CN113392018B - Traffic distribution method and device, storage medium and electronic equipment - Google Patents
Traffic distribution method and device, storage medium and electronic equipment Download PDFInfo
- Publication number
- CN113392018B CN113392018B CN202110721538.1A CN202110721538A CN113392018B CN 113392018 B CN113392018 B CN 113392018B CN 202110721538 A CN202110721538 A CN 202110721538A CN 113392018 B CN113392018 B CN 113392018B
- Authority
- CN
- China
- Prior art keywords
- test
- index data
- version
- determining
- flow distribution
- 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
- 238000000034 method Methods 0.000 title claims abstract description 94
- 238000012360 testing method Methods 0.000 claims abstract description 286
- 230000008569 process Effects 0.000 claims abstract description 51
- 238000013101 initial test Methods 0.000 claims abstract description 13
- 238000004590 computer program Methods 0.000 claims description 19
- 238000004364 calculation method Methods 0.000 claims description 18
- 238000012545 processing Methods 0.000 claims description 13
- 238000004422 calculation algorithm Methods 0.000 claims description 8
- 238000012512 characterization method Methods 0.000 claims description 8
- 238000005070 sampling Methods 0.000 claims description 5
- 238000010998 test method Methods 0.000 claims 3
- 230000007613 environmental effect Effects 0.000 abstract description 5
- 238000006243 chemical reaction Methods 0.000 description 19
- 238000004891 communication Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 7
- 230000006870 function Effects 0.000 description 7
- 230000004048 modification Effects 0.000 description 6
- 238000012986 modification Methods 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 5
- 230000003287 optical effect Effects 0.000 description 5
- 230000000694 effects Effects 0.000 description 3
- 230000004913 activation Effects 0.000 description 2
- 239000013307 optical fiber Substances 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 239000004065 semiconductor Substances 0.000 description 2
- 239000003086 colorant Substances 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
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
- G06F11/3688—Test management for test execution, e.g. scheduling of test suites
-
- 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
- G06F11/368—Test management for test version control, e.g. updating test cases to a new software version
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D30/00—Reducing energy consumption in communication networks
- Y02D30/50—Reducing energy consumption in communication networks in wire-line communication networks, e.g. low power modes or reduced link rate
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)
- Debugging And Monitoring (AREA)
Abstract
The disclosure relates to a traffic distribution method, a device, a storage medium and an electronic apparatus, wherein the method comprises the following steps: determining a test version corresponding to the application program; for each test version, determining index data of the application program in the test version within a preset duration according to the initial test flow corresponding to the test version, and determining historical index data of the application program in the current release version; determining a target flow distribution model according to the type of the index data; and determining the test flow distributed to each test version and release version in the next test process according to the index data, the historical index data and the target flow distribution model. By the method, intelligent flow distribution in the testing process can be realized, the testing efficiency of the application program is improved, the testing time of the application program can be shortened, and the invariance of the environmental conditions in the continuous testing process is ensured.
Description
Technical Field
The disclosure relates to the technical field of computing, and in particular relates to a traffic distribution method, a traffic distribution device, a storage medium and electronic equipment.
Background
With the continuous development of computer technology, various application programs are layered endlessly, and the update iteration speed of the application programs is very fast. In the update iteration process of the application program, the related technology generally modifies the published application program according to the assumed situation to obtain a new version of the application program to be tested, and then tests the new version of the application program to be tested to determine a preferred application program version as a final online update version. In each process of testing the new application program, the number of test users is manually determined, so that more manual participation is needed, and the test efficiency is affected.
Disclosure of Invention
This summary is provided to introduce a selection of concepts in a simplified form that are further described below in the detailed description. This summary is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to be used to limit the scope of the claimed subject matter.
In a first aspect, the present disclosure provides a traffic distribution method, the method comprising:
determining a test version corresponding to the application program;
for each test version, determining index data of the application program in a preset duration under the test version according to initial test flow corresponding to the test version, and determining historical index data of the application program under the current release version;
Determining a target flow distribution model according to the type of the index data, wherein the target flow distribution model is used for carrying out flow distribution according to the input index data;
and determining the test flow distributed to each test version and the release version in the next test process according to the index data, the historical index data and the target flow distribution model.
In a second aspect, the present disclosure provides a flow distribution device, the device comprising:
the first determining module is used for determining a test version corresponding to the application program;
the second determining module is used for determining index data of the application program in a preset duration under the test version according to the initial test flow corresponding to the test version and determining historical index data of the application program under the current release version;
the third determining module is used for determining a target flow distribution model according to the type of the index data, and the target flow distribution model is used for carrying out flow distribution according to the input index data;
and the fourth determining module is used for determining the test flow distributed to each test version and the release version in the next test process according to the index data, the historical index data and the target flow distribution model.
In a third aspect, the present disclosure provides a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processing device, implements the steps of the method described in the first aspect.
In a fourth aspect, the present disclosure provides an electronic device comprising:
a storage device having a computer program stored thereon;
processing means for executing said computer program in said storage means to carry out the steps of the method described in the first aspect.
Through the technical scheme, the target flow distribution model can be determined according to the type of the index data. Then, according to the index data, the historical index data and the target flow distribution model, the test flow distributed to each test version and release version in the next test process can be determined, namely, the number of test users corresponding to each version of application program can be automatically determined through the model, and the test flow is not required to be distributed manually, so that the test efficiency can be improved. In addition, through automatic distribution of test flow, a plurality of test versions can be tested at the same time, and compared with a serial test mode, the test time is shortened, so that the test efficiency can be further improved. And because a plurality of test versions can be tested at the same time, the invariance of the environmental conditions in the test process can be ensured, thereby ensuring the test effect.
