CN113778894A - Test case construction method, device, equipment and storage medium - Google Patents
Test case construction method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN113778894A CN113778894A CN202111095909.6A CN202111095909A CN113778894A CN 113778894 A CN113778894 A CN 113778894A CN 202111095909 A CN202111095909 A CN 202111095909A CN 113778894 A CN113778894 A CN 113778894A
- Authority
- CN
- China
- Prior art keywords
- test
- test case
- target
- training data
- keyword
- 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
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/36—Preventing errors by testing or debugging software
- G06F11/3668—Software testing
- G06F11/3672—Test management
- G06F11/3676—Test management for coverage analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/36—Preventing errors by testing or debugging software
- G06F11/3668—Software testing
- G06F11/3672—Test management
- G06F11/3684—Test management for test design, e.g. generating new test cases
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computer Hardware Design (AREA)
- Quality & Reliability (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention relates to the field of artificial intelligence and discloses a method, a device, equipment and a storage medium for constructing a test case. The method comprises the following steps: according to the type of a product to be tested, obtaining a plurality of test standard labels from a test standard database, and classifying the test standard labels to obtain a plurality of industry keywords; generating at least one business keyword according to the original data of the product to be tested; acquiring a plurality of initial test cases from a test standard database according to the industry keywords and the service keywords, and performing test standard detection on each initial test case to obtain a plurality of candidate test cases; carrying out normalization processing on the original test case and the candidate test case to construct a target training data set; and calling a preset language model, and predicting a target test case based on the test standard label. The method and the device are combined with the standard test case of the machine learning prediction product, so that the coverage rate of a test scene is improved, and the test accuracy is further improved.
Description
Technical Field
The invention relates to the field of artificial intelligence, in particular to a method, a device, equipment and a storage medium for constructing a test case.
Background
The construction of the test case is an important technical means for realizing automatic testing, and a test engineer usually designs the test case by using methods such as an equivalence class division method, a boundary value analysis method and the like according to a service scene of a product, and tests the product based on the test case, so that test coverage of various possible abnormal service scenes is realized, and the quality of a software product is improved.
In the existing method for constructing the test cases, the test cases are manually designed according to the service scenes of the products, and partial abnormal scenes may not be covered in the test cases, so that the accuracy of the test results is low.
Disclosure of Invention
The invention mainly aims to solve the problem of low accuracy of the existing construction method of the test case.
The invention provides a method for constructing a test case in a first aspect, which comprises the following steps:
obtaining a plurality of test standard labels from a preset test standard library according to the type of a product to be tested, and classifying the test standard labels according to a preset industry category to obtain a plurality of industry keywords, wherein each type of test standard label corresponds to one industry keyword;
generating a service keyword set according to the original data of the product to be tested, wherein the original data of the product to be tested comprises demand data and a plurality of original test cases, and the service keyword set comprises at least one service keyword;
acquiring a plurality of initial test cases from the test standard library according to the industry keywords and the service keywords in the service keyword set, and performing test standard detection on each initial test case to obtain a plurality of candidate test cases, wherein the candidate test cases are initial test cases which are qualified in detection;
constructing an initial training data set based on the original test case and the candidate test cases, and performing normalization processing on each test case in the initial training data set to obtain a target training data set;
and calling a preset language model, predicting a target test case contained in the target training data set based on the test standard label, and obtaining a plurality of target test cases, wherein the matching probability between the target test case and the test standard label is greater than a preset threshold value.
Optionally, in a first implementation manner of the first aspect of the present invention, the generating a service keyword according to the original data of the product to be tested includes:
performing word segmentation processing on the original data of the product to be tested based on a preset word segmentation tool to obtain target data containing a plurality of words;
performing word segmentation statistics on the target data containing a plurality of words to obtain word segmentation frequency distribution, wherein the word segmentation frequency distribution comprises an initial frequency value corresponding to each word segmentation, and the initial frequency value is used for the occurrence frequency of each word segmentation in the target data;
and determining a service keyword according to the word segmentation frequency distribution, wherein the service keyword is a word segmentation corresponding to a target frequency value, and the target frequency value is greater than a preset threshold value.
Optionally, in a second implementation manner of the first aspect of the present invention, after generating a set of service keywords according to the original data of the product to be tested, the method further includes:
receiving an approval instruction input by a user, identifying the service keywords in the service keyword set according to the approval instruction, and determining the qualified target service keywords according to the result of identification;
and processing the target business keywords based on a preset keyword expansion tool to obtain expanded business keywords, and adding the expanded business keywords to the business keyword set.
Optionally, in a third implementation manner of the first aspect of the present invention, the performing test standard detection on each initial test case to obtain a plurality of candidate test cases includes:
classifying the initial test cases according to the industry keywords to obtain a plurality of test rules, wherein each test rule comprises a plurality of initial test cases, and each test rule corresponds to at least one industry keyword;
and verifying the test cases in each test rule based on the test standard content corresponding to the test standard label, and determining a plurality of candidate test cases according to a verification result.
Optionally, in a fourth implementation manner of the first aspect of the present invention, the invoking a preset language model, and predicting the target test case included in the target training data set based on the test standard label to obtain a plurality of target test cases includes:
calling a multilayer translation network in a preset prediction model, and coding each test case in the target training data set to obtain an effective word vector corresponding to each training data;
calculating the matching probability between each test case in the target training data set and the test standard label based on the effective word vector corresponding to each training data to obtain multi-class matching probability distribution;
and screening out the test cases with the matching probability larger than a preset threshold value from the multi-classification matching probability distribution to obtain target test cases.
Optionally, in a fifth implementation manner of the first aspect of the present invention, after the calling a multi-layer translation network in a preset prediction model, encoding each test case in the target training data set to obtain an effective word vector corresponding to each training data, and calculating a matching probability between each test case in the target training data set and the test standard label based on the effective word vector corresponding to each training data to obtain a multi-class matching probability distribution, the method further includes:
and calling an embedded layer network in the prediction model, and performing convolution on the effective word vector corresponding to each piece of training data to obtain a low-dimensional and dense text vector.
