CN114095336A - End-to-end problem diagnosis method and system - Google Patents
End-to-end problem diagnosis method and system Download PDFInfo
- Publication number
- CN114095336A CN114095336A CN202010790127.3A CN202010790127A CN114095336A CN 114095336 A CN114095336 A CN 114095336A CN 202010790127 A CN202010790127 A CN 202010790127A CN 114095336 A CN114095336 A CN 114095336A
- Authority
- CN
- China
- Prior art keywords
- diagnosis
- data
- network
- internet
- things
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000003745 diagnosis Methods 0.000 title claims abstract description 184
- 238000000034 method Methods 0.000 title claims abstract description 82
- 238000003066 decision tree Methods 0.000 claims description 36
- 238000012545 processing Methods 0.000 claims description 33
- 230000005540 biological transmission Effects 0.000 claims description 10
- 238000012544 monitoring process Methods 0.000 claims description 9
- 230000004044 response Effects 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 6
- 230000002159 abnormal effect Effects 0.000 claims description 4
- 238000010276 construction Methods 0.000 claims description 4
- 238000003860 storage Methods 0.000 claims description 3
- 239000000126 substance Substances 0.000 claims description 2
- 230000008569 process Effects 0.000 abstract description 17
- 238000004458 analytical method Methods 0.000 abstract description 7
- 238000011835 investigation Methods 0.000 abstract description 6
- 238000004422 calculation algorithm Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 238000007726 management method Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 3
- 238000005284 basis set Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000005192 partition Methods 0.000 description 2
- 230000011664 signaling Effects 0.000 description 2
- 230000004913 activation Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000007635 classification algorithm Methods 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000013024 troubleshooting Methods 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/06—Management of faults, events, alarms or notifications
- H04L41/0631—Management of faults, events, alarms or notifications using root cause analysis; using analysis of correlation between notifications, alarms or events based on decision criteria, e.g. hierarchy, tree or time analysis
- H04L41/0636—Management of faults, events, alarms or notifications using root cause analysis; using analysis of correlation between notifications, alarms or events based on decision criteria, e.g. hierarchy, tree or time analysis based on a decision tree analysis
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/02—Standardisation; Integration
- H04L41/0246—Exchanging or transporting network management information using the Internet; Embedding network management web servers in network elements; Web-services-based protocols
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/06—Management of faults, events, alarms or notifications
- H04L41/0631—Management of faults, events, alarms or notifications using root cause analysis; using analysis of correlation between notifications, alarms or events based on decision criteria, e.g. hierarchy, tree or time analysis
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/22—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks comprising specially adapted graphical user interfaces [GUI]
Abstract
The embodiment of the application discloses an end-to-end problem diagnosis method and system, the diagnosis efficiency is high, a convenient one-key type investigation interface is adopted, the manual process consuming several days is converted into an automatic process within one minute, the time cost and the labor cost are saved, and the technical capability requirement on an analyst is also reduced. The method has the advantages of high diagnosis accuracy, coverage of a data source of the whole process of the Internet of things service, diagnosis for end-to-end fault points, no need of manual intervention in the whole diagnosis process, avoidance of errors caused by manual investigation, and more accurate and reliable analysis results.
Description
[ technical field ] A method for producing a semiconductor device
The application relates to the technical field of fault diagnosis of the Internet of things, in particular to an end-to-end problem diagnosis method and system.
[ background of the invention ]
The Internet of things service is issued nationwide at one point, complaint fault handling needs to be associated with 8 major fields of a user side system, a terminal, a charging, a wireless, a transmission, a bearing, a core network and an Internet of things private network, is the service which is the most related to the most links, the most complex flow and the most major fields at present, and is a method for detecting and treating complaint faults of the Internet of things at present, and mainly comprises the steps of collecting indexes and abnormal conditions of each professional system through issuing a single to a relevant unit, and manually analyzing and judging original signaling message data.
At present, complaints of the Internet of things are mainly processed through manual analysis, the method needs to cooperate with a client side, an intra-provincial wireless transmission department, an intra-provincial core network department, an Internet of things company side and a content server side to perform joint troubleshooting, and the complaints are processed by 5 links, wherein information transmission may have deviation, time consumption is long in complaint processing each time, workload is large, and processing timeliness and accuracy of the complaints of the Internet of things are low.
[ application contents ]
In view of this, the embodiment of the present application provides an end-to-end problem diagnosis method and system, so as to solve the technical problem in the prior art that the processing timeliness and the accuracy of internet of things complaints are low.
In a first aspect, an embodiment of the present application provides an end-to-end problem diagnosis method, including the following steps:
the system acquires data information in a network data source;
the system respectively diagnoses a plurality of diagnosis points of each diagnosis dimension in the system according to the data information, and obtains a diagnosis result corresponding to each diagnosis point;
the system establishes a data set based on the diagnosis points and the diagnosis results, and constructs a decision tree according to the data set.