Additional features and advantages of the present disclosure will be set forth in the detailed description which follows.
Drawings
The above and other features, advantages, and aspects of embodiments of the present disclosure will become more apparent by reference to the following detailed description when taken in conjunction with the accompanying drawings. The same or similar reference numbers will be used throughout the drawings to refer to the same or like elements. It should be understood that the figures are schematic and that elements and components are not necessarily drawn to scale. In the drawings:
FIG. 1 is a flow chart illustrating a method of traffic distribution according to an exemplary embodiment of the present disclosure;
FIG. 2 is a block diagram of a flow distribution device according to an exemplary embodiment of the present disclosure;
fig. 3 is a block diagram of an electronic device, according to an exemplary embodiment of the present disclosure.
Detailed Description
Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While certain embodiments of the present disclosure have been shown in the accompanying drawings, it is to be understood that the present disclosure may be embodied in various forms and should not be construed as limited to the embodiments set forth herein, but are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are for illustration purposes only and are not intended to limit the scope of the present disclosure.
It should be understood that the various steps recited in the method embodiments of the present disclosure may be performed in a different order and/or performed in parallel. Furthermore, method embodiments may include additional steps and/or omit performing the illustrated steps. The scope of the present disclosure is not limited in this respect.
The term "including" and variations thereof as used herein are intended to be open-ended, i.e., including, but not limited to. The term "based on" is based at least in part on. The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments. Related definitions of other terms will be given in the description below.
It should be noted that the terms "first," "second," and the like in this disclosure are merely used to distinguish between different devices, modules, or units and are not used to define an order or interdependence of functions performed by the devices, modules, or units. It is further noted that references to "one" or "a plurality" in this disclosure are intended to be illustrative rather than limiting, and those of ordinary skill in the art will appreciate that "one or more" is intended to be understood as "one or more" unless the context clearly indicates otherwise.
The names of messages or information interacted between the various devices in the embodiments of the present disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.
As to the background art, in the update iteration process of an application program, the related technology generally modifies the published application program according to the assumed situation to obtain a new version of the application program to be tested, and then tests the new version of the application program to be tested to determine a preferred application program version as the final online update version. In each process of testing the new application program, the number of test users is manually determined, so that more manual participation is needed, and the test efficiency is affected.
In addition, the related technology generally performs serial test, specifically, firstly modifies an application program according to an assumed situation to obtain an application program of a test version, then performs new assumption again and modifies the application program according to the use feedback of a manually designated test user on the application program of the test version to obtain an application program of another test version for testing, and repeats the test process until a better test version is determined, and the update iteration of the application program is completed. In this way, the overall test time is long and the invariance of the environmental conditions during the continuous test cannot be ensured, thereby affecting the test results.
In view of the above, the present disclosure provides a flow distribution method, so as to implement intelligent flow distribution in a testing process, improve testing efficiency of an application program, reduce testing time of the application program, and ensure invariance of environmental conditions in a continuous testing process.
Fig. 1 is a flow chart illustrating a method of traffic distribution according to an exemplary embodiment of the present disclosure. Referring to fig. 1, the flow distribution method includes:
step 101, determining a test version corresponding to the application program.
Step 102, for each test version, determining index data of the application program under the test version within a preset duration according to the initial test flow corresponding to the test version, and determining historical index data of the application program under the current release version.
And step 103, determining a target flow distribution model according to the type of the index data, wherein the target flow distribution model is used for carrying out flow distribution according to the input index data.
And 104, determining the test flow distributed to each test version and release version in the next test process according to the index data, the historical index data and the target flow distribution model.
For example, the test version corresponding to the application program may be obtained by modifying the current release version according to a modification operation of a tester, for example, for the application program of the current release version, a display color of an operation control in the application program is modified in response to a control color modification operation, or a skip mode among pages in the application program is modified in response to a page skip modification operation, and so on. It should be understood that different test versions may be obtained for different modifications of the application program, where the different modifications may include multiple modifications to the same content of the application program, such as modifying the display color of the operation control to three different colors, respectively, and three different test versions may be obtained. In practical application, the application program of the current release version may be modified according to the update iteration requirement of the application program to obtain a corresponding test version, which is not limited by the embodiment of the present disclosure.
For example, the test flow refers to the number of test users, and the initial test flow may be pre-specified by a tester, for example, the preset test users are distributed evenly according to the number of test versions, where the initial test flow corresponding to each test version is equal. Alternatively, a plurality of test versions may be distributed to a corresponding number of test users according to a preset distribution ratio.
For example, the preset duration may be set according to actual situations, and the index data may include different types of index data such as conversion data, click data, browsing duration, and the like, which is not limited in the embodiment of the present disclosure. The conversion data can characterize whether the test user corresponding to the test version performs an activation operation or a registration operation, that is, whether the user is successfully converted into the activation user or the registration user after using the test version can be determined through the conversion data. The clicking data can represent whether the testing user corresponding to the testing version performs clicking operation, and the browsing duration can be the browsing duration of the testing user on the testing version.
After the initial test flow corresponding to each test version is determined, namely, the number of test users corresponding to each test version is determined, the test version can be distributed to the corresponding test user for use, so that index data of the application program under the test version in a preset duration can be determined. In addition, the historical index data of the application program under the current release version can be determined, so that the test flow distributed to each version is determined by comparing the test version with the historical index data of the current release version, and the preferred application program version is determined by multiple tests.
