponding to the feature similarity to obtain a target repair script, where the filtering and splicing are performed to obtain the target repair script, include:

if the feature similarity is larger than the preset similarity threshold, performing combination calculation and splicing sequence calculation on the repair script modules corresponding to the feature similarity through a preset greedy algorithm to obtain module combination information and splicing sequence information;

and acquiring a target repair script module from the repair script modules corresponding to the feature similarity through the module combination information, and splicing the target repair script module according to the splicing sequence information to obtain a target repair script.

Optionally, in a sixth implementation manner of the first aspect of the present invention, the invoking the target repair script to perform repair and perform detection to obtain detection information, and triggering a repair end instruction based on the detection information includes:

calling the target repair script to execute repair, acquiring a repair state of the target repair script after the target repair script executes repair and execution information generated in the process of executing repair by the target repair script, and determining the repair state and the execution information as information to be analyzed;

comparing and analyzing the information to be analyzed with a preset execution ending condition to obtain detection information;

and triggering a preset terminal manual repair instruction or a repair finishing instruction according to the detection information.

The second aspect of the present invention provides a self-repairing device based on early warning information, including:

the system comprises a first extraction module, a second extraction module and a third extraction module, wherein the first extraction module is used for acquiring monitoring data of a preset monitoring system, and extracting early warning information of the monitoring data through a preset early warning analysis model to obtain to-be-processed early warning information, and the to-be-processed early warning information comprises host internet interconnection protocol information and monitoring item information;

the analysis and verification module is used for sequentially carrying out state analysis, configuration analysis, white list library analysis and verification processing on the early warning information to be processed to obtain information to be matched;

the second extraction module is used for calling a preset feature extraction model, performing early warning feature extraction on the information to be matched and performing early warning feature matching based on an early warning feature library to obtain target early warning features;

the matching and splicing module is used for matching and splicing a preset repair script module library through the target early warning feature, the host internet interconnection protocol information and the monitoring item information to obtain a target repair script;

and the detection triggering module is used for calling the target repair script to execute repair and carry out detection to obtain detection information, and triggering a repair ending instruction based on the detection information.

Optionally, in a first implementation manner of the second aspect of the present invention, the first extraction module is specifically configured to:

Optionally, in a second implementation manner of the second aspect of the present invention, the analysis and verification module includes:

a first judging unit, configured to obtain corresponding state information from a preset configuration management database through the host internet interconnection protocol information in the to-be-processed early warning information, and judge whether the state information is preset non-processing state information;

a second judging unit, configured to obtain self-repair configuration information if the state information is not preset non-processing state information, and judge whether the self-repair configuration information exists in the monitoring item information;

a third judging unit, configured to judge whether the host internet interconnection protocol information and the monitoring item information exist in a preset self-repair white list library if the monitoring item information exists in the self-repair configuration information;

and the verification processing unit is used for verifying the information of the early warning information to be processed to obtain the information to be matched if the host internet interconnection protocol information and the monitoring item information exist in the self-repairing white list library.

Optionally, in a third implementation manner of the second aspect of the present invention, the verification processing unit is specifically configured to:

Optionally, in a fourth implementation manner of the second aspect of the present invention, the matching and splicing module includes:

the calculation and judgment unit is used for calculating the feature similarity between the information to be matched and a repair script module in a preset repair script module library through the target early warning feature, the host internet interconnection protocol information and the monitoring item information and judging whether the feature similarity is a preset target value or not;

the splicing unit is used for splicing the repair script modules corresponding to the feature similarity according to a preset merging strategy to obtain a target repair script if the feature similarity is the preset target value;

a fourth determining unit, configured to determine whether the feature similarity is greater than a preset similarity threshold if the feature similarity is not the preset target value;

and the filtering and splicing unit is used for filtering and splicing the repair script modules corresponding to the feature similarity to obtain the target repair script if the feature similarity is greater than the preset similarity threshold.

Optionally, in a fifth implementation manner of the second aspect of the present invention, the filtering and splicing unit is specifically configured to:

Optionally, in a sixth implementation manner of the second aspect of the present invention, the detection triggering module is specifically configured to:

the detection unit is used for calling the target repair script to execute repair, acquiring a repair state of the target repair script after the target repair script executes repair and execution information generated in the process of executing repair by the target repair script, and determining the repair state and the execution information as information to be analyzed;

the comparison analysis unit is used for comparing and analyzing the information to be analyzed with a preset execution end condition to obtain detection information;

and the triggering unit is used for triggering a preset terminal manual repair instruction or a repair ending instruction according to the detection information.