According to the scheme provided by the embodiment, data of a plurality of business departments in the service of the Internet of things can be fused into the system, the data which are originally processed in each business department are all brought into one system for centralized processing by utilizing the end-to-end capacity, one-key diagnosis of the end-to-end problem of the Internet of things is realized, the fault complaint is automated, and the complaint processing efficiency and accuracy of the Internet of things are comprehensively improved.
In a preferred embodiment, the step of the system acquiring data information from a network data source comprises:
the system is in network connection with a plurality of professional departments with end-to-end service of the Internet of things;
the system receives data information in a plurality of specialized departments via a network.
Through the scheme provided by the embodiment, the whole internet of things network is communicated, and the data information in the network data source of the whole internet of things is accessed, so that one-point cleaning, one-point opening and one-point analysis can be carried out on the data in the system, the conversion from a plurality of platforms to a single platform is completed, the capacity sharing is realized, and one-point support is realized.
In a preferred embodiment, the step of the system respectively diagnosing a plurality of diagnosis points existing in each diagnosis dimension in the system according to the data information and obtaining a diagnosis result corresponding to each diagnosis point includes:
setting a plurality of diagnostic dimensions in the system, each diagnostic dimension having a plurality of diagnostic points;
setting a plurality of diagnosis bases aiming at each diagnosis point according to the data information;
and diagnosing each diagnosis point based on the diagnosis basis, and obtaining a corresponding diagnosis result.
According to the scheme provided by the embodiment, the system diagnoses each fault by adopting a mode of diagnosing from a plurality of diagnosis dimensions, and the diagnosis basis set according to actual requirements or conditions is referred to for the diagnosis points in the diagnosis dimensions, so that the diagnosis of each diagnosis point is completed and the diagnosis result is obtained.
In a preferred embodiment, the plurality of diagnostic dimensions comprises: the method comprises the steps of (1) terminal dimension, user dimension, network dimension and Internet of things private network dimension; wherein the content of the first and second substances,
the diagnosing of the terminal dimension comprises: the method comprises the steps that whether a fault exists in a terminal is comprehensively judged through an error code and a service response code accessed by a monitoring terminal and a network index of the terminal type in the same comparison;
the diagnosing of the user dimension includes: the method comprises the steps of comprehensively judging whether the configuration of a user per se has problems by acquiring the authentication configuration condition of a terminal and the APN configuration condition of the terminal;
the diagnosing of the network dimension includes: the method is used for comprehensively judging whether the network of each link is abnormal or not by monitoring the network coverage condition of a wireless network, the equipment fault condition of a wireless/transmission/core network and the network element quality difference condition and combining network error code diagnosis;
the diagnosis of the private network dimension of the internet of things comprises the following steps: the method is used for judging whether the private network of the Internet of things has faults or not by monitoring the error code of the platform of the Internet of things and the server time delay index and combining the signing error code and the server response code.
By the scheme provided by the embodiment, the method can basically meet the requirements of end-to-end problem diagnosis of most of the Internet of things, so that the fault processing capability of the diagnosis method is more comprehensive and more specific.
In a preferred embodiment, the step of the system building a data set based on the diagnosis points and the diagnosis results, and building a decision tree based on the data set, comprises:
dividing a plurality of fault types according to complaint scenes of users of the Internet of things, and corresponding each fault type with a diagnosis point;
respectively solving the diagnosis result of each diagnosis point according to a plurality of fault types, and forming a data set according to the diagnosis result;
constructing a decision tree from the data set;
and obtaining a processing suggestion corresponding to the diagnosis result of each diagnosis dimension according to the decision tree.
According to the scheme provided by the embodiment, the processing suggestions which should be adopted for processing each fault type are respectively corresponding to the professional departments of the Internet of things in a decision tree mode, so that the processing suggestions which are originally distributed to the professional departments for processing are not omitted, and the processing suggestions of the faults generated among the related professional departments can be fused, so that the fault processing capacity of the diagnosis method is more comprehensive and more effective.
In a preferred embodiment, the process of establishing the decision tree includes the following steps:
calculating an empirical entropy of the data set;
calculating the information gain of each characteristic value to the data set;
circularly calculating the information entropy of the leaf nodes and the information gain of each characteristic on the subset of the data set;
and establishing the decision tree based on the calculation result.
By the scheme provided by the embodiment, a method for recursively calculating information gain is adopted, which professional department the problem of each diagnosis point belongs to can be traversed in detail, and thus the decision tree is effectively and accurately established.
In a preferred embodiment, the data information includes interface data, intra-provincial network index data, internet of things private network service data and third party support system data, the interface data is used for providing interface information of an internet of things platform, the intra-provincial network index data is used for providing information of a network management system, the internet of things private network service data is used for providing information of the internet of things platform at a user side, and the third party support system data is used for providing information of a system supporting the operation of the internet of things platform.
