CN113971136B - Page testing method and system based on image recognition - Google Patents
Page testing method and system based on image recognition Download PDFInfo
- Publication number
- CN113971136B CN113971136B CN202111461243.1A CN202111461243A CN113971136B CN 113971136 B CN113971136 B CN 113971136B CN 202111461243 A CN202111461243 A CN 202111461243A CN 113971136 B CN113971136 B CN 113971136B
- Authority
- CN
- China
- Prior art keywords
- behavior
- user operation
- operation behavior
- description
- habit
- 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
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
- G06F11/3688—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
- G06F11/3692—Test management for test results analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Hardware Design (AREA)
- General Health & Medical Sciences (AREA)
- Quality & Reliability (AREA)
- Molecular Biology (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Medical Informatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention relates to a page testing method and a page testing system based on image recognition, which are used for comprehensively analyzing and considering correlation conditions among a plurality of user operation behavior tracks, splicing a plurality of first remarkable behavior habit descriptions to obtain a global behavior habit description, optimizing the first remarkable behavior habit description through the global behavior habit description to weaken interference on the first remarkable behavior habit description, ensuring that the obtained second remarkable behavior habit description can reflect the remarkable behavior habit description of the user operation behavior tracks more accurately and reliably as much as possible, and further improving the precision and the reliability of the remarkable behavior habit description. Therefore, the visual output content corresponding to the page theme distribution information can be tested according to the second obvious behavior habit description, so that the accurate test of the visual output content is ensured, and the page test is ensured to be performed strictly according to the operation habit of the user as far as possible.
Description
Technical Field
The invention relates to the technical field of page testing, in particular to a page testing method and system based on image recognition.
Background
The continuous development of scientific progress enables the function of visual business interaction to be continuously improved, and various page interaction services from televisions, computers to terminals provide convenience for the working life of users. At present, with the continuous increase of the demand of users for page interaction services, the optimization and updating of the page interaction services are very critical. In the practical application process, the optimization updating of the page interaction service is usually realized based on a page test, however, the inventor finds out in the research and analysis process that how to ensure the matching of the page test and the user operation habit is a technical problem which needs to be improved at present.
Disclosure of Invention
In a first aspect, an embodiment of the present invention provides a page testing method based on image recognition, which is applied to a page testing system, and the method at least includes: determining page theme distribution information and a user operation behavior log bound by the page theme distribution information, wherein the page theme distribution information contains a plurality of localized visual contents, the user operation behavior log contains a plurality of user operation behavior tracks, and a page interaction behavior event in each user operation behavior track is activated based on a group of localized visual contents; mining the page theme distribution information and the user operation behavior log to obtain a first significant behavior habit description of each user operation behavior track, wherein the first significant behavior habit description aims to express a correlation coefficient between a reference type behavior habit of localized visual content bound by the user operation behavior track and the user operation behavior track; splicing the first significant behavior habit description of each user operation behavior track with the first significant behavior habit descriptions of the rest user operation behavior tracks to obtain a global behavior habit description of each user operation behavior track; optimizing the first significant behavior habit description of each user operation behavior trajectory through the global behavior habit description of each user operation behavior trajectory to obtain a second significant behavior habit description of each user operation behavior trajectory; and testing the visual output content corresponding to the page theme distribution information according to the second remarkable behavior habit description.
In some possible embodiments, the first significant behavior habit description of each user operation behavior trajectory is spliced with the first significant behavior habit descriptions of the remaining user operation behavior trajectories to obtain a global behavior habit description of each user operation behavior trajectory; optimizing the first significant behavior habit description of each user operation behavior trajectory through the global behavior habit description of each user operation behavior trajectory to obtain a second significant behavior habit description of each user operation behavior trajectory, including: splicing the first significant behavior habit description of each user operation behavior track with the first significant behavior habit descriptions of the rest user operation behavior tracks by means of an interference weakening network to obtain a global behavior habit description of each user operation behavior track; and optimizing the first significant behavior habit description of each user operation behavior trajectory through the global behavior habit description of each user operation behavior trajectory to obtain a second significant behavior habit description of each user operation behavior trajectory.
In some possible embodiments, the step of debugging the interference mitigation network comprises: determining an example debugging set, wherein the example debugging set comprises example page subject distribution information and an example user operation behavior log bound by the example page subject distribution information, the example page subject distribution information covers a plurality of example localized visual contents, the example user operation behavior log covers a plurality of example user operation behavior tracks, and a page interaction behavior event in each example user operation behavior track is activated based on a set of example localized visual contents; determining a first example behavior habit description and a second example behavior habit description of each example user operation behavior trajectory, wherein the first example behavior habit description is intended to express a correlation coefficient between a reference type behavior habit of example localized visual content bound to the example user operation behavior trajectory and the example user operation behavior trajectory, and the second example behavior habit description is obtained after performing interference reduction operation on the first example behavior habit description; optimizing the first example behavior habit description of each example user operation behavior trace respectively by means of the interference mitigation network to obtain a candidate significant behavior habit description of each example user operation behavior trace, and debugging the interference mitigation network by comparing the candidate significant behavior habit description of each example user operation behavior trace with the second example behavior habit description.
In some possible embodiments, the example commissioning set further includes an example quality evaluation of the example user operation behavior log, the interference mitigation network includes a description optimization unit and a description concatenation unit, the first example behavior habit description of each example user operation behavior trace is optimized separately by means of the interference mitigation network to obtain a candidate significant behavior habit description of each example user operation behavior trace, and the debugging the interference mitigation network is performed through a comparison result between the candidate significant behavior habit description of each example user operation behavior trace and the second example behavior habit description, including: optimizing the first example behavior habit description of each example user operation behavior trajectory by means of the description optimization unit to obtain candidate significant behavior habit descriptions of each example user operation behavior trajectory; splicing candidate remarkable behavior habit descriptions of a plurality of example user operation behavior tracks by means of the description splicing unit to obtain candidate quality evaluation of the example user operation behavior log; debugging the description optimization unit through the comparison result between the candidate quality evaluation and the example quality evaluation.