Optionally, in a sixth implementation manner of the first aspect of the present invention, after the calculating, based on the valid word vector corresponding to each piece of training data, a matching probability between each test case in the target training data set and the test standard label to obtain a multi-class matching probability distribution, and screening, from the multi-class matching probability distribution, a test case whose matching probability is greater than a preset threshold, before obtaining the target test case, the method further includes:
calculating a loss value corresponding to the multi-class matching probability distribution according to a preset loss function;
and updating the multi-class matching probability distribution based on the loss value corresponding to the multi-class matching probability distribution.
The second aspect of the present invention provides a device for constructing a test case, including:
the system comprises an industry keyword generation module, a test module and a display module, wherein the industry keyword generation module is used for acquiring a plurality of test standard labels from a preset test standard library according to the type of a product to be tested, and classifying the test standard labels according to a preset industry category to obtain a plurality of industry keywords, wherein each type of test standard label corresponds to one industry keyword;
the business keyword generating module is used for generating a business keyword according to the original data of the product to be tested, wherein the original data of the product to be tested comprises demand data and a plurality of original test cases;
the standard detection module is used for acquiring a plurality of initial test cases from the test standard library according to the industry keywords and the service keywords, and performing test standard detection on each initial test case to obtain a plurality of candidate test cases, wherein the candidate test cases are initial test cases qualified in detection;
the data preprocessing module is used for constructing an initial training data set based on the original test cases and the candidate test cases, and carrying out normalization processing on each test case in the initial training data set to obtain a target training data set;
and the model prediction module is used for calling a preset language model and predicting a target test case contained in the target training data set based on the test standard label to obtain a plurality of target test cases, wherein the matching probability between the target test case and the test standard label is greater than a preset threshold value.
Optionally, in a first implementation manner of the second aspect of the present invention, the service keyword generation module specifically includes:
the word segmentation unit is used for carrying out word segmentation on the original data of the product to be tested based on a preset word segmentation tool to obtain target data containing a plurality of words;
the counting unit is used for carrying out word segmentation counting on the target data containing the multiple words to obtain word segmentation frequency distribution, wherein the word segmentation frequency distribution comprises an initial frequency value corresponding to each word segmentation, and the initial frequency value is used for representing the occurrence frequency of each word segmentation in the target data;
and the construction unit is used for determining at least one service keyword according to the word segmentation frequency distribution and constructing a service keyword set according to the service keyword, wherein the service keyword is a word segmentation corresponding to an initial frequency value which is greater than a preset threshold value.
Optionally, in a second implementation manner of the second aspect of the present invention, the service keyword generation module specifically includes:
the word segmentation unit is used for carrying out word segmentation on the original data of the product to be tested based on a preset word segmentation tool to obtain target data containing a plurality of words;
the counting unit is used for carrying out word segmentation counting on the target data containing the multiple words to obtain word segmentation frequency distribution, wherein the word segmentation frequency distribution comprises an initial frequency value corresponding to each word segmentation, and the initial frequency value is used for representing the occurrence frequency of each word segmentation in the target data;
the construction unit is used for determining at least one service keyword according to the word segmentation frequency distribution and constructing a service keyword set according to the service keyword, wherein the service keyword is a word segmentation corresponding to an initial frequency value larger than a preset threshold value;
the approval unit is used for receiving an approval instruction input by a user, identifying each business keyword in the business keyword set according to the approval instruction, and determining a target business keyword qualified for approval according to an identification result;
and the expansion unit is used for processing the target business keywords based on a preset keyword expansion tool to obtain expanded business keywords and adding the expanded business keywords to the business keyword set.
Optionally, in a third implementation manner of the second aspect of the present invention, the standard detection module specifically includes:
the acquisition unit is used for acquiring a plurality of initial test cases according to the industry keywords and the service keywords;
the classification unit is used for classifying the initial test cases according to the industry keywords to obtain a plurality of test rules, wherein each test rule comprises a plurality of initial test cases, and each test rule corresponds to at least one industry keyword;
and the verification unit is used for verifying the test cases in each test rule based on the test standard content corresponding to the test standard label and determining a plurality of candidate test cases according to the verification result.
Optionally, in a fourth implementation manner of the second aspect of the present invention, the model prediction module specifically includes:
the coding unit is used for calling a multilayer translation network in a preset prediction model, coding each test case in the target training data set and obtaining an effective word vector corresponding to each training data;
the calculation unit is used for calculating the matching probability between each test case in the target training data set and the test standard label based on the effective word vector corresponding to each piece of training data to obtain multi-class matching probability distribution;
and the screening unit is used for screening the test cases with the matching probability larger than a preset threshold value from the multi-classification matching probability distribution to obtain target test cases.
Optionally, in a fifth implementation manner of the second aspect of the present invention, the model prediction module specifically includes:
the coding unit is used for calling a multilayer translation network in a preset prediction model, coding each test case in the target training data set and obtaining an effective word vector corresponding to each training data;
the convolution unit is used for calling an embedded layer network in the prediction model, and performing convolution on the effective word vector corresponding to each piece of training data to obtain a low-dimensional and dense text vector;
the calculation unit is used for calculating the matching probability between each test case in the target training data set and the test standard label based on the effective word vector corresponding to each piece of training data to obtain multi-class matching probability distribution;
and the screening unit is used for screening the test cases with the matching probability larger than a preset threshold value from the multi-classification matching probability distribution to obtain target test cases.
Optionally, in a sixth implementation manner of the second aspect of the present invention, the model prediction module specifically includes:
the coding unit is used for calling a multilayer translation network in a preset prediction model, coding each test case in the target training data set and obtaining an effective word vector corresponding to each training data;
the calculation unit is used for calculating the matching probability between each test case in the target training data set and the test standard label based on the effective word vector corresponding to each piece of training data to obtain multi-class matching probability distribution;
the loss value calculation unit is used for calculating the loss value corresponding to the multi-class matching probability distribution according to a preset loss function;
the updating unit is used for updating the multi-class matching probability distribution based on the loss value corresponding to the multi-class matching probability distribution;
and the screening unit is used for screening the test cases with the matching probability larger than a preset threshold value from the multi-classification matching probability distribution to obtain target test cases.