In a second aspect, an embodiment of the present application provides an end-to-end problem diagnosis system, including:
the acquisition module is used for acquiring data information in a network data source;
the diagnosis module is used for respectively diagnosing a plurality of diagnosis points in each diagnosis dimension according to the data information and obtaining a diagnosis result corresponding to each diagnosis point;
and the construction module is used for forming a data set based on the diagnosis result, constructing a decision tree according to the data set, and obtaining a processing suggestion corresponding to the diagnosis result of each diagnosis dimension through the decision tree.
According to the scheme provided by the embodiment, data of a plurality of business departments in the service of the Internet of things can be fused into the system, the data which are originally processed in each business department are all brought into one system for centralized processing by utilizing the end-to-end capacity, one-key diagnosis of the end-to-end problem of the Internet of things is realized, the fault complaint is automated, and the complaint processing efficiency and accuracy of the Internet of things are comprehensively improved.
In a third aspect, an embodiment of the present application provides an electronic device, including: a memory and a processor:
the memory for storing a computer program;
the processor is configured to execute the computer program stored in the memory to cause the electronic device to perform the method according to the first aspect.
In a fourth aspect, embodiments of the present application provide a computer-readable storage medium, comprising a program or instructions, which when run on a computer, performs the method according to the first aspect.
Compared with the prior art, the technical scheme at least has the following beneficial effects:
the end-to-end problem diagnosis method and system disclosed by the embodiment of the application have the following two technical advantages:
the diagnosis efficiency is high: this application adopts convenient one-touch formula investigation interface, changes this several days's that consume time manual process into the automatic flow in a minute, has not only practiced thrift time cost and human cost, has also reduced the technological capability requirement to analyst.
(II) the diagnosis accuracy is high: the method and the system cover the data source of the whole process of the Internet of things service, can diagnose the end-to-end fault point, do not need manual intervention in the whole diagnosis process, avoid errors caused by manual investigation, and enable the analysis result to be more accurate and reliable.
[ description of the drawings ]
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
FIG. 1 is a schematic diagram of the steps of an end-to-end problem diagnosis method provided in embodiment 1 of the present application;
fig. 2 is a flowchart of implementation of Step100 in the end-to-end problem diagnosis method provided in embodiment 1 of the present application;
fig. 3 is a flowchart of implementation of Step200 in the end-to-end problem diagnosis method provided in embodiment 1 of the present application;
fig. 4 is a multi-dimensional diagnostic score chart of an example of the Step200 of the end-to-end problem diagnosis method provided in embodiment 1 of the present application;
fig. 5 is a flowchart illustrating implementation of Step300 in the end-to-end problem diagnosis method provided in embodiment 1 of the present application;
FIG. 6 is a flow chart of a decision tree constructed in the end-to-end problem diagnosis method provided in embodiment 1 of the present application;
FIG. 7 is a schematic diagram of a decision tree of an example of the end-to-end problem diagnosis method provided in embodiment 1 of the present application;
FIG. 8 is a block diagram of an end-to-end problem diagnosis system provided in embodiment 2 of the present application;
fig. 9 is an architecture diagram of a one-touch diagnostic tool of the internet of things in embodiment 2 of the present application.
Reference numerals:
1-an acquisition module;
2-a diagnostic module;
3-building a module.
[ detailed description ] embodiments
For better understanding of the technical solutions of the present application, the following detailed descriptions of the embodiments of the present application are provided with reference to the accompanying drawings.
It should be understood that the embodiments described are only a few embodiments of the present application, and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
Example 1
The embodiment 1 of the application discloses an end-to-end problem diagnosis method, which is an automatic diagnosis method for end-to-end problems of the Internet of things, and aims at solving the problem that the prior complaint and treatment of the Internet of things are low in efficiency. The method gets through the end-to-end whole flow of the Internet of things by accessing data such as wireless data, transmission data, DPI data, Internet of things platforms and the like. On the basis of big data of the Internet of things, an independent research core architecture and diagnosis logic are combined, a one-key diagnosis tool of the Internet of things is developed, automatic delimiting positioning of fault complaints is achieved, and the problems of low timeliness and accuracy of complaint handling of the Internet of things are comprehensively solved.
As shown in fig. 1, the end-to-end problem diagnosis method includes the steps of:
step 100: the system obtains data information in a network data source.
The service of the internet of things relates to eight major specialties of a user side system, a terminal, charging, wireless, transmission, bearing, a core network and a private network of the internet of things. The data information comprises interface data, intra-provincial network index data, Internet of things private network service data and third party support system data, the interface data is used for providing interface information of an Internet of things platform, the intra-provincial network index data is used for providing information of a network management system, the Internet of things private network service data is used for providing information of the Internet of things platform on a user side, and the third party support system data is used for providing information of a system supporting the operation of the Internet of things platform. As shown in table 1.
Table 1: data information statistical table of network data source
As shown in fig. 2, Step100 further includes the following steps:
step 101: the system is in network connection with a plurality of professional departments with end-to-end services of the Internet of things.