In some possible embodiments, the example commissioning set further comprises example quality evaluations of the example user operation behavior logs, after optimizing the first example behavior habit description of each example user operation behavior trace separately by means of the interference mitigation network to obtain candidate significant behavior habit descriptions of each example user operation behavior trace, the method further comprising: analyzing the candidate prominent behavioral habit descriptions of the sample user operation behavior traces and the sample localized visual contents by means of a description stitching unit to obtain candidate quality evaluations of the sample user operation behavior log; debugging the interference mitigation network by a comparison between the candidate quality assessments and the example quality assessments.
In some possible embodiments, the mining the page theme distribution information and the user operation behavior log to obtain a first significant behavior habit description of each user operation behavior trace includes: mining the page subject distribution information and the user operation behavior log to obtain a first significant behavior habit description of each user operation behavior track and a visual content expression of each localized visual content, wherein the visual content expression aims at expressing the distribution characteristics of the localized visual content in the page subject distribution information and corresponding visual content keywords; the splicing the first significant behavior habit description of each user operation behavior trajectory with the first significant behavior habit descriptions of the remaining user operation behavior trajectories to obtain the global behavior habit description of each user operation behavior trajectory includes: splicing the first significant behavior habit description of each user operation behavior track with the first significant behavior habit descriptions of the rest user operation behavior tracks to obtain a spliced significant behavior habit description of each user operation behavior track; stitching the visual content representation of each localized visual content with the visual content representations of the remaining localized visual content to obtain a stitched visual content representation of each localized visual content.
In some possible embodiments, the mining the page subject distribution information and the user operation behavior log to obtain a first significant behavior habit description of each user operation behavior trace includes: mining the page theme distribution information and the user operation behavior log to obtain a first significant behavior habit description of each user operation behavior track and an interference type behavior habit description of each user operation behavior track, wherein the interference type behavior habit description aims to express interference behavior habits carried in the user operation behavior tracks; the optimizing the first significant behavior habit description of each user operation behavior trajectory through the global behavior habit description of each user operation behavior trajectory to obtain a second significant behavior habit description of each user operation behavior trajectory includes: and optimizing the first remarkable behavior habit description of each user operation behavior trajectory through the global behavior habit description and the interference type behavior habit description of each user operation behavior trajectory to obtain a second remarkable behavior habit description of each user operation behavior trajectory.
In some possible embodiments, after the optimizing, by the global behavior habit description of each user operation behavior trajectory, the first significant behavior habit description of each user operation behavior trajectory to obtain the second significant behavior habit description of each user operation behavior trajectory, respectively, the method further includes: analyzing the plurality of localized visual contents and the second significant behavior habit descriptions of the plurality of user operation behavior tracks to obtain behavior habit quality evaluation of the user operation behavior log.
In some possible embodiments, the analyzing the number of localized visual contents and the second significant behavior habit descriptions of the number of user operation behavior traces to obtain the behavior habit quality assessment of the user operation behavior log includes: analyzing the plurality of localized visual contents and the second remarkable behavior habit descriptions of the plurality of user operation behavior tracks respectively to obtain behavior habit quality evaluations of the plurality of user operation behavior tracks; and splicing the behavior habit quality evaluations of the user operation behavior tracks to obtain the behavior habit quality evaluation of the user operation behavior log.
In some possible embodiments, the analyzing the number of localized visual contents and the second significant behavior habit descriptions of the number of user operation behavior traces to obtain a behavior habit quality evaluation of the user operation behavior log includes: and analyzing the plurality of localized visual contents and the second remarkable behavior habit descriptions of the plurality of user operation behavior tracks by means of a description splicing unit to obtain behavior habit quality evaluation of the user operation behavior log.
In some possible embodiments, after analyzing the number of localized visual contents and the second significant behavior habit descriptions of the number of user operation behavior traces to obtain a behavior habit quality evaluation of the user operation behavior log, the method further includes: and transmitting the behavior habit quality evaluation of the user operation behavior log to page interaction user equipment, wherein the page interaction user equipment is used for outputting the behavior habit quality evaluation in a visual interaction thread carrying the page theme distribution information.
In some possible embodiments, the determining the page subject distribution information and the log of the user operation behavior to which the page subject distribution information is bound includes: responding the page theme distribution information fed back by the page interaction user equipment and the user operation behavior log, wherein the page interaction user equipment is used for outputting a visual interaction thread covering the page theme distribution information, and crawling the user operation behavior log based on a behavior capturing request.
In a second aspect, an embodiment of the present invention further provides a page testing system based on image recognition, including a processing engine, a network module, and a memory, where the processing engine and the memory communicate through the network module, and the processing engine is configured to read a computer program from the memory and operate the computer program, so as to implement the foregoing method.
According to the page testing method and system based on image recognition provided by the embodiment of the invention, page subject distribution information and user operation behavior logs are mined to obtain first remarkable behavior habit descriptions of a plurality of user operation behavior tracks, and the first remarkable behavior habit descriptions possibly caused by interference of the user operation behavior logs are difficult to ensure the accuracy of the remarkable behavior habit descriptions of the user operation behavior tracks to a certain extent And describing the obvious behavior habit of the trace, thereby improving the precision and the reliability of the description of the obvious behavior habit. Therefore, the visual output content corresponding to the page theme distribution information can be tested according to the second obvious behavior habit description, so that the accurate test of the visual output content is ensured, and the page test is ensured to be performed strictly according to the operation habit of the user as far as possible.