A third aspect of the present invention provides a device for constructing a test case, including: a memory and at least one processor, the memory having instructions stored therein; the at least one processor calls the instructions in the memory to enable the test case building equipment to execute the test case building method.
A fourth aspect of the present invention provides a computer-readable storage medium, which stores instructions that, when executed on a computer, cause the computer to execute the above-mentioned test case construction method.
According to the technical scheme provided by the invention, relevant test cases are matched through the industry keywords and the service keywords of the products to be tested, so that the test cases which can meet the service requirements and the industry test standards are obtained. Meanwhile, the original test case and the candidate test case of the product to be tested are integrated into the standard test case of the product by combining machine learning, so that the coverage rate of a test scene is improved, and the test accuracy is further improved.
Drawings
FIG. 1 is a diagram of a first embodiment of a method for constructing a test case according to an embodiment of the present invention;
FIG. 2 is a diagram of a second embodiment of a method for constructing a test case according to an embodiment of the present invention;
FIG. 3 is a diagram of a third embodiment of a method for constructing a test case according to an embodiment of the present invention;
FIG. 4 is a diagram of a fourth embodiment of a method for constructing a test case according to an embodiment of the present invention;
FIG. 5 is a diagram of an embodiment of a device for constructing test cases in an embodiment of the present invention;
FIG. 6 is a diagram of another embodiment of a device for constructing test cases according to an embodiment of the present invention;
FIG. 7 is a diagram of an embodiment of a device for constructing test cases in the embodiment of the present invention.
Detailed Description
The embodiment of the invention provides a method, a device, equipment and a storage medium for constructing a test case, which have higher test accuracy.
The terms "first," "second," "third," "fourth," and the like in the description and in the claims, as well as in the drawings, if any, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It will be appreciated that the data so used may be interchanged under appropriate circumstances such that the embodiments described herein may be practiced otherwise than as specifically illustrated or described herein. Furthermore, the terms "comprises," "comprising," or "having," and any variations thereof, are intended to cover non-exclusive inclusions, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
Embodiments in the present application may acquire and process relevant data based on artificial intelligence techniques. Among them, Artificial Intelligence (AI) is a theory, method, technique and application system that simulates, extends and expands human Intelligence using a digital computer or a machine controlled by a digital computer, senses the environment, acquires knowledge and uses the knowledge to obtain the best result.
The artificial intelligence infrastructure generally includes technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technologies, operation/interaction systems, mechatronics, and the like. The artificial intelligence software technology mainly comprises a computer vision technology, a robot technology, a biological recognition technology, a voice processing technology, a natural language processing technology, machine learning/deep learning and the like.
The server may be an independent server, or may be a cloud server that provides basic cloud computing services such as a cloud service, a cloud database, cloud computing, a cloud function, cloud storage, a Network service, cloud communication, a middleware service, a domain name service, a security service, a Content Delivery Network (CDN), and a big data and artificial intelligence platform.
For convenience of understanding, a specific flow of the embodiment of the present invention is described below, and referring to fig. 1, an embodiment of a method for constructing a test case in the embodiment of the present invention includes:
101. obtaining a plurality of test standard labels from a preset test standard library according to the type of a product to be tested, and classifying the test standard labels according to a preset industry category to obtain a plurality of industry keywords, wherein each type of test standard label corresponds to one industry keyword;
it can be understood that the test standard database is a database corresponding to a technical forum or a resource station certified by a test industry, and the test standard database includes test standards (i.e. test standard labels) corresponding to different industries, such as a capacity test, a network test, a DIFF test, etc. of service software, a compatibility test of App software, etc. The server firstly searches corresponding test standard tags, such as compatibility test, page abnormity test, load test and the like, according to the types (such as App test) of products to be tested, and then crawls the test standard tags according to the dimensionalities of the corresponding evaluation rates, sources and the like of the test standard tags, such as only crawling the test standard tags with the evaluation rates in the interval of [ 60%, 80% ]. After crawling a plurality of test standard labels corresponding to a product to be tested, classifying the test standard labels by the server according to different test industry categories to obtain a plurality of industry keywords, such as abnormal tests, network tests and the like.
102. Generating a business keyword set according to original data of a product to be tested, wherein the original data of the product to be tested comprises demand data and a plurality of original test cases, and the business keyword set comprises at least one business keyword;
it is understood that the raw data of the product to be tested includes product requirement information and test cases designed by the test engineer according to preset test rules (e.g., equivalence class division, boundary value division). The server takes the word with the highest frequency of occurrence in the original data as a service keyword, for example, the service keyword is "pay".
103. Acquiring a plurality of initial test cases from a test standard library according to the industry keywords and the service keywords in the service keyword set, and performing test standard detection on each initial test case to obtain a plurality of candidate test cases, wherein the candidate test cases are initial test cases which are qualified in detection;
it can be understood that the test standard database further includes initial test cases corresponding to different industries, the quality of the test case used in the test determines the final test effect, and the initial test case in the test standard database is a test case designed strictly according to the test standard (including data used in the test, test environment, and test rule), and has excellent quality and is accepted in the industry. The server takes the industry key words and the business key words as data matching conditions, acquires corresponding initial test cases from the test standard database through corresponding database query statements, then detects each acquired initial test case, judges whether the initial test case meets the test industry standard (namely the content corresponding to the test standard label), and takes the initial test case meeting the test industry standard as a candidate test case.
104. Constructing an initial training data set based on the original test cases and the candidate test cases, and performing normalization processing on each test case in the initial training data set to obtain a target training data set;
it can be understood that the initial training data set includes a plurality of original test cases and a plurality of candidate test cases, where the original test cases are test cases designed by a test engineer according to a current product to be tested, and the candidate test cases are test cases meeting the test industry standard and the business requirement. In this embodiment, an engineering function is used to perform normalization processing on the test cases, for example, a mapminmax function in matlab (mathematic software) is used to perform maximum and minimum normalization processing on data, and the data in the test cases are all mapped into an interval of [ -1,1], so that the degree of dispersion between data is reduced, and the calculation amount during model processing is reduced.