The third aspect of the present invention provides a self-repairing apparatus based on early warning information, including: a memory and at least one processor, the memory having instructions stored therein; the at least one processor invokes the instructions in the memory to cause the pre-alarm information-based self-healing apparatus to perform the pre-alarm information-based self-healing method described above.

A fourth aspect of the present invention provides a computer-readable storage medium having stored therein instructions, which, when run on a computer, cause the computer to execute the above-mentioned early warning information-based self-healing method.

In the technical scheme provided by the invention, monitoring data of a preset monitoring system are obtained, and early warning information extraction is carried out on the monitoring data through a preset early warning analysis model to obtain to-be-processed early warning information, wherein the to-be-processed early warning information comprises host internet interconnection protocol information and monitoring item information; sequentially performing state analysis, configuration analysis, white list library analysis and verification processing on the early warning information to be processed to obtain information to be matched; calling a preset feature extraction model, and performing early warning feature extraction and early warning feature matching based on an early warning feature library on the information to be matched to obtain target early warning features; matching and splicing a preset repair script module library through the target early warning feature, the host internet interconnection protocol information and the monitoring item information to obtain a target repair script; and calling the target repair script to execute repair and detect to obtain detection information, and triggering a repair ending instruction based on the detection information. In the embodiment of the invention, by combining complex judgment/inspection logic and convenient repair strategy issuing operation, and combining the matching mode of the model and the template and the combination and splicing mode of the repair script module, the identification accuracy, the self-repair accuracy and the self-repair efficiency of the early warning information and the matching accuracy and the calling accuracy of the target repair script are improved, so that the identification and self-repair reliability of the early warning information is improved.

Drawings

FIG. 1 is a schematic diagram of an embodiment of a self-repairing method based on early warning information in the embodiment of the present invention;

FIG. 2 is a schematic diagram of another embodiment of a self-repairing method based on early warning information in the embodiment of the present invention;

FIG. 3 is a schematic diagram of an embodiment of a self-repairing apparatus based on warning information in an embodiment of the present invention;

FIG. 4 is a schematic diagram of another embodiment of a self-healing apparatus based on warning information according to an embodiment of the present invention;

fig. 5 is a schematic diagram of an embodiment of a self-repairing apparatus based on warning information in the embodiment of the present invention.

Detailed Description

The embodiment of the invention provides a self-repairing method, device, equipment and storage medium based on early warning information, and improves the reliability of identification and self-repairing of the early warning information.

The terms "first," "second," "third," "fourth," and the like in the description and in the claims, as well as in the drawings, if any, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It will be appreciated that the data so used may be interchanged under appropriate circumstances such that the embodiments described herein may be practiced otherwise than as specifically illustrated or described herein. Furthermore, the terms "comprises," "comprising," or "having," and any variations thereof, are intended to cover non-exclusive inclusions, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

For convenience of understanding, a specific flow of the embodiment of the present invention is described below, and referring to fig. 1, an embodiment of a self-repairing method based on early warning information in the embodiment of the present invention includes:

101. acquiring monitoring data of a preset monitoring system, and extracting early warning information of the monitoring data through a preset early warning analysis model to obtain to-be-processed early warning information, wherein the to-be-processed early warning information comprises host internet interconnection protocol information and monitoring item information.

It is understood that the execution subject of the present invention may be a self-repairing device based on the warning information, and may also be a terminal or a server, which is not limited herein. The embodiment of the present invention is described by taking a server as an execution subject.

The to-be-processed early warning information comprises pre-fault information and failed information, the pre-fault information is used for indicating that potential faults exist, and the failed information is used for indicating that faults exist. The to-be-processed warning information includes, in addition to host Internet Protocol (IP) information and monitoring item information, current data, monitoring level, status, and warning time, for example: host IP: 10.10.10.10, monitoring item information: bytes, free, percent/mount/(e.g., disk usage), current data: 96, monitoring level: critical, state: PROBLEM, early warning time: 2021-02-0215:30:21. The monitoring data can comprise data for monitoring doctor-patient sign data through medical instruments and monitoring data during operation of a system for processing medical data.