In the following description, other features will be set forth in part. These features will be in part apparent to those of ordinary skill in the art upon examination of the following and the accompanying drawings or may be learned by production or use. The features of the present application may be realized and attained by practice or use of various aspects of the methodologies, instrumentalities and combinations particularly pointed out in the detailed examples that follow.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained according to the drawings without inventive efforts.
The methods, systems, and/or processes of the figures are further described in accordance with the exemplary embodiments. These exemplary embodiments will be described in detail with reference to the drawings. These exemplary embodiments are non-limiting exemplary embodiments in which reference numerals represent similar mechanisms throughout the various views of the drawings.
FIG. 1 is a block diagram illustrating an application scenario of an exemplary image recognition-based page testing method, according to some embodiments of the present invention.
FIG. 2 is a diagram illustrating the hardware and software components of an exemplary page test system in accordance with some embodiments of the present invention.
FIG. 3 is a flow diagram illustrating an exemplary image recognition-based page testing method and/or process according to some embodiments of the invention.
Detailed Description
In order to better understand the technical solutions of the present invention, the following detailed descriptions of the technical solutions of the present invention are provided with the accompanying drawings and the specific embodiments, and it should be understood that the specific features in the embodiments and the examples of the present invention are the detailed descriptions of the technical solutions of the present invention, and are not limitations of the technical solutions of the present invention, and the technical features in the embodiments and the examples of the present invention may be combined with each other without conflict.
In the following detailed description, numerous specific details are set forth by way of examples in order to provide a thorough understanding of the relevant guidance. It will be apparent, however, to one skilled in the art that the present invention may be practiced without these specific details. In other instances, well-known methods, procedures, systems, components, and/or circuits have been described at a relatively high-level, without detail, in order to avoid unnecessarily obscuring aspects of the invention.
These and other features, functions, methods of execution, and combination of functions and elements of related elements in the structure disclosed in the present application, and the economics of production may become more apparent upon consideration of the following description with reference to the accompanying drawings, all of which form a part of this disclosure. It is to be expressly understood, however, that the drawings are for the purpose of illustration and description only and are not intended as a definition of the limits of the invention. It should be understood that the drawings are not to scale. It is to be expressly understood, however, that the drawings are for the purpose of illustration and description only and are not intended as a definition of the limits of the invention. It should be understood that the drawings are not to scale.
The present invention uses flowcharts to illustrate the implementations performed by a system according to embodiments of the present invention. It should be expressly understood that the execution of the flow diagrams may be performed out of order. Rather, these implementations may be performed in the reverse order or simultaneously. In addition, at least one other implementation may be added to the flowchart. One or more implementations may be deleted from the flowchart.
FIG. 1 is a block diagram illustrating an exemplary image recognition based page testing system 300, which may include a page testing system 100 and a page interaction user device 200, according to some embodiments of the present invention.
In some embodiments, as shown in FIG. 2, the page test system 100 may include a processing engine 110, a network module 120, and a memory 130, the processing engine 110 and the memory 130 communicating through the network module 120.
Processing engine 110 may process the relevant information and/or data to perform one or more of the functions described in this disclosure. For example, in some embodiments, processing engine 110 may include at least one processing engine (e.g., a single core processing engine or a multi-core processor). By way of example only, the Processing engine 110 may include a Central Processing Unit (CPU), an Application-Specific Integrated Circuit (ASIC), an Application-Specific Instruction Set Processor (ASIP), a Graphics Processing Unit (GPU), a Physical Processing Unit (PPU), a Digital Signal Processor (DSP), a Field Programmable Gate Array (FPGA), a Programmable Logic Device (PLD), a controller, a microcontroller Unit, a Reduced Instruction Set Computer (RISC), a microprocessor, or the like, or any combination thereof.
Network module 120 may facilitate the exchange of information and/or data. In some embodiments, the network module 120 may be any type of wired or wireless network or combination thereof. Merely by way of example, the Network module 120 may include a cable Network, a wired Network, a fiber optic Network, a telecommunications Network, an intranet, the internet, a Local Area Network (LAN), a Wide Area Network (WAN), a Wireless Local Area Network (WLAN), a Metropolitan Area Network (MAN), a Public Switched Telephone Network (PSTN), a bluetooth Network, a Wireless personal Area Network, a Near Field Communication (NFC) Network, and the like, or any combination thereof. In some embodiments, the network module 120 may include at least one network access point. For example, the network module 120 may include wired or wireless network access points, such as base stations and/or network access points.
The Memory 130 may be, but is not limited to, a Random Access Memory (RAM), a Read Only Memory (ROM), a Programmable Read-Only Memory (PROM), an Erasable Read-Only Memory (EPROM), an electrically Erasable Read-Only Memory (EEPROM), and the like. The memory 130 is used for storing a program, and the processing engine 110 executes the program after receiving the execution instruction.
It will be appreciated that the configuration shown in FIG. 2 is merely illustrative and that page test system 100 may also include more or fewer components than shown in FIG. 2 or have a different configuration than shown in FIG. 2. The components shown in fig. 2 may be implemented in hardware, software, or a combination thereof.
Fig. 3 is a flowchart illustrating an exemplary image recognition-based page testing method and/or process, which is applied to the page testing system 100 in fig. 1, and further may include the technical solutions described in the following, according to some embodiments of the present invention.
Step 100, determining page theme distribution information and a user operation behavior log bound by the page theme distribution information.