105. And calling a preset language model, predicting target test cases contained in the target training data set based on the test standard labels, and obtaining a plurality of target test cases, wherein the matching probability between the target test cases and the test standard labels is greater than a preset threshold value.
It can be understood that the language model may adopt a Bert model, an N-gram model, etc., after the server initializes the language model, the server inputs a test standard label and a target training data set into the language model, firstly performs feature extraction on the input data through an input layer of the language model to obtain a corresponding feature vector, secondly performs function activation on the feature vector through a hidden layer of the language model, and finally calculates a matching degree between each test case in the target training data set and the test standard label through an output layer of the language model, and outputs the test case in which the matching degree is greater than a preset threshold value, thereby obtaining a general test case with higher scene coverage.
In the embodiment, the relevant test cases are matched through the industry keywords and the service keywords of the product to be tested, so that the test cases which can meet the service requirements and the industry test standards are obtained. Meanwhile, the original test case and the candidate test case of the product to be tested are integrated into the standard test case of the product by combining machine learning, so that the coverage rate of a test scene is improved, and the test accuracy is further improved.
Referring to fig. 2, a second embodiment of the method for constructing a test case according to the embodiment of the present invention includes:
201. obtaining a plurality of test standard labels from a preset test standard library according to the type of a product to be tested, and classifying the test standard labels according to a preset industry category to obtain a plurality of industry keywords, wherein each type of test standard label corresponds to one industry keyword;
step 201 is similar to the step 101, and is not described herein again.
202. Performing word segmentation processing on original data of a product to be tested based on a preset word segmentation tool to obtain target data containing a plurality of words, wherein the original data of the product to be tested comprises demand data and a plurality of original test cases;
it is understood that the word segmentation tool may adopt Jieba, SnowNLP, etc., and the present embodiment is not limited thereto, and the server inputs the raw data into the word segmentation tool for processing, so as to divide each sentence into a plurality of different words, for example, "in case of weak net, WeChat Payment failure" is divided into "in case of weak net | in | WeChat | Payment | failure", and each word is divided by "|", in the middle.
203. Performing word segmentation statistics on target data containing a plurality of words to obtain word segmentation frequency distribution, wherein the word segmentation frequency distribution comprises an initial frequency value corresponding to each word segmentation, and the initial frequency value is used for representing the occurrence frequency of each word segmentation in the target data;
it is understood that the segmentation frequency distribution is a frequency (initial frequency value) of occurrence of each segmentation in the raw data after the statistical segmentation process, for example, the segmentation frequency distribution T ═ WeChat: 10, payment: 65, weak net: 3].
204. Determining at least one service keyword according to the word segmentation frequency distribution, and constructing a service keyword set according to the service keyword, wherein the service keyword is a word segmentation corresponding to an initial frequency value larger than a preset threshold value;
it can be understood that the server determines, as a service keyword, a participle in the participle frequency distribution, where an initial frequency value is greater than a preset threshold, for example, the preset threshold is 30, and the participle frequency distribution T ═ WeChat: 10, payment: 65, weak net: 3], the service keyword is "Payment".
205. Acquiring a plurality of initial test cases from a test standard library according to the industry keywords and the service keywords in the service keyword set, and performing test standard detection on each initial test case to obtain a plurality of candidate test cases, wherein the candidate test cases are initial test cases which are qualified in detection;
206. constructing an initial training data set based on the original test cases and the candidate test cases, and performing normalization processing on each test case in the initial training data set to obtain a target training data set;
207. and calling a preset language model, predicting target test cases contained in the target training data set based on the test standard labels, and obtaining a plurality of target test cases, wherein the matching probability between the target test cases and the test standard labels is greater than a preset threshold value.
Wherein, the steps 205-207 are similar to the steps of the steps 103-105, and detailed description thereof is omitted here.
In this embodiment, a process of generating a service keyword is described in detail, and the occurrence frequency of each word is counted after the original data is segmented, and the segment with the highest occurrence frequency is used as the service keyword, so that the service keyword is accurately obtained.
Referring to fig. 3, a third embodiment of the method for constructing a test case according to the embodiment of the present invention includes:
301. obtaining a plurality of test standard labels from a preset test standard library according to the type of a product to be tested, and classifying the test standard labels according to a preset industry category to obtain a plurality of industry keywords, wherein each type of test standard label corresponds to one industry keyword;
302. generating a business keyword set according to original data of a product to be tested, wherein the original data of the product to be tested comprises demand data and a plurality of original test cases, and the business keyword set comprises at least one business keyword;
303. obtaining a plurality of initial test cases from a test standard library according to the industry keywords and the service keywords in the service keyword set, and classifying the initial test cases according to the industry keywords to obtain a plurality of test rules, wherein each test rule comprises a plurality of initial test cases, and each test rule corresponds to at least one industry keyword;
it can be understood that each initial test case includes a test target, a test environment, input data, a test step, an expected result, a test script, and the like, and one test rule corresponds to a plurality of test cases, that is, includes different test targets, different test environments, different input data, and the like; and each test rule corresponds to at least one industry keyword, for example, if one test case in the network test rules is ' weak network ', the WeChat payment fails ', the corresponding business keyword is ' WeChat payment ', and the industry keyword is ' weak network '.
304. Verifying the test cases in each test rule based on the test standard content corresponding to the test standard label, and determining a plurality of candidate test cases according to the verification result, wherein the candidate test cases are initial test cases qualified in detection;
it can be understood that the content of the test standard is a real test result, the test case in each test rule is a hypothetical test result, the server determines the correctness of the hypothetical result according to the real result, if the description in the test case conforms to the real result (correct), a corresponding data identifier is added to the test case in the database, and the server acquires the test case containing the data identifier and determines the test case as a candidate test case.
305. Constructing an initial training data set based on the original test cases and the candidate test cases, and performing normalization processing on each test case in the initial training data set to obtain a target training data set;
306. and calling a preset language model, predicting target test cases contained in the target training data set based on the test standard labels, and obtaining a plurality of target test cases, wherein the matching probability between the target test cases and the test standard labels is greater than a preset threshold value.