When the preset monitoring system generates monitoring data, the monitoring data are sent to the server, the server receives the monitoring data sent by the preset monitoring system, or when the preset monitoring system generates the monitoring data, a reading instruction is triggered, and the server reads the monitoring data from a database corresponding to the preset monitoring system based on the reading instruction. The preset early warning analysis model can be formed by combining a plurality of neural network structures, and is used for classifying and extracting information with potential failure possibility and information indicating failure occurrence in the monitoring data, for example, a server calls the early warning analysis model to predict the development trend of the monitoring data to obtain predicted data, and the predicted data is identified according to the preset early warning information to obtain pre-failure information; and calling an early warning analysis model by the server, classifying the monitoring data and calculating a probability value based on preset early warning information, and determining the failure information in the monitoring data according to the probability value.

102. And sequentially carrying out state analysis, configuration analysis, white list library analysis and verification processing on the early warning information to be processed to obtain the information to be matched.

The server creates a cascade tree for line state analysis, configuration analysis and white list library analysis in advance, the cascade tree comprises a state tree, a repair configuration item tree and a white list tree, the state tree, the repair configuration item tree and the white list tree are connected in series in sequence, namely the output of the state tree is the input of the repair configuration item tree, and the output of the repair configuration item tree is the input of the white list tree. And the server matches the early warning information to be processed with the cascade tree through a preset edit distance algorithm and/or a preset recursion algorithm to obtain corresponding comparative analysis information. And calling a preset template or corresponding historical early warning information by the server, and judging and analyzing the comparative analysis information to obtain the information to be matched.

103. And calling a preset feature extraction model, performing early warning feature extraction on the information to be matched and performing early warning feature matching based on an early warning feature library to obtain target early warning features.

The target early warning features include, but are not limited to, downtime features, disk space abnormality features, and service abnormality features. The early warning features in the early warning feature library are used as features matched with the template, and the early warning features in the early warning feature library are used for judging whether the early warning features in the information to be matched are the features corresponding to the early warning information and the features needing self-repairing. The server calls a preset feature extraction model, based on effective network EfficientNet, vector convolution operation processing, batch normalization processing, activation function processing and splicing processing are carried out on information to be matched for multiple times to obtain initial features, early warning features of an early warning feature library are retrieved according to the initial features to obtain target early warning features, namely the server calculates the matching degree of the initial features and the early warning features in the preset early warning feature library, whether the matching degree is larger than a preset target value is judged, if not, a judgment result is returned, and if yes, the corresponding initial features are determined to be the target early warning features.

104. And matching and splicing the preset repair script module library through the target early warning characteristics, the host internet interconnection protocol information and the monitoring item information to obtain a target repair script.

The server calculates similarity and regresses a preset repair script module library through a preset collaborative filtering algorithm based on target early warning characteristics, host internet interconnection protocol information and monitoring item information to obtain a matched repair script module set, calls a preset genetic algorithm to perform population selection, crossing and mutation processing on the matched repair script module set to obtain a candidate repair script module set, and splices the candidate repair script module set according to a preset splicing strategy to obtain a target repair script, wherein the splicing strategy is used for splicing the repair script modules to form a script meeting grammar and rules.

105. And calling a target repair script to execute repair and detect to obtain detection information, and triggering a repair ending instruction based on the detection information.

The server calls a target repair script to execute corresponding repair, the repair is to eliminate the fault corresponding to the pre-fault information and the failed information, the execution process of the repair is monitored through a preset monitoring pool, when the repair is finished, the current state information is obtained, the current state information is detected through a preset command (including but not limited to ping, Telnet, curl, nc and the like), whether the state information is successful in repair is judged, and therefore detection information is obtained, if the detection information is that the state information is successful in repair, a repair finishing instruction is triggered, the target repair script execution of the fault repair is finished, if the detection information is that the state information is failed in repair, the information of the repair failure is obtained, the script corresponding to the information of the repair failure is matched, the fault repair is executed through the script, and detection is carried out, and the re-detection information is obtained, if the detection information is that the state information is the repair success, a repair ending instruction is triggered, if the detection information is that the state information is the repair failure, corresponding unrepaired information is obtained, a preset terminal repair instruction is triggered to send the unrepaired information to the mobile terminal, and manual maintenance is carried out by a user of the mobile terminal.

The server calls the target repair script to execute repair and detect to obtain detection information, after a repair finishing instruction is triggered based on the detection information, historical repair information corresponding to the target repair script can be obtained, the detection information is evaluated based on the historical repair information to obtain evaluation information, and a matching process and an execution process of the target repair script are optimized based on the evaluation information to improve the accuracy and efficiency of identification and processing of the target repair script.

In the embodiment of the invention, by combining complex judgment/inspection logic and convenient repair strategy issuing operation, and combining the matching mode of the model and the template and the combination and splicing mode of the repair script module, the identification accuracy, the self-repair accuracy and the self-repair efficiency of the early warning information and the matching accuracy and the calling accuracy of the target repair script are improved, so that the identification and self-repair reliability of the early warning information is improved. This scheme can be applied to in the wisdom medical field to promote the construction in wisdom city.

Referring to fig. 2, another embodiment of the self-repair method based on the warning information in the embodiment of the present invention includes:

201. acquiring monitoring data of a preset monitoring system, and extracting early warning information of the monitoring data through a preset early warning analysis model to obtain to-be-processed early warning information, wherein the to-be-processed early warning information comprises host internet interconnection protocol information and monitoring item information.

Specifically, the server acquires monitoring data of a preset monitoring system, extracts and fuses fault features of the monitoring data through a preset early warning analysis model and based on a preset attention mechanism, and obtains fault information; deleting fault information in the monitoring data to obtain filtering information, and performing fault prediction on the filtering information through an early warning analysis model to obtain potential early warning information; matching the monitoring data with a preset early warning information template to obtain initial early warning information; and merging the fault information, the potential early warning information and the initial early warning information to obtain the early warning information to be processed.

The early warning analysis model is a combined model and comprises a plurality of models, namely the early warning analysis model comprises a plurality of model network structures (namely network structures corresponding to different algorithms) with the same function and/or different functions, such as: an inverse graph network structure, a convolutional neural network, a periodic neural network, and the like. The monitoring data can comprise data for monitoring doctor-patient sign data through medical instruments and monitoring data during operation of a system for processing medical data.

After the server obtains monitoring data of a preset monitoring system, feature extraction and fault feature matching are respectively carried out on the monitoring data through a plurality of models in an early warning analysis model to obtain initial fault features corresponding to the models, attention matrixes of the initial fault features corresponding to the models are respectively calculated through a preset attention mechanism, the attention matrixes of the initial fault features corresponding to the models are fused to obtain fault information, information except the fault information in the monitoring data, namely filtering information, is obtained, the development trend of the filtering information is predicted through the early warning analysis model to obtain trend prediction data, and the trend prediction data is identified and analyzed according to the preset early warning information to obtain pre-fault information.

The preset early warning information template comprises a first template corresponding to fault information (namely fault information) and a second template corresponding to potential early warning information (namely pre-fault information). The server determines the fault information with the first matching degree larger than a first preset value as first early warning information by calculating the first matching degree between the fault information and a first template, calculates the second matching degree between the potential early warning information and a second template, determines the fault information with the second matching degree larger than a second preset value as second early warning information, and determines the first early warning information and the second early warning information as initial early warning information. And carrying out duplicate removal processing on the potential early warning information, the fault information and the initial early warning information to obtain the early warning information to be processed. By combining the early warning information matching analysis of the model and the template, the accuracy of the early warning information to be processed is improved.

202. And sequentially carrying out state analysis, configuration analysis, white list library analysis and verification processing on the early warning information to be processed to obtain the information to be matched.

Specifically, the server acquires corresponding state information from a preset configuration management database through host internet interconnection protocol information in the to-be-processed early warning information, and judges whether the state information is preset non-processing state information or not; if the state information is not the preset non-processing state information, self-repairing configuration information is obtained, and whether the self-repairing configuration information exists in the monitoring item information or not is judged; if the monitoring item information has self-repairing configuration information, judging whether the host Internet interconnection protocol information and the monitoring item information exist in a preset self-repairing white list library or not; and if the host internet interconnection protocol information and the monitoring item information exist in the self-repairing white list library, performing information verification processing on the early warning information to be processed to obtain the information to be matched.

For example, the server searches a preset Configuration Management Database (CMDB) through host internet protocol information IP in the to-be-processed warning information to obtain status information corresponding to the host internet protocol information IP, and determines whether the status information is preset non-processed status information including, but not limited to, maintenance, release, offline, and the like, if so, the server stops executing, writes the corresponding to-be-processed warning information into a preset recording list, if not, obtains self-repair configuration information, where the self-repair configuration information is monitoring item information configured in a self-repair system (i.e., a repair system), and determines whether self-repair configuration information exists in the monitoring item information, if not, triggers a warning instruction, and sends the to-be-processed warning information to the mobile terminal in the form of a telephone or a short message based on the warning instruction, the method comprises the steps that a user of a mobile terminal carries out early warning maintenance according to early warning to be processed, if yes, whether host internet interconnection protocol information and monitoring item information exist in a preset self-repairing white list library or not is judged, a white list in the self-repairing white list library is used for allowing the set host internet interconnection protocol information and monitoring item information to carry out repairing process execution so as to avoid error operation of repairing process execution, if yes, verification processing is carried out on correctness and/or integrity of the early warning information to be processed, information to be matched is obtained, if not, an early warning instruction is triggered, the early warning information to be processed is sent to the mobile terminal in the form of a telephone or a short message based on the early warning instruction, and early warning maintenance is carried out according to early warning to be processed by the user of the mobile terminal.

Specifically, if the internet interconnection protocol information and the monitoring item information of the host computer exist in the self-repairing white list library, the server traverses a preset historical early warning information knowledge graph through the monitoring item information to obtain comparison information; calculating the information similarity of the early warning information to be processed and the comparison information, and judging whether the information similarity is greater than a preset contrast threshold value or not; and if the information similarity is greater than the preset contrast threshold, determining the early warning information to be processed as the information to be matched.

For example, the server calls a preset entity extraction model, carries out word segmentation processing, entity identification, entity relation identification, entity extraction and entity relation extraction on monitoring item information in sequence to obtain entity information, the entity information comprises an entity and an entity relation, generates a monitoring item information sequence of the monitoring item information according to the entity information, calls preset random walk information, carries out random walk on a historical early warning information knowledge graph to obtain a plurality of matching sequences, respectively calculates the similarity between the monitoring item information sequence and the matching sequences to obtain sequence similarity, judges whether the sequence similarity is greater than a preset sequence threshold value, determines the corresponding matching sequence as comparison information if the sequence similarity is greater than the preset sequence threshold value, stops execution if the sequence similarity is not greater than the preset sequence threshold value, calculates the information similarity between the early warning information to be processed and the comparison information through a preset cosine similarity calculation method after the server obtains the comparison information, and judging whether the information similarity is greater than a preset contrast threshold, if so, determining the early warning information to be processed as the information to be matched, otherwise, stopping execution and setting the information to be a null value.

203. And calling a preset feature extraction model, performing early warning feature extraction on the information to be matched and performing early warning feature matching based on an early warning feature library to obtain target early warning features.

The process of step 203 is similar to the process of step 103, and is not described herein again.

204. And matching and splicing the preset repair script module library through the target early warning characteristics, the host internet interconnection protocol information and the monitoring item information to obtain a target repair script.

Specifically, the server calculates the feature similarity between the information to be matched and the repair script modules in a preset repair script module library through the target early warning feature, the host internet interconnection protocol information and the monitoring item information, and judges whether the feature similarity is a preset target value; if the feature similarity is a preset target value, splicing the repair script modules corresponding to the feature similarity according to a preset merging strategy to obtain a target repair script; if the feature similarity is not the preset target value, judging whether the feature similarity is larger than a preset similarity threshold value; and if the feature similarity is greater than a preset similarity threshold value, filtering and splicing the repair script modules corresponding to the feature similarity to obtain the target repair script.

For example, the server calculates cosine similarity between the information to be matched and the repair script modules in the preset repair script module library through the target early warning feature, the host internet interconnection protocol information and the monitoring item information, calculates the pearson correlation coefficient between the information to be matched and the repair script modules in the preset repair script module library through the target early warning feature, the host internet interconnection protocol information and the monitoring item information, obtains the feature similarity by performing weighted summation on the cosine similarity and the pearson correlation coefficient, and judges whether the feature similarity is a preset target value, the preset target value is preferably 100%, if yes, the repair script modules corresponding to the feature similarity are spliced according to a preset merging strategy to obtain a target repair script, the merging strategy splices the repair script modules to form a script meeting grammar and rules, if not, judging whether the feature similarity is greater than a preset similarity threshold value, if not, stopping execution, if so, filtering and splicing the repair script modules corresponding to the feature similarity or splicing and filtering the repair script modules, and thus obtaining a target repair script, wherein the specific execution process of the filtering after splicing is as follows: and combining and splicing the repair script modules corresponding to the feature similarity according to preset script grammar and script rules to obtain a combined script, calculating a weighted average value of the feature similarity in the combined script, sequencing the combined script according to the descending order of the weighted average value, and determining the first sequenced combined script as a target repair script.