In the embodiment of the present disclosure, the target traffic distribution model may be determined first according to the type of the index data. Then, according to the index data, the historical index data and the target flow distribution model, the test flow distributed to each test version and release version in the next test process can be determined, namely, the number of test users corresponding to each version of application program can be automatically determined through the model, and the test flow is not required to be distributed manually, so that the test efficiency can be improved. In addition, through automatic distribution of test flow, a plurality of test versions can be tested at the same time, and compared with a serial test mode, the test time is shortened, so that the test efficiency can be further improved. And because a plurality of test versions can be tested at the same time, the invariance of the environmental conditions in the test process can be ensured, thereby ensuring the test effect.
In order to make those skilled in the art more understand the flow distribution method provided by the present disclosure, the following details of each of the above steps are illustrated.
In a possible manner, the determining the target traffic distribution model may be: among the preset first flow distribution model and second flow distribution model, a target flow distribution model is determined according to the type of the index data. The first flow distribution model is used for carrying out probability calculation according to the index data and the historical index data to determine the test flow distributed to each test version and release version, and the second flow distribution model is used for determining the flow distribution proportion according to the index data, the historical index data and the preset model parameters and determining the test flow distributed to each test version and release version according to the flow distribution proportion.
By way of example, two different types of flow distribution models, such as a first flow distribution model and a second flow distribution model, may be preset in the test system. Accordingly, in the subsequent process, the target flow distribution model may be determined according to the type of the index data in the first flow distribution model and the second flow distribution model. Therefore, the model with better performance can be determined for different types of index data to carry out flow distribution, and therefore accuracy of flow distribution is improved.
Of course, in other possible manners, more kinds of flow distribution models may be preset in the test system, so as to select a model with better performance for finer index data types to perform flow distribution, so that accuracy of flow distribution is further improved, which is not limited by the embodiment of the present disclosure.
For example, the first flow distribution model may perform probability calculation according to the index data and the historical index data to determine the test flow distributed to each test version and release version, and for example, the first flow distribution model may be a probability estimation model such as a thompson sampling model. The second flow distribution model can determine a flow distribution proportion according to the index data, the historical index data and the preset model parameters, and determine test flows distributed to each test version and release version according to the flow distribution proportion. For example, the second flow distribution model may be an e-greedy algorithm model or the like that does not perform probability estimation. It should be appreciated that the e-greedy algorithm trades off exploration and utilization based on probability, explores with probability of e each attempt, utilizes with probability of 1-e, and if the second traffic distribution model is an e-greedy algorithm model, the preset model parameters may be preset parameters e.
In a possible manner, among the preset first flow distribution model and second flow distribution model, the determining the target flow distribution model according to the type of the index data may be: in the case where the index data is the target type data, the first flow distribution model is determined as the target flow distribution model, the target type data is index data that can be divided into a first category and a second category, and the result of the index data characterization in the first category is opposite to the result of the index data characterization in the second category. In the case where the index data is not the target type data, the second traffic distribution model is determined as the target traffic distribution model.
It should be appreciated that the first flow distribution model is flow distribution by probability calculation with higher accuracy than the second flow distribution model without probability calculation. However, since the first flow distribution model needs to perform probability calculation, the index data input into the first flow distribution model should be able to distinguish between two different data categories, so that probability estimation can be performed according to the first flow distribution model according to the data amounts of the two data categories, and thus the corresponding test flow is output. For example, the conversion data can distinguish between two different data categories of successful conversion and unsuccessful conversion, so that the conversion data can be input into a first flow distribution model for probability calculation so as to realize flow distribution. In addition, the click data can distinguish two different data categories of clicking and not clicking, so that the click data can be input into a first flow distribution model for probability calculation so as to realize flow distribution. For the browsing duration, two data categories with completely opposite results cannot be distinguished, so that the method is not suitable for inputting a first flow distribution model to perform probability calculation so as to realize flow distribution.
In the embodiment of the present disclosure, if the index data is the target type data, the first traffic distribution model may be determined as the target traffic distribution model. The target type data is index data which can be divided into a first category and a second category, and the result represented by the index data in the first category is opposite to the result represented by the index data in the second category, such as the conversion data, the click data and the like. Conversely, if the index data is not the target type data, the second traffic distribution model may be determined as the target traffic distribution model. It should be understood that the second flow distribution model determines a flow distribution proportion according to the index data, the historical index data and the preset model parameters, and determines the test flow distributed to each test version and the release version according to the flow distribution proportion, and probability calculation is not performed, so that flow distribution can be performed on the index data which cannot be distinguished between the first category and the second category.
In a possible manner, if the target flow distribution model is the first flow distribution model, determining, according to the index data, the historical index data, and the target flow distribution model, the test flow distributed to each test version and the release version in the next test process may be: classifying the index data and the historical index data to determine the quantity of first class data and the quantity of second class data in the index data and the historical index data, then determining the first probability of each version corresponding to the first class data or the second probability of each version corresponding to the second class data according to the first flow distribution model, the quantity of the first class data and the quantity of the second class data, and finally determining the test flow distributed to each test version and release version in the next test process according to the first probability or the second probability of each version. Wherein each version includes each test version and a current release version.