In the embodiment of the present invention, the page theme distribution information includes a plurality of localized visual contents, the user operation behavior log includes a plurality of user operation behavior tracks, and the page interaction behavior event in each user operation behavior track is activated based on a set of localized visual contents. The page theme distribution information may be a plate distribution of various information displayed on the page interaction user equipment interface. Further, the user operation behavior log may be understood as log information collected by the page testing system after the user performs some series of operations through the page interaction user device, such as a touch operation log, a click operation log, and the like. In addition, the page interaction behavior event can be understood as a video viewing event, a file downloading event, and the like.
In some possible embodiments, the determining of the page subject distribution information and the log of the user operation behavior bound by the page subject distribution information described in step 100 may include the following: responding the page theme distribution information fed back by the page interaction user equipment and the user operation behavior log, wherein the page interaction user equipment is used for outputting a visual interaction thread covering the page theme distribution information, and crawling the user operation behavior log based on a behavior capturing request. The crawling user operation behavior log can be realized through a legal and authorized crawler program, so that the integrity of the user operation behavior log can be ensured, and the important privacy of the user can not be revealed in the user operation behavior log.
Step 200, mining the page theme distribution information and the user operation behavior log to obtain a first significant behavior habit description of each user operation behavior track.
In an embodiment of the present invention, the first significant behavior habit description is intended to express a correlation coefficient between a reference type behavior habit of localized visual content bound by the user operation behavior trajectory and the user operation behavior trajectory. For example, the correlation coefficient may be understood as a degree of matching or a degree of correlation. The remarkable behavior habit description can be understood as the behavior habit characteristics of the user, including but not limited to operation preference, interest points and the like of the user.
Under some design ideas which can be implemented independently, the mining of the page theme distribution information and the user operation behavior log described in step 200 to obtain the first significant behavior habit description of each user operation behavior trajectory may include the technical solutions described in the following embodiment 1 and embodiment 2.
Embodiment 1, the page subject distribution information and the user operation behavior log are mined to obtain a first significant behavior habit description of each user operation behavior track and a visual content expression of each localized visual content, where the visual content expression is intended to express a distribution feature of the localized visual content in the page subject distribution information and a corresponding visual content keyword.
And in an implementation mode 2, mining the page theme distribution information and the user operation behavior log to obtain a first significant behavior habit description of each user operation behavior trace and an interference type behavior habit description of each user operation behavior trace, wherein the interference type behavior habit description aims to express interference behavior habits carried in the user operation behavior traces.
In some possible embodiments, the first significant behavior habit description of each user operation behavior trajectory described in step 300 is spliced with the first significant behavior habit descriptions of the remaining user operation behavior trajectories to obtain a global behavior habit description of each user operation behavior trajectory; the optimizing the first significant behavior habit description of each user operation behavior trajectory through the global behavior habit description of each user operation behavior trajectory to obtain the second significant behavior habit description of each user operation behavior trajectory may include the following technical solutions described in steps 310 and 320.
And 310, by means of an interference weakening network, splicing the first significant behavior habit description of each user operation behavior track with the first significant behavior habit descriptions of the remaining user operation behavior tracks to obtain a global behavior habit description of each user operation behavior track.
For example, the interference mitigation network may be a neural network model generated based on machine learning techniques. The global behavior habit description can be understood as a concatenation behavior habit description.
And step 320, optimizing the first significant behavior habit description of each user operation behavior trajectory through the global behavior habit description of each user operation behavior trajectory to obtain a second significant behavior habit description of each user operation behavior trajectory.
By the design, the second remarkable behavior habit description can be ensured to reflect the remarkable behavior habit description of the user operation behavior trajectory more accurately and reliably as far as possible, and the precision and the reliability of the remarkable behavior habit description are further improved.
In some possible embodiments, the optimizing the first significant behavior habit description of each user operation behavior trajectory to obtain the second significant behavior habit description of each user operation behavior trajectory through the global behavior habit description of each user operation behavior trajectory described in step 320 may include the following: and optimizing the first significant behavior habit description of each user operation behavior trajectory through the global behavior habit description and the interference type behavior habit description of each user operation behavior trajectory to obtain a second significant behavior habit description of each user operation behavior trajectory.
By means of the design, the richness degree of the second remarkable behavior habit description can be ensured.
In some embodiments, the step of debugging the interference mitigation network may include the following steps 410-430.
Step 410, determining a sample debugging set, wherein the sample debugging set comprises sample page subject distribution information and a sample user operation behavior log bound by the sample page subject distribution information, the sample page subject distribution information covers a plurality of sample localized visual contents, the sample user operation behavior log covers a plurality of sample user operation behavior traces, and a page interaction behavior event in each sample user operation behavior trace is activated based on a set of sample localized visual contents.
Step 420, determining a first example behavior habit description and a second example behavior habit description of each example user operation behavior trajectory, wherein the first example behavior habit description is intended to express a correlation coefficient between a reference type behavior habit of the example localized visual content bound by the example user operation behavior trajectory and the example user operation behavior trajectory, and the second example behavior habit description is obtained after performing an interference reduction operation on the first example behavior habit description.
Step 430, optimizing the first example behavior habit description of each example user operation behavior trace by means of the interference mitigation network to obtain a candidate significant behavior habit description of each example user operation behavior trace, and debugging the interference mitigation network according to a comparison result between the candidate significant behavior habit description of each example user operation behavior trace and the second example behavior habit description.
In some further embodiments, the example debug set further includes example quality assessments of the example user operational behavior logs, and the interference mitigation network includes a description optimization unit and a description stitching unit. Based on this, the optimizing the first example behavior habit description of each example user operation behavior trace to obtain the candidate significant behavior habit description of each example user operation behavior trace by means of the interference mitigation network described in step 430, and the tuning the interference mitigation network according to the comparison result between the candidate significant behavior habit description of each example user operation behavior trace and the second example behavior habit description may include the technical solutions described in steps 431 to 433.
And 431, optimizing the first example behavior habit description of each example user operation behavior trajectory by means of the description optimization unit to obtain a candidate significant behavior habit description of each example user operation behavior trajectory.
And step 432, by means of the description splicing unit, splicing the candidate significant behavior habit descriptions of a plurality of example user operation behavior tracks to obtain candidate quality evaluation of the example user operation behavior log.
Step 433, debugging the description optimization unit according to the comparison result between the candidate quality evaluation and the example quality evaluation.
For example, the quality evaluation may be understood as an accuracy, which can be generally represented by a value between 0 and 1, and thus, the quality evaluation is taken as a debugging basis, and accurate debugging of the relevant model unit can be realized.
In some further embodiments, the example debug set further includes example quality evaluations of the example user operation behavior log. Based on this, after the optimizing the first example behavior habit description of each example user operation behavior trajectory by the interference mitigation network to obtain the candidate significant behavior habit description of each example user operation behavior trajectory as described in step 430, the method may further include the following steps: analyzing the plurality of example localized visual content and the candidate prominent behavior habit descriptions of the plurality of example user operational behavior trajectories by a description stitching unit to obtain candidate quality evaluations of the example user operational behavior log; debugging the interference mitigation network by a comparison between the candidate quality assessments and the example quality assessments. Thus, the robustness of the interference-weakened network can be guaranteed.
On the basis of the foregoing related embodiments, the splicing the first significant behavior habit description of each user operation behavior trace with the first significant behavior habit descriptions of the remaining user operation behavior traces to obtain the global behavior habit description of each user operation behavior trace, which is described in step 300, may include the following: splicing the first significant behavior habit description of each user operation behavior track with the first significant behavior habit descriptions of the rest user operation behavior tracks to obtain a spliced significant behavior habit description of each user operation behavior track; stitching the visual content representation of each localized visual content with the visual content representations of the remaining localized visual content to obtain a stitched visual content representation of each localized visual content.
Therefore, the integrity of the global behavior habit description can be ensured, and the loss of the global behavior habit description is avoided.
In other embodiments that can be implemented independently, after the step 300 optimizes the first significant behavior habit description of each user operation behavior trajectory through the global behavior habit description of each user operation behavior trajectory to obtain the second significant behavior habit description of each user operation behavior trajectory, the method may further include the following steps: analyzing the plurality of localized visual contents and the second significant behavior habit descriptions of the plurality of user operation behavior tracks to obtain behavior habit quality evaluation of the user operation behavior log. Thus, the behavior habit quality evaluation can be accurately determined.
On the basis of the above related contents, analyzing the several localized visual contents and the second significant behavior habit descriptions of the several user operation behavior traces to obtain a behavior habit quality evaluation of the user operation behavior log, which may include the following contents: analyzing the plurality of localized visual contents and the second remarkable behavior habit descriptions of the plurality of user operation behavior tracks respectively to obtain behavior habit quality evaluations of the plurality of user operation behavior tracks; and splicing the behavior habit quality evaluations of the user operation behavior tracks to obtain the behavior habit quality evaluation of the user operation behavior log.
On the basis of the related content, analyzing the plurality of localized visual contents and the second significant behavior habit descriptions of the plurality of user operation behavior traces to obtain behavior habit quality evaluation of the user operation behavior log, which can be realized by the following steps: and analyzing the plurality of localized visual contents and the second significant behavior habit descriptions of the plurality of user operation behavior tracks by means of a description splicing unit to obtain behavior habit quality evaluation of the user operation behavior log.
In some possible embodiments, after analyzing the number of localized visual contents and the second significant behavior habit descriptions of the number of user operation behavior traces to obtain a behavior habit quality evaluation of the user operation behavior log, the method may further include: and transmitting the behavior habit quality evaluation of the user operation behavior log to page interaction user equipment, wherein the page interaction user equipment is used for outputting the behavior habit quality evaluation in a visual interaction thread carrying the page theme distribution information.
It can be understood that the visual output content corresponding to the page theme distribution information is tested according to the second significant behavior habit description, and the operation behavior matching test can be performed on the image content corresponding to the visual output content, so that the accuracy of the page test is improved.
According to the page testing method and system based on image recognition provided by the embodiment of the application, page theme distribution information and user operation behavior logs are mined to obtain first remarkable behavior habit descriptions of a plurality of user operation behavior tracks, and the first remarkable behavior habit descriptions are difficult to ensure the accuracy of the remarkable behavior habit descriptions of the user operation behavior tracks to a certain extent in view of the fact that the user operation behavior logs are likely to be interfered And describing the obvious behavior habit of the trace, thereby improving the precision and the reliability of the description of the obvious behavior habit. Therefore, the visual output content corresponding to the page theme distribution information can be tested according to the second obvious behavior habit description, so that the accurate test of the visual output content is ensured, and the page test is ensured to be performed strictly according to the operation habit of the user as far as possible.
The skilled person can unambiguously determine some preset, reference, predetermined, set and target technical features/terms, such as threshold values, threshold intervals, threshold ranges, etc., from the above disclosure. For some technical characteristic terms which are not explained, the technical solution can be clearly and completely implemented by those skilled in the art by reasonably and unambiguously deriving the technical solution based on the logical relations in the previous and following paragraphs. Prefixes of technical-feature terms not to be explained, such as "first", "second", "previous", "next", "current", "history", "latest", "best", "target", "specified", and "real-time", etc., can be unambiguously derived and determined from the context. Suffixes of technical feature terms not explained, such as "list", "feature", "sequence", "set", "matrix", "unit", "element", "track", and "list", etc., may also be derived and determined unambiguously from the foregoing and following text.
The foregoing disclosure of embodiments of the present invention will be apparent to those skilled in the art. It should be understood that the derivation and analysis of technical terms, which are not explained, by those skilled in the art based on the above disclosure are based on the description of the present invention, and thus the above description is not an inventive judgment of the overall scheme.
Having thus described the basic concept, it will be apparent to those skilled in the art that the foregoing detailed disclosure is to be regarded as illustrative only and not as limiting. Various modifications, improvements and adaptations to the present invention may occur to those skilled in the art, although not explicitly described herein. Such alterations, modifications, and improvements are intended to be suggested in this disclosure, and are intended to be within the spirit and scope of the exemplary embodiments of the invention.
Meanwhile, the present invention uses specific terms to describe embodiments of the present invention. Such as "one embodiment," "an embodiment," and/or "some embodiments" means a feature, structure, or characteristic described in connection with at least one embodiment of the invention. Therefore, it is emphasized and should be appreciated that two or more references to "an embodiment" or "one embodiment" or "an alternative embodiment" in various portions of this specification are not necessarily all referring to the same embodiment. Furthermore, some of the features, structures, or characteristics of at least one embodiment of the present invention may be combined as suitable.
In addition, those skilled in the art will recognize that the various aspects of the invention may be illustrated and described in terms of several patentable species or situations, including any new and useful combination of processes, machines, articles of manufacture, or materials, or any new and useful modifications thereto. Accordingly, aspects of the present invention may be embodied entirely in hardware, entirely in software (including firmware, resident software, micro-code, etc.) or in a combination of hardware and software. The above hardware or software may be referred to as a "unit", "component", or "system". Furthermore, aspects of the present invention may be embodied as a computer product, located in at least one computer-readable medium, comprising computer-readable program code.
A computer readable signal medium may comprise a propagated data signal with computer program code embodied therein, for example, on a baseband or as part of a carrier wave. The propagated signal may take any of a variety of forms, including electromagnetic, optical, and the like, or any suitable combination. A computer readable signal medium may 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 on a computer readable signal medium may be propagated over any suitable medium, including radio, electrical cable, fiber optic cable, RF, or the like, or any combination of the preceding.
Computer program code required for the execution of aspects of the present invention may be written in any combination of one or more programming languages, including object oriented programming, such as Java, Scala, Smalltalk, Eiffel, JADE, Emerald, C + +, C #, VB.NET, Python, and the like, or similar conventional programming languages, such as the "C" programming language, Visual Basic, Fortran 2003, Perl, COBOL 2002, PHP, ABAP, dynamic programming languages, such as Python, Ruby, and Groovy, or other programming languages. The programming code may execute entirely on the user's computer, as a stand-alone software package, partly on the user's computer, partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer may be connected to the user's computer through any form of network, such as a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet), or in a cloud computing environment, or as a service using, for example, software as a service (SaaS).
Furthermore, unless otherwise indicated by the claims, the order of processing elements and sequences, the use of numerical letters or other designations of the invention are not intended to limit the order of the processes and methods described herein. While various presently contemplated embodiments of the invention have been discussed in the foregoing disclosure by way of example, it should be understood that such detail is solely for that purpose and that the appended claims are not limited to the disclosed embodiments, but, on the contrary, are intended to cover all modifications and equivalent arrangements that are within the spirit and scope of the embodiments of the invention. For example, although the system components described above may be implemented by hardware means, they may also be implemented by software-only solutions, such as installing the described system on an existing server or mobile device.
It should also be appreciated that in the foregoing description of embodiments of the invention, various features are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure aiding in the understanding of at least one embodiment of the invention. However, this method of disclosure is not intended to suggest that the claimed subject matter requires more features than are expressly recited in the claims. Indeed, the embodiments may be characterized as having less than all of the features of a single embodiment disclosed above.
Claims (9)
1. A page testing method based on image recognition is characterized in that the method is applied to a page testing system and at least comprises the following steps:
determining page theme distribution information and a user operation behavior log bound by the page theme distribution information, wherein the page theme distribution information contains a plurality of localized visual contents, the user operation behavior log contains a plurality of user operation behavior tracks, and a page interaction behavior event in each user operation behavior track is activated based on a group of localized visual contents;
mining the page subject distribution information and the user operation behavior log to obtain a first significant behavior habit description of each user operation behavior track, wherein the first significant behavior habit description aims to express a correlation coefficient between a reference type behavior habit of the localized visual content bound by the user operation behavior track and the user operation behavior track;
splicing the first significant behavior habit description of each user operation behavior track with the first significant behavior habit descriptions of the rest user operation behavior tracks to obtain a global behavior habit description of each user operation behavior track; optimizing the first significant behavior habit description of each user operation behavior trajectory through the global behavior habit description of each user operation behavior trajectory to obtain a second significant behavior habit description of each user operation behavior trajectory; and testing the visual output content corresponding to the page theme distribution information according to the second remarkable behavior habit description.
2. The method of claim 1, wherein the first significant behavior habit descriptions of each user operation behavior trajectory are spliced with the first significant behavior habit descriptions of the remaining user operation behavior trajectories to obtain a global behavior habit description of each user operation behavior trajectory;
optimizing the first significant behavior habit description of each user operation behavior trajectory through the global behavior habit description of each user operation behavior trajectory to obtain a second significant behavior habit description of each user operation behavior trajectory, comprising:
splicing the first significant behavior habit description of each user operation behavior track with the first significant behavior habit descriptions of the rest user operation behavior tracks by means of an interference weakening network to obtain a global behavior habit description of each user operation behavior track;
and optimizing the first significant behavior habit description of each user operation behavior trajectory through the global behavior habit description of each user operation behavior trajectory to obtain a second significant behavior habit description of each user operation behavior trajectory.
3. The method of claim 2, wherein the step of debugging the interference mitigation network comprises:
determining an example debugging set, wherein the example debugging set comprises example page subject distribution information and an example user operation behavior log bound by the example page subject distribution information, the example page subject distribution information covers a plurality of example localized visual contents, the example user operation behavior log covers a plurality of example user operation behavior tracks, and a page interaction behavior event in each example user operation behavior track is activated based on a set of example localized visual contents;
determining a first example behavior habit description and a second example behavior habit description of each example user operation behavior trajectory, wherein the first example behavior habit description is intended to express a correlation coefficient between a reference type behavior habit of example localized visual content bound to the example user operation behavior trajectory and the example user operation behavior trajectory, and the second example behavior habit description is obtained after performing interference reduction operation on the first example behavior habit description;
optimizing the first example behavior habit description of each example user operation behavior trace respectively by means of the interference mitigation network to obtain a candidate significant behavior habit description of each example user operation behavior trace, and debugging the interference mitigation network by comparing the candidate significant behavior habit description of each example user operation behavior trace with the second example behavior habit description.
4. The method of claim 3, wherein the example debug set further includes example quality evaluations of the example user operation behavior logs, the interference mitigation network includes a description optimization unit and a description stitching unit, the first example behavior habit description of each example user operation behavior trace is optimized by the interference mitigation network to obtain a candidate significant behavior habit description of each example user operation behavior trace, and the debugging the interference mitigation network is performed through a comparison result between the candidate significant behavior habit description of each example user operation behavior trace and the second example behavior habit description, includes:
optimizing the first example behavior habit descriptions of each example user operation behavior trajectory by means of the description optimization unit to obtain candidate significant behavior habit descriptions of each example user operation behavior trajectory;
by means of the description splicing unit, splicing candidate significant behavior habit descriptions of a plurality of example user operation behavior tracks to obtain candidate quality evaluation of the example user operation behavior log;
debugging the description optimization unit through the comparison result between the candidate quality evaluation and the example quality evaluation.
5. The method of claim 3, wherein the example debug set further comprises example quality evaluations of the example user-operated behavior logs, and wherein after the first example behavior habit description of each example user-operated behavior trace is optimized separately by the interference mitigation network to obtain candidate significant behavior habit descriptions of each example user-operated behavior trace, the method further comprises:
analyzing the plurality of example localized visual content and the candidate prominent behavior habit descriptions of the plurality of example user operational behavior trajectories by a description stitching unit to obtain candidate quality evaluations of the example user operational behavior log;
debugging the interference mitigation network by a comparison between the candidate quality evaluations and the example quality evaluation.
6. The method of claim 1 or 2, wherein the mining the page subject distribution information and the user operation behavior log to obtain a first significant behavior habit description of each user operation behavior trace comprises: mining the page subject distribution information and the user operation behavior log to obtain a first significant behavior habit description of each user operation behavior track and a visual content expression of each localized visual content, wherein the visual content expression aims at expressing the distribution characteristics of the localized visual content in the page subject distribution information and corresponding visual content keywords;
the splicing the first significant behavior habit description of each user operation behavior trajectory with the first significant behavior habit descriptions of the remaining user operation behavior trajectories to obtain the global behavior habit description of each user operation behavior trajectory includes: splicing the first significant behavior habit description of each user operation behavior track with the first significant behavior habit descriptions of the rest user operation behavior tracks to obtain a spliced significant behavior habit description of each user operation behavior track; stitching the visual content representation of each localized visual content with the visual content representations of the remaining localized visual content to obtain a stitched visual content representation of each localized visual content.
7. The method according to claim 1 or 2, wherein after optimizing the first significant behavior habit description of each user operation behavior trajectory to obtain the second significant behavior habit description of each user operation behavior trajectory through the global behavior habit description of each user operation behavior trajectory, respectively, the method further comprises: analyzing the plurality of localized visual contents and the second significant behavior habit descriptions of the plurality of user operation behavior tracks to obtain behavior habit quality evaluation of the user operation behavior log;
wherein the analyzing the plurality of localized visual contents and the second significant behavior habit descriptions of the plurality of user operation behavior traces to obtain the behavior habit quality evaluation of the user operation behavior log comprises: analyzing the plurality of localized visual contents and the second remarkable behavior habit descriptions of the plurality of user operation behavior tracks respectively to obtain behavior habit quality evaluations of the plurality of user operation behavior tracks; splicing the behavior habit quality evaluations of the user operation behavior tracks to obtain the behavior habit quality evaluation of the user operation behavior log;
wherein the analyzing the plurality of localized visual contents and the second significant behavioral habit descriptions of the plurality of user operation behavior traces to obtain the behavioral habit quality assessment of the user operation behavior log comprises: analyzing the plurality of localized visual contents and the second remarkable behavior habit descriptions of the plurality of user operation behavior tracks by means of a description splicing unit to obtain behavior habit quality evaluation of the user operation behavior log;
the mining the page theme distribution information and the user operation behavior log to obtain a first significant behavior habit description of each user operation behavior trace includes: mining the page theme distribution information and the user operation behavior log to obtain a first significant behavior habit description of each user operation behavior track and an interference type behavior habit description of each user operation behavior track, wherein the interference type behavior habit description aims to express interference behavior habits carried in the user operation behavior tracks;
the optimizing the first significant behavior habit description of each user operation behavior trajectory through the global behavior habit description of each user operation behavior trajectory to obtain a second significant behavior habit description of each user operation behavior trajectory comprises: optimizing the first significant behavior habit description of each user operation behavior trajectory through the global behavior habit description and the interference type behavior habit description of each user operation behavior trajectory to obtain a second significant behavior habit description of each user operation behavior trajectory;
after analyzing the plurality of localized visual contents and the second significant behavior habit descriptions of the plurality of user operation behavior tracks to obtain behavior habit quality evaluations of the user operation behavior log, the method further comprises: and transmitting the behavior habit quality evaluation of the user operation behavior log to page interaction user equipment, wherein the page interaction user equipment is used for outputting the behavior habit quality evaluation in a visual interaction thread carrying the page theme distribution information.
8. The method of claim 1, wherein the determining the page subject distribution information and the log of the user operation behavior to which the page subject distribution information is bound comprises:
responding the page theme distribution information fed back by the page interaction user equipment and the user operation behavior log, wherein the page interaction user equipment is used for outputting a visual interaction thread covering the page theme distribution information, and crawling the user operation behavior log based on a behavior capturing request.
9. A page testing system based on image recognition, comprising a processing engine, a network module and a memory, the processing engine and the memory communicating through the network module, the processing engine being configured to read a computer program from the memory and to execute the computer program to implement the method of any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111461243.1A CN113971136B (en) | 2021-12-03 | 2021-12-03 | Page testing method and system based on image recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111461243.1A CN113971136B (en) | 2021-12-03 | 2021-12-03 | Page testing method and system based on image recognition |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113971136A CN113971136A (en) | 2022-01-25 |
| CN113971136B true CN113971136B (en) | 2022-09-09 |
Family
ID=79590517
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111461243.1A Active CN113971136B (en) | 2021-12-03 | 2021-12-03 | Page testing method and system based on image recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113971136B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114638234B (en) * | 2022-03-31 | 2022-11-15 | 逑美科技(上海)有限公司 | Big data mining method and system applied to online business handling |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107730038A (en) * | 2017-10-09 | 2018-02-23 | 小草数语（北京）科技有限公司 | The other Forecasting Methodology of user preference, device and its equipment |
| US10114733B1 (en) * | 2016-08-29 | 2018-10-30 | Cadence Design Systems, Inc. | System and method for automated testing of user interface software for visual responsiveness |
| CN110929196A (en) * | 2019-11-26 | 2020-03-27 | 泰康保险集团股份有限公司 | Display method and device of mobile terminal Web page |
| CN113553596A (en) * | 2021-08-02 | 2021-10-26 | 广州米捷网络科技有限公司 | Information protection method applied to big data service and server |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8458115B2 (en) * | 2010-06-08 | 2013-06-04 | Microsoft Corporation | Mining topic-related aspects from user generated content |
| CN110580486B (en) * | 2018-06-07 | 2024-04-12 | 斑马智行网络(香港)有限公司 | Data processing method, device, electronic equipment and readable medium |
-
2021
- 2021-12-03 CN CN202111461243.1A patent/CN113971136B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10114733B1 (en) * | 2016-08-29 | 2018-10-30 | Cadence Design Systems, Inc. | System and method for automated testing of user interface software for visual responsiveness |
| CN107730038A (en) * | 2017-10-09 | 2018-02-23 | 小草数语（北京）科技有限公司 | The other Forecasting Methodology of user preference, device and its equipment |
| CN110929196A (en) * | 2019-11-26 | 2020-03-27 | 泰康保险集团股份有限公司 | Display method and device of mobile terminal Web page |
| CN113553596A (en) * | 2021-08-02 | 2021-10-26 | 广州米捷网络科技有限公司 | Information protection method applied to big data service and server |
Non-Patent Citations (2)
| Title |
|---|
| Android手机应用界面布局的可用性测试研究;朱婧茜 等;《包装工程》;20140520;第35卷(第10期);第61-64页 * |
| 前端页面的性能测试与调优;寻虫测试;《https://www.modb.pro/db/373638》;20210827;第1-7页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113971136A (en) | 2022-01-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Schlegel et al. | Towards a rigorous evaluation of XAI methods on time series | |
| US10032114B2 (en) | Predicting application performance on hardware accelerators | |
| CN108959059B (en) | Test method and test platform | |
| CN107506300B (en) | User interface testing method, device, server and storage medium | |
| CN108459964B (en) | Test case selection method, device, equipment and computer readable storage medium | |
| CN108614970B (en) | Virus program detection method, model training method, device and equipment | |
| CN112418935B (en) | Data processing method and big data platform based on big data and advertisement push | |
| CN113779431B (en) | Service information processing method based on time sequence characteristics and server | |
| CN112749081A (en) | User interface testing method and related device | |
| CN107015841B (en) | Preprocessing method for program compiling and program compiling device | |
| CN116680689B (en) | Security situation prediction method and system applied to big data | |
| CN113971136B (en) | Page testing method and system based on image recognition | |
| EP2810184A1 (en) | Filtering redundant consumer transaction rules | |
| CN114911992A (en) | Intelligent interactive data processing method based on intelligent lock | |
| CN113065279A (en) | Method, device, equipment and storage medium for predicting total organic carbon content | |
| CN115128438A (en) | Chip internal fault monitoring method and device | |
| CN114661994B (en) | User interest data processing method and system based on artificial intelligence and cloud platform | |
| CN113778890B (en) | Code testing method and device, electronic equipment and storage medium | |
| CN116112746B (en) | Online education live video compression method and system | |
| CN116030115B (en) | Visual design image analysis method and system applied to AI | |
| CN112463205A (en) | AI and big data based application program management method and artificial intelligence server | |
| CN112417460A (en) | Payment data processing method based on big data and block chain and cloud server | |
| CN113780582B (en) | Wind control feature screening method and system based on machine learning model | |
| CN113220955A (en) | Big data visualization method and big data cloud server | |
| CN113486404A (en) | Big data information protection method for dealing with smart medical treatment and medical server |
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 |