Specifically, if the feature similarity is greater than a preset similarity threshold, the server performs combination calculation and splicing sequence calculation on the repair script modules corresponding to the feature similarity through a preset greedy algorithm to obtain module combination information and splicing sequence information; and acquiring a target repair script module from the repair script modules corresponding to the feature similarity through the module combination information, and splicing the target repair script modules according to the splicing sequence information to obtain a target repair script.

For example, if the feature similarity is greater than the preset similarity threshold, the server calculates the combination and splicing sequence of the repair script modules corresponding to the feature similarity through a target function established in advance based on a preset greedy algorithm based on a preset repair strategy, the repair strategy comprises repair time, repair scheme, repair item field and repair sequence corresponding to the early warning information, the module combination information and splicing sequence information are obtained, the target repair script modules corresponding to the module combination information are extracted from the repair script modules corresponding to the feature similarity, the target repair script modules are spliced according to the splicing sequence information to obtain an initial repair script, the initial repair script is subjected to detection of grammar, rules and integrity to obtain a detection repair script, a preset test case is called, and the detection repair script is subjected to running test and test adjustment, and obtaining a target repair script which passes the test, wherein the test adjustment is used for self-revising the test failed item through a preset revision strategy.

205. And calling the target repair script to execute repair, acquiring a repair state of the target repair script after the target repair script executes repair and execution information generated in the process of executing repair by the target repair script, and determining the repair state and the execution information as information to be analyzed.

And the server calls the target repair script to execute corresponding repair, acquires execution information generated when the target repair script executes repair, and reads a repair state when the target repair script executes repair, so as to obtain information to be analyzed.

206. And comparing and analyzing the information to be analyzed with a preset execution ending condition to obtain detection information.

The server judges whether the information to be analyzed meets a preset execution ending condition, if so, returns a return value indicating yes, and if not, returns a return value indicating no, so that detection information is obtained, wherein the execution ending condition can include but is not limited to completion of repair and effectiveness of repair of all early warning information.

207. And triggering a preset terminal manual repair instruction or a repair finishing instruction according to the detection information.

If the detection information is yes, a repair ending instruction is triggered, and the execution of repair is stopped; if the detection information is not, triggering a preset terminal manual repair instruction, analyzing the information to be analyzed and the detection information based on starting the preset terminal manual repair instruction, generating a report, obtaining a repair report, sending the repair report to the preset terminal according to a preset strategy, performing manual repair through the preset terminal, and specifically including: executing repair corresponding to the target early warning feature based on a preset strategy through a preset terminal, wherein the preset strategy comprises an execution priority and an execution level, and if: the preset terminal comprises a preset terminal A, a preset terminal B and a preset terminal C, and the execution priority of the preset terminal is as follows: the method comprises the following steps that a preset terminal A, a preset terminal B and a preset terminal C are provided, and the execution level of the preset terminal is as follows: the method comprises the steps that a preset terminal A, a preset terminal B and a preset terminal C are provided, namely a repair report is sent to the preset terminal A, repair personnel of the preset terminal A carry out manual repair according to the repair report to obtain a repair result 1, the preset terminal A sends the repair result 1 to the preset terminal B, the repair personnel of the preset terminal B carry out manual repair according to the repair report and the repair result 1 to obtain a repair result 2, the preset terminal B sends the repair result 2 to the preset terminal C, the repair personnel of the preset terminal C carry out manual repair according to the repair report and the repair result 2, and the manual repair of the preset terminal corresponding to a preset terminal repair instruction can comprise manual maintenance of the preset terminal.