Step 306 is similar to the step 104, and is not described herein again.
In this embodiment, the process of testing standard detection is described in detail, and a plurality of test cases are obtained from the test standard library, classified into a plurality of test rules, and checked whether each test rule meets the industrial test standard, so that a test case meeting the industrial test standard is obtained.
Referring to fig. 4, a fourth embodiment of the method for constructing a test case according to the embodiment of the present invention includes:
401. obtaining a plurality of test standard labels from a preset test standard library according to the type of a product to be tested, and classifying the test standard labels according to a preset industry category to obtain a plurality of industry keywords, wherein each type of test standard label corresponds to one industry keyword;
402. generating a business keyword set according to original data of a product to be tested, wherein the original data of the product to be tested comprises demand data and a plurality of original test cases, and the business keyword set comprises at least one business keyword;
403. acquiring a plurality of initial test cases from a test standard library according to the industry keywords and the service keywords in the service keyword set, and performing test standard detection on each initial test case to obtain a plurality of candidate test cases, wherein the candidate test cases are initial test cases which are qualified in detection;
404. constructing an initial training data set based on the original test cases and the candidate test cases, and performing normalization processing on each test case in the initial training data set to obtain a target training data set;
405. calling a multilayer translation network in a preset prediction model, and coding each test case in the target training data set to obtain an effective word vector corresponding to each training data;
the server codes each test case in the target training data set by calling a multi-layer translation network of the language model, wherein each layer of translation network comprises a multi-head self-attention subnetwork and a feedforward subnetwork, the relation between words is learned in the multi-head self-attention subnetwork by a self-attention mechanism (self-attention) mechanism, the context of a sentence is coded, a corresponding sentence vector is obtained, secondly, the sentence vector is subjected to nonlinear change through the feedforward subnetwork, and the nonlinear transformation is that more information in the original sentence is introduced through a nonlinear function, for example, a logarithmic function is used for obtaining a corresponding effective word vector.
Optionally, the server further calls an embedded layer network in the prediction model, and performs convolution on the effective word vector corresponding to each piece of training data to obtain a low-dimensional and dense text vector. It can be understood that the embedded layer network at least includes a convolution kernel with a size of 1 × 1, and the server performs convolution processing on the valid word vector corresponding to each piece of training data through the embedded layer network, so as to convert the valid word vector represented by the discrete high-dimensional vector into a low-dimensional dense vector, thereby reducing the calculation amount of the model and increasing the processing speed.
406. Calculating the matching probability between each test case in the target training data set and the test standard label based on the effective word vector corresponding to each training data to obtain multi-class matching probability distribution;
it can be understood that the server inputs the valid word vector corresponding to each piece of training data into a fully-connected network of the language model, sums the valid word vectors of each test case in a linear layer in the network, and then calculates an average value to obtain a corresponding average vector, and processes the average vector corresponding to each test case based on a preset multi-classifier (e.g., softmax) to obtain a corresponding initial multi-class matching probability distribution, that is, to represent the matching probability between each test case and the test standard label.
407. Calculating a loss value corresponding to the multi-class matching probability distribution according to a preset loss function, and updating the multi-class matching probability distribution based on the loss value corresponding to the multi-class matching probability distribution;
it will be appreciated that the loss function may employ the L1 loss, with the loss value representing the deviation of the actual result from before the ideal result, indicating that the actual result is closer to the ideal result when the loss value is smaller. Further, the server adopts a random gradient descent algorithm to iteratively update the network parameters of the language model, and after each time of updating the network parameters, calculates the corresponding initial multi-class matching probability distribution and the corresponding loss value again until the loss value is smaller than a preset threshold value, determines the current language model to be converged, takes the initial multi-class matching probability distribution calculated at the moment as a target multi-class matching probability distribution, and outputs the test cases with the matching probabilities larger than the preset threshold value in the target multi-class matching probability distribution to obtain the general test cases with higher scene coverage rate.
408. And screening out the test cases with the matching probability larger than a preset threshold value from the multi-classification matching probability distribution to obtain target test cases, wherein the matching probability between the target test cases and the test standard labels is larger than the preset threshold value.
It can be understood that the preset threshold value can be determined by actual service requirements, wherein the target test case not only meets the service requirements, but also meets the test cases of the test standard, and the test scenes of the test cases are covered comprehensively, so that the product quality is improved.
In the embodiment, a process of predicting a target test case by a model is described in detail, features are extracted by encoding training samples, the training samples are classified based on the features, the matching probability of each class is obtained, the test case with the maximum matching probability is output, and the accuracy of prediction is improved by performing quantitative calculation on unstructured text data.
With reference to fig. 5, the method for constructing a test case in the embodiment of the present invention is described above, and a device for constructing a test case in the embodiment of the present invention is described below, where an embodiment of the device for constructing a test case in the embodiment of the present invention includes:
an industry keyword generation module 501, configured to obtain multiple test standard tags from a preset test standard library according to the type of a product to be tested, and classify the test standard tags according to a preset industry category to obtain multiple industry keywords, where each type of test standard tag corresponds to one industry keyword;
a service keyword generation module 502, configured to generate a service keyword set according to original data of the product to be tested, where the original data of the product to be tested includes demand data and a plurality of original test cases, and the service keyword set includes at least one service keyword;
the test standard detection module 503 is configured to obtain a plurality of initial test cases from the test standard library according to the industry keyword and the service keyword in the service keyword set, and perform test standard detection on each initial test case to obtain a plurality of candidate test cases, where the candidate test cases are initial test cases that are qualified in detection;
a training data set construction module 504, configured to construct an initial training data set based on the original test case and the candidate test case, and perform normalization processing on each test case in the initial training data set to obtain a target training data set;
and the model prediction module 505 is configured to invoke a preset language model, and predict a target test case included in the target training data set based on the test standard label to obtain a plurality of target test cases, where a matching probability between the target test case and the test standard label is greater than a preset threshold.
In the embodiment, the relevant test cases are matched through the industry keywords and the service keywords of the product to be tested, so that the test cases which can meet the service requirements and the industry test standards are obtained. Meanwhile, the original test case and the candidate test case of the product to be tested are integrated into the standard test case of the product by combining machine learning, so that the coverage rate of a test scene is improved, and the test accuracy is further improved.
Referring to fig. 6, another embodiment of the device for constructing a test case according to the embodiment of the present invention includes:
an industry keyword generation module 501, configured to obtain multiple test standard tags from a preset test standard library according to the type of a product to be tested, and classify the test standard tags according to a preset industry category to obtain multiple industry keywords, where each type of test standard tag corresponds to one industry keyword;
a service keyword generation module 502, configured to generate a service keyword set according to original data of the product to be tested, where the original data of the product to be tested includes demand data and a plurality of original test cases, and the service keyword set includes at least one service keyword;
the test standard detection module 503 is configured to obtain a plurality of initial test cases from the test standard library according to the industry keyword and the service keyword in the service keyword set, and perform test standard detection on each initial test case to obtain a plurality of candidate test cases, where the candidate test cases are initial test cases that are qualified in detection;
a training data set construction module 504, configured to construct an initial training data set based on the original test case and the candidate test case, and perform normalization processing on each test case in the initial training data set to obtain a target training data set;
and the model prediction module 505 is configured to invoke a preset language model, and predict a target test case included in the target training data set based on the test standard label to obtain a plurality of target test cases, where a matching probability between the target test case and the test standard label is greater than a preset threshold.
The service keyword generation module 502 specifically includes:
a word segmentation unit 5021, configured to perform word segmentation processing on the original data of the product to be tested based on a preset word segmentation tool, so as to obtain target data including multiple words;
a counting unit 5022, configured to perform word segmentation counting on the target data including multiple words to obtain word segmentation frequency distribution, where the word segmentation frequency distribution includes an initial frequency value corresponding to each word segmentation, and the initial frequency value is used to indicate the occurrence frequency of each word segmentation in the target data;
a constructing unit 5023, configured to determine at least one service keyword according to the word segmentation frequency distribution, and construct a service keyword set according to the service keyword, where the service keyword is a word segmentation corresponding to an initial frequency value greater than a preset threshold.
The test standard detection module 503 specifically includes:
an obtaining unit 5031, configured to obtain a plurality of initial test cases according to the industry keyword and the service keyword;
a classifying unit 5032, configured to classify the initial test cases according to the industry keywords to obtain multiple test rules, where each test rule includes multiple initial test cases, and each test rule corresponds to at least one industry keyword;
a verifying unit 5033, configured to verify the test case in each test rule based on the test standard content corresponding to the test standard tag, and determine multiple candidate test cases according to a verification result.
The model prediction module 505 specifically includes:
the encoding unit 5051 is configured to invoke a multi-layer translation network in a preset prediction model, and encode each test case in the target training data set to obtain an effective word vector corresponding to each piece of training data;
a convolution unit 5052, configured to call an embedded layer network in the prediction model, and perform convolution on the effective word vector corresponding to each piece of training data to obtain a low-dimensional and dense text vector;
a calculating unit 5053, configured to calculate, based on the valid word vector corresponding to each piece of training data, a matching probability between each test case in the target training data set and the test standard label, so as to obtain a multi-class matching probability distribution;
a screening unit 5054, configured to screen out, from the multi-class matching probability distribution, a test case with a matching probability greater than a preset threshold, so as to obtain a target test case.
In the embodiment of the invention, the modularized design ensures that hardware of each part of the construction device of the test case is concentrated on realizing a certain function, the performance of the hardware is realized to the maximum extent, and meanwhile, the modularized design also reduces the coupling between modules of the device, thereby being more convenient to maintain.
Fig. 5 and fig. 6 describe the building apparatus of the test case in the embodiment of the present invention in detail from the perspective of the modular functional entity, and the building apparatus of the test case in the embodiment of the present invention is described in detail from the perspective of hardware processing.
Fig. 7 is a schematic structural diagram of a test case constructing apparatus 700 according to an embodiment of the present invention, which may generate relatively large differences due to different configurations or performances, and may include one or more processors (CPUs) 710 (e.g., one or more processors) and a memory 720, one or more storage media 730 (e.g., one or more mass storage devices) for storing applications 733 or data 732. Memory 720 and storage medium 730 may be, among other things, transient storage or persistent storage. The program stored in the storage medium 730 may include one or more modules (not shown), each of which may include a series of instruction operations in the device for building test cases 700. Further, the processor 710 may be configured to communicate with the storage medium 730, and execute a series of instruction operations in the storage medium 730 on the test case constructing apparatus 700.
The test case builder 700 may also include one or more power supplies 740, one or more wired or wireless network interfaces 750, one or more input-output interfaces 760, and/or one or more operating systems 731 such as Windows Server, Mac OS X, Unix, Linux, FreeBSD, etc. Those skilled in the art will appreciate that the test case building apparatus configuration shown in FIG. 7 does not constitute a limitation on the test case building apparatus, and may include more or fewer components than shown, or some components in combination, or a different arrangement of components.
The invention further provides a test case constructing device, which includes a memory and a processor, wherein the memory stores computer readable instructions, and when the computer readable instructions are executed by the processor, the processor executes the steps of the test case constructing method in the above embodiments.
The present invention also provides a computer-readable storage medium, which may be a non-volatile computer-readable storage medium, and may also be a volatile computer-readable storage medium, where instructions are stored, and when the instructions are executed on a computer, the instructions cause the computer to execute the steps of the method for constructing the test case.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a read-only memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
The above-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; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. A method for constructing a test case is characterized by comprising the following steps:
obtaining a plurality of test standard labels from a preset test standard library according to the type of a product to be tested, and classifying the test standard labels according to a preset industry category to obtain a plurality of industry keywords, wherein each type of test standard label corresponds to one industry keyword;
generating a service keyword set according to the original data of the product to be tested, wherein the original data of the product to be tested comprises demand data and a plurality of original test cases, and the service keyword set comprises at least one service keyword;
acquiring a plurality of initial test cases from the test standard library according to the industry keywords and the service keywords in the service keyword set, and performing test standard detection on each initial test case to obtain a plurality of candidate test cases, wherein the candidate test cases are initial test cases which are qualified in detection;
constructing an initial training data set based on the original test case and the candidate test cases, and performing normalization processing on each test case in the initial training data set to obtain a target training data set;
and calling a preset language model, predicting a target test case contained in the target training data set based on the test standard label, and obtaining a plurality of target test cases, wherein the matching probability between the target test case and the test standard label is greater than a preset threshold value.
2. The method for constructing a test case according to claim 1, wherein the generating a set of service keywords according to the raw data of the product to be tested comprises:
performing word segmentation processing on the original data of the product to be tested based on a preset word segmentation tool to obtain target data containing a plurality of words;
performing word segmentation statistics on the target data containing a plurality of words to obtain word segmentation frequency distribution, wherein the word segmentation frequency distribution comprises an initial frequency value corresponding to each word segmentation, and the initial frequency value is used for representing the occurrence frequency of each word segmentation in the target data;
determining at least one service keyword according to the word segmentation frequency distribution, and constructing a service keyword set according to the service keyword, wherein the service keyword is a word segmentation corresponding to an initial frequency value larger than a preset threshold value.
3. The method for constructing a test case according to claim 2, after generating the set of service keywords according to the raw data of the product to be tested, further comprising:
receiving an approval instruction input by a user, identifying each business keyword in the business keyword set according to the approval instruction, and determining a target business keyword qualified for approval according to an identification result;
and processing the target business keywords based on a preset keyword expansion tool to obtain expanded business keywords, and adding the expanded business keywords to the business keyword set.
4. The method for constructing test cases according to claim 1, wherein the performing test standard detection on each initial test case to obtain a plurality of candidate test cases comprises:
classifying the initial test cases according to the industry keywords to obtain a plurality of test rules, wherein each test rule comprises a plurality of initial test cases, and each test rule corresponds to at least one industry keyword;
and verifying the test cases in each test rule based on the test standard content corresponding to the test standard label, and determining a plurality of candidate test cases according to a verification result.
5. The method for constructing the test case according to claim 1, wherein the calling a preset language model and predicting the target test case included in the target training data set based on the test standard label to obtain a plurality of target test cases comprises:
calling a multilayer translation network in a preset prediction model, and coding each test case in the target training data set to obtain an effective word vector corresponding to each training data;
calculating the matching probability between each test case in the target training data set and the test standard label based on the effective word vector corresponding to each training data to obtain multi-class matching probability distribution;
and screening out the test cases with the matching probability larger than a preset threshold value from the multi-classification matching probability distribution to obtain target test cases.
6. The method for constructing the test case according to claim 5, wherein after the calling a multi-layer translation network in a preset prediction model, encoding each test case in the target training data set to obtain an effective word vector corresponding to each training data, and calculating a matching probability between each test case in the target training data set and the test standard label based on the effective word vector corresponding to each training data, before obtaining a multi-class matching probability distribution, the method further comprises:
and calling an embedded layer network in the prediction model, and performing convolution on the effective word vector corresponding to each piece of training data to obtain a low-dimensional and dense text vector.
7. The method according to any one of claims 1 to 6, wherein after the matching probability between each test case in the target training data set and the test standard label is calculated based on the valid word vector corresponding to each piece of training data, and a multi-class matching probability distribution is obtained, before the test case with the matching probability greater than a preset threshold is screened from the multi-class matching probability distribution, the method further includes:
calculating a loss value corresponding to the multi-class matching probability distribution according to a preset loss function;
and updating the multi-class matching probability distribution based on the loss value corresponding to the multi-class matching probability distribution.
8. A device for constructing a test case is characterized in that the device for constructing the test case comprises:
the system comprises an industry keyword generation module, a database management module and a database management module, wherein the industry keyword generation module is used for acquiring a plurality of test standard labels from a preset test standard library according to the type of a product to be tested, and classifying the test standard labels according to preset industry categories to obtain a plurality of industry keywords, wherein each type of test standard label corresponds to one industry keyword;
the business keyword generating module is used for generating a business keyword set according to the original data of the product to be tested, wherein the original data of the product to be tested comprises demand data and a plurality of original test cases, and the business keyword set comprises at least one business keyword;
the test standard detection module is used for acquiring a plurality of initial test cases from the test standard library according to the industry keywords and the service keywords in the service keyword set, and performing test standard detection on each initial test case to obtain a plurality of candidate test cases, wherein the candidate test cases are initial test cases which are qualified in detection;
the training data set construction module is used for constructing an initial training data set based on the original test case and the candidate test case, and carrying out normalization processing on each test case in the initial training data set to obtain a target training data set;
and the model prediction module is used for calling a preset language model and predicting a target test case contained in the target training data set based on the test standard label to obtain a plurality of target test cases, wherein the matching probability between the target test case and the test standard label is greater than a preset threshold value.
9. The device for constructing the test case is characterized by comprising the following steps: a memory and at least one processor, the memory having instructions stored therein;
the at least one processor calls the instructions in the memory to cause the test case construction equipment to execute the test case construction method according to any one of claims 1 to 7.
10. A computer-readable storage medium having instructions stored thereon, wherein the instructions, when executed by a processor, implement the method for constructing a test case according to any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111095909.6A CN113778894B (en) | 2021-09-18 | 2021-09-18 | Method, device, equipment and storage medium for constructing test cases |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111095909.6A CN113778894B (en) | 2021-09-18 | 2021-09-18 | Method, device, equipment and storage medium for constructing test cases |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113778894A true CN113778894A (en) | 2021-12-10 |
| CN113778894B CN113778894B (en) | 2023-09-15 |
Family
ID=78852076
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111095909.6A Active CN113778894B (en) | 2021-09-18 | 2021-09-18 | Method, device, equipment and storage medium for constructing test cases |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113778894B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114490396A (en) * | 2022-01-27 | 2022-05-13 | 北京京航计算通讯研究所 | Software test requirement mining method and system |
| CN115828638A (en) * | 2023-01-09 | 2023-03-21 | 西安深信科创信息技术有限公司 | Automatic driving test scene script generation method and device and electronic equipment |
| CN117271373A (en) * | 2023-11-21 | 2023-12-22 | 太平金融科技服务(上海)有限公司深圳分公司 | Automatic construction method and device for test cases, electronic equipment and storage medium |
| CN117313111A (en) * | 2023-11-30 | 2023-12-29 | 中汽智联技术有限公司 | Labeling and indexing method and system based on automobile information security test cases |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110688288A (en) * | 2019-09-09 | 2020-01-14 | 平安普惠企业管理有限公司 | Automatic testing method, device, equipment and storage medium based on artificial intelligence |
| CN111026671A (en) * | 2019-12-16 | 2020-04-17 | 腾讯科技（深圳）有限公司 | Test case set construction method and test method based on test case set |
| CN111124898A (en) * | 2019-12-10 | 2020-05-08 | 平安国际智慧城市科技股份有限公司 | Question-answering system testing method and device, computer equipment and storage medium |
| CN111209185A (en) * | 2019-12-23 | 2020-05-29 | 厦门市美亚柏科信息股份有限公司 | Keyword-based automated testing method and computer-readable storage medium |
| WO2021012645A1 (en) * | 2019-07-22 | 2021-01-28 | 创新先进技术有限公司 | Method and device for generating pushing information |
| CN112527649A (en) * | 2020-12-15 | 2021-03-19 | 建信金融科技有限责任公司 | Test case generation method and device |
-
2021
- 2021-09-18 CN CN202111095909.6A patent/CN113778894B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021012645A1 (en) * | 2019-07-22 | 2021-01-28 | 创新先进技术有限公司 | Method and device for generating pushing information |
| CN110688288A (en) * | 2019-09-09 | 2020-01-14 | 平安普惠企业管理有限公司 | Automatic testing method, device, equipment and storage medium based on artificial intelligence |
| CN111124898A (en) * | 2019-12-10 | 2020-05-08 | 平安国际智慧城市科技股份有限公司 | Question-answering system testing method and device, computer equipment and storage medium |
| CN111026671A (en) * | 2019-12-16 | 2020-04-17 | 腾讯科技（深圳）有限公司 | Test case set construction method and test method based on test case set |
| CN111209185A (en) * | 2019-12-23 | 2020-05-29 | 厦门市美亚柏科信息股份有限公司 | Keyword-based automated testing method and computer-readable storage medium |
| CN112527649A (en) * | 2020-12-15 | 2021-03-19 | 建信金融科技有限责任公司 | Test case generation method and device |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114490396A (en) * | 2022-01-27 | 2022-05-13 | 北京京航计算通讯研究所 | Software test requirement mining method and system |
| CN115828638A (en) * | 2023-01-09 | 2023-03-21 | 西安深信科创信息技术有限公司 | Automatic driving test scene script generation method and device and electronic equipment |
| CN117271373A (en) * | 2023-11-21 | 2023-12-22 | 太平金融科技服务(上海)有限公司深圳分公司 | Automatic construction method and device for test cases, electronic equipment and storage medium |
| CN117271373B (en) * | 2023-11-21 | 2024-03-01 | 太平金融科技服务(上海)有限公司深圳分公司 | Automatic construction method and device for test cases, electronic equipment and storage medium |
| CN117313111A (en) * | 2023-11-30 | 2023-12-29 | 中汽智联技术有限公司 | Labeling and indexing method and system based on automobile information security test cases |
| CN117313111B (en) * | 2023-11-30 | 2024-04-09 | 中汽智联技术有限公司 | Labeling and indexing method and system based on automobile information security test cases |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113778894B (en) | 2023-09-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113778894B (en) | Method, device, equipment and storage medium for constructing test cases | |
| CN111198817B (en) | SaaS software fault diagnosis method and device based on convolutional neural network | |
| CN112070138B (en) | Construction method of multi-label mixed classification model, news classification method and system | |
| CN105426356A (en) | Target information identification method and apparatus | |
| CN111866004B (en) | Security assessment method, apparatus, computer system, and medium | |
| CN111177367B (en) | Case classification method, classification model training method and related products | |
| CN112036168B (en) | Event main body recognition model optimization method, device, equipment and readable storage medium | |
| CN115809887B (en) | Method and device for determining main business scope of enterprise based on invoice data | |
| CN112416778A (en) | Test case recommendation method and device and electronic equipment | |
| CN111931809A (en) | Data processing method and device, storage medium and electronic equipment | |
| CN115204536A (en) | Building equipment fault prediction method, device, equipment and storage medium | |
| CN116415581A (en) | Teaching data analysis system based on intelligent education | |
| CN114691525A (en) | Test case selection method and device | |
| CN116361147A (en) | Method for positioning root cause of test case, device, equipment, medium and product thereof | |
| CN112685374A (en) | Log classification method and device and electronic equipment | |
| CN106484913A (en) | Method and server that a kind of Target Photo determines | |
| CN113628043A (en) | Complaint validity judgment method, device, equipment and medium based on data classification | |
| CN111723182B (en) | Key information extraction method and device for vulnerability text | |
| CN115809796B (en) | Project intelligent dispatching method and system based on user portrait | |
| CN116881971A (en) | Sensitive information leakage detection method, device and storage medium | |
| CN110879821A (en) | Method, device, equipment and storage medium for generating rating card model derivative label | |
| CN116485185A (en) | Enterprise risk analysis system and method based on comparison data | |
| CN116795978A (en) | Complaint information processing method and device, electronic equipment and medium | |
| CN111522750B (en) | Method and system for processing function test problem | |
| CN114528908A (en) | Network request data classification model training method, classification method 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 | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20220923 Address after: Room 2601 (Unit 07), Qianhai Free Trade Building, No. 3048, Xinghai Avenue, Nanshan Street, Qianhai Shenzhen-Hong Kong Cooperation Zone, Shenzhen, Guangdong 518000 Applicant after: Shenzhen Ping An Smart Healthcare Technology Co.,Ltd. Address before: 1-34 / F, Qianhai free trade building, 3048 Xinghai Avenue, Mawan, Qianhai Shenzhen Hong Kong cooperation zone, Shenzhen, Guangdong 518000 Applicant before: Ping An International Smart City Technology Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |