CN111309572B - Test analysis method and device, computer equipment and storage medium - Google Patents
Test analysis method and device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN111309572B CN111309572B CN202010091087.3A CN202010091087A CN111309572B CN 111309572 B CN111309572 B CN 111309572B CN 202010091087 A CN202010091087 A CN 202010091087A CN 111309572 B CN111309572 B CN 111309572B
- Authority
- CN
- China
- Prior art keywords
- performance
- data
- vector
- test
- module
- 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.)
- Active
Links
- 238000004458 analytical method Methods 0.000 title claims abstract description 90
- 238000012360 testing method Methods 0.000 title claims abstract description 52
- 238000011056 performance test Methods 0.000 claims abstract description 38
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 20
- 238000000034 method Methods 0.000 claims abstract description 18
- 230000002457 bidirectional effect Effects 0.000 claims abstract description 13
- 238000013528 artificial neural network Methods 0.000 claims abstract description 12
- 239000013598 vector Substances 0.000 claims description 80
- 238000004590 computer program Methods 0.000 claims description 13
- 238000005516 engineering process Methods 0.000 claims description 9
- 238000012545 processing Methods 0.000 claims description 9
- 238000012549 training Methods 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 3
- 238000006243 chemical reaction Methods 0.000 claims description 2
- 238000000638 solvent extraction Methods 0.000 claims description 2
- 238000005457 optimization Methods 0.000 abstract description 2
- 238000013522 software testing Methods 0.000 abstract description 2
- 230000008569 process Effects 0.000 description 8
- 210000002569 neuron Anatomy 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 238000012544 monitoring process Methods 0.000 description 5
- 230000004044 response Effects 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 230000001537 neural effect Effects 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000003556 assay Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 230000002441 reversible effect Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/34—Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of user activity, e.g. usability assessment
- G06F11/3447—Performance evaluation by modeling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/34—Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of user activity, e.g. usability assessment
- G06F11/3466—Performance evaluation by tracing or monitoring
- G06F11/3476—Data logging
Landscapes
- Engineering & Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computer Hardware Design (AREA)
- Quality & Reliability (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Debugging And Monitoring (AREA)
Abstract
The invention relates to the field of software testing, and discloses a test analysis method, a test analysis device, computer equipment and a storage medium, wherein the method comprises the following steps: acquiring performance test data; inputting the performance test data into a performance analysis model, wherein the performance analysis model is based on a bidirectional long-time and short-time memory neural network algorithm; acquiring a retrieval keyword output by a performance analysis model; and searching an analysis result of the performance test data in the expert opinion database according to the search keyword. The invention can provide guiding measures suitable for solving technical problems and improve the efficiency of software performance optimization.
Description
Technical Field
The invention relates to the field of software testing, in particular to a test analysis method, a test analysis device, computer equipment and a storage medium.
Background
With the development of the automatic performance testing technology, the process of performance testing tends to be systematized and standardized continuously. The efficiency of the performance test is greatly improved, and the cost of the performance test report is greatly reduced.
However, the existing performance test reports can only objectively reflect the technical problems occurring during the test. The technical problem is solved by depending on the analysis of workers, and the dependence on the processing experience of the workers is large. Existing performance test reports fail to provide an instructive measure suitable for solving the technical problem.
Disclosure of Invention
In view of the above, it is necessary to provide a test analysis method, an apparatus, a computer device and a storage medium for solving the above technical problems.
A test analysis method, comprising:
acquiring performance test data;
inputting the performance test data into a performance analysis model, wherein the performance analysis model is based on a bidirectional long-time and short-time memory neural network algorithm;
acquiring a retrieval keyword output by the performance analysis model;
and searching the analysis result of the performance test data in an expert opinion database according to the search keyword.
A test assay device, comprising:
the test data acquisition module is used for acquiring performance test data;
the model processing module is used for inputting the performance test data into a performance analysis model, and the performance analysis model is based on a bidirectional long-time memory neural network algorithm;
the key word obtaining module is used for obtaining the retrieval key words output by the performance analysis model;
and the searching and analyzing result module is used for searching the analyzing result of the performance testing data in an expert opinion database according to the search keyword.
A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, the processor implementing the test analysis method when executing the computer program.
A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the above-mentioned test analysis method.
According to the test analysis method, the test analysis device, the computer equipment and the storage medium, the performance test data is processed through the performance analysis model, the search keyword used for positioning the technical problem existing in the performance test data is obtained, and then the matched expert opinions are searched in the expert opinion database through the search keyword to obtain the analysis result. The invention can provide guiding measures suitable for solving technical problems and improve the efficiency of software performance optimization.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments of the present invention will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to these drawings without inventive labor.
FIG. 1 is a schematic diagram of an application environment of a test analysis method according to an embodiment of the present invention;
FIG. 2 is a flow chart of a test analysis method according to an embodiment of the present invention;
FIG. 3 is a flow chart of a test analysis method according to an embodiment of the present invention;
FIG. 4 is a data processing diagram of the LSTM model in an embodiment of the present invention;
FIG. 5 is a flow chart of a test analysis method according to an embodiment of the present invention;
FIG. 6 is a flow chart of a test analysis method according to an embodiment of the present invention;
FIG. 7 is a schematic diagram of a test analysis apparatus according to an embodiment of the present invention;
FIG. 8 is a schematic diagram of a computer device according to an embodiment of the invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, not all, embodiments of the present invention. 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 invention.
The test analysis method provided by the embodiment can be applied to the application environment shown in fig. 1, in which the client communicates with the server through the network. The client includes, but is not limited to, various personal computers, notebook computers, smart phones, tablet computers, and portable wearable devices. The server can be implemented by an independent server or a server cluster composed of a plurality of servers.
In an embodiment, as shown in fig. 2, a test analysis method is provided, which is described by taking the application of the method to the server in fig. 1 as an example, and includes the following steps:
s10, acquiring performance test data;
s20, inputting the performance test data into a performance analysis model, wherein the performance analysis model is based on a bidirectional long-time memory neural network algorithm;
s30, acquiring the retrieval key words output by the performance analysis model;
and S40, searching the analysis result of the performance test data in an expert opinion database according to the search keyword.
In this embodiment, the performance test data refers to test data generated in a performance test process, and includes, but is not limited to, a test process running log, an http request header state and response time, a server CPU/memory/IO condition, a data usage CPU condition, a memory space usage condition, and a database connection usage condition. When the performance test is finished, the performance test data can be obtained.
The performance analysis model is an analysis model constructed based on a bidirectional long-and-short-term memory neural network algorithm (LSTM algorithm for short). After the performance data samples are trained using the LSTM algorithm, a performance analysis model may be obtained. The performance data sample includes collected performance issue data and opinion keywords associated therewith.
The performance test data is processed through the performance analysis model, and the retrieval keywords of the performance test data can be obtained. The search key may include one or more keywords. In some cases, each keyword also includes a weight value corresponding thereto.
The database of expert opinions may be a pre-established database containing a plurality of expert opinions. In the database of expert opinions, each expert opinion is associated with at least one keyword. After the search keyword is obtained, the expert opinions matching the keyword can be searched in the expert opinion database, and then the matched expert opinions are further screened through a preset screening method to form a finally obtained analysis result. The expert opinions corresponding to each keyword may be one or more. If the expert opinions corresponding to the keywords are multiple, the matched expert opinions have differentiated priority.
Optionally, as shown in fig. 3, before step S20, the method further includes:
s21, constructing a performance data vector according to the performance problem data, and setting the performance data vector as a problem vector;
s22, constructing an opinion keyword vector according to the expert opinion, and setting the opinion keyword vector as an answer vector;
and S23, training the question vector and the answer vector through an LSTM standard back propagation algorithm, and generating the performance analysis model.
In this embodiment, a performance data vector may be constructed according to the performance problem data, and the performance data vector may be set as a problem vector. An opinion keyword vector may be constructed according to expert opinions and set as an answer vector. As shown in fig. 4, based on the strong correlation between the question vector and the answer vector, an attention (attention) is added in the LSTM model, so that an attention relationship is established between an output layer in the question vector and each LSTM hidden vector in the answer vector, and a corresponding attention value is solved. For a performance data vector, it may correspond to a plurality of similar opinion keyword vectors. Here, different priorities may be set for these similar opinion keyword vectors.
In the LSTM model, bidirectional long-time memory network neural calculation is firstly carried out on performance data information. The algorithm follows the standard LSTM algorithm. In this calculation, the latter calculation unit feeds back the former one. And then N expansion is carried out on the basis. And then carrying out network neural convolution (if a standard RNN algorithm can be adopted, no special processing is carried out), and selecting expert opinions by combining the attention values of the calculated vectors of the performance data information to the opinion keyword vectors.
In the process of training the performance analysis model, the output matrix of the bidirectional LSTM can be expanded by N numbers on the left and right of each word, so that more details can be obtained, and the utilization of local information is facilitated. Meanwhile, for the processing of vectors (including performance data vectors and opinion keyword vectors), LSTM is firstly carried out, then convolution is carried out, and high-loss operation of information is put behind, so that information loss caused by convolution is avoided, and the fidelity degree of the information is improved.
The step of training the question vector and answer vector by the LSTM standard back propagation algorithm comprises:
1. calculating the output value of each neuron in a forward direction;
2. the error term value for each neuron is calculated in reverse. Like the recurrent neural network, the back propagation of the LSTM error term also includes two directions: one is the backward propagation along the time, namely, the error term of each moment is calculated from the current t moment; one is to propagate the error term up one layer;
3. the gradient of each weight is calculated according to the corresponding error term.
Alternatively, as shown in fig. 5, step S21 includes:
s211, dividing the performance problem data into a plurality of data inputs based on the label separators;
and S212, inputting the data into an embedding method through a wordebeading technology to generate the performance data vector.
In constructing the performance data vector, tag separators are used as units. For example, one performance issue datum is:
request response status 200,200,200,200;
request response time is 1s,2s,3s and 5 s;
20 percent of server cpu, 23 percent of server cpu, 24 percent of server cpu and 25 percent of server cpu;
20 percent of database cpu, 20 percent of database cpu;
the application log error is 0,0,0,0, 0.
The inputs are split with tag separators, the first being "request response status:200,200,200,200".
Chinese characters cannot be used as vector values, and are required to be embedded by using wordebeading technology, and then performance data vectors [1.3,0.9,3.1,2.3,0.7,2.3,3.2,6.3,2.4,9.2,3.1,3.2,4.2,6.5,4.2,3.6,2.1,3.3,3.1,5.8,0.5,3.2,6.2,7.4,1.1,2.4,2.7,2.8,8.9,3.6,5.4,7.3,2.1,6.3,8.2,7.1,6.7,3.2,3.9,0.2] are obtained. This is a 40-dimensional vector that requires 40 LSTM neurons to receive. The above 40 neurons are LSTM units. The latter inputs are processed in sequence as inputs at different times until all are completed. In fact, the number of input layer neurons (the number of neurons in LSTMunit) is equal to the size of the word vector.
The opinion keyword vector is in units of keywords. Each key is processed as an independent vector. For each keyword, embedding is carried out through the wordebeading technology, and a corresponding opinion keyword vector can be obtained. The vectors are independent, and n keywords form an n-dimensional vector space.
Optionally, as shown in fig. 6, before step S21, the method further includes:
s201, collecting problem data, setting classification and labels of the problem data, and forming the performance problem data;
s202, associating the performance problem data with expert opinions, and extracting opinion keywords from the performance problem data according to a preset extraction rule;
s203, setting the priority of the expert opinions according to the opinion keywords.
In this embodiment, various issue data, such as performance issue data within an enterprise, may be collected. Problem data are sorted and analyzed through a pattern recognition and big data technology, a processing model is established to mark the problem data according to the classification of performance problems (such as a server, middleware, a database and an application program), and each problem data is provided with a corresponding label, so that the performance problem data are formed. A library of performance issues may be constructed from a number of performance issue data.
Performance issue data may be associated with the expert opinions and monitoring parameters set for each expert opinion. For example, there are a number of situations for the memory overflow problem:
a)java.lang.OutOfMemoryError:......javaheap space.....
b)java.lang.OutOfMemoryError:GC overhead limit exceeded
c)java.lang.OutOfMemoryError:PermGen space
d)java.lang.OutOfMemoryError:Directbuffermemory
e)java.lang.StackOverflowError
f)java.lang.OutOfMemoryError:unable to create new native thread
g)java.lang.OutOfMemoryError:request{}byte for{}out ofswap
in the above 7 different cases, different key monitoring parameters can be set, such as: javaheal space, GC overhead limit exceeded, PermGen space, and the like. The expert opinions corresponding to different monitoring parameters are different. The combination of multiple key monitoring parameters can pinpoint the performance issues that actually occur.
Keywords that may cause performance improvement problems may be matched and associated in combination with performance problem data, expert opinions, key monitoring parameters. For example: establishing a search keyword matching rule to make according to error information keywords in log file words, http request header states and corresponding time, server CPU/memory/IO conditions, data CPU conditions, memory space use conditions, database connection use conditions and the like. And setting the priority of the expert opinions according to the keywords so that the performance problems can be positioned through the keywords and the adaptive expert opinions can be automatically given.
Optionally, the classification of the problem data includes a server, middleware, a database, and an application.
The problem data can be divided into four categories of servers, middleware, databases and applications. A complete performance problem data may include these four classification data. Each classified data has a corresponding keyword. For example, server performance data corresponds to server keywords, application data (e.g., log) corresponds to application keywords, database data (referring to usage data for the database) corresponds to database keywords, and middleware data (which may include some tool test data) corresponds to middleware keywords. In some cases, the issue data may also include other data. The expert opinion library may be established based on an association between keywords (including the above-mentioned four keywords) and expert opinions. In the expert opinion database, a keyword is associated with at least one expert opinion. One expert opinion may be associated with a plurality of keywords.
It should be understood that, the sequence numbers of the steps in the foregoing embodiments do not imply an execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.
In an embodiment, a test analysis apparatus is provided, and the test analysis apparatus corresponds to the test analysis method in the above embodiments one to one. As shown in fig. 7, the test analysis apparatus includes a test data acquiring module 10, a model processing module 20, a keyword acquiring module 30, and a search analysis result module 40. The functional modules are explained in detail as follows:
the module for obtaining test data 10 is used for obtaining performance test data;
the model processing module 20 is configured to input the performance test data into a performance analysis model, where the performance analysis model is based on a bidirectional long-and-short-term memory neural network algorithm;
an obtaining keyword module 30, configured to obtain a search keyword output by the performance analysis model;
and the searching and analyzing result module 40 is used for searching the analyzing result of the performance testing data in the expert opinion database according to the search keyword.
Optionally, the test analysis apparatus further comprises:
the problem vector setting module is used for constructing a performance data vector according to the performance problem data and setting the performance data vector as a problem vector;
the system comprises an answer vector setting module, a search module and a search module, wherein the answer vector setting module is used for constructing an opinion keyword vector according to expert opinions and setting the opinion keyword vector as an answer vector;
and the generation model module is used for training the question vector and the answer vector through an LSTM standard back propagation algorithm to generate the performance analysis model.
Optionally, the problem vector setting module includes:
a partitioning unit to divide the performance issue data into a plurality of data inputs based on tag delimiters;
and the conversion unit is used for inputting the data into the embedding unit through a wordebeading technology to generate the performance data vector.
Optionally, the test analysis apparatus further comprises:
the collecting module is used for collecting problem data, setting the classification and the label of the problem data and forming the performance problem data;
the association module is used for associating the performance problem data with expert opinions and extracting opinion keywords from the performance problem data according to a preset extraction rule;
and the priority setting module is used for setting the priority of the expert opinions according to the opinion keywords.
Optionally, the classification of the problem data includes a server, middleware, a database, and an application.
For the specific definition of the test analysis device, reference may be made to the above definition of the test analysis method, which is not described herein again. The modules in the test analysis device can be wholly or partially implemented by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as shown in fig. 8. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The database of the computer device is used for storing data related to the test analysis method. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a test analysis method.
In one embodiment, a computer device is provided, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor implementing the following steps when executing the computer program:
acquiring performance test data;
inputting the performance test data into a performance analysis model, wherein the performance analysis model is based on a bidirectional long-time and short-time memory neural network algorithm;
acquiring a retrieval keyword output by the performance analysis model;
and searching the analysis result of the performance test data in an expert opinion database according to the search keyword.
In one embodiment, a computer-readable storage medium is provided, having a computer program stored thereon, which when executed by a processor, performs the steps of:
acquiring performance test data;
inputting the performance test data into a performance analysis model, wherein the performance analysis model is based on a bidirectional long-time and short-time memory neural network algorithm;
acquiring a retrieval keyword output by the performance analysis model;
and searching the analysis result of the performance test data in an expert opinion database according to the search keyword.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-mentioned division of the functional units and modules is illustrated, and in practical applications, the above-mentioned function distribution may be performed by different functional units and modules according to needs, that is, the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-mentioned functions.
The above-mentioned embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting 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; such modifications and substitutions do not substantially depart from the spirit and scope of the embodiments of the present invention, and are intended to be included within the scope of the present invention.
Claims (8)
1. A method of test analysis, comprising:
acquiring performance test data of a software test;
inputting the performance test data into a performance analysis model, wherein the performance analysis model is based on a bidirectional long-time and short-time memory neural network algorithm;
acquiring retrieval keywords output by the performance analysis model, wherein the retrieval keywords comprise one or more keywords, and each keyword comprises a weight value corresponding to the keyword;
searching an analysis result of the performance test data in an expert opinion database according to the search keyword;
before the performance test data is input into a performance analysis model, and the performance analysis model is based on a bidirectional long-time memory neural network, the method further includes:
constructing a performance data vector according to the performance problem data, and setting the performance data vector as a problem vector;
constructing an opinion keyword vector according to expert opinions, and setting the opinion keyword vector as an answer vector;
and training the question vector and the answer vector through an LSTM standard back propagation algorithm to generate the performance analysis model.
2. The test analysis method of claim 1, wherein the constructing a performance data vector from the performance issue data and setting the performance data vector as an issue vector comprises:
dividing the performance issue data into a plurality of data inputs based on tag delimiters;
and inputting the data into an embedding technology through a wordebeading technology to generate the performance data vector.
3. The test analysis method of claim 1, wherein before constructing the performance data vector based on the performance issue data and setting the performance data vector as an issue vector, further comprising:
collecting problem data, setting the classification and label of the problem data, and forming the performance problem data;
associating the performance problem data with expert opinions, and extracting opinion keywords from the performance problem data according to a preset extraction rule;
and setting the priority of the expert opinions according to the opinion keywords.
4. The test analysis method of claim 3, wherein the classification of the issue data includes servers, middleware, databases, and applications.
5. A test analysis device, comprising:
the test data acquisition module is used for acquiring performance test data of the software test;
the model processing module is used for inputting the performance test data into a performance analysis model, and the performance analysis model is based on a bidirectional long-time memory neural network algorithm;
the key word obtaining module is used for obtaining a search key word output by the performance analysis model, wherein the search key word comprises one or more key words, and each key word comprises a weight value corresponding to the key word;
the search analysis result module is used for searching the analysis result of the performance test data in an expert opinion database according to the search keyword;
the problem vector setting module is used for constructing a performance data vector according to the performance problem data and setting the performance data vector as a problem vector;
the system comprises an answer vector setting module, a search module and a search module, wherein the answer vector setting module is used for constructing an opinion keyword vector according to expert opinions and setting the opinion keyword vector as an answer vector;
and the generation model module is used for training the question vector and the answer vector through an LSTM standard back propagation algorithm to generate the performance analysis model.
6. The test analysis device of claim 5, wherein the set problem vector module comprises:
a partitioning unit to divide the performance issue data into a plurality of data inputs based on tag delimiters;
and the conversion unit is used for inputting the data into the embedding unit through a wordebeading technology to generate the performance data vector.
7. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor implements the test analysis method according to any one of claims 1 to 4 when executing the computer program.
8. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out a test analysis method according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010091087.3A CN111309572B (en) | 2020-02-13 | 2020-02-13 | Test analysis method and device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010091087.3A CN111309572B (en) | 2020-02-13 | 2020-02-13 | Test analysis method and device, computer equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111309572A CN111309572A (en) | 2020-06-19 |
| CN111309572B true CN111309572B (en) | 2021-05-04 |
Family
ID=71159927
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010091087.3A Active CN111309572B (en) | 2020-02-13 | 2020-02-13 | Test analysis method and device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111309572B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103902731A (en) * | 2014-04-16 | 2014-07-02 | 国家电网公司 | Intelligent information maintenance method based on knowledge base inquiry |
| CN107943911A (en) * | 2017-11-20 | 2018-04-20 | 北京大学深圳研究院 | Data pick-up method, apparatus, computer equipment and readable storage medium storing program for executing |
| CN108197014A (en) * | 2017-12-29 | 2018-06-22 | 东软集团股份有限公司 | Method for diagnosing faults, device and computer equipment |
Family Cites Families (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102521604B (en) * | 2011-11-21 | 2014-11-19 | 上海交通大学 | Device and method for estimating performance degradation of equipment based on inspection system |
| CN105050132B (en) * | 2015-08-10 | 2018-10-19 | 北京邮电大学 | The method of estimation of cell extreme value handling capacity |
| CN105323111B (en) * | 2015-11-17 | 2018-08-10 | 南京南瑞集团公司 | A kind of O＆M automated system and method |
| CN107301118B (en) * | 2017-06-15 | 2019-11-19 | 中国科学院计算技术研究所 | A kind of fault indices automatic marking method and system based on log |
| CN108073497B (en) * | 2018-01-29 | 2021-02-12 | 上海洞识信息科技有限公司 | Multi-index transaction analysis method based on data center data acquisition platform |
| CN108347352B (en) * | 2018-02-05 | 2021-03-16 | 中国电力科学研究院有限公司 | Method for diagnosing performance of information system and equipment in power system |
| US10558554B2 (en) * | 2018-02-28 | 2020-02-11 | Sap Se | Machine learning based software correction |
| US20210233615A1 (en) * | 2018-04-22 | 2021-07-29 | Viome, Inc. | Systems and methods for inferring scores for health metrics |
| CN108874943B (en) * | 2018-06-04 | 2021-10-22 | 上海交通大学 | Dark net resource detection system based on long-term and short-term memory neural network |
| CN109918280B (en) * | 2019-01-31 | 2022-07-12 | 北京无线电测量研究所 | Health management method and device for servo system |
-
2020
- 2020-02-13 CN CN202010091087.3A patent/CN111309572B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103902731A (en) * | 2014-04-16 | 2014-07-02 | 国家电网公司 | Intelligent information maintenance method based on knowledge base inquiry |
| CN107943911A (en) * | 2017-11-20 | 2018-04-20 | 北京大学深圳研究院 | Data pick-up method, apparatus, computer equipment and readable storage medium storing program for executing |
| CN108197014A (en) * | 2017-12-29 | 2018-06-22 | 东软集团股份有限公司 | Method for diagnosing faults, device and computer equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111309572A (en) | 2020-06-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111859960B (en) | Semantic matching method, device, computer equipment and medium based on knowledge distillation | |
| CN111666401B (en) | Document recommendation method, device, computer equipment and medium based on graph structure | |
| CN108427707B (en) | Man-machine question and answer method, device, computer equipment and storage medium | |
| EP3855324A1 (en) | Associative recommendation method and apparatus, computer device, and storage medium | |
| CN109800307B (en) | Product evaluation analysis method and device, computer equipment and storage medium | |
| CN111176996A (en) | Test case generation method and device, computer equipment and storage medium | |
| CN110674319A (en) | Label determination method and device, computer equipment and storage medium | |
| CN110888911A (en) | Sample data processing method and device, computer equipment and storage medium | |
| CN113626241B (en) | Abnormality processing method, device, equipment and storage medium for application program | |
| CN112395500A (en) | Content data recommendation method and device, computer equipment and storage medium | |
| CN111104242A (en) | Method and device for processing abnormal logs of operating system based on deep learning | |
| CN112766319A (en) | Dialogue intention recognition model training method and device, computer equipment and medium | |
| CN112883030A (en) | Data collection method and device, computer equipment and storage medium | |
| CN112685475A (en) | Report query method and device, computer equipment and storage medium | |
| CN111124898B (en) | Question-answering system testing method and device, computer equipment and storage medium | |
| CN109656947B (en) | Data query method and device, computer equipment and storage medium | |
| CN114138977A (en) | Log processing method and device, computer equipment and storage medium | |
| CN112596723B (en) | Database script generation method, device, equipment and medium | |
| CN113419950A (en) | Method and device for generating UI automation script, computer equipment and storage medium | |
| CN111309572B (en) | Test analysis method and device, computer equipment and storage medium | |
| CN111400340A (en) | Natural language processing method and device, computer equipment and storage medium | |
| CN114547257B (en) | Class matching method and device, computer equipment and storage medium | |
| CN115374849A (en) | Enterprise related patent retrieval method, device, equipment and medium | |
| CN112732423B (en) | Process migration method, device, equipment and medium | |
| CN113627514A (en) | Data processing method and device of knowledge graph, electronic equipment and storage medium |
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 | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: Test analysis methods, devices, computer equipment, and storage media Granted publication date: 20210504 Pledgee: CITIC Bank Limited by Share Ltd. Shanghai branch Pledgor: Shanghai Fu Shen Lan Software Co.,Ltd. Registration number: Y2024310000249 |