CN111614508A - Method and system for analyzing switch test result based on artificial intelligence - Google Patents

Method and system for analyzing switch test result based on artificial intelligence Download PDF

Info

Publication number
CN111614508A
CN111614508A CN202010251939.0A CN202010251939A CN111614508A CN 111614508 A CN111614508 A CN 111614508A CN 202010251939 A CN202010251939 A CN 202010251939A CN 111614508 A CN111614508 A CN 111614508A
Authority
CN
China
Prior art keywords
test
data
neural network
convolutional neural
test result
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.)
Granted
Application number
CN202010251939.0A
Other languages
Chinese (zh)
Other versions
CN111614508B (en
Inventor
周厚明
张翔
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Wuhan Maiwei Communications Co ltd
Original Assignee
Wuhan Maiwei Communications Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Wuhan Maiwei Communications Co ltd filed Critical Wuhan Maiwei Communications Co ltd
Priority to CN202010251939.0A priority Critical patent/CN111614508B/en
Publication of CN111614508A publication Critical patent/CN111614508A/en
Application granted granted Critical
Publication of CN111614508B publication Critical patent/CN111614508B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L43/00—Arrangements for monitoring or testing data switching networks
    • H04L43/08—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • 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
    • H04L41/14—Network analysis or design
    • H04L41/142—Network analysis or design using statistical or mathematical methods
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L43/00—Arrangements for monitoring or testing data switching networks
    • H04L43/04—Processing captured monitoring data, e.g. for logfile generation
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L43/00—Arrangements for monitoring or testing data switching networks
    • H04L43/50—Testing arrangements

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Signal Processing (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Mathematical Physics (AREA)
  • General Physics & Mathematics (AREA)
  • Computational Linguistics (AREA)
  • Artificial Intelligence (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Biophysics (AREA)
  • Biomedical Technology (AREA)
  • Software Systems (AREA)
  • Evolutionary Computation (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Algebra (AREA)
  • Mathematical Analysis (AREA)
  • Mathematical Optimization (AREA)
  • Probability & Statistics with Applications (AREA)
  • Pure & Applied Mathematics (AREA)
  • Environmental & Geological Engineering (AREA)
  • Test And Diagnosis Of Digital Computers (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention relates to a method and a system for analyzing a switch test result, wherein the method comprises the following steps: classifying the test data of the test case according to the data type of the test result of the test case and then preprocessing the test data; inputting the preprocessed data into a convolutional neural network for artificial intelligence deep learning, and outputting the relation between the problems in the test result and the codes by the convolutional neural network; test data for testing the switch is analyzed using a convolutional neural network. The relationship between the test result and the modified code when the switch is subjected to black box test by using deep learning analysis greatly shortens the problem positioning time and precision.

Description

Method and system for analyzing switch test result based on artificial intelligence
Technical Field
The invention relates to the field of data switching networks, in particular to a method and a system for analyzing a test result of a switch.
Background
With the functions of the switches becoming more and more complex, the code base maintenance amount becomes larger and larger, and the requirement for testing becomes higher and higher.
The tests of the switch are currently divided into a white box test and a black box test, and the black box test is only limited to the final test result and is difficult to locate to a specific problem code position or a logic conflict point. Often, testers and developers need a lot of time to locate the error position in the code, and because of the particularity of the black box test, the location accuracy is very related to the experience of the testers and developers. In the product development process, a large amount of time is spent for positioning, and great resource waste is caused for test and research.
Disclosure of Invention
The invention provides a method and a system for analyzing a switch test result, aiming at the technical problems in the prior art, and solving the problem that the switch black box test result is difficult to locate in the prior art.
The technical scheme for solving the technical problems is as follows: an artificial intelligence based switch test result analysis method, the method comprising:
step 1, classifying test data of a test case according to the data type of a test result of the test case and then preprocessing the test data;
step 2, inputting the preprocessed data into a convolutional neural network for artificial intelligence deep learning, wherein the convolutional neural network outputs the relation between the problem in the test result and the code;
and 3, analyzing test data for testing the switch by using the convolutional neural network.
An artificial intelligence based switch test result analysis system, the system comprising: the device comprises a data preprocessing module, a convolutional neural network establishing module and an analysis processing module;
the data preprocessing module is used for classifying the test data of the test case according to the data type of the test result of the test case and then preprocessing the test data;
the convolutional neural network establishing module is used for inputting the preprocessed data into a convolutional neural network for artificial intelligence deep learning, and the convolutional neural network outputs the relation between the problem in the test result and the code;
and the analysis processing module is used for analyzing the test data for testing the switch by utilizing the convolutional neural network.
The invention has the beneficial effects that: according to the method and the system for analyzing the switch test result based on artificial intelligence, provided by the invention, the relationship between the test result and the modified code when the switch is subjected to black box test by using deep learning analysis is utilized, so that the problem positioning time and precision are greatly shortened.
On the basis of the technical scheme, the invention can be further improved as follows.
Further, the data type of the test result in the step 1 includes numerical value class data and judgment class data.
Further, when the data type of the test result is judged to be numerical data, the process of preprocessing the test data comprises normalization and standardization.
Further, when the data type of the test result is judged to be judgment type data, the process of preprocessing the test data comprises Boolean value conversion.
Further, the process of preprocessing the test report further includes: and carrying out thermal independent coding conversion on the test report subjected to normalization and standardization processing or Boolean value conversion to form a thermal independent matrix.
Further, the convolutional neural network in the step 2 links the question in the test result with the code in a softmax mode.
Further, the step 2 further comprises: and manually checking the accuracy of the prediction result, and improving the accuracy of the prediction result by adjusting the parameters of the convolutional neural network and/or newly adding a modification test case.
The beneficial effect of adopting the further scheme is that: the artificial intelligence deep learning system analyzes the hot independent matrix by using the convolutional neural network, analyzes the relation between the problem and the code, predicts the relevance between the problem and the modified code in a softmax mode, and proves that the data prediction of the convolutional neural network after hot independent processing has obvious prediction effect through actual tests. By accumulating the results of multiple tests, the convolutional neural network is subjected to parameter adjustment and/or newly added and modified test cases, so that the prediction precision can be greatly improved, and the time for positioning problems can be greatly reduced.
Drawings
FIG. 1 is a flow chart of an analysis method for switch test results based on artificial intelligence provided by the present invention;
FIG. 2 is a flowchart of an embodiment of a method for analyzing test results of an artificial intelligence-based switch according to the present invention;
FIG. 3 is a block diagram of an embodiment of an artificial intelligence-based switch test result analysis system according to the present invention;
FIG. 4 is a schematic diagram of an embodiment of performing artificial intelligence deep learning in an artificial intelligence-based method for analyzing switch test results according to the present invention;
FIG. 5 is a block diagram of an artificial intelligence-based system for analyzing test results of a switch according to the present invention;
fig. 6 is a schematic physical structure diagram of an electronic device according to an embodiment of the present invention.
In the drawings, the components represented by the respective reference numerals are listed below:
101. the device comprises a data preprocessing module 102, a convolutional neural network establishing module 103, an analysis processing module 201, a processor 202, a communication interface 203, a memory 204 and a communication bus.
Detailed Description
The principles and features of this invention are described below in conjunction with the following drawings, which are set forth by way of illustration only and are not intended to limit the scope of the invention.
Fig. 1 is a flowchart of an artificial intelligence-based switch test result analysis method provided by the present invention, and as can be seen from fig. 1, the method includes:
step 1, classifying the test data of the test case according to the data type of the test result of the test case and then preprocessing the test data.
And 2, inputting the preprocessed data into a convolutional neural network for artificial intelligence deep learning, wherein the convolutional neural network outputs the relation between the problems in the test result and the codes.
And 3, analyzing test data for testing the switch by using the convolutional neural network.
According to the method for analyzing the switch test result based on artificial intelligence, provided by the invention, the relationship between the test result and the modified code when the switch is subjected to black box test by using deep learning analysis is utilized, so that the problem positioning time and precision are greatly shortened.
Example 1
Embodiment 1 provided by the present invention is an embodiment of an artificial intelligence based switch test result analysis method provided by the present invention, and as shown in fig. 2, is a flowchart of an embodiment of an artificial intelligence based switch test result analysis method provided by the present invention, and as can be seen from fig. 2, in the embodiment of the switch test result analysis method provided by the present invention, a test case and a test result are combined with a software version management system and a code submission system, and the method includes:
and submitting the codes to a code submitting system, recording the complete codes of each version, compiling the versions of the codes, and passing the compiling.
The version management system records the modified content and the added functions of the version.
For detailed test steps of functional testing, a test case is established, which contains expected data or test results for each step.
And forming a test report according to the test data after the test case is executed. The test report comprises but is not limited to excel table, txt, JSON and other forms for storage, and the data can be conveniently standardized.
Extracting, classifying and preprocessing test data, and specifically comprises the following steps:
step 1, classifying the test data of the test case according to the data type of the test result of the test case and then preprocessing the test data.
As shown in fig. 3, which is a flowchart of classifying and preprocessing test data in the method for analyzing the switch test result based on artificial intelligence provided by the present invention, it can be seen from fig. 3 that the data type of the test result in step 1 includes numerical data and judgment data.
After the test data is classified, each class is labeled.
Specifically, when the data type of the test result is judged to be numerical data, the process of preprocessing the test data includes normalization and standardization. The normalization and normalization processes may be performed by a standard deviation method, a feature scaling method, or the like.
And when the data type of the test result is judged to be judgment type data, the process of preprocessing the test data comprises Boolean value conversion.
Preferably, the process of preprocessing the test report further includes: and carrying out thermal independent coding conversion on the test report subjected to normalization and standardization processing or Boolean value conversion to form a thermal independent matrix.
One-Hot coding, or One-Hot coding, also known as One-bit-efficient coding, uses an N-bit state register to encode N states, each state having its own independent register bit and only One of which is active at any time.
The process of one-hot encoding is: if only one feature is a discrete value: { sex: { large, mail, other } }.
The feature has 3 different classification values, at this time, 3 bits are needed to indicate what value the feature is, and the position corresponding to the bit being 1 corresponds to the value of the original feature (in general, the values of the original feature may be sorted for later use), and then the obtained unique hot codes are {100} male, {010} female, {001} other.
According to the method and the system for analyzing the switch test result based on artificial intelligence, the artificial intelligence deep learning system analyzes the heat independent matrix by using the convolutional neural network, analyzes the relation between the problem and the code, predicts the relevance between the problem and the modified code in a softmax mode, and proves that the data prediction of the convolutional neural network after heat independent processing has a very obvious prediction effect through actual tests. By accumulating the results of multiple tests, the convolutional neural network is subjected to parameter adjustment and/or newly added and modified test cases, so that the prediction precision can be greatly improved, and the time for positioning problems can be greatly reduced.
And 2, inputting the preprocessed data into a convolutional neural network for artificial intelligence deep learning, and outputting the relation between the problems in the test result and the codes by the convolutional neural network.
Fig. 4 is a schematic diagram of an embodiment of inputting preprocessed data into a convolutional neural network for artificial intelligence deep learning in the method for analyzing the switch test result based on artificial intelligence provided by the present invention, and as can be seen from fig. 4, the convolutional neural network tests the association between the problems in the result and the codes in a softmax manner, specifically, the associated probability between each problem and the corresponding code.
Preferably, the step 2 further comprises: and manually checking the accuracy of the prediction result, and improving the accuracy of the prediction result by adjusting the parameters of the convolutional neural network and/or newly adding a modification test case.
And 3, analyzing test data for testing the switch by using the convolutional neural network.
Example 2
Embodiment 2 provided in the present invention is an embodiment of an artificial intelligence based switch test result analysis system provided in the present invention, and as shown in fig. 5, is a block diagram of an embodiment of an artificial intelligence based switch test result analysis system provided in the present invention, as can be seen from fig. 5, the system includes: a data preprocessing module 101, a convolutional neural network establishing module 102 and an analysis processing module 103.
The data preprocessing module 101 classifies the test data of the test case according to the data type of the test result of the test case and then preprocesses the test data.
The convolutional neural network establishing module 102 is configured to input the preprocessed data into a convolutional neural network for artificial intelligence deep learning, and the convolutional neural network outputs a relationship between a problem in a test result and a code.
And the analysis processing module 103 analyzes the test data for testing the switch by using the convolutional neural network.
Fig. 6 is a schematic entity structure diagram of an electronic device according to an embodiment of the present invention, and as shown in fig. 6, the electronic device may include: the system comprises a processor 201, a communication interface 202, a memory 203 and a communication bus 204, wherein the processor 201, the communication interface 202 and the memory 203 are communicated with each other through the communication bus 204. The processor 201 may invoke a computer program stored on the memory 203 and executable on the processor 201 to perform the artificial intelligence based switch test result analysis method provided by the above embodiments, for example, including: step 1, classifying the test data of the test case according to the data type of the test result of the test case and then preprocessing the test data. And 2, inputting the preprocessed data into a convolutional neural network for artificial intelligence deep learning, and outputting the relation between the problems in the test result and the codes by the convolutional neural network. And 3, analyzing test data for testing the switch by using the convolutional neural network.
An embodiment of the present invention further provides a non-transitory computer-readable storage medium, on which a computer program is stored, where the computer program is implemented to perform the method for analyzing the switch test result based on artificial intelligence provided in the foregoing embodiments when executed by a processor, and the method includes: step 1, classifying the test data of the test case according to the data type of the test result of the test case and then preprocessing the test data. And 2, inputting the preprocessed data into a convolutional neural network for artificial intelligence deep learning, and outputting the relation between the problems in the test result and the codes by the convolutional neural network. And 3, analyzing test data for testing the switch by using the convolutional neural network.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.

Claims (10)

1. An artificial intelligence based switch test result analysis method is characterized by comprising the following steps:
step 1, classifying test data of a test case according to the data type of a test result of the test case and then preprocessing the test data;
step 2, inputting the preprocessed data into a convolutional neural network for artificial intelligence deep learning, wherein the convolutional neural network outputs the relation between the problem in the test result and the code;
and 3, analyzing test data for testing the switch by using the convolutional neural network.
2. The method of claim 1, wherein the data types of the test results in step 1 comprise numerical class data and judgment class data.
3. The method of claim 2, wherein when the data type of the test result is judged to be numerical data, the preprocessing of the test data comprises normalization and normalization.
4. The method of claim 2, wherein when the data type of the test result is judged to be judgment-type data, the preprocessing of the test data comprises performing boolean value conversion.
5. The method of claim 3 or 4, wherein preprocessing the test report further comprises: and carrying out thermal independent coding conversion on the test report subjected to normalization and standardization processing or Boolean value conversion to form a thermal independent matrix.
6. The method of claim 1, wherein the convolutional neural network in step 2 associates the question in the test result with the code in a softmax manner.
7. The method of claim 6, wherein the step 2 further comprises: and manually checking the accuracy of the prediction result, and improving the accuracy of the prediction result by adjusting the parameters of the convolutional neural network and/or newly adding a modification test case.
8. An artificial intelligence based switch test result analysis system, the system comprising: the device comprises a data preprocessing module, a convolutional neural network establishing module and an analysis processing module;
the data preprocessing module is used for classifying the test data of the test case according to the data type of the test result of the test case and then preprocessing the test data;
the convolutional neural network establishing module is used for inputting the preprocessed data into a convolutional neural network for artificial intelligence deep learning, and the convolutional neural network outputs the relation between the problem in the test result and the code;
and the analysis processing module is used for analyzing the test data for testing the switch by utilizing the convolutional neural network.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor when executing the program performs the steps of the artificial intelligence based switch test result analysis method according to any one of claims 1 to 7.
10. A non-transitory computer readable storage medium having stored thereon a computer program, wherein the computer program when executed by a processor implements the steps of the artificial intelligence based switch test result analysis method according to any one of claims 1 to 7.
CN202010251939.0A 2020-04-01 2020-04-01 Switch test result analysis method and system based on artificial intelligence Active CN111614508B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010251939.0A CN111614508B (en) 2020-04-01 2020-04-01 Switch test result analysis method and system based on artificial intelligence

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010251939.0A CN111614508B (en) 2020-04-01 2020-04-01 Switch test result analysis method and system based on artificial intelligence

Publications (2)

Publication Number Publication Date
CN111614508A true CN111614508A (en) 2020-09-01
CN111614508B CN111614508B (en) 2022-05-13

Family

ID=72205472

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010251939.0A Active CN111614508B (en) 2020-04-01 2020-04-01 Switch test result analysis method and system based on artificial intelligence

Country Status (1)

Country Link
CN (1) CN111614508B (en)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105893256A (en) * 2016-03-30 2016-08-24 西北工业大学 Software failure positioning method based on machine learning algorithm
CN109634833A (en) * 2017-10-09 2019-04-16 北京京东尚科信息技术有限公司 A kind of Software Defects Predict Methods and device
CN109783496A (en) * 2019-01-14 2019-05-21 东北大学 Data collection and processing automation tools and application method based on Excel&VBA
US20190213115A1 (en) * 2018-01-08 2019-07-11 Accenture Global Solutions Limited Utilizing artificial intelligence to test cloud applications
US20190391904A1 (en) * 2018-06-20 2019-12-26 Hcl Technologies Limited Automated bug fixing

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105893256A (en) * 2016-03-30 2016-08-24 西北工业大学 Software failure positioning method based on machine learning algorithm
CN109634833A (en) * 2017-10-09 2019-04-16 北京京东尚科信息技术有限公司 A kind of Software Defects Predict Methods and device
US20190213115A1 (en) * 2018-01-08 2019-07-11 Accenture Global Solutions Limited Utilizing artificial intelligence to test cloud applications
US20190391904A1 (en) * 2018-06-20 2019-12-26 Hcl Technologies Limited Automated bug fixing
CN109783496A (en) * 2019-01-14 2019-05-21 东北大学 Data collection and processing automation tools and application method based on Excel&VBA

Also Published As

Publication number Publication date
CN111614508B (en) 2022-05-13

Similar Documents

Publication Publication Date Title
CN107391369B (en) Cross-project defect prediction method based on data screening and data oversampling
CN109635292B (en) Work order quality inspection method and device based on machine learning algorithm
CN109783785B (en) Method and device for generating experiment detection report and computer equipment
US20100333073A1 (en) Systems and methods for automated generation of software tests based on modeling the software test domain
CN109740347B (en) Method for identifying and cracking fragile hash function of intelligent device firmware
CN113778894B (en) Method, device, equipment and storage medium for constructing test cases
CN113221960A (en) Construction method and collection method of high-quality vulnerability data collection model
CN116151845A (en) Product full life cycle management system and method based on industrial Internet of things technology
CN115617614A (en) Log sequence anomaly detection method based on time interval perception self-attention mechanism
CN110647461B (en) Multi-information fusion regression test case sequencing method and system
CN116795886A (en) Data analysis engine and method for sales data
CN111614508B (en) Switch test result analysis method and system based on artificial intelligence
CN111290953B (en) Method and device for analyzing test logs
CN117407313A (en) Automatic quality testing method and system based on machine learning analysis
CN111859862A (en) Text data labeling method and device, storage medium and electronic device
CN116304721A (en) Data standard making method and system for big data management based on data category
Lakshmanan et al. Detecting changes in a semi-structured business process through spectral graph analysis
CN113312485B (en) Log automatic classification method and device and computer readable storage medium
KR20200065820A (en) Energy and security efficiency analysis system based on digital twin modeling for smart factory introduction
CN116032726A (en) Fault root cause positioning model training method, device, equipment and readable storage medium
CN111522750B (en) Method and system for processing function test problem
CN115618355A (en) Injection attack result judgment method, device, equipment and storage medium
CN115328753A (en) Fault prediction method and device, electronic equipment and storage medium
CN115099359A (en) Address recognition method, device, equipment and storage medium based on artificial intelligence
CN114218462A (en) Data classification method, device, equipment and storage medium based on LSTM

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
GR01 Patent grant
GR01 Patent grant