For example, conversion data of each test version in a preset time period and historical conversion data of the current release version before the preset time period are obtained, the conversion data and the historical conversion data can be classified first, and the number of users (namely the number of first type data) successfully converted and the number of users (namely the number of second type data) unsuccessfully converted in the conversion data and the historical conversion data are determined. The categorized conversion data and the historical conversion data may then be input into a first flow distribution model. In the calculation process of the first flow distribution model, beta distribution can be called, and the number of successfully converted users and the number of unsuccessfully converted users are respectively used as parameters alpha and beta of the beta distribution to generate a random number. The random number may characterize the probability of a successfully transformed user in each version, i.e. the value of the random number is the first probability. Alternatively, if the number of unsuccessfully transformed users and the distribution of the number of successfully transformed users are used as parameters α and β of the beta distribution to generate a random number, the random number may represent the probability of unsuccessfully transformed users in each version, i.e. the value of the random number is the second probability.
And then, according to the first probability or the second probability corresponding to each version, determining the test flow distributed to each test version and release version in the next test process. For example, the first traffic distribution model may sort the first probabilities and output the application version with the first highest probability, and then may distribute more test traffic for the application version and less test traffic for other application versions. Alternatively, the first traffic distribution model may sort the second probabilities and output the application version with the highest second probability, and then may distribute less test traffic for that application version and more test traffic for other application versions. Therefore, the version with higher successful conversion probability or lower failure conversion probability has more testing flow in the next testing process, namely more testing users can use the version, so that the testing effect of the version can be better verified, the version of the application program which meets the use requirement of the user better is determined, and the optimization of the application program is realized.
Through the mode, probability calculation can be performed through the first flow distribution model, so that flow distribution can be performed on index data which can be used for obviously distinguishing data types, the accuracy of flow distribution can be improved, the efficiency of flow distribution can be improved, and the testing efficiency is further improved.
In a possible manner, if the target flow distribution model is the second flow distribution model, determining, according to the index data, the historical index data, and the target flow distribution model, the test flow distributed to each test version and the release version in the next test process may be: according to preset model parameters of the second flow distribution model, determining first flow distribution proportions of each test version and release version, then according to index performance represented by index data and historical index data, determining a target version with better index performance in each test version and release version, determining second distribution proportions of the target version according to the preset model parameters, and finally determining test flows distributed to each test version and release version in the next test process according to the first distribution proportions, the second distribution proportions and preset total flows.
Taking the second flow distribution model as an epsilon-greedy algorithm model as an example, the preset total flow is set to 100, namely the total number of test users is 100, the preset model parameter epsilon is set to 0.1, and the number of versions (including test version and release version) of the application program is 2. Firstly, average value of preset model parameters can be carried out according to the number of versions, and the first flow distribution proportion of each test version and release version is determined, so that the first flow distribution proportion is 0.05. Then, a target version with better performance can be determined according to the index data and the historical index data. For example, if the conversion data and the click data of the test version are higher than those of the release version, the test version can be determined to be a target version with better performance. A second distribution ratio of the target version may then be determined based on the first distribution ratio of the flow. For example, on the basis of the first traffic distribution ratio, the remaining traffic distribution ratio 0.9 is determined as the second distribution ratio of the target version. Thus, the traffic distribution ratio of the test version was 0.95, and the traffic distribution ratio of the release version was 0.05. And combining the preset flow, determining that the test flow of the test version in the next test process is 95, and the test flow of the release version is 5, namely, the number of test users of the test version in the next test process is 95, and the number of test users of the release version is 5.
Therefore, the flow distribution proportion can be determined according to the index data, the historical index data and the preset model parameters, and the test flow distributed to each test version and release version is determined according to the flow distribution proportion, so that automatic flow distribution is realized, and the test efficiency is improved. In addition, since probability estimation is not performed, automatic flow distribution can be performed on more types of data, and the applicability of flow distribution is improved.
In a possible manner, according to the index data, the historical index data and the target flow distribution model, determining the test flow distributed to each test version and release version in the next test process may further be: and carrying out weighted summation on a plurality of index data of the same type through a target flow distribution model to obtain target index data, carrying out weighted summation on a plurality of historical index data of the same type to obtain target historical index data, and then determining the test flow distributed to each test version and release version in the next test process through the target flow distribution model based on the target index data and the target historical index data.
As described above, the target flow distribution model may be selected according to the type of the index data from a preset first flow distribution model and a preset second flow distribution model, where the first flow distribution model may be a thompson sampling model, and the second flow distribution model may be an e-greedy algorithm model. However, the thompson sampling model and the e-greedy algorithm model generally only perform data prediction on single data, but in order to improve accuracy of flow distribution and enhance application range of the flow distribution model in the embodiment of the disclosure, content of comprehensive calculation on a plurality of index data of the same type can be added in the model, that is, a formula of weighted summation is added, so that the model can perform flow distribution according to the index data after comprehensive calculation. Compared with the mode of carrying out flow distribution according to single index data, the method can improve the accuracy of flow distribution and the application range of a target flow distribution model.
Based on the same inventive concept, the embodiments of the present disclosure also provide a flow distribution device, which may be part or all of an electronic device through software, hardware, or a combination of both. Referring to fig. 2, the flow distribution device 200 may include:
a first determining module 201, configured to determine a test version corresponding to an application program;
a second determining module 202, configured to determine, for each of the test versions, according to an initial test flow corresponding to the test version, index data of the application program in a preset duration under the test version, and determine historical index data of the application program under a current release version;
a third determining module 203, configured to determine a target flow distribution model according to the type of the index data, where the target flow distribution model is used for performing flow distribution according to the input index data;
and a fourth determining module 204, configured to determine, according to the index data, the historical index data, and the target flow distribution model, a test flow distributed to each test version and the release version in a next test process.
Optionally, the third determining module 203 is configured to:
determining a target flow distribution model according to the type of the index data in a preset first flow distribution model and a preset second flow distribution model;
The first flow distribution model is used for carrying out probability calculation according to the index data and the historical index data to determine the test flow distributed to each test version and the release version, and the second flow distribution model is used for determining the flow distribution proportion according to the index data, the historical index data and preset model parameters and determining the test flow distributed to each test version and the release version according to the flow distribution proportion.
Optionally, the third determining module 203 is configured to:
determining the first flow distribution model as a target flow distribution model in the case that the index data is target type data, wherein the target type data is index data that can be divided into a first category and a second category, and a result of the index data characterization in the first category is opposite to a result of the index data characterization in the second category;
in the case where the index data is not the target type data, the second traffic distribution model is determined as a target traffic distribution model.
Optionally, the fourth determining module 204 is configured to:
classifying the index data and the historical index data to determine the number of first category data and the number of second category data in the index data and the historical index data;
Determining a first probability that each version corresponds to the first class data or a second probability that each version corresponds to the second class data according to the first flow distribution model, the number of the first class data and the number of the second class data;
and determining the test flow distributed to each test version and the release version in the next test process according to the first probability or the second probability corresponding to each version.
Optionally, the fourth determining module 204 is configured to:
determining the value of a preset model parameter in the second flow distribution model according to the index data and the historical index data, and determining a first distribution proportion and a second distribution proportion according to the value of the preset model parameter, wherein the first distribution proportion is used for representing the total flow distribution proportion corresponding to each test version, and the second distribution proportion is used for representing the flow distribution proportion corresponding to the release version;
determining a target flow according to the first distribution proportion and the preset total flow, and equally dividing the target flow according to the number of the test versions to determine the test flow distributed to each test version in the next test process;
And determining the test flow distributed to the release version in the next test process according to the second distribution proportion and the preset total flow.
Optionally, the fourth determining module 204 is configured to:
weighting and summing a plurality of index data of the same type through the target flow distribution model to obtain target index data, and weighting and summing a plurality of historical index data of the same type to obtain target historical index data;
and determining the test flow distributed to each test version and release version in the next test process based on the target index data and the target historical index data through the target flow distribution model.
The specific manner in which the various modules perform the operations in the apparatus of the above embodiments have been described in detail in connection with the embodiments of the method, and will not be described in detail herein.
Based on the same inventive concept, the embodiments of the present disclosure also provide a non-transitory computer-readable storage medium having stored thereon a computer program which, when executed by a processing device, implements the steps of any of the above-described flow distribution methods.
Based on the same inventive concept, the embodiments of the present disclosure further provide an electronic device, including:
A storage device having a computer program stored thereon;
processing means for executing the computer program in the storage means to implement the steps of any of the above-described flow distribution methods.
Referring now to fig. 3, a schematic diagram of an electronic device 300 suitable for use in implementing embodiments of the present disclosure is shown. The terminal devices in the embodiments of the present disclosure may include, but are not limited to, mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and the like, and stationary terminals such as digital TVs, desktop computers, and the like. The electronic device shown in fig. 3 is merely an example and should not be construed to limit the functionality and scope of use of the disclosed embodiments.
As shown in fig. 3, the electronic device 300 may include a processing means (e.g., a central processing unit, a graphics processor, etc.) 301 that may perform various suitable actions and processes in accordance with a program stored in a Read Only Memory (ROM) 302 or a program loaded from a storage means 308 into a Random Access Memory (RAM) 303. In the RAM 303, various programs and data required for the operation of the electronic apparatus 300 are also stored. The processing device 301, the ROM 302, and the RAM 303 are connected to each other via a bus 304. An input/output (I/O) interface 305 is also connected to bus 304.
In general, the following devices may be connected to the I/O interface 305: input devices 306 including, for example, a touch screen, touchpad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; an output device 307 including, for example, a Liquid Crystal Display (LCD), a speaker, a vibrator, and the like; storage 308 including, for example, magnetic tape, hard disk, etc.; and communication means 309. The communication means 309 may allow the electronic device 300 to communicate with other devices wirelessly or by wire to exchange data. While fig. 3 shows an electronic device 300 having various means, it is to be understood that not all of the illustrated means are required to be implemented or provided. More or fewer devices may be implemented or provided instead.
In particular, according to embodiments of the present disclosure, the processes described above with reference to flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a non-transitory computer readable medium, the computer program comprising program code for performing the method shown in the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network via a communication device 309, or installed from a storage device 308, or installed from a ROM 302. The above-described functions defined in the methods of the embodiments of the present disclosure are performed when the computer program is executed by the processing means 301.
It should be noted that the computer readable medium described in the present disclosure may be a computer readable signal medium or a computer readable storage medium, or any combination of the two. The computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this disclosure, a computer-readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In the present disclosure, however, the computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, with the computer-readable program code embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: electrical wires, fiber optic cables, RF (radio frequency), and the like, or any suitable combination of the foregoing.
In some implementations, communications may be made using any currently known or future developed network protocol, such as HTTP (HyperText Transfer Protocol ), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), the internet (e.g., the internet), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future developed networks.
The computer readable medium may be contained in the electronic device; or may exist alone without being incorporated into the electronic device.
The computer readable medium carries one or more programs which, when executed by the electronic device, cause the electronic device to: determining a test version corresponding to the application program;
for each test version, determining index data of the application program in a preset duration under the test version according to initial test flow corresponding to the test version, and determining historical index data of the application program under the current release version; determining a target flow distribution model according to the type of the index data, wherein the target flow distribution model is used for carrying out flow distribution according to the input index data; and determining the test flow distributed to each test version and the release version in the next test process according to the index data, the historical index data and the target flow distribution model.
Computer program code for carrying out operations of the present disclosure may be written in one or more programming languages, including, but not limited to, an object oriented programming language such as Java, smalltalk, C ++ and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computer (for example, through the Internet using an Internet service provider).
The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The modules described in the embodiments of the present disclosure may be implemented in software or hardware. The name of a module does not in some cases define the module itself.
The functions described above herein may be performed, at least in part, by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: a Field Programmable Gate Array (FPGA), an Application Specific Integrated Circuit (ASIC), an Application Specific Standard Product (ASSP), a system on a chip (SOC), a Complex Programmable Logic Device (CPLD), and the like.
In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. The machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
In accordance with one or more embodiments of the present disclosure, example 1 provides a traffic distribution method, comprising:
determining a test version corresponding to the application program;
for each test version, determining index data of the application program in a preset duration under the test version according to initial test flow corresponding to the test version, and determining historical index data of the application program under the current release version;
determining a target flow distribution model according to the type of the index data, wherein the target flow distribution model is used for carrying out flow distribution according to the input index data;
and determining the test flow distributed to each test version and the release version in the next test process according to the index data, the historical index data and the target flow distribution model.
According to one or more embodiments of the present disclosure, example 2 provides the method of example 1, the determining a target traffic distribution model according to the type of the index data, comprising:
determining a target flow distribution model according to the type of the index data in a preset first flow distribution model and a preset second flow distribution model;
The first flow distribution model is used for carrying out probability calculation according to the index data and the historical index data to determine the test flow distributed to each test version and the release version, and the second flow distribution model is used for determining the flow distribution proportion according to the index data, the historical index data and preset model parameters and determining the test flow distributed to each test version and the release version according to the flow distribution proportion.
According to one or more embodiments of the present disclosure, example 3 provides the method of example 2, wherein the determining, in a first flow distribution model and a second flow distribution model set in advance, a target flow distribution model according to the type of the index data includes:
determining the first flow distribution model as a target flow distribution model in the case that the index data is target type data, wherein the target type data is index data that can be divided into a first category and a second category, and a result of the index data characterization in the first category is opposite to a result of the index data characterization in the second category;
in the case where the index data is not the target type data, the second traffic distribution model is determined as a target traffic distribution model.
According to one or more embodiments of the present disclosure, example 4 provides the method of example 2 or 3, the determining, according to the metric data, the historical metric data, and the target traffic distribution model, test traffic to be distributed to each test version and the release version in a next test process, including:
classifying the index data and the historical index data to determine the number of first category data and the number of second category data in the index data and the historical index data;
determining a first probability that each version corresponds to the first class data or a second probability that each version corresponds to the second class data according to the first flow distribution model, the number of the first class data and the number of the second class data;
and determining the test flow distributed to each test version and the release version in the next test process according to the first probability or the second probability corresponding to each version.
According to one or more embodiments of the present disclosure, example 5 provides the method of example 2 or 3, the determining, according to the metric data, the historical metric data, and the target traffic distribution model, test traffic to be distributed to each test version and the release version in a next test process, including:
Determining the value of a preset model parameter in the second flow distribution model according to the index data and the historical index data, and determining a first distribution proportion and a second distribution proportion according to the value of the preset model parameter, wherein the first distribution proportion is used for representing the total flow distribution proportion corresponding to each test version, and the second distribution proportion is used for representing the flow distribution proportion corresponding to the release version;
determining a target flow according to the first distribution proportion and the preset total flow, and equally dividing the target flow according to the number of the test versions to determine the test flow distributed to each test version in the next test process;
and determining the test flow distributed to the release version in the next test process according to the second distribution proportion and the preset total flow.
Example 6 provides the method of any one of examples 1-3, according to one or more embodiments of the present disclosure, the determining test traffic distributed to each test version and the release version in a next test process according to the metric data, the historical metric data, and the target traffic distribution model, comprising:
Weighting and summing a plurality of index data of the same type through the target flow distribution model to obtain target index data, and weighting and summing a plurality of historical index data of the same type to obtain target historical index data;
and determining the test flow distributed to each test version and release version in the next test process based on the target index data and the target historical index data through the target flow distribution model.
Example 7 provides a flow distribution apparatus according to one or more embodiments of the present disclosure, the apparatus comprising:
the first determining module is used for determining a test version corresponding to the application program;
the second determining module is used for determining index data of the application program in a preset duration under the test version according to the initial test flow corresponding to the test version and determining historical index data of the application program under the current release version;
the third determining module is used for determining a target flow distribution model according to the type of the index data, and the target flow distribution model is used for carrying out flow distribution according to the input index data;
And the fourth determining module is used for determining the test flow distributed to each test version and the release version in the next test process according to the index data, the historical index data and the target flow distribution model.
According to one or more embodiments of the present disclosure, example 8 provides the apparatus of example 7, the third determining module is to:
determining a target flow distribution model according to the type of the index data in a preset first flow distribution model and a preset second flow distribution model;
the first flow distribution model is used for carrying out probability calculation according to the index data and the historical index data to determine the test flow distributed to each test version and the release version, and the second flow distribution model is used for determining the flow distribution proportion according to the index data, the historical index data and preset model parameters and determining the test flow distributed to each test version and the release version according to the flow distribution proportion.
According to one or more embodiments of the present disclosure, example 9 provides a non-transitory computer-readable storage medium having stored thereon a computer program that, when executed by a processing device, performs the steps of the method of any of examples 1-6.
In accordance with one or more embodiments of the present disclosure, example 10 provides an electronic device, comprising:
a storage device having a computer program stored thereon;
processing means for executing the computer program in the storage means to implement the steps of the method of any one of examples 1-6.
The foregoing description is only of the preferred embodiments of the present disclosure and description of the principles of the technology being employed. It will be appreciated by persons skilled in the art that the scope of the disclosure referred to in this disclosure is not limited to the specific combinations of features described above, but also covers other embodiments which may be formed by any combination of features described above or equivalents thereof without departing from the spirit of the disclosure. Such as those described above, are mutually substituted with the technical features having similar functions disclosed in the present disclosure (but not limited thereto).
Moreover, although operations are depicted in a particular order, this should not be understood as requiring that such operations be performed in the particular order shown or in sequential order. In certain circumstances, multitasking and parallel processing may be advantageous. Likewise, while several specific implementation details are included in the above discussion, these should not be construed as limiting the scope of the present disclosure. Certain features that are described in the context of separate embodiments can also be implemented in combination in a single embodiment. Conversely, various features that are described in the context of a single embodiment can also be implemented in multiple embodiments separately or in any suitable subcombination.
Although the subject matter has been described in language specific to structural features and/or methodological acts, it is to be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are example forms of implementing the claims. The specific manner in which the various modules perform the operations in the apparatus of the above embodiments have been described in detail in connection with the embodiments of the method, and will not be described in detail herein.
Claims (10)
1. A method of traffic distribution, the method comprising:
determining a test version corresponding to the application program;
for each test version, determining index data of the application program in a preset duration under the test version according to initial test flow corresponding to the test version, and determining historical index data of the application program under the current release version;
determining a target flow distribution model according to the type of the index data, wherein the target flow distribution model is used for carrying out flow distribution according to the input index data;
and determining the test flow distributed to each test version and the release version in the next test process according to the index data, the historical index data and the target flow distribution model.
2. The method of claim 1, wherein determining a target traffic distribution model based on the type of the index data comprises:
determining a target flow distribution model according to the type of the index data in a preset first flow distribution model and a preset second flow distribution model;
the first flow distribution model is a thompson sampling model and is used for carrying out probability calculation according to the index data and the historical index data to determine test flows distributed to each test version and the release version, and the second flow distribution model is an epsilon-greedy algorithm model and is used for determining flow distribution proportion according to the index data, the historical index data and preset model parameters and determining test flows distributed to each test version and the release version according to the flow distribution proportion.
3. The method according to claim 2, wherein the determining a target flow distribution model according to the type of the index data in the preset first flow distribution model and second flow distribution model includes:
determining the first flow distribution model as a target flow distribution model in the case that the index data is target type data, wherein the target type data is index data that can be divided into a first category and a second category, and a result of the index data characterization in the first category is opposite to a result of the index data characterization in the second category;
In the case where the index data is not the target type data, the second traffic distribution model is determined as a target traffic distribution model.
4. A method according to claim 2 or 3, wherein said determining test traffic to be distributed to each test version and said release version in a next test procedure based on said index data, said historical index data and said target traffic distribution model comprises:
classifying the index data and the historical index data to determine the number of first category data and the number of second category data in the index data and the historical index data;
determining a first probability that each version corresponds to the first class data or a second probability that each version corresponds to the second class data according to the first flow distribution model, the number of the first class data and the number of the second class data;
and determining the test flow distributed to each test version and the release version in the next test process according to the first probability or the second probability corresponding to each version.
5. A method according to claim 2 or 3, wherein said determining test traffic to be distributed to each test version and said release version in a next test procedure based on said index data, said historical index data and said target traffic distribution model comprises:
Determining a first distribution proportion of each test version and the release version according to preset model parameters of the second flow distribution model;
determining a target version with better index performance in a test version and a release version according to the index data and the historical index data, and determining the remaining flow distribution proportion as a second distribution proportion of the target version on the basis of the first distribution proportion of each test version and the release version;
and determining the test flow distributed to each test version and the release version in the next test process according to the first distribution proportion, the second distribution proportion and the preset total flow.
6. A method according to any one of claims 1-3, wherein said determining test traffic to be distributed to each test version and said release version in a next test procedure based on said index data, said historical index data and said target traffic distribution model comprises:
weighting and summing a plurality of index data of the same type through the target flow distribution model to obtain target index data, and weighting and summing a plurality of historical index data of the same type to obtain target historical index data;
And determining the test flow distributed to each test version and the release version in the next test process based on the target index data and the target historical index data through the target flow distribution model.
7. A flow distribution device, the device comprising:
the first determining module is used for determining a test version corresponding to the application program;
the second determining module is used for determining index data of the application program in a preset duration under the test version according to the initial test flow corresponding to the test version and determining historical index data of the application program under the current release version;
the third determining module is used for determining a target flow distribution model according to the type of the index data, and the target flow distribution model is used for carrying out flow distribution according to the input index data;
and the fourth determining module is used for determining the test flow distributed to each test version and the release version in the next test process according to the index data, the historical index data and the target flow distribution model.
8. The apparatus of claim 7, wherein the third determination module is configured to:
Determining a target flow distribution model according to the type of the index data in a preset first flow distribution model and a preset second flow distribution model;
the first flow distribution model is a thompson sampling model and is used for carrying out probability calculation according to the index data and the historical index data to determine test flows distributed to each test version and the release version, and the second flow distribution model is an epsilon-greedy algorithm model and is used for determining flow distribution proportion according to the index data, the historical index data and preset model parameters and determining test flows distributed to each test version and the release version according to the flow distribution proportion.
9. A non-transitory computer readable storage medium, on which a computer program is stored, characterized in that the program, when being executed by a processing device, implements the steps of the method according to any one of claims 1-6.
10. An electronic device, comprising:
a storage device having a computer program stored thereon;
processing means for executing said computer program in said storage means to carry out the steps of the method according to any one of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110721538.1A CN113392018B (en) | 2021-06-28 | 2021-06-28 | Traffic distribution method and device, storage medium and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110721538.1A CN113392018B (en) | 2021-06-28 | 2021-06-28 | Traffic distribution method and device, storage medium and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113392018A CN113392018A (en) | 2021-09-14 |
| CN113392018B true CN113392018B (en) | 2024-01-16 |
Family
ID=77624353
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110721538.1A Active CN113392018B (en) | 2021-06-28 | 2021-06-28 | Traffic distribution method and device, storage medium and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113392018B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114124819B (en) * | 2021-10-22 | 2024-02-09 | 北京乐我无限科技有限责任公司 | Flow distribution control method and device, storage medium and computer equipment |
| CN115509890B (en) * | 2022-08-11 | 2024-01-26 | 创新奇智(深圳)技术有限公司 | Test method and device based on reinforcement learning, electronic equipment and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108664397A (en) * | 2018-05-03 | 2018-10-16 | 北京奇虎科技有限公司 | A kind of user's shunt method and device for application test |
| CN109299014A (en) * | 2018-09-28 | 2019-02-01 | 北京云测信息技术有限公司 | A method of the adjust automatically flow in version test |
| CN111309614A (en) * | 2020-02-17 | 2020-06-19 | 支付宝(杭州)信息技术有限公司 | A/B test method and device and electronic equipment |
| CN112445699A (en) * | 2019-09-05 | 2021-03-05 | 北京达佳互联信息技术有限公司 | Strategy matching method and device, electronic equipment and storage medium |
| CN112700131A (en) * | 2020-12-30 | 2021-04-23 | 平安科技（深圳）有限公司 | AB test method and device based on artificial intelligence, computer equipment and medium |
| CN112965742A (en) * | 2021-02-10 | 2021-06-15 | 中国工商银行股份有限公司 | Application version release method and system based on user map |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10630789B2 (en) * | 2016-07-13 | 2020-04-21 | Adobe Inc. | Facilitating consistent A/B testing assignment |
-
2021
- 2021-06-28 CN CN202110721538.1A patent/CN113392018B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108664397A (en) * | 2018-05-03 | 2018-10-16 | 北京奇虎科技有限公司 | A kind of user's shunt method and device for application test |
| CN109299014A (en) * | 2018-09-28 | 2019-02-01 | 北京云测信息技术有限公司 | A method of the adjust automatically flow in version test |
| CN112445699A (en) * | 2019-09-05 | 2021-03-05 | 北京达佳互联信息技术有限公司 | Strategy matching method and device, electronic equipment and storage medium |
| CN111309614A (en) * | 2020-02-17 | 2020-06-19 | 支付宝(杭州)信息技术有限公司 | A/B test method and device and electronic equipment |
| CN112700131A (en) * | 2020-12-30 | 2021-04-23 | 平安科技（深圳）有限公司 | AB test method and device based on artificial intelligence, computer equipment and medium |
| CN112965742A (en) * | 2021-02-10 | 2021-06-15 | 中国工商银行股份有限公司 | Application version release method and system based on user map |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113392018A (en) | 2021-09-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113392018B (en) | Traffic distribution method and device, storage medium and electronic equipment | |
| CN110765354A (en) | Information pushing method and device, electronic equipment and storage medium | |
| CN115357350A (en) | Task configuration method and device, electronic equipment and computer readable medium | |
| CN111738316A (en) | Image classification method and device for zero sample learning and electronic equipment | |
| US20240118984A1 (en) | Prediction method and apparatus for faulty gpu, electronic device and storage medium | |
| CN117236805B (en) | Power equipment control method, device, electronic equipment and computer readable medium | |
| CN116225886A (en) | Test case generation method, device, equipment, storage medium and program product | |
| CN117241092A (en) | Video processing method and device, storage medium and electronic equipment | |
| CN116483891A (en) | Information prediction method, device, equipment and storage medium | |
| CN116149978A (en) | Service interface testing method and device, electronic equipment and storage medium | |
| CN111309323B (en) | Parameter initialization method and device and electronic equipment | |
| CN111680754B (en) | Image classification method, device, electronic equipment and computer readable storage medium | |
| CN111898061B (en) | Method, apparatus, electronic device and computer readable medium for searching network | |
| CN113177176A (en) | Feature construction method, content display method and related device | |
| CN113435528B (en) | Method, device, readable medium and electronic equipment for classifying objects | |
| CN111694755B (en) | Application program testing method and device, electronic equipment and medium | |
| CN116467178B (en) | Database detection method, apparatus, electronic device and computer readable medium | |
| CN111367555B (en) | Assertion method, assertion device, electronic equipment and computer readable medium | |
| CN113177174B (en) | Feature construction method, content display method and related device | |
| CN117725420A (en) | Data set generation method and device, readable medium and electronic equipment | |
| CN116401173A (en) | Test case generation method and device, medium and electronic equipment | |
| CN117707916A (en) | Code testing method, device, equipment, computer readable storage medium and product | |
| CN116010867A (en) | Negative sample determination method, device, medium and electronic equipment | |
| CN117197565A (en) | Content understanding model training, content understanding method, device, medium and equipment | |
| CN113760254A (en) | Data model generation method and device, electronic equipment and computer readable 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 |