In the above description of the self-repairing method based on the warning information in the embodiment of the present invention, the self-repairing device based on the warning information in the embodiment of the present invention is described below with reference to fig. 3, and an embodiment of the self-repairing device based on the warning information in the embodiment of the present invention includes:

the first extraction module 301 is configured to obtain monitoring data of a preset monitoring system, and extract early warning information of the monitoring data through a preset early warning analysis model to obtain to-be-processed early warning information, where the to-be-processed early warning information includes host internet interconnection protocol information and monitoring item information;

the analysis and verification module 302 is configured to perform state analysis, configuration analysis, white list library analysis and verification processing on the to-be-processed early warning information in sequence to obtain to-be-matched information;

the second extraction module 303 is configured to call a preset feature extraction model, perform early warning feature extraction on information to be matched and perform early warning feature matching based on an early warning feature library to obtain a target early warning feature;

the matching and splicing module 304 is used for matching and splicing a preset repair script module library through the target early warning feature, the host internet interconnection protocol information and the monitoring item information to obtain a target repair script;

and the detection triggering module 305 is configured to call the target repair script to perform repair and perform detection, obtain detection information, and trigger a repair end instruction based on the detection information.

The function realization of each module in the self-repairing device based on the early warning information corresponds to each step in the embodiment of the self-repairing method based on the early warning information, and the functions and the realization process are not repeated here.

Referring to fig. 4, another embodiment of a self-repairing apparatus based on warning information in the embodiment of the present invention includes:

the detection triggering module 305 is configured to call a target repair script to perform repair and perform detection, obtain detection information, and trigger a repair end instruction based on the detection information;

the detection triggering module 305 specifically includes:

the detection unit 3051 is configured to call the target repair script to perform repair, acquire a repair state of the target repair script after performing repair and execution information generated by the target repair script during performing a repair process, and determine the repair state and the execution information as information to be analyzed;

the comparison analysis unit 3052 is configured to perform comparison analysis on the information to be analyzed and a preset execution end condition to obtain detection information;

and the triggering unit 3053 is configured to trigger a preset terminal manual repair instruction or a repair end instruction according to the detection information.

Optionally, the first extraction module 301 may be further specifically configured to:

deleting fault information in the monitoring data to obtain filtering information, and performing fault prediction on the filtering information through an early warning analysis model to obtain potential early warning information;

and merging the fault information, the potential early warning information and the initial early warning information to obtain the early warning information to be processed.

Optionally, the analysis and verification module 302 includes:

a first judging unit 3021, configured to obtain corresponding state information from a preset configuration management database through host internet interconnection protocol information in the to-be-processed early warning information, and judge whether the state information is preset non-processed state information;

a second judging unit 3022, configured to obtain self-repair configuration information if the status information is not preset non-processing status information, and judge whether the self-repair configuration information exists in the monitoring item information;

a third judging unit 3023, configured to judge whether the host internet interconnection protocol information and the monitoring item information exist in a preset self-repair white list library if the monitoring item information has self-repair configuration information;

and the verification processing unit 3024 is configured to, if the host internet interconnection protocol information and the monitoring item information exist in the self-repair white list library, perform information verification processing on the to-be-processed early warning information to obtain to-be-matched information.

Optionally, the verification processing unit 3024 may be further specifically configured to:

calculating the information similarity of the early warning information to be processed and the comparison information, and judging whether the information similarity is greater than a preset contrast threshold value or not;

and if the information similarity is greater than the preset contrast threshold, determining the early warning information to be processed as the information to be matched.

Optionally, the match-splice module 304 includes:

a calculation and judgment unit 3041, configured to calculate, through the target early warning feature, the host internet interconnection protocol information, and the monitoring item information, a feature similarity between the information to be matched and a repair script module in a preset repair script module library, and judge whether the feature similarity is a preset target value;

a splicing unit 3042, configured to splice, if the feature similarity is a preset target value, the repair script modules corresponding to the feature similarity according to a preset merging strategy, to obtain a target repair script;

a fourth determining unit 3043, configured to determine whether the feature similarity is greater than a preset similarity threshold if the feature similarity is not the preset target value;

and the filtering and splicing unit 3044 is configured to, if the feature similarity is greater than the preset similarity threshold, filter and splice the repair script modules corresponding to the feature similarity to obtain a target repair script.

Optionally, the filtering and splicing unit 3044 may be further specifically configured to:

if the characteristic similarity is greater than a preset similarity threshold, performing combined calculation and splicing sequence calculation on the repair script modules corresponding to the characteristic similarity through a preset greedy algorithm to obtain module combined information and splicing sequence information;

and acquiring a target repair script module from the repair script modules corresponding to the feature similarity through the module combination information, and splicing the target repair script modules according to the splicing sequence information to obtain a target repair script.

The function realization of each module and each unit in the self-repairing device based on the early warning information corresponds to each step in the embodiment of the self-repairing method based on the early warning information, and the functions and the realization process are not repeated herein.

Fig. 3 and 4 describe the self-repairing device based on the warning information in the embodiment of the present invention in detail from the perspective of the modular functional entity, and the self-repairing device based on the warning information in the embodiment of the present invention is described in detail from the perspective of hardware processing.

Fig. 5 is a schematic structural diagram of a self-healing apparatus based on warning information according to an embodiment of the present invention, where the self-healing apparatus 500 based on warning information may generate relatively large differences due to different configurations or performances, and may include one or more processors (CPUs) 510 (e.g., one or more processors) and a memory 520, and one or more storage media 530 (e.g., one or more mass storage devices) storing applications 533 or data 532. Memory 520 and storage media 530 may be, among other things, transient or persistent storage. The program stored on the storage medium 530 may include one or more modules (not shown), each of which may include a series of instructions operating on the self-healing apparatus 500 based on pre-alarm information. Still further, the processor 510 may be configured to communicate with the storage medium 530 to execute a series of instruction operations in the storage medium 530 on the self-healing apparatus 500 based on pre-alarm information.

The self-healing device 500 based on pre-alarm information may also include one or more power supplies 540, one or more wired or wireless network interfaces 550, one or more input-output interfaces 560, and/or one or more operating systems 531, such as Windows server, Mac OS X, Unix, Linux, FreeBSD, and the like. Those skilled in the art will appreciate that the pre-alarm information-based self-healing apparatus structure illustrated in fig. 5 does not constitute a limitation of pre-alarm information-based self-healing apparatuses and may include more or fewer components than those illustrated, or some components in combination, or a different arrangement of components.

The present invention also provides a computer readable storage medium, which may be a non-volatile computer readable storage medium, and which may also be a volatile computer readable storage medium, having stored therein instructions, which, when executed on a computer, cause the computer to perform the steps of the self-healing method based on pre-alarm information.

Further, the computer-readable storage medium may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function, and the like; the storage data area may store data created according to the use of the blockchain node, and the like.

The block chain is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, a consensus mechanism, an encryption algorithm and the like. A block chain (Blockchain), which is essentially a decentralized database, is a series of data blocks associated by using a cryptographic method, and each data block contains information of a batch of network transactions, so as to verify the validity (anti-counterfeiting) of the information and generate a next block. The blockchain may include a blockchain underlying platform, a platform product service layer, an application service layer, and the like.

It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.

The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a read-only memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.

The above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.

Claims

1. A self-repairing method based on early warning information is characterized by comprising the following steps:

2. The self-repairing method based on early warning information of claim 1, wherein the obtaining of the monitoring data of a preset monitoring system and the extraction of the early warning information of the monitoring data through a preset early warning analysis model to obtain the early warning information to be processed comprises:

3. The self-repairing method based on early warning information of claim 1, wherein the performing state analysis, configuration analysis, white list library analysis and verification processing on the early warning information to be processed in sequence to obtain information to be matched comprises:

4. The self-repairing method based on early warning information of claim 3, wherein if the host internetworking protocol information and the monitoring item information exist in the self-repairing white list library, performing information verification processing on the early warning information to be processed to obtain information to be matched, the method comprises:

5. The self-repairing method based on early warning information of claim 1, wherein the matching and splicing of preset repair script module libraries through the target early warning feature, the host internetworking protocol information and the monitoring item information to obtain a target repair script comprises:

6. The self-repairing method based on early warning information of claim 5, wherein if the feature similarity is greater than the preset similarity threshold, filtering and splicing the repairing script modules corresponding to the feature similarity to obtain a target repairing script comprises:

7. The self-repairing method based on early warning information of any one of claims 1-6, wherein the calling the target repairing script to perform repairing and detect to obtain detection information, and triggering a repairing ending instruction based on the detection information comprises:

8. A self-repairing device based on early warning information is characterized in that the self-repairing device based on early warning information comprises:

9. The self-repairing device based on the early warning information is characterized by comprising: a memory and at least one processor, the memory having instructions stored therein;

the at least one processor invokes the instructions in the memory to cause the warning information based self-healing apparatus to perform the warning information based self-healing method of any of claims 1-7.

10. A computer-readable storage medium having instructions stored thereon, wherein the instructions, when executed by a processor, implement the self-healing method based on pre-alarm information as recited in any one of claims 1-7.