Step 102: the system receives data information in a plurality of specialized departments via a network.
In the end-to-end problem diagnosis method provided by this embodiment, in Step100, the data information of the full-flow data source located in the network bookyard is accessed through the open network, the network of the whole internet of things is opened, and the data information in the network data source of the whole internet of things is accessed, so that data can be cleaned, opened and analyzed at one point in the system. And the end-to-end capability is opened, the conversion from a plurality of platforms to a single platform is completed, the capability sharing is realized, and one-point support is realized.
Step 200: and the system respectively diagnoses a plurality of diagnosis points of each diagnosis dimension in the system according to the data information, and obtains a diagnosis result corresponding to each diagnosis point.
Specifically, in Step200, after the data source of the whole process is accessed, problems existing in four links, namely a terminal, a user, a network and an internet of things, are diagnosed synchronously around error codes, indexes, alarms and the like, and a diagnosis result is given to all diagnosis points in each link. And each dimension is scored comprehensively based on the weight of the diagnostic points. As shown in fig. 3, Step200 is implemented by the following steps:
step 201: a plurality of diagnostic dimensions are set in the system, each diagnostic dimension having a plurality of diagnostic points.
Step 202: and according to the data information, setting a plurality of diagnosis bases aiming at each diagnosis point.
Step 203: and diagnosing each diagnosis point based on the diagnosis basis, and obtaining a corresponding diagnosis result.
Wherein the plurality of diagnostic dimensions include: terminal dimension, user dimension, network dimension and internet of things private network dimension. The diagnosis of the terminal dimensions comprises: the method comprises the steps that whether a fault exists in a terminal is comprehensively judged through an error code and a service response code accessed by a monitoring terminal and a network index of the terminal type in the same comparison; the diagnosis of the user dimension includes: the method comprises the steps of comprehensively judging whether the configuration of a user per se has problems by acquiring the authentication configuration condition of a terminal and the APN configuration condition of the terminal; the diagnosis of the network dimension includes: the method is used for comprehensively judging whether the network of each link is abnormal or not by monitoring the network coverage condition of a wireless network, the equipment fault condition of a wireless/transmission/core network and the network element quality difference condition and combining network error code diagnosis; the diagnosis of the private network dimension of the Internet of things comprises the following steps: the method is used for judging whether the private network of the Internet of things has faults or not by monitoring the error code of the platform of the Internet of things and the server time delay index and combining the signing error code and the server response code. The multiple diagnosis dimensions are set, so that the requirements of end-to-end problem diagnosis of most of the Internet of things can be basically met, and the fault processing capability of the diagnosis method is more comprehensive and more specific.
For example, the diagnostic basis and scoring weight for each dimension diagnostic point are shown in table 2 below.
Table 2: diagnosis discrimination scoring table
Specifically, as shown in fig. 4, the terminal side, the user side, the network side and the internet of things private network side are respectively subjected to diagnosis scoring through the multidimensional diagnosis scoring system of Step200, and the scores on the terminal side, the user side and the internet of things private network side are 100 points, while the score on the network side is only 50 points. Therefore, in the end-to-end process of the platform of the Internet of things, the network side has faults and needs to be maintained, and an engineer can maintain equipment and a system of the network side.
In Step200, the system diagnoses each fault in multiple diagnosis dimensions, and referring to the diagnosis basis set according to actual needs or situations for the diagnosis points in the diagnosis dimensions, so as to complete the diagnosis of each diagnosis point and obtain the diagnosis result.
Step 300: the system builds a data set based on the diagnostic points and diagnostic results and builds a decision tree from the data set.
Specifically, based on the complaint scene of the user of the internet of things, the fault types can be divided into multiple types, diagnosis is performed from four dimensions in the system of Step200 according to various fault types, a diagnosis result is obtained, a data set is formed, and then a decision tree is constructed according to the data set to obtain corresponding processing suggestions. As shown in fig. 5, the implementation steps are as follows:
step 301: and (3) dividing a plurality of fault types according to the complaint scene of the user of the Internet of things, and corresponding each fault type with a diagnosis point.
Step 302: and respectively obtaining the diagnosis result of each diagnosis point according to the plurality of fault types, and forming a data set according to the diagnosis results.
Step 303: a decision tree is constructed from the data set.
Step 304: and obtaining a processing proposal corresponding to the diagnosis result of each diagnosis dimension according to the decision tree.
In Step303, the construction of the decision tree needs to be implemented through four steps, and the specific flow shown in fig. 6 is as follows:
step 3031: an empirical entropy of the data set is calculated.
Step 3032: and calculating the information gain of each characteristic value to the data set.
Step 3033: and circularly calculating the information entropy of the leaf nodes and the information gain of each characteristic on the subset of the data set.
Step 3034: and establishing a decision tree based on the calculation result.
For example, based on a complaint scene of a user of the internet of things, the fault types are divided into four types, namely user offline, network access failure, service access failure and service use abnormity. The phenomena of the four failure types on the network side are shown in the following table 3:
| ID | type of | Network phenomena | |
| 1 | User off-line | Gb/Gn/S1-MME/S1-U interface |
|
| 2 | Network access failure | Attachment success rate and PDP activation success rate<70％ | |
| 3 | Service access failure | Service access success rate and TCP link establishment success rate<70％ | |
| 3 | Traffic usage exceptions | The uplink or downlink flow rate is 0 |
Table 3: network side phenomena for each fault type
Based on the four implementation steps of table 3 and Step300, 100 complaint worksheets of the internet of things in three months are diagnosed at each diagnosis point by using the multidimensional diagnosis system in Step200 to obtain a data set D, which is detailed in table 4 below.
Table 4: complaint data set of Internet of things
Since the 12 feature values in the dataset have an uncertain effect on the diagnostic result, it was decided to construct a decision tree using the ID3 algorithm, a classification algorithm for decision trees.
Data set D { (x)(1),y(1)),...(x(100),y(100))}。
Set of features a ═ { failure type (a) }1) Same type of terminal failure condition (A)2) Terminal authentication configuration case (A)3) ,., service response code diagnosis result (a)12)}。
And (3) a category set Y is { poor quality terminal, SIM card/terminal damaged, terminal configuration error, base station equipment fault, high interference of a wireless side, weak coverage of the wireless side, transmission link fault, core network element fault, signed data abnormity and server abnormity }.
The ID3 algorithm uses information gain as a criterion for feature selection. In the selection process, information gain is calculated for each feature, the diagnosis point with the maximum information gain is selected as the current node feature, and the leaf nodes are established according to different values of the current node feature. This method is then used recursively for the leaf nodes until all the feature information gains are small or there are no optional features. The calculation flow of the ID3 algorithm is as follows:
first, the empirical entropy h (D) of the data set D is calculated:
the number of samples in the diagnosis result type set Y is (a, b, c, d, e, f, g, h, i, j)
Next, the information gain for each feature for D is calculated:
first, the failure type (A)1) It has four possible values, the number of times is DA1 (1)(A1Off-line for subscriber (A, D)A1 (2)(A1Network access failure, B, DA1 (3)(A1Service access failure ═ C, DA1 (4)(A1Traffic usage exception) D. Respectively calculating the information entropy H (D) of four valuesA1 (1))，H(DA1 (2))，H(DA1 (3))，
H(DA1 (4)) The information gain of the feature for D is thus obtained according to the formula:
the same algorithm is adopted to obtain the information gain g (D, A) of other 11 characteristic values2)，g(D,A3)，g(D,A4)...g(D,A12)
Comparing 12 information gains, the largest information gain is g (D, A)1) I.e. type of failure (A)1) The criteria for feature selection partition the data set. There are 4 values, according to the user off-line, the network access failure, the service use abnormity divides the data set into 4 subsets D'1，D’2，D’3，D’4。
Thirdly, the information entropy of the leaf nodes and the information gain of each feature for the subset D' are calculated in a loop:
the above method is repeated for each of the four subsets, for D'1And (3) calculating:
D(D’1),g(D’1,A2)，g(D’1,A3)，...g(D’1,A12)
comparing 11 information gains, and selecting the characteristics with the maximum information gain to divide and establish leaf nodes.
For D 'in the same way'2，D’3，D’4Leaf nodes are also established separately in this way until the subsets can no longer partition down leaf nodes (subset D)nEmpirical entropy of (D) H (D)n)＝0)。
Finally, a decision tree is established based on the calculation results:
according to the previous process (namely, the information entropy of the leaf nodes and the information gain of each feature to the subset D' are calculated circularly), after the leaf nodes are divided circularly, the category set Y is all separated.
According to the above calculation process, a decision tree as shown in fig. 7 can be established. And finally classifying the result into 10 diagnosis results according to decision tree judgment logic, wherein the diagnosis results are respectively poor terminals, SIM cards/terminals are damaged, terminal configuration errors, base station equipment faults, high wireless side interference, weak wireless side coverage, transmission link faults, core network element faults, signed data abnormity and server abnormity. And matching the corresponding processing recommendations against the diagnostic results. In the process of constructing the decision tree, a method of recursively calculating information gain is adopted, which professional department each diagnosis point belongs to can be traversed in detail, and therefore the decision tree is effectively and accurately established.
In Step300, the processing suggestions to be adopted for processing each fault type are respectively corresponding to the professional departments of the internet of things in a decision tree manner, so that the processing suggestions originally distributed to each professional department for processing are not omitted, and the processing suggestions of the faults generated among the related professional departments can be fused, so that the fault processing capability of the diagnosis method is more comprehensive and more effective.
By adopting the end-to-end problem diagnosis method disclosed by the embodiment, data of a plurality of business departments in the service of the internet of things can be fused into a system, and all data originally processed in each business department are brought into one system for centralized processing by utilizing the end-to-end capability, so that one-key diagnosis of the end-to-end problem of the internet of things is realized, fault complaint is automated, and the efficiency and accuracy of complaint processing of the internet of things are comprehensively improved.
Example 2
As shown in fig. 8, embodiment 2 of the present application discloses an end-to-end problem diagnosis system, which includes:
the acquisition module 1 is used for acquiring data information in a network data source;
the diagnosis module 2 is used for respectively diagnosing a plurality of diagnosis points existing in each diagnosis dimension according to the data information and obtaining a diagnosis result corresponding to each diagnosis point;
and the construction module 3 is used for forming a data set based on the diagnosis result, constructing a decision tree according to the data set, and obtaining a processing suggestion corresponding to the diagnosis result of each diagnosis dimension through the decision tree.
The end-to-end problem diagnosis system disclosed in this embodiment is located in the internet of things one-key diagnosis tool, as shown in fig. 9, the overall architecture of the internet of things one-key diagnosis tool is mainly divided into an acquisition layer, a rule layer and an application layer, and by dividing the layers, the coupling degree between the layers is reduced, the functions are distinguished, and the increase and the change of each function and the change of each module are facilitated.
Specifically, the acquisition layer comprises DPI data of each interface between network elements, link data, automatic dial test data, core network management data, wireless network management data and the like, and is a source for generating platform data. The rule layer comprises index alarm correlation, error code analysis and big data integration analysis. The data collected by the acquisition layer is mainly sorted by formulating corresponding rules to form related structured data available for the application layer. The application layer forms a complete automatic diagnosis function by deeply integrating the structured data provided by the rule layer, and provides a convenient operable interface.
The end-to-end problem diagnosis system disclosed by the embodiment can fuse data of a plurality of business departments in the service of the internet of things into the system, and all data which are originally processed in each business department are brought into one system for centralized processing by utilizing the end-to-end capability, so that one-key diagnosis of the end-to-end problem of the internet of things is realized, the fault complaint is automated, and the complaint processing efficiency and accuracy of the internet of things are comprehensively improved.
An embodiment of the present application further provides an electronic device, including: a memory and a processor:
a memory for storing a computer program;
a processor for executing the computer program stored in the memory to make the electronic device execute the method disclosed in embodiment 1 of the present application.
Embodiments of the present application also provide a computer-readable storage medium, which includes a program or instructions, and when the program or instructions are run on a computer, the method disclosed in embodiment 1 of the present application is executed.
The end-to-end problem diagnosis method and system disclosed by the embodiment of the application have the following two technical advantages:
the diagnosis efficiency is high: this application adopts convenient one-touch formula investigation interface, changes this several days's that consume time manual process into the automatic flow in a minute, has not only practiced thrift time cost and human cost, has also reduced the technological capability requirement to analyst.
(II) the diagnosis accuracy is high: the method and the system cover the data source of the whole process of the Internet of things service, can diagnose the end-to-end fault point, do not need manual intervention in the whole diagnosis process, avoid errors caused by manual investigation, and enable the analysis result to be more accurate and reliable.
The present invention is not intended to be limited to the particular embodiments shown and described, but is to be accorded the widest scope consistent with the principles and novel features herein disclosed.
Claims (10)
1. A method of end-to-end problem diagnosis, the method comprising the steps of:
the system acquires data information in a network data source;
the system respectively diagnoses a plurality of diagnosis points of each diagnosis dimension in the system according to the data information, and obtains a diagnosis result corresponding to each diagnosis point;
the system establishes a data set based on the diagnosis points and the diagnosis results, and constructs a decision tree according to the data set.
2. The end-to-end problem diagnosis method of claim 1, wherein the step of the system obtaining data information in a network data source comprises:
the system is in network connection with a plurality of professional departments with end-to-end service of the Internet of things;
the system receives data information in a plurality of specialized departments via a network.
3. The end-to-end problem diagnosis method according to claim 1, wherein the step of the system respectively diagnosing a plurality of diagnosis points existing in each diagnosis dimension in the system according to the data information and obtaining a diagnosis result corresponding to each diagnosis point comprises:
setting a plurality of diagnostic dimensions in the system, each diagnostic dimension having a plurality of diagnostic points;
setting a plurality of diagnosis bases aiming at each diagnosis point according to the data information;
and diagnosing each diagnosis point based on the diagnosis basis, and obtaining a corresponding diagnosis result.
4. The end-to-end problem diagnosis method of claim 3, wherein said plurality of diagnostic dimensions comprises: the method comprises the steps of (1) terminal dimension, user dimension, network dimension and Internet of things private network dimension; wherein the content of the first and second substances,
the diagnosing of the terminal dimension comprises: the method comprises the steps that whether a fault exists in a terminal is comprehensively judged through an error code and a service response code accessed by a monitoring terminal and a network index of the terminal type in the same comparison;
the diagnosing of the user dimension includes: the method comprises the steps of comprehensively judging whether the configuration of a user per se has problems by acquiring the authentication configuration condition of a terminal and the APN configuration condition of the terminal;
the diagnosing of the network dimension includes: the method is used for comprehensively judging whether the network of each link is abnormal or not by monitoring the network coverage condition of a wireless network, the equipment fault condition of a wireless/transmission/core network and the network element quality difference condition and combining network error code diagnosis;
the diagnosis of the private network dimension of the internet of things comprises the following steps: the method is used for judging whether the private network of the Internet of things has faults or not by monitoring the error code of the platform of the Internet of things and the server time delay index and combining the signing error code and the server response code.
5. The end-to-end problem diagnosis method according to claim 3, wherein the step of the system building a data set based on the diagnosis points and the diagnosis results, and building a decision tree based on the data set, comprises:
dividing a plurality of fault types according to complaint scenes of users of the Internet of things, and corresponding each fault type with a diagnosis point;
respectively solving the diagnosis result of each diagnosis point according to a plurality of fault types, and forming a data set according to the diagnosis result;
constructing a decision tree from the data set;
and obtaining a processing suggestion corresponding to the diagnosis result of each diagnosis dimension according to the decision tree.
6. The end-to-end problem diagnosis method according to claim 5, characterized in that the decision tree establishment procedure comprises the following procedures:
calculating an empirical entropy of the data set;
calculating the information gain of each characteristic value to the data set;
circularly calculating the information entropy of the leaf nodes and the information gain of each characteristic on the subset of the data set;
and establishing the decision tree based on the calculation result.
7. The end-to-end problem diagnosis method according to claim 1, wherein the data information includes interface data, intra-provincial network index data, internet of things private network service data and third party support system data, the interface data is used for providing interface information of an internet of things platform, the intra-provincial network index data is used for providing information of a network management system, the internet of things private network service data is used for providing information of the internet of things platform at a user side, and the third party support system data is used for providing information of a system supporting the operation of the internet of things platform.
8. An end-to-end problem diagnosis system, the system comprising:
the acquisition module is used for acquiring data information in a network data source;
the diagnosis module is used for respectively diagnosing a plurality of diagnosis points in each diagnosis dimension according to the data information and obtaining a diagnosis result corresponding to each diagnosis point;
and the construction module is used for forming a data set based on the diagnosis result, constructing a decision tree according to the data set, and obtaining a processing suggestion corresponding to the diagnosis result of each diagnosis dimension through the decision tree.
9. An electronic device, comprising: a memory and a processor:
the memory for storing a computer program;
the processor configured to execute a computer program stored in the memory to cause the electronic device to perform the method of any of claims 1 to 7.
10. A computer-readable storage medium comprising a program or instructions for performing the method of any one of claims 1 to 7 when the program or instructions are run on a computer.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010790127.3A CN114095336A (en) | 2020-08-07 | 2020-08-07 | End-to-end problem diagnosis method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010790127.3A CN114095336A (en) | 2020-08-07 | 2020-08-07 | End-to-end problem diagnosis method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114095336A true CN114095336A (en) | 2022-02-25 |
Family
ID=80295253
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010790127.3A Pending CN114095336A (en) | 2020-08-07 | 2020-08-07 | End-to-end problem diagnosis method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114095336A (en) |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1786141A1 (en) * | 2005-11-11 | 2007-05-16 | Accenture Global Services GmbH | End-to-end test and diagnostic manager as well as corresponding system and method |
| CN103873274A (en) * | 2012-12-12 | 2014-06-18 | 中国电信股份有限公司 | End-to-end network element fault diagnosis method and device |
| CN105490862A (en) * | 2016-01-08 | 2016-04-13 | 成都网丁科技有限公司 | Efficient fault diagnosis engine |
| CN106291445A (en) * | 2016-10-20 | 2017-01-04 | 国网上海市电力公司 | A kind of Intelligence Diagnosis method that power collection systems is abnormal |
| CN108989136A (en) * | 2017-05-31 | 2018-12-11 | 中国移动通信集团公司 | Business end to end performance monitoring method and device |
| CN109218114A (en) * | 2018-11-12 | 2019-01-15 | 西安微电子技术研究所 | A kind of server failure automatic checkout system and detection method based on decision tree |
| CN109996284A (en) * | 2017-12-31 | 2019-07-09 | 中国移动通信集团贵州有限公司 | Mobile communication Trouble call worksheet method, apparatus, equipment and medium |
| CN110188834A (en) * | 2019-06-04 | 2019-08-30 | 广东电网有限责任公司 | A kind of method for diagnosing faults of power telecom network, device and equipment |
| CN110445647A (en) * | 2019-08-05 | 2019-11-12 | 苏州凌瑞智能技术有限公司 | A kind of diagnosis of internet of things data and error correction method |
| CN110569867A (en) * | 2019-07-15 | 2019-12-13 | 山东电工电气集团有限公司 | Decision tree algorithm-based power transmission line fault reason distinguishing method, medium and equipment |
| CN110995484A (en) * | 2019-11-29 | 2020-04-10 | 中盈优创资讯科技有限公司 | Automatic diagnosis method and device for service recovery of Internet of things |
| CN111314113A (en) * | 2020-01-19 | 2020-06-19 | 赣江新区智慧物联研究院有限公司 | Internet of things node fault detection method and device, storage medium and computer equipment |
-
2020
- 2020-08-07 CN CN202010790127.3A patent/CN114095336A/en active Pending
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1786141A1 (en) * | 2005-11-11 | 2007-05-16 | Accenture Global Services GmbH | End-to-end test and diagnostic manager as well as corresponding system and method |
| CN103873274A (en) * | 2012-12-12 | 2014-06-18 | 中国电信股份有限公司 | End-to-end network element fault diagnosis method and device |
| CN105490862A (en) * | 2016-01-08 | 2016-04-13 | 成都网丁科技有限公司 | Efficient fault diagnosis engine |
| CN106291445A (en) * | 2016-10-20 | 2017-01-04 | 国网上海市电力公司 | A kind of Intelligence Diagnosis method that power collection systems is abnormal |
| CN108989136A (en) * | 2017-05-31 | 2018-12-11 | 中国移动通信集团公司 | Business end to end performance monitoring method and device |
| CN109996284A (en) * | 2017-12-31 | 2019-07-09 | 中国移动通信集团贵州有限公司 | Mobile communication Trouble call worksheet method, apparatus, equipment and medium |
| CN109218114A (en) * | 2018-11-12 | 2019-01-15 | 西安微电子技术研究所 | A kind of server failure automatic checkout system and detection method based on decision tree |
| CN110188834A (en) * | 2019-06-04 | 2019-08-30 | 广东电网有限责任公司 | A kind of method for diagnosing faults of power telecom network, device and equipment |
| CN110569867A (en) * | 2019-07-15 | 2019-12-13 | 山东电工电气集团有限公司 | Decision tree algorithm-based power transmission line fault reason distinguishing method, medium and equipment |
| CN110445647A (en) * | 2019-08-05 | 2019-11-12 | 苏州凌瑞智能技术有限公司 | A kind of diagnosis of internet of things data and error correction method |
| CN110995484A (en) * | 2019-11-29 | 2020-04-10 | 中盈优创资讯科技有限公司 | Automatic diagnosis method and device for service recovery of Internet of things |
| CN111314113A (en) * | 2020-01-19 | 2020-06-19 | 赣江新区智慧物联研究院有限公司 | Internet of things node fault detection method and device, storage medium and computer equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108020752B (en) | Distribution line loss diagnosis method and system based on multi-source through correlation | |
| EP1374486A1 (en) | Method for configuring a network by defining clusters | |
| CN112565095B (en) | Automatic discovery and analysis method and device for internet special line | |
| CN111652661B (en) | Mobile phone client user loss early warning processing method | |
| CN111460315B (en) | Community portrait construction method, device, equipment and storage medium | |
| CN107944487B (en) | Crop breeding variety recommendation method based on mixed collaborative filtering algorithm | |
| CN108733698A (en) | A kind of processing method and background service system of log information | |
| CN110895506A (en) | Construction method and construction system of test data | |
| CN114996525A (en) | Big data analysis method and system | |
| CN113867966A (en) | Cloud resource scheduling method in hybrid cloud mode | |
| CN116452154B (en) | Project management system suitable for communication operators | |
| CN112241820B (en) | Risk identification method and device for key nodes in fund flow and computing equipment | |
| CN111401478B (en) | Data anomaly identification method and device | |
| CN114095336A (en) | End-to-end problem diagnosis method and system | |
| CN116522111A (en) | Automatic diagnosis method for remote power failure | |
| CN113377683B (en) | Software test case generation method, system, device, terminal, medium and application | |
| CN110752970B (en) | cuss platform monitoring system | |
| CN114330720A (en) | Knowledge graph construction method and device for cloud computing and storage medium | |
| CN114331665A (en) | Training method and device for credit judgment model of predetermined applicant and electronic equipment | |
| CN113936157A (en) | Abnormal information processing method and device, storage medium and electronic device | |
| CN105590224A (en) | Method for determining failure node in transaction process | |
| CN114793200B (en) | Important internet of things node identification method based on electric power internet of things network structure | |
| CN109816276B (en) | Method, device and equipment for evaluating reliability index of power distribution network | |
| CN115271434A (en) | Intelligent party building workflow engine design method and system based on cloud computing | |
| CN115640128A (en) | Cloud resource scheduling method in hybrid cloud mode |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |