CN115840689A

CN115840689A - Promotion information testing method and device, storage medium and program product

Info

Publication number: CN115840689A
Application number: CN202111097442.9A
Authority: CN
Inventors: 李娜; 朱兰; 漆洪凯; 许炳相
Original assignee: Tencent Technology Shenzhen Co Ltd
Current assignee: Tencent Technology Shenzhen Co Ltd
Priority date: 2021-09-18
Filing date: 2021-09-18
Publication date: 2023-03-24

Abstract

The application discloses a promotion information testing method and device, a storage medium and a program product, wherein in response to a testing operation instruction, a content page is entered through a target promotion information bit inlet, then promotion information judgment processing is carried out on the content page to obtain a promotion information judgment result, when the promotion information judgment result indicates that the content page contains target promotion information, a trigger test is carried out on the target promotion information, after the trigger test is carried out, the screen display content is intercepted to obtain a first page image, then the first page image is input to a promotion information page detection model to obtain a first detection result, and then the correctness of the first page image is determined according to the first detection result. The method and the device can realize the automatic test of the promotion information, and improve the test efficiency and test effectiveness of the promotion information test. The method and the device can be widely applied to the testing technology of software in terminal equipment such as vehicle-mounted terminals, tablet computers, smart phones, smart watches and smart bands.

Description

Promotion information testing method and device, storage medium and program product

Technical Field

The present application relates to the field of software testing technologies, and in particular, to a method and an apparatus for testing popularization information, a storage medium, and a program product.

Background

With the development of media information technology, users can acquire information through more ways, and further the requirements of the users for acquiring various information are met. In order to meet the greater demand of users for obtaining information, promotion information providers often push promotion information to users through various internet platforms and various push approaches.

In order to enable a user to effectively acquire promotion information, a promotion information test is often required to determine whether the promotion information can be skipped normally. At present, most of popularization information testing operations are manually performed by testers, and the problems of low testing efficiency, low testing effectiveness and the like are easily caused due to the defects of complicated testing process, large workload, more repetitive work and the like.

Disclosure of Invention

The following is a summary of the subject matter described in detail herein. This summary is not intended to limit the scope of the claims.

The embodiment of the application provides a promotion information testing method and device, a storage medium and a program product, which can realize automatic testing of promotion information and improve the testing efficiency and testing effectiveness of promotion information testing.

On one hand, the embodiment of the application provides a method for testing popularization information, which comprises the following steps:

responding to a test operation instruction, and entering a content page through a target promotion information bit inlet;

carrying out promotion information judgment processing on the content page to obtain a promotion information judgment result;

when the promotion information judgment result indicates that the content page contains target promotion information, executing a trigger test on the target promotion information, wherein the trigger test is used for skipping the content page;

after the trigger test is executed, screen display content is intercepted to obtain a first page image;

inputting the first page image to a promotion information page detection model to obtain a first detection result of a page element in the first page image, wherein the page element is an information bearing element for displaying page information in a page;

and determining the correctness of the first page image according to the first detection result and page elements of a preset target promotion information page.

On the other hand, this application embodiment still provides a popularization information testing arrangement, includes:

the interaction module is used for responding to the test operation instruction and entering a content page through a target promotion information bit inlet;

the promotion information judgment module is used for judging and processing promotion information of the content page to obtain a promotion information judgment result;

the trigger test module is used for executing a trigger test on the target promotion information when the promotion information judgment result indicates that the content page contains the target promotion information, wherein the trigger test is used for skipping the content page;

the first intercepting module is used for intercepting the display content of the screen to obtain a first page image after the trigger test is executed;

the page detection module is used for inputting the first page image to a promotion information page detection model to obtain a first detection result of a page element in the first page image, wherein the page element is an information bearing element used for displaying page information in a page;

and the result determining module is used for determining the correctness of the first page image according to the first detection result and page elements of a preset target promotion information page.

Optionally, the result determination module includes:

the first comparison module is used for comparing the first detection result with page elements of a preset target promotion information page to obtain a first comparison result;

and the correctness determining module is used for determining the correctness of the first page image according to the first comparison result.

Optionally, the first comparing module includes at least one of:

the first comparison submodule is used for comparing the page element type detection information with page element type information of a preset target promotion information page when the first detection result comprises page element type detection information;

alternatively, the first and second electrodes may be,

and the second comparison submodule is used for comparing the page element layout detection information with page element layout information of a preset target promotion information page when the first detection result comprises page element layout detection information.

Optionally, the correctness determining module includes:

the first determining sub-module is used for determining that the first page image is correct when the first comparison result is that the first detection result is consistent with page elements of the target promotion information page;

alternatively, the first and second electrodes may be,

and the second determining submodule is used for determining the first page image error when the first comparison result is that the first detection result is inconsistent with the page elements of the target popularization information page.

Optionally, the promotion information determination module includes:

the second interception module is used for intercepting the content page to obtain a second page image;

the type prediction module is used for inputting the second page image to a promotion information type prediction model to obtain a second prediction result;

and the information judgment module is used for judging and processing the first promotion information to obtain a promotion information judgment result when the second page image is determined to contain the first promotion information according to the second prediction result.

Optionally, the test operation instruction includes a promotion information identifier, and the first promotion information includes a promotion information text; the information judgment module comprises:

the information identification module is used for carrying out information identification processing on the first popularization information to obtain the popularization information text;

the first sending module is used for sending the popularization information identifier to a server so that the server can obtain target text information according to the popularization information identifier;

the first receiving module is used for receiving the target text information sent by the server;

and the information judgment sub-module is used for comparing the promotion information text with the target text information, and when the promotion information text is consistent with the target text information, performing element information judgment processing on the first promotion information to obtain a promotion information judgment result.

Optionally, the information determining sub-module includes:

the element detection module is used for inputting the second page image to an element information detection model to obtain a third detection result;

and the second comparison module is used for comparing the third detection result with preset target element information, and when the third detection result is consistent with the target element information, obtaining a promotion information judgment result that the first promotion information is the target promotion information.

Optionally, the second prediction result includes a promotion information prediction type and a confidence level; the information judgment module comprises:

the third comparison module is used for comparing the confidence coefficient with a confidence coefficient threshold value to obtain a second comparison result;

and the promotion information determining module is used for determining that the second page image contains first promotion information when the second comparison result shows that the confidence coefficient is greater than or equal to the confidence coefficient threshold value, and the promotion information type of the first promotion information is consistent with the promotion information prediction type.

Optionally, the trigger test module includes:

the region prediction module is used for inputting the second page image into a trigger region prediction model to obtain trigger region prediction information of the target popularization information;

the region determining module is used for determining a trigger region in the target popularization information according to the trigger region prediction information;

and the trigger test submodule is used for executing a trigger test according to the trigger area.

Optionally, the test operation instruction includes a promotion information identifier; the interaction module comprises:

the second sending module is used for responding to a test operation instruction and sending the promotion information identifier to a server so that the server can obtain target promotion information bit information according to the promotion information identifier;

the second receiving module is used for receiving the target promotion information bit information sent by the server;

the entrance determining module is used for determining a target promotion information bit entrance according to the target promotion information bit information;

and the page entering module is used for entering the content page through the target promotion information bit entry.

Optionally, the trigger test module is further configured to execute a trigger test on the target popularization information again;

the first interception module is further used for intercepting the screen display content again to obtain a new first page image after the triggering test is executed again;

the page detection module is further configured to input the new first page image to the promotion information page detection model to obtain a new first detection result;

and the result determining module is further used for determining the correctness of the new first page image according to the new first detection result until the number of times of the trigger test reaches a preset threshold value.

Optionally, the promotion information testing apparatus further includes:

the first label adding module is used for adding a first type label to the first page image;

the first feature labeling module is used for performing first feature labeling processing on the first page image according to the first type label;

and the first model training module is used for taking the first page image subjected to the first feature labeling processing as a training sample of the promotion information page detection model and training the promotion information page detection model.

Optionally, the promotion information testing apparatus further includes:

the second label adding module is used for adding a second type label to the second page image;

the second feature labeling module is used for performing second feature labeling processing on the second page image according to the second type tag;

and the second model training module is used for taking the second page image subjected to the second feature labeling processing as a training sample of the popularization information type prediction model and carrying out training processing on the popularization information type prediction model.

Optionally, the promotion information testing apparatus further includes:

the third label adding module is used for adding a third type label to the second page image;

the third feature labeling module is used for performing third feature labeling processing on the second page image according to the third type tag;

and the third model training module is used for taking the second page image subjected to the third feature labeling processing as a training sample of the element information detection model and training the element information detection model.

Optionally, the promotion information testing apparatus further includes:

the fourth label adding module is used for adding a fourth type label to the second page image;

the fourth feature labeling module is used for performing fourth feature labeling processing on the second page image according to the fourth type label;

and the fourth model training module is used for taking the second page image subjected to the fourth feature labeling processing as a training sample of the trigger area prediction model and training the trigger area prediction model.

at least one processor;

at least one memory for storing at least one program;

at least one of the programs, when executed by at least one of the processors, implements a promotional information testing method as previously described.

In another aspect, an embodiment of the present application further provides a computer-readable storage medium, in which a program executable by a processor is stored, and when the program executable by the processor is executed by the processor, the program is used to implement the promotion information test method as described above.

In another aspect, the present application further provides a computer program product, which includes a computer program or a computer instruction, where the computer program or the computer instruction is stored in a computer-readable storage medium, and a processor of a computer device reads the computer program or the computer instruction from the computer-readable storage medium, and executes the computer program or the computer instruction, so that the computer device executes the promotion information test method described above.

The embodiment of the application at least comprises the following beneficial effects: responding to a test operation instruction, entering a content page through a target promotion information bit inlet, then carrying out promotion information judgment processing on the content page to obtain a promotion information judgment result, when the promotion information judgment result is that the content page contains target promotion information, executing a trigger test on the target promotion information, after executing the trigger test, intercepting screen display content to obtain a first page image, then inputting the first page image to a promotion information page detection model to obtain a first detection result, and then determining the correctness of the first page image according to the first detection result. The whole process of the promotion information test is executed in response to the test operation instruction, so that the test operation is not required to be manually performed by a tester, the automatic test of the promotion information is realized, and the test efficiency of the promotion information test can be improved; secondly, after the promotion information judgment result is determined that the content page contains the target promotion information, performing trigger test on the target promotion information, namely, the trigger test performed each time is specific to the target promotion information, so that the test effectiveness of the promotion information test can be improved; in addition, after the trigger test is executed, the correctness test is also carried out on the screen display content, and whether the screen display content after the trigger test is executed is correct or not can be checked, so that the popularization information test is more effective; in addition, because the correctness test of the screen display content is realized according to the popularization information page detection model, a test script does not need to be set manually, and the test script does not need to be modified manually for different popularization information pages, the universality of the popularization information test can be improved.

Additional features and advantages of the application will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by the practice of the application. The objectives and other advantages of the application may be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.

Drawings

The accompanying drawings are included to provide a further understanding of the invention, and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the example serve to explain the principles of the invention.

FIG. 1 is a schematic illustration of an implementation environment provided by an embodiment of the present application;

FIG. 2 is a diagram of a software architecture of a test terminal provided by one embodiment of the present application;

fig. 3 is a flowchart of a method for testing promotional information according to an embodiment of the present application;

FIG. 4 is a schematic diagram of a content page provided by an embodiment of the present application;

FIG. 5 is a schematic diagram of another content page provided by an embodiment of the present application;

FIG. 6 is a flowchart of one specific method of step 160 of FIG. 3;

FIG. 7 is a flowchart of one specific method of step 120 of FIG. 3;

FIG. 8 is a flowchart of one specific method of step 123 of FIG. 7;

FIG. 9 is a flowchart of another specific method of step 123 of FIG. 7;

FIG. 10 is a flowchart of one particular method of step 1236 of FIG. 9;

FIG. 11 is a flowchart of one specific method of step 130 of FIG. 3;

FIG. 12 is a flowchart of one particular method of step 110 of FIG. 3;

fig. 13 is a flowchart of a promotional information testing method provided in a specific example of the present application;

FIG. 14 is a schematic illustration of a second page image provided by a specific example of the present application;

FIG. 15 is a schematic illustration of a second page image provided by another specific example of the present application;

FIG. 16 is a schematic illustration of a promotional information provider profile page provided by a specific example of the present application;

FIG. 17 is a flowchart of a promotional information testing method provided in another specific example of the present application;

FIG. 18 is a flow diagram illustrating a promotional information testing methodology according to another embodiment of the present application;

fig. 19 is a schematic diagram of a promotional information testing apparatus according to an embodiment of the present application;

fig. 20 is a schematic diagram of a promotional information testing apparatus according to another embodiment of the present application.

Detailed Description

The present application is further described with reference to the following figures and specific examples. The described embodiments should not be considered as limiting the present application, and all other embodiments obtained by a person skilled in the art without making any inventive step are within the scope of protection of the present application.

In the following description, reference is made to "some embodiments" which describe a subset of all possible embodiments, but it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict.

Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of the present application only and is not intended to be limiting of the application.

Before further detailed description of the embodiments of the present application, terms and expressions referred to in the embodiments of the present application will be described, and the terms and expressions referred to in the embodiments of the present application will be used for the following explanation.

1) An interactive application refers to an application that can provide a User Interface (UI) to a User for interactive operation, such as an instant messaging application, an information browsing application, and the like.

2) The promotion information bit entry is a skip port capable of entering a content page with a promotion information interface displayed. The interactive application may include a plurality of promotion information bit entries, for example, in some instant messaging applications, a social program promotion information bit entry, a public service platform promotion information bit entry, a portable application promotion information bit entry, a portable game program promotion information bit entry, and the like. Different promotion information bit entries can correspond to different promotion information interfaces. The social program is an application program which displays the information of the social friends in an information flow mode; the public service platform is a service platform capable of providing various service information and information for a target object; the portable application program refers to an application program which can be used without downloading and installing; the portable game program refers to a game program that can be used without downloading and installing.

3) The promotion information interface is a terminal screen interface used for displaying promotion information. The position and the range of the promotion information interface in the terminal screen are flexible, and the position and the range of the promotion information interface in the terminal screen can be set according to actual requirements. Different promotion information interfaces may have different interface elements.

4) The interface element refers to an information bearing element used for displaying the promotion information in the promotion information interface, wherein the promotion information may include pictures, texts, links, head portraits, nicknames, and the like. The interface elements constitute the interface style of the promotion information interface. The element information of the interface element comprises an element type, element position information and the like, wherein different element types bear different types of promotion information, and the element position information comprises position coordinates and ranges of the interface element in a promotion information interface.

5) Artificial Intelligence (AI) is a theory, method, technique and application system that uses a digital computer or a machine controlled by a digital computer to simulate, extend and expand human Intelligence, perceive the environment, acquire knowledge and use the knowledge to obtain the best results. In other words, artificial intelligence is a comprehensive technique of computer science that attempts to understand the essence of intelligence and produce a new intelligent machine that can react in a manner similar to human intelligence. Artificial intelligence is the research of the design principle and the realization method of various intelligent machines, so that the machines have the functions of perception, reasoning and decision making. The artificial intelligence technology is a comprehensive subject, and relates to the field of extensive technology, namely the technology of a hardware level and the technology of a software level. The artificial intelligence infrastructure generally includes technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technologies, operation/interaction systems, mechatronics, and the like. The artificial intelligence software technology mainly comprises a computer vision technology, a voice processing technology, a natural language processing technology, machine learning/deep learning and the like.

6) Machine Learning (ML) is a multi-domain cross discipline, relating to multi-domain disciplines such as probability theory, statistics, approximation theory, convex analysis, algorithm complexity theory and the like. The special research on how a computer simulates or realizes the learning behavior of human beings so as to acquire new knowledge or skills and reorganize the existing knowledge structure to continuously improve the performance of the computer. Machine learning is the core of artificial intelligence, is the fundamental approach for computers to have intelligence, and is applied to all fields of artificial intelligence. Machine learning and deep learning generally include techniques such as artificial neural networks, belief networks, reinforcement learning, transfer learning, inductive learning, and the like.

7) Deep Learning (DL) is a new research direction in the field of machine Learning, and is used for Learning the intrinsic regularity and expression level of sample data, and the information obtained in the Learning process is very helpful for the interpretation of data such as characters, images and sounds. The final aim of the method is to enable the machine to have the analysis and learning capability like a human, and to recognize data such as characters, images and sounds.

8) The block chain (Blockchain) is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, a consensus mechanism, an encryption algorithm and the like. The blockchain is essentially a decentralized database, which is a string of data blocks associated by using cryptography, each data block contains information of a batch of network transactions, and the information is used for verifying the validity (anti-counterfeiting) of the information and generating the next block. The blockchain may include a blockchain underlying platform, a platform product service layer, and an application service layer. The block chain underlying platform can comprise processing modules such as user management, basic service, intelligent contract and operation monitoring. The user management module is responsible for identity information management of all blockchain participants, and comprises public and private key generation maintenance (account management), key management, user real identity and blockchain address corresponding relation maintenance (authority management) and the like, and under the authorization condition, the user management module supervises and audits the transaction condition of certain real identities and provides rule configuration (wind control audit) of risk control; the basic service module is deployed on all block chain node equipment and used for verifying the validity of the service request, recording the service request to storage after consensus on the valid request is completed, for a new service request, the basic service firstly performs interface adaptation analysis and authentication processing (interface adaptation), then encrypts service information (consensus management) through a consensus algorithm, transmits the service information to a shared account (network communication) completely and consistently after encryption, and performs recording and storage; the intelligent contract module is responsible for registering and issuing contracts, triggering the contracts and executing the contracts, developers can define contract logics through a certain programming language, issue the contract logics to a block chain (contract registration), call keys or other event triggering and executing according to the logics of contract clauses, complete the contract logics and simultaneously provide the function of upgrading and canceling the contracts; the operation monitoring module is mainly responsible for deployment, configuration modification, contract setting, cloud adaptation in the product release process and visual output of real-time states in product operation, such as: alarm, monitoring network conditions, monitoring node equipment health status, and the like. The platform product service layer provides basic capability and an implementation framework of typical application, and developers can complete block chain implementation of business logic based on the basic capability and the characteristics of the superposed business. The application service layer provides the application service based on the block chain scheme to the business participants for use.

In order to meet the requirement of users for obtaining information, promotion information providers often push promotion information to users through various internet platforms and various push routes, for example, pushing advertisement information in specific pages of various applications. In order to enable a user to effectively acquire promotion information, a promotion information test is often required to determine whether the promotion information can be skipped normally. At present, most of popularization information testing operations are manually performed by testers, and the problems that the testing process is complicated, the workload is large, the repeated work is large, the testing efficiency is low, the testing effectiveness is not high and the like are easily caused exist. In order to solve the technical problem brought by manual testing, a popularization information testing mode based on Monkey testing is provided in the related art. The Monkey test can send a pseudo-random user event stream (such as key input, touch screen input, gesture input and the like) to an operating system of the terminal, so that the pressure test of the application is realized, namely, the operation of clicking or touching and the like can be randomly generated to simulate the operation of a user, and the pressure test of the application is realized. For example, a promotion information interface in a page is found, then interface elements in the promotion information interface are clicked in a simulated mode, whether the page jumps normally is checked, then the original page is returned, other interface elements which can be clicked in a simulated mode are clicked, whether the page jumps normally is checked again, and the like. However, the promotion information test method in the related art can only check whether the promotion information appears, whether the page can be skipped, and the like, and cannot check whether the content (for example, picture content) in the promotion information is correct and whether the skipped page is correct. In addition, the generalized information testing method in the related art only performs testing on a specific page, which is preset in a script program to be tested, for example, a Native (Native) page or a WebView page (WebView is a control for displaying a web page in an android system). When popularization information testing needs to be performed on different pages, corresponding modification needs to be performed on a tested script program, so that the popularization information testing mode in the related technology still has the problems of low testing efficiency, low testing effectiveness, low testing universality and the like to a certain extent.

In order to realize the automatic test of the promotion information and improve the test efficiency, test effectiveness and test universality of the promotion information test, the embodiment of the application provides a promotion information test method, a promotion information test device, a computer readable storage medium and a computer program product. The whole process of the promotion information test is executed in response to the test operation instruction, so that the test operation is not required to be manually performed by a tester, the automatic test of the promotion information is realized, and the test efficiency of the promotion information test can be improved; secondly, after the promotion information judgment result is determined that the content page contains the target promotion information, performing a trigger test on the target promotion information, namely, the trigger test performed each time is specific to the target promotion information, so that the test effectiveness of the promotion information test can be improved; in addition, after the trigger test is executed, the correctness test is also carried out on the screen display content, and whether the screen display content after the trigger test is executed is correct or not can be checked, so that the popularization information test is more effective; in addition, because the correctness test of the screen display content is realized according to the popularization information page detection model, a test script does not need to be set manually, and the test script does not need to be modified manually for different popularization information pages, the universality of the popularization information test can be improved.

Fig. 1 is a schematic diagram of an implementation environment provided by an embodiment of the present application. Referring to fig. 1, the implementation environment includes an operation terminal 101, a test terminal 102, and a server 103, and the server 103 is communicatively connected to the operation terminal 101 and the test terminal 102, respectively. The operation terminal 101, the test terminal 102, and the server 103 may be nodes in a block chain, which is not particularly limited in this embodiment.

The operation terminal 101 may be a terminal device such as a tablet computer, a notebook computer, a desktop computer, or the like, but is not limited thereto. Optionally, a test client is installed on the operation terminal 101, and the operation terminal 101 may perform a test such as clicking or touching on promotion information (for example, advertisement information) displayed in the test terminal 102 through the test client.

The test terminal 102 may be a tablet computer, a smart phone, a vehicle-mounted terminal, a smart watch, a smart bracelet, or other terminal devices, but is not limited thereto. The test terminal 102 and the operation terminal 101 may be directly or indirectly connected through wired or wireless communication, which is not limited in this embodiment of the present application.

The server 103 may be an independent physical server, a server cluster or a distributed system formed by a plurality of physical servers, or a cloud server providing basic cloud computing services such as a cloud service, a cloud database, cloud computing, a cloud function, cloud storage, a Network service, cloud communication, a middleware service, a domain name service, a security service, a CDN (Content Delivery Network), a big data and artificial intelligence platform.

As shown in fig. 2, fig. 2 is a software architecture diagram of the test terminal 102. Referring to fig. 2, the software architecture of the test terminal 102 includes a promotion information service unit, an automation service unit, an AI service unit, a notification service unit, a storage service unit, and the like.

The promotion information service unit can provide relevant basic services for normal operation of the application and provide relevant services of the promotion information, for example, the basic services include basic client services of the application, public service platform services, portable application program services and the like, and the relevant services of the promotion information include determining promotion information bit entries, selecting promotion information contents, acquiring the promotion information contents, rendering and displaying and the like.

The automatic service unit can provide UI automatic service and test automatic service, wherein the UI automatic service can automatically render and display the content of a UI interface; the test automation service enables automated testing of the test terminals 102. For example, when the test terminal 102 is a terminal of an android system, the popularization information test processing may be performed on the test terminal 102 by using a Uiautomator automation framework; when the test terminal 102 is a terminal of the iOS system, a webdrivegene automation framework may be used to perform the promotion information test processing on the test terminal 102. The Uiautomator automation framework is an automation testing tool for a terminal adopting an android system, and provides a library for an API (Application Programming Interface) to customize a UI test. The Webdriveragent automation framework is an open source framework which can be used for end-to-end UI testing, and can call an XCtest framework at the bottom of the iOS, and then the XCtest framework calls an API of the iOS system to execute a UI instruction.

The promotion information type prediction model can predict promotion information in the page, and the element information detection model can identify interface elements in the promotion information interface. In addition, the promotion information page detection model can identify the content of the page after the jump, identify whether the page after the jump is abnormal or not, and the like. In addition, the AI service unit can also train each AI model through a training sample, for example, train a promotion information prediction model and a promotion information page detection model by using the relevant information acquired in the promotion information test process as the training sample.

And the notification service unit can perform report notification when the promotion information test is finished, or perform alarm notification when the promotion information test is abnormal, for example, perform report notification or alarm notification to a tester by means of mails, instant messaging information and the like.

The storage service unit can store relevant information of the test terminal 102 in the promotion information test process, for example, store a promotion information interface screenshot in the promotion information test process, a promoted information page screenshot after jumping, and the like.

The operation terminal 101 at least has a function of performing a click test or a touch test on the promotion information displayed in the test terminal 102, for example, an operation instruction can be sent to the test terminal 102 in response to an operation of a user in the test client, so that the test terminal 102 can perform a click test or a touch test on the promotion information displayed thereon. In addition, the operation terminal 101 has functions of downloading a test result, generating a test report according to the test result, displaying the test report, and providing a download path of the test report, for example, after the promotion information test is completed, the operation terminal 101 may download the test result from the server 103, generate the test report according to the test result, and after the operation terminal 101 generates the test report, may display the test report or provide the download path of the test report to the user.

The test terminal 102 has at least functions of entering a content page through a target promotion information bit entry according to an operation instruction sent by the operation terminal 101, performing promotion information judgment processing on the content page, performing click test or touch test on target promotion information in the content page, judging the correctness of a page after the content page jumps, and the like, for example, the test terminal can respond to a test operation instruction sent by the operation terminal 101, enter the content page through the target promotion information bit entry, then perform promotion information judgment processing on the content page to obtain a promotion information judgment result, when the promotion information judgment result is that the content page contains the target promotion information, perform a trigger test on the target promotion information, intercept screen display content to obtain a first page image after performing the trigger test, input the first page image to a promotion information page detection model to obtain a first detection result, and then determine the correctness of the first page image according to the first detection result. In addition, the test terminal 102 can also store screenshot information such as the first page image, and perform model training on a promotion information page detection model and the like by using the screenshot information. Further, after the promotion information test is completed, the test terminal 102 can also transmit the test results to the server 103, so that the server 103 can save the test results so that the test results can be transmitted according to the request of the operation terminal 101.

The server 103 at least has functions of receiving and storing the test result sent by the test terminal 102, allowing the operation terminal 101 to download the test result, and the like, and for example, can send the test result uploaded by the test terminal 102 to the operation terminal 101 in response to an information download request sent by the operation terminal 101, so that the operation terminal 101 can generate a test report according to the test result, display the test report, or provide a download path of the test report to a user. In addition, the server 103 also stores contents such as an AID (promotional Identity Document), promotional information bit information corresponding to the AID, and a promotional information text corresponding to the AID, and the server 103 can transmit the corresponding contents such as the promotional information bit information and the promotional information text to the operation terminal 101 or the test terminal 102 in response to an information acquisition request including the AID transmitted from the operation terminal 101 or the test terminal 102.

In an alternative implementation manner, the operation terminal 101 is a desktop computer installed with a test client, and the test terminal 102 is a smart phone. In response to the test operation of the user in the test client, the operation terminal 101 sends a test operation instruction to the test terminal 102, wherein the test operation instruction comprises a promotion information identifier; in response to the test operation instruction, the test terminal 102 acquires corresponding promotion information bit entry information from the server 103 according to the promotion information identifier, determines a target promotion information bit entry according to the promotion information bit entry information, then enters a content page through the target promotion information bit entry, then performs promotion information judgment processing on the content page to obtain a promotion information judgment result, when the promotion information judgment result indicates that the content page contains target promotion information, the test terminal 102 performs a trigger test on the target promotion information, after the trigger test is performed, the test terminal 102 intercepts screen display content to obtain a first page image, then inputs the first page image to a promotion information page detection model to obtain a first detection result, then determines the correctness of the first page image according to the first detection result, and after the promotion information test is completed, the test terminal 102 sends the test result to the server 103; in response to receiving the test result sent by the test terminal 102, the server 103 saves the test result; in response to the information downloading request sent by the operation terminal 101, the server 103 issues the test result to the operation terminal 101, so that the operation terminal 101 can generate a test report according to the test result; in response to receiving the test results sent by the server 103, the operation terminal 101 generates a test report according to the test results, and after the operation terminal 101 generates the test report, the test report may be displayed or a download path of the test report may be provided to the user.

In another alternative implementation manner, the operation terminal 101 is a desktop computer installed with a test client, and the test terminal 102 is a smart phone. In response to a test operation of a user in a test client, the operation terminal 101 sends promotion information bit request information to the server 103, wherein the promotion information bit request information includes a promotion information identifier; in response to the promotion information bit request message, the server 103 obtains corresponding promotion information bit entry information according to the promotion information identifier, and returns the promotion information bit entry information to the operation terminal 101; in response to receiving the promotion information bit entry information, the operation terminal 101 sends a test operation instruction including the promotion information bit entry information to the test terminal 102; in response to the test operation instruction, the test terminal 102 determines a target promotion information bit entry according to the promotion information bit entry information, then enters a content page through the target promotion information bit entry, then carries out promotion information judgment processing on the content page to obtain a promotion information judgment result, when the promotion information judgment result indicates that the content page contains target promotion information, the test terminal 102 executes a trigger test on the target promotion information, after the trigger test is executed, the test terminal 102 intercepts screen display content to obtain a first page image, then inputs the first page image to a promotion information page detection model to obtain a first detection result, then determines the correctness of the first page image according to the first detection result, and after the promotion information test is completed, the test terminal 102 sends the test result to the server 103; in response to receiving the test result sent by the test terminal 102, the server 103 saves the test result; in response to the information downloading request sent by the operation terminal 101, the server 103 issues the test result to the operation terminal 101, so that the operation terminal 101 can generate a test report according to the test result; in response to receiving the test results sent by the server 103, the operation terminal 101 generates a test report according to the test results, and after the operation terminal 101 generates the test report, the test report may be displayed or a download path of the test report may be provided to the user.

Fig. 3 is a flowchart of a method for testing promotional information according to an embodiment of the present application. In the present embodiment, the test terminal 102 in fig. 1 is taken as an example of an execution subject. Referring to fig. 3, the promotional information testing method includes, but is not limited to, steps 110 to 160.

Step 110: and responding to the test operation instruction, and entering a content page through a target promotion information bit entry.

In this step, when a test operation instruction from the operation terminal is received, the content page can be entered through the target promotion information bit entry in response to the test operation instruction, so that the promotion information in the content page can be subjected to operations such as click test or touch test in subsequent steps, and the purpose of executing the promotion information test is achieved.

It should be noted that the target promotion information bit entry is a promotion information bit entry in the interactive application, in some embodiments, the interactive application may include a plurality of promotion information bit entries, the target promotion information bit entry may be one randomly selected from the plurality of promotion information bit entries, or may be a specific one of the plurality of promotion information bit entries, which is not limited in this embodiment. For example, when the test operation instruction includes the promotion information bit entry, the target promotion information bit entry is a specific promotion information bit entry determined among the plurality of promotion information bit entries according to the promotion information identification. In a specific example, assuming that a certain instant messaging application has 4 types of promotion information bit entries, namely, a public service platform promotion information bit entry, a portable application program promotion information bit entry, a portable game program promotion information bit entry and a social program promotion information bit entry, wherein different types of promotion information bit entries may correspond to different promotion information bit entry numbers, then one of the promotion information bit entries may be randomly selected as a target promotion information bit entry, or a corresponding target promotion information bit entry may be determined in the promotion information bit entries according to a promotion information identifier.

It should be noted that, for different promotion information bit entries, different ways may be used to enter the corresponding content page. For example, for a social program promotion information site entry, the social program page may be entered through a social program option of the instant messaging application. At this time, if the social program page is refreshed, as shown in fig. 4, a promotion information interface 104 for showing promotion information may be displayed in the social program page. For another example, for a public service platform promotion information bit entry, a public service platform option may be found in a main page of the instant messaging application, then the public service platform option is clicked to enter the main page of the public service platform, and then a specific service account in the main page of the public service platform is clicked to enter a specific information page. At this time, as shown in fig. 5, a promotion information interface 104 for displaying promotion information may be displayed in the information page.

Step 120: and carrying out promotion information judgment processing on the content page to obtain a promotion information judgment result.

It should be noted that the content page entered through the target promotion information bit entry does not necessarily contain promotion information, and therefore, in order to effectively perform subsequent promotion information test operation, in this step, after entering the content page through the target promotion information bit entry, promotion information determination processing may be performed on the content page to obtain a promotion information determination result, so that the subsequent step may determine whether to perform promotion information test operation according to the promotion information determination result. For example, when the promotion information judgment result indicates that the content page contains promotion information, the subsequent steps can execute test operation on the promotion information in the content page; and if the promotion information judgment result is that the content page does not contain the promotion information, exiting the current promotion information test operation.

It should be noted that, different embodiments may be used to perform the promotion information judgment processing on the content page to obtain the promotion information judgment result, and this embodiment is not particularly limited in this respect. For example, when the promotion information is advertisement information, whether the content page contains text information in the form of "advertisement" can be identified through a Character Recognition (OCR) technology, and if the content page contains the text information in the form of "advertisement", a promotion information judgment result that the content page contains the promotion information can be obtained; if the content page is identified to contain no text information of the words of 'advertisement', a promotion information judgment result that the content page contains no promotion information can be obtained. If the prediction result is that the screenshot image contains the promotion information, a promotion information judgment result of the content page containing the promotion information can be obtained; if the prediction result is that the screenshot image does not contain the promotion information, a promotion information judgment result that the content page does not contain the promotion information can be obtained.

Step 130: and when the promotion information judgment result shows that the content page contains the target promotion information, executing a trigger test on the target promotion information.

In this step, since the promotion information determination result is obtained in step 120, when the promotion information determination result indicates that the content page contains the target promotion information, it indicates that the promotion information displayed in the content page is correct, so that the trigger test can be performed on the target promotion information in the content page, so that the correctness of the trigger test can be further checked in the subsequent steps, and the promotion information test is more effective, wherein the trigger test is used for skipping the content page.

It should be noted that, because the popularization information interface is a terminal screen interface for displaying the popularization information, when it is determined that the content page contains the target popularization information, it is described that the content page contains the popularization information interface for displaying the target popularization information, so the test terminal can generate a trigger information in the popularization information interface, simulate a click operation or a touch operation of a user, perform a trigger test on the target popularization information, and achieve the purpose of performing the popularization information test. For example, when the test terminal is a terminal of an android system, the test terminal may trigger the Uiautomator automation framework to perform promotion information test processing on the target promotion information; when the test terminal is the terminal of the iOS system, the test terminal can adopt a Webdriveragent automation framework to carry out promotion information test processing on the target promotion information.

It should be noted that the trigger test executed on the target popularization information may specifically be different test operations, and this embodiment does not specifically limit this. For example, when the trigger information generated by the test terminal simulates the click operation of the user, the trigger test is a click test; for another example, when the trigger information generated by the test terminal simulates the touch operation of the user, the trigger test performed is a touch test.

Step 140: after the trigger test is executed, screen display content is intercepted to obtain a first page image.

It should be noted that although the trigger test is performed on the target popularization information in step 130, it cannot be determined whether the content page is skipped or whether the skipped screen display content is correct, and in order to solve these problems, in this step, after the trigger test is performed, the screen display content is intercepted to obtain the first page image, so that the subsequent step can determine whether the content page is skipped or the skipped screen display content is correct according to the first page image, thereby enabling the popularization information test to be more complete and effective.

Step 150: and inputting the first page image to the promotion information page detection model to obtain a first detection result of the page elements in the first page image.

It should be noted that a page element refers to an information bearing element in a page for displaying page information, where the page information may include a picture, a text, a link, an avatar, a nickname, and the like. An information bearing element is an element that exhibits information content. The element information of the page element includes an element type, element position information, and the like, wherein different element types carry different types of information content, that is, different element types correspond to different information carrying elements. The element position information includes position coordinates and a range of the page element in the page.

In this step, since the first page image is obtained in step 140, the first page image may be input to the promotion information page detection model to obtain a first detection result of the page element in the first page image, so that the subsequent step may determine whether the content page has executed the jump or whether the screen display content after the jump is correct according to the first detection result, thereby enabling the promotion information test to be more complete and effective.

It should be noted that the promotion information page detection model may be implemented by different algorithms, which is not specifically limited in this embodiment. For example, the promotion information page detection model may be implemented by a conventional deep neural network algorithm, and the output first detection result may be a classification value (e.g., 1 or 0), and the subsequent step may determine the correctness of the first page image according to the classification value; for another example, the promotion information page detection model may be implemented by a YOLO (young Only Look Once) algorithm, the output first detection result may be a page style of the first page image, and the subsequent step may determine the correctness of the first page image according to the page style of the first page image and a page style of a pre-stored promotion information page.

It should be noted that, the YOLO algorithm applies a single Convolutional Neural Network (CNN) to the entire image, divides the entire image into a plurality of grids, and predicts the class probability and the size of the object bounding box corresponding to each grid. The output of the YOLO algorithm may include the center coordinate value of the object bounding box, the height value of the object bounding box, the width value of the object bounding box, and the object class of the recognized object, and thus, the YOLO algorithm can be used to detect objects in the image. In addition, the YOLO algorithm may also predict a probability that an object exists in the object bounding box, and if the probability is greater than or equal to a preset probability threshold, it may be considered that a corresponding object is recognized, and if the probability is less than the preset probability threshold, it may be considered that a corresponding object is not recognized, so the YOLO algorithm can be used to implement prediction processing on an image.

It should be noted that the first page image obtained in the promotional information testing process can also be used as a training sample of the promotional information page detection model to train the promotional information page detection model, so as to improve the detection accuracy of the promotional information page detection model. For example, after the content displayed on the screen is captured to obtain a first page image, a first type tag may be added to the first page image, then the first page image is subjected to first feature labeling processing according to the first type tag, and then the first page image subjected to the first feature labeling processing is used as a training sample of the promotion information page detection model to train the promotion information page detection model. The first page image obtained in the promotion information testing process can be used as a training sample of the promotion information page detection model, so that the number and the types of the training samples of the promotion information page detection model can be effectively expanded, and the detection accuracy of the promotion information page detection model can be improved.

Step 160: and determining the correctness of the first page image according to the first detection result and page elements of a preset target promotion information page.

In this step, since the first detection result is obtained in step 150, the correctness of the first page image can be determined according to the first detection result and the page elements of the preset target promotion information page, so that the promotion information test is more complete and effective.

In an optional implementation manner, assuming that the promotion information page detection model is implemented by a conventional deep neural network algorithm, and the first detection result output by the promotion information page detection model is a classification value (such as 1 or 0), when the first detection result is 1, the skipped screen display content can be considered to be a correct promotion information page, that is, the first page image can be determined to be correct, and meanwhile, the content page can be determined to normally perform the skipping; when the first detection result is 0, it can be considered that the content page fails to perform the jump normally, or the screen display content after the jump is not the correct promotion information page, that is, it can be determined that the first page image is wrong.

In another optional implementation, the promotion information page detection model is implemented by a YOLO algorithm, and the output first detection result is the page style of the first page image, so that when the page style of the first page image is consistent with the page style of a pre-stored target promotion information page (which can be determined according to page elements of the target promotion information page), the skipped screen display content can be considered as a correct promotion information page, that is, the first page image can be determined to be correct, and meanwhile, the content page can be determined to have normally performed the skipping; when the page style of the first page image is inconsistent with the page style of the pre-stored promotion information page, it can be considered that the content page fails to perform the jump normally, or the display content of the screen after the jump is not the correct promotion information page, that is, it can be determined that the first page image is wrong.

In this embodiment, by using the popularization information testing method including the foregoing steps 110 to 160, after a test operation instruction is received, the content page is entered through the target popularization information bit entry, then, the popularization information is judged and processed on the content page, a popularization information judgment result is obtained, when the popularization information judgment result indicates that the content page contains the target popularization information, a trigger test is performed on the target popularization information, after the trigger test is performed, the screen display content is intercepted, a first page image is obtained, the first page image is input to the popularization information page detection model, a first detection result is obtained, and then, the correctness of the first page image is determined according to the first detection result. The whole process of the promotion information test is executed in response to the test operation instruction, so that the test operation is not required to be manually performed by a tester, the automatic test of the promotion information is realized, and the test efficiency of the promotion information test can be improved; secondly, after the promotion information judgment result is determined that the content page contains the target promotion information, performing a trigger test on the target promotion information, namely, the trigger test performed each time is specific to the target promotion information, so that the test effectiveness of the promotion information test can be improved; in addition, after the trigger test is executed, the correctness test is also carried out on the screen display content, whether the screen display content after the trigger test is executed is correct or not can be checked, and the promotion information test is more effective; in addition, because the correctness test of the screen display content is realized according to the popularization information page detection model, a test script does not need to be set manually, and the test script does not need to be modified manually for different popularization information pages, the universality of the popularization information test can be improved.

Referring to fig. 6, in an embodiment of the present application, step 160 is further described, and step 160 may include, but is not limited to, step 161 and step 162.

Step 161: and comparing the first detection result with page elements of a preset target promotion information page to obtain a first comparison result.

In this step, since the first detection result is obtained in step 150, the first detection result may be compared with page elements of a preset target popularization information page to obtain a first comparison result, so that the correctness of the first page image may be determined according to the first comparison result in subsequent steps, and the popularization information test is more complete and effective.

It should be noted that the target promotion information page is a jump page corresponding to the target promotion information in the content page, which is pre-stored before the promotion information test operation is performed. For example, the target promotion information in the content page corresponds to a jump link, and when the target promotion information in the content page is clicked, the content page jumps to the target promotion information page pointed by the jump link. Before the promotion information test operation is executed, the target promotion information page can be stored, when the promotion information test operation is executed, when the trigger test on the promotion information in the content page is completed, the screen display content can be intercepted to obtain a first page image, the first page image is input to a promotion information page detection model to obtain a first detection result, and then the first detection result is compared with the page elements of the target promotion information page.

It should be noted that, different embodiments may be implemented by comparing the first detection result with a page element of a preset target promotion information page, and this embodiment is not limited in this respect. For example, when the first detection result includes page element type detection information, the page element type detection information may be compared with page element type information of a preset target promotion information page; when the first detection result includes page element layout detection information, the page element layout detection information may be compared with page element layout information of a preset target promotion information page; when the first detection result includes the page element type detection information and the page element layout detection information, any one of the page element type detection information and the page element layout detection information may be compared with a preset target promotion information page, and when the comparison result is consistent, the remaining one of the page element type detection information and the page element layout detection information may be compared with the target promotion information page.

It should be noted that the page element type information includes a text type, a picture type, a video type, and the like, where the text type refers to an element type using the text information as main content, the picture type refers to an element type using the picture information as main content, and the video type refers to an element type using the video information as main content. The page element layout information refers to layout style information of page elements in a page.

Step 162: and determining the correctness of the first page image according to the first comparison result.

In this step, since the first comparison result is obtained in step 161, it can be determined whether the first page image is the skipped page image according to the first comparison result, and it can be determined whether the content of the first page image is correct, so that the promotion information test is more complete and effective.

It should be noted that, different embodiments may be used to determine the correctness of the first page image according to the first comparison result, and this embodiment is not limited in this respect. For example, when the first comparison result is that the first detection result is consistent with the page elements of the target promotion information page, it may be determined that the first page image is a correct page image; when the first comparison result is that the first detection result is inconsistent with the page element of the target promotion information page, it may be determined that the first page image is an erroneous page image, it should be noted that the first page image is an erroneous page image, and specifically there may be two cases, one of which is that the content page is not jumped, that is, the first page image is a screenshot image of the content page; the other is that the content page is jumped, but the screen display content after the jump is not the target promotion information page. Therefore, in this embodiment, the first detection result is compared with the page elements of the preset target popularization information page to obtain a first comparison result, and then the correctness of the first page image is determined according to the first comparison result, so that the technical problem that whether the content page performs the jump or not or whether the screen display content after the jump is correct or not cannot be determined in the related art can be solved, and the popularization information test is more complete and effective.

Referring to fig. 7, in an embodiment of the present application, step 120 is further described, and step 120 may include, but is not limited to, steps 121 to 123.

Step 121: and intercepting the content page to obtain a second page image.

It should be noted that, after entering the content page through the target promotion information bit entry, the content page is the current screen display content, and since the current screen display content may be dynamic and is not beneficial to performing promotion information judgment processing on the content page, in this step, the content page may be captured first to obtain a second page image, so that subsequent steps may perform promotion information judgment processing according to the second page image.

Step 122: and inputting the second page image into the promotion information type prediction model to obtain a second prediction result.

In this step, since the second page image is obtained in step 121, the second page image may be input to the promotion information type prediction model to obtain a second prediction result, so that a promotion information determination result may be obtained according to the second prediction result in a subsequent step.

It should be noted that the popularization information type prediction model may be implemented by different algorithms, and this embodiment is not limited in this respect. For example, the promotion information type prediction model may be implemented by a conventional deep neural network algorithm, and the output second prediction result may be a classification value (e.g., 1 or 0), and when the second prediction result is 1, it may be determined that the second page image contains promotion information corresponding to the target promotion information type; when the second prediction result is 0, it may be determined that the second page image does not contain popularization information or does not contain popularization information corresponding to the target popularization information type. For another example, the promotion information type prediction model may be implemented by a YOLO algorithm, and the output second prediction result may include a promotion information prediction type and a confidence level, and when the confidence level meets a preset condition, for example, the confidence level is greater than or equal to a confidence level threshold, it may be determined that the second page image contains promotion information, and the promotion information type of the promotion information is consistent with the promotion information prediction type; when the confidence coefficient does not meet the preset condition, for example, when the confidence coefficient is smaller than a confidence coefficient threshold value, it may be determined that the second page image does not contain the promotion information, or the second page image contains the promotion information, but the promotion information type of the promotion information is not consistent with the promotion information prediction type.

It should be noted that the promotion information prediction type refers to a promotion information type that may be included in the second page image, where the promotion information type includes a banner promotion information type, a screen insertion promotion information type, a cover promotion information type, a video stream promotion information type, and the like. The banner popularization information type refers to a rectangular popularization information type stretching across a webpage, and when the rectangular popularization information is clicked, the banner popularization information type can be linked to the webpage of a popularization information provider; the screen insertion promotion information type refers to a promotion information type which is popped up in a half-screen or full-screen mode when the application is started, paused or quitted, and the normal experience of a user on the application can not be influenced; the front cover popularization information type refers to a popularization information type displayed in an immersive full screen mode when an application program is opened, and information such as a head portrait and a name of a popularization information provider can be displayed below the front cover popularization information; the video stream promotion information type is one of the information stream promotion information types, the display form is video content, and the video stream promotion information integrates products or services into the promotion information in a video mode, for example, a commodity mark or a commodity pattern appears at a certain corner in a video.

It should be noted that the second page image obtained in the promotional information testing process can also be used as a training sample of the promotional information type prediction model to train the promotional information type prediction model, so as to improve the prediction accuracy of the promotional information type prediction model. For example, after a content page is intercepted to obtain a second page image, a second type label may be added to the second page image, then second feature labeling processing is performed on the second page image according to the second type label, and then the second page image subjected to the second feature labeling processing is used as a training sample of the popularization information type prediction model to perform training processing on the popularization information type prediction model. The second page image obtained in the promotion information testing process can be used as a training sample of the promotion information type prediction model, so that the quantity and the type of the training sample of the promotion information type prediction model can be effectively expanded, and the improvement of the prediction accuracy of the promotion information type prediction model is facilitated.

Step 123: and when the second page image is determined to contain the first popularization information according to the second prediction result, performing information judgment processing on the first popularization information to obtain a popularization information judgment result.

In this step, since the second prediction result is obtained in step 122, it can be determined whether the second page image contains the promotion information according to the second prediction result. Under the condition that the second page image is determined to contain the first promotion information according to the second prediction result, the first promotion information is not necessarily the target promotion information, so that information judgment processing can be carried out on the first promotion information to obtain a promotion information judgment result, and whether promotion information test operation can be carried out on the target promotion information or not can be determined according to the promotion information judgment result in the subsequent step.

It should be noted that, the information judgment processing on the first popularization information may have different embodiments, and may be adaptively selected according to the actual application situation, which is not specifically limited in this embodiment. For example, in the case that the first promotion information takes text information as main content, the text information in the first promotion information may be extracted first, and then the text information and preset target text information are subjected to information judgment processing; for another example, in a case that the first popularization information takes the picture information as a main content, the picture information in the first popularization information may be identified first, and then the picture information and preset target picture information may be subjected to information judgment processing.

Referring to fig. 8, in an embodiment of the present application, the determining that the second page image contains the first popularization information according to the second prediction result in step 123 is further described, and in a case that the second prediction result includes a popularization information prediction type and a confidence, the determining that the second page image contains the first popularization information according to the second prediction result in step 123 may specifically include, but is not limited to, step 1231 and step 1232.

Step 1231: and comparing the confidence with a confidence threshold to obtain a second comparison result.

It should be noted that, when the second prediction result includes the promotion information prediction type and the confidence, it is described that the second page image may include promotion information corresponding to the target promotion information type, but may not include promotion information corresponding to the target promotion information type, and whether the second page image includes promotion information corresponding to the target promotion information type or not needs to be determined according to the confidence. Therefore, in this step, the confidence level may be compared with the confidence level threshold value to obtain a second comparison result, and then it is determined whether the second page image contains the promotion information corresponding to the target promotion information type in the subsequent steps according to the second comparison result.

It should be noted that the confidence threshold is a preset threshold, and may be appropriately selected according to the actual application, which is not specifically limited in this embodiment, for example, the confidence threshold may be set to 0.5.

Step 1232: and when the second comparison result is that the confidence coefficient is greater than or equal to the confidence coefficient threshold value, determining that the second page image contains the first promotion information, and the promotion information type of the first promotion information is consistent with the promotion information prediction type.

In this step, since the second comparison result is obtained in step 1231, it can be determined whether the second page image contains the promotion information corresponding to the target promotion information type according to the second comparison result. When the second comparison result is that the confidence degree is greater than or equal to the confidence degree threshold value, it can be determined that the second page image contains the first popularization information, and the popularization information type of the first popularization information is consistent with the popularization information prediction type, so that information judgment processing can be performed on the first popularization information in subsequent steps to obtain a popularization information judgment result, and whether popularization information test operation is performed or not can be determined according to the popularization information judgment result.

It should be noted that, when the second comparison result is that the confidence is smaller than the confidence threshold, it may be determined that the second page image does not contain the promotion information, or the second page image does not contain the promotion information corresponding to the promotion information prediction type, at this time, the promotion information test operation may be exited, so as to avoid performing an invalid promotion information test operation, and improve the effectiveness of the promotion information test.

Referring to fig. 9, in an embodiment of the present application, further describing step 123, in the case that it is determined that the second page image contains the first popularization information according to the second prediction result, and the test operation instruction includes the popularization information identifier, and the first popularization information includes the popularization information text, step 123 may include, but is not limited to, step 1233 to step 1236.

Step 1233: performing information identification processing on the first popularization information to obtain a popularization information text;

step 1234: sending a promotion information identifier to a server, so that the server acquires target text information according to the promotion information identifier;

step 1235: receiving target text information sent by a server;

step 1236: and comparing the promotion information text with the target text information, and when the promotion information text is consistent with the target text information, performing element information judgment processing on the first promotion information to obtain a promotion information judgment result.

It should be noted that, although it is determined according to the second prediction result that the second page image contains the first promotional information, it is unclear whether the first promotional information is the target promotional information required for the promotional information test, in order to perform the promotional information test more accurately, in this embodiment, the promotional information text in the first promotional information is identified, and then the promotional information text is compared with the target text information of the target promotional information, and when the two are consistent, it is indicated that the first promotional information is likely to be the target promotional information, and then the element information judgment processing may be performed on the first promotional information, so as to obtain a promotional information judgment result whether the content page contains the target promotional information, so that the subsequent step may determine whether to perform the promotional information test operation according to the promotional information judgment result. Specifically, since the test operation instruction includes the promotion information identifier, which is identification information of target promotion information required for performing promotion information test, in order to determine whether the first promotion information is the target promotion information, in this embodiment, information identification processing may be performed on the first promotion information to obtain a promotion information text, and then the promotion information identifier may be sent to the server, so that the server may obtain target text information according to the promotion information identifier, and then receive the target text information sent by the server. In addition, if the promotion information text is inconsistent with the target text information, it is indicated that the first promotion information is not the target promotion information required for promotion information test, and at this time, the promotion information test operation can be quitted, so as to avoid invalid promotion information test operation, and improve the effectiveness of promotion information test.

It should be noted that, different embodiments may be provided for performing information identification processing on the first popularization information to obtain the popularization information text, and this embodiment is not limited in this respect. For example, in an optional implementation manner, interface elements in the first popularization information may be traversed, whether the interface elements in the first popularization information include a target interface element for displaying text information is identified, and when the target interface element is identified, text information in the target interface element is extracted, so as to obtain a popularization information text. For another example, in another optional implementation, the text information in the first promotion information may be recognized through an OCR technology to obtain the promotion information text.

It should be noted that the server may store different promotion information identifiers, different promotion information bit information, different text information of promotion information, and the like, where the promotion information identifiers, the promotion information bit information, and the text information of the promotion information correspond to each other, for example, for a certain promotion information identifier, a promotion information bit information and a text information of promotion information correspond to each other. Therefore, after the server receives the promotion information identifier, the server can acquire the text information of the corresponding promotion information according to the promotion information identifier.

Referring to fig. 10, an embodiment of the present application further describes that "performing element information determination processing on first popularization information to obtain a popularization information determination result" in step 1236, and "performing element information determination processing on first popularization information to obtain a popularization information determination result" in step 1236 may include, but is not limited to, step 12361 and step 12362.

Step 12361: inputting the second page image into the element information detection model to obtain a third detection result;

step 12362: and comparing the third detection result with preset target element information, and when the third detection result is consistent with the target element information, obtaining a promotion information judgment result that the first promotion information is the target promotion information.

It should be noted that, although the comparison between the promotion information text and the target text information obtains a result that the promotion information text is consistent with the target text information, it only indicates that the text information (e.g., the content of the document) in the first promotion information is the same as the text information (e.g., the content of the document) of the target promotion information required for the promotion information test, however, the interface style of the promotion information interface may be different for two promotion information having the same text information, and the coordinate positions of the interface elements in different interface styles are also different, so that the two promotion information having the same text information are not necessarily the same promotion information, and therefore, in order to determine whether the first promotion information is the target promotion information required for the promotion information test, and in order to perform the promotion information test more accurately, in this embodiment, the second page image may be input into the element information detection model to obtain a third detection result, then the third detection result may be compared with the preset target element information, and when the third detection result is consistent with the target element information, the first promotion information may be the promotion information.

It should be noted that the element information detection model may be implemented by a YOLO algorithm, and the output third detection result may include element detection information of an interface element of the first popularization information in the second page image, for example, including element coordinate detection information, element length detection information, element width detection information, and the like, where the element coordinate detection information may be center coordinate detection information of an element or corner coordinate detection information of an element, and therefore, by comparing the element detection information with preset target element information, it may be determined whether the element detection information is consistent with preset target element information, and when it is determined that the element detection information is consistent with preset target element information, a popularization information determination result may be obtained that the first popularization information is target popularization information. In a specific example, assuming that the first popularization information in the second page image includes an interface element a and an interface element B, after the second page image is input to the element information detection model, the element coordinate detection information, the element length detection information, and the element width detection information of the interface element a, and the element coordinate detection information, the element length detection information, and the element width detection information of the interface element B are obtained, and then, these pieces of detection information are compared with preset target element information, where the preset target element information includes the element coordinate information, the element length information, and the element width information of a plurality of interface elements, and when these pieces of detection information can find out the same content in the preset target element information, the first popularization information in the second page image can be considered as the target popularization information required for the popularization information test.

It should be noted that the second page image obtained in the process of popularizing the information test can also be used as a training sample of the element information detection model to train the element information detection model, so as to improve the detection accuracy of the element information detection model. For example, after a content page is intercepted to obtain a second page image, a third type tag may be added to the second page image, then third feature labeling processing is performed on the second page image according to the third type tag, and then the second page image subjected to the third feature labeling processing is used as a training sample of the element information detection model to perform training processing on the element information detection model. The second page image obtained in the process of popularizing the information test can be used as a training sample of the element information detection model, so that the quantity and the type of the training sample of the element information detection model can be effectively expanded, and the detection accuracy of the element information detection model is improved.

Referring to fig. 11, in an embodiment of the present application, step 130 is further described, and step 130 may include, but is not limited to, step 131 to step 133.

Step 131: inputting the second page image into the trigger area prediction model to obtain trigger area prediction information of the target popularization information;

step 132: determining a trigger area in the target popularization information according to the trigger area prediction information;

step 133: and executing the trigger test according to the trigger area.

In this embodiment, after the promotion information determination processing is performed on the content page in the execution step 120 to obtain the promotion information determination result, when the promotion information determination result indicates that the content page contains the target promotion information, the trigger test may be performed on the target promotion information. However, since the target popularization information may include contents such as picture information, text information, link information, avatar information, and nickname information, where the text information may not be generally linked to other pages, and the picture information, the link information, the avatar information, and the nickname information may be generally linked to different pages, for example, the picture information and the link information may be linked to a popularization information page, and the avatar information and the nickname information may be linked to a popularization information provider profile page, it is necessary to identify linkable information in the target popularization information, and then the popularization information test operation may be accurately performed through the linkable information. Since the interface element is an information bearing element for displaying the promotion information, the trigger area in the target promotion information is identified, and the linkable information in the target promotion information can be effectively identified, so in this embodiment, the second page image can be input into the trigger area prediction model to obtain the trigger area prediction information of the target promotion information, then the trigger area in the target promotion information is determined according to the trigger area prediction information, and then the trigger test is executed according to the trigger area, so that the purpose of accurately executing the promotion information test operation is achieved.

It should be noted that the trigger area prediction model may be implemented by a YOLO algorithm, and the output trigger area prediction information may include area coordinate prediction information, area length prediction information, area width prediction information, and the like of the trigger area, where the area coordinate prediction information may be center coordinate prediction information of the trigger area or corner coordinate prediction information of the trigger area, and therefore, the trigger area in the target popularization information may be determined according to the trigger area prediction information, so that the trigger test may be executed according to the trigger areas, and the test effectiveness of the popularization information test may be improved.

It should be noted that the second page image obtained in the process of popularizing the information test can also be used as a training sample of the trigger area prediction model to train the trigger area prediction model, so as to improve the prediction accuracy of the trigger area prediction model. For example, after a content page is intercepted to obtain a second page image, a fourth type label may be added to the second page image, then fourth feature labeling processing is performed on the second page image according to the fourth type label, and then the second page image subjected to the fourth feature labeling processing is used as a training sample of the trigger area prediction model to perform training processing on the trigger area prediction model. The second page image obtained in the process of popularizing information testing can be used as a training sample of the trigger area prediction model, so that the quantity and the type of the training sample of the trigger area prediction model can be effectively expanded, and the prediction accuracy of the trigger area prediction model is favorably improved.

Referring to fig. 12, in an embodiment of the present application, step 110 is further described, and in a case that the test operation instruction includes the promotion information identifier, step 110 may include, but is not limited to, step 111 to step 114.

Step 111: responding to the test operation instruction, sending a promotion information identifier to the server, and enabling the server to obtain target promotion information bit information according to the promotion information identifier;

step 112: receiving target promotion information bit information sent by a server;

step 113: determining a target promotion information bit entry according to the target promotion information bit information;

step 114: and entering a content page through a target promotion information bit entry.

In this embodiment, under the condition that the test operation instruction includes the promotion information identifier, the target promotion information bit entry required for the promotion information test may be determined according to the promotion information identifier, and then the corresponding content page may be entered through the target promotion information bit entry, so that the corresponding promotion information test operation may be performed in the subsequent step. Because the promotion information identifier, the promotion information bit information corresponding to the promotion information identifier, the promotion information text corresponding to the promotion information identifier and the like can be stored in the server, under the condition that a test operation instruction including the promotion information identifier sent by the operation terminal is received, the promotion information identifier can be sent to the server in response to the test operation instruction, so that the server obtains the corresponding target promotion information bit information according to the promotion information identifier, then the target promotion information bit information sent by the server is received, then the corresponding target promotion information bit inlet is determined according to the target promotion information bit information, and then the corresponding content page is entered through the target promotion information bit inlet, so that the corresponding promotion information test operation can be executed according to the content page in the subsequent step.

In addition, in an embodiment of the present application, the promotion information testing method is further described, and after the step 160 is executed, the promotion information testing method may further include, but is not limited to, the following steps:

executing the trigger test on the target promotion information again;

after the trigger test is executed again, screen display content is intercepted again to obtain a new first page image;

inputting the new first page image to the promotion information page detection model to obtain a new first detection result;

and determining the correctness of the new first page image according to the new first detection result until the number of times of the trigger test reaches a preset threshold value.

In this embodiment, in order to implement a more accurate and effective promotional information test, an upper limit of the number of times of performing the promotional information test (that is, a preset threshold) may be preset, after the correctness of the first page image is determined according to the first detection result each time, the trigger test is performed on the target promotional information again, after the trigger test is performed again, the screen display content is captured again to obtain a new first page image, then the new first page image is input to the promotional information page detection model to obtain a new first detection result, and then the correctness of the new first page image is determined according to the new first detection result until the number of times of performing the trigger test reaches the preset threshold.

It should be noted that, in the process of performing the promotion information test, if a trigger test is performed on a certain trigger region in the target promotion information, then the first page image obtained after the trigger test is input to the promotion information page detection model to obtain a first detection result, and the correctness of the first page image is determined according to the first detection result, that is, after the promotion information test operation for a certain trigger region is completed, the trigger test can be performed again on another trigger region in the target promotion information, then the new first page image obtained after the trigger test is performed again is input to the promotion information page detection model to obtain a new first detection result, then the correctness of the new first page image is determined according to the new first detection result, and so on, until the number of times of performing the trigger test reaches the preset threshold. In addition, under the condition that the quantity value of the trigger area of the target popularization information is smaller than the preset threshold value, when all the trigger areas of the target popularization information complete the popularization information test operation, the execution of the popularization information test operation can be stopped, at the moment, the relevant screenshot information, the test result information and other contents in the popularization information test process can be uploaded to the server to be stored, and therefore the subsequent steps can carry out test analysis, interactive application optimization and other processing according to the screenshot information, the test result information and other contents.

It should be noted that the preset threshold may be appropriately selected according to the actual application, and this embodiment is not limited in particular.

In order to more clearly describe the processing flow of the promotion information test method provided in the embodiment of the present application, a specific example is described below.

Example one:

as shown in fig. 13, fig. 13 is a flowchart of a promotional information testing method provided in a specific example of the present application. In fig. 13, the popularization information testing method includes steps 210 to 340.

Step 210: and inputting the promotion information identifier in the operation terminal, and sending a test operation instruction comprising the promotion information identifier to the test terminal by the operation terminal.

Step 220: and the test terminal acquires promotion information bit entry information corresponding to the promotion information identifier from the server according to the promotion information identifier in the test operation instruction.

Step 230: and the test terminal determines a target promotion information bit entry according to the promotion information bit entry information.

Step 240: and the test terminal enters the corresponding content page through the target promotion information bit inlet.

It should be noted that, when the test terminal is a terminal of an android system, the automatic framework of the uaiautorator may be used to trigger the test terminal to enter a corresponding content page through the target promotion information bit entry; when the test terminal is the terminal of the iOS system, the Webdriveragent automation framework can be used for triggering the test terminal to enter the corresponding content page through the target promotion information bit inlet.

Step 250: and intercepting the content page to obtain a second page image, and inputting the second page image to the promotion information type prediction model to obtain a second prediction result.

Step 260: judging whether the second page image contains the first promotion information according to the second prediction result, if so, executing step 270; if not, the popularization information test operation is quitted.

In this step, when it is determined that the second page image includes the promotion information interface 104 shown in fig. 14 according to the second prediction result, it may be determined that the second page image includes the first promotion information, where the promotion information interface 104 in fig. 14 is used to display the first promotion information.

Step 270: and identifying a promotion information text in the first promotion information, acquiring target text information from the server according to the promotion information identifier, comparing the promotion information text with the target text information, if the comparison result is that the promotion information text and the target text information are consistent, executing the step 280, otherwise, exiting the promotion information test operation.

Step 280: and inputting the second page image into the element information detection model to obtain a third detection result.

In this step, after the second page image is input to the element information detection model, the element information detection model may output element detection information of the interface element in the first popularization information, where the element detection information may include element coordinate detection information, element length detection information, element width detection information, and the like of different interface elements, and therefore, according to the element detection information, all interface elements in the first popularization information may be determined, for example, as shown in fig. 15, it may be determined that the first popularization information includes a first interface element 1041, a second interface element 1042, a third interface element 1043, a fourth interface element 1044, a fifth interface element 1045, and a sixth interface element 1046.

Step 290: and comparing the third detection result with preset target element information, if the comparison result is that the third detection result is consistent with the preset target element information, determining that the first promotion information is target promotion information, and executing the step 300, otherwise, exiting the promotion information test operation.

Step 300: and inputting the second page image into the trigger area prediction model, and identifying the trigger area in the target popularization information.

Step 310: and randomly selecting one trigger area from the target promotion information, and executing a trigger test according to the selected trigger area.

Step 320: after the trigger test is executed, screen display content is intercepted to obtain a first page image, and the first page image is input to the promotion information page detection model to obtain a first detection result.

It should be noted that, because different trigger regions in the target popularization information are linked to different pages, in this step, after the trigger test is performed, the screen display content needs to be captured to obtain the first page image, so that the subsequent step can determine whether the first page image is the correct popularization information page. For example, as shown in fig. 16, after the trigger test is performed on the avatar information in the target popularization information, the correct screen display content is the popularization information provider profile page in fig. 16.

Step 330: and comparing the first detection result with a preset target promotion information page, if the comparison result is that the first detection result and the target promotion information page are consistent, executing the step 340, otherwise, exiting the promotion information test operation.

Step 340: the content is returned to the original content page from the current screen display content and the process goes to step 310 until the number of times of performing the trigger test reaches the preset threshold.

Example two:

as shown in fig. 17, fig. 17 is a flowchart of a promotional information testing method provided in another specific example of the present application. In fig. 17, the promotion information test method includes a training process of an AI model and a process of performing an automated promotion information test using the AI model.

When the test terminal executes the training process of the AI model, the test terminal intercepts related page images, including a second page image of a content page entering through the target promotion information bit entry and a first page image of screen display content after executing the trigger test, then the test terminal performs feature labeling processing on the first page image and the second page image respectively, and then inputs the first page image and the second page image which have been subjected to the feature labeling processing to corresponding AI models respectively for model training, for example, the first page image which has been subjected to the feature labeling processing is input to a promotion information page detection model for model training, the second page image which has been subjected to the feature labeling processing is input to a promotion information type prediction model for model training, the second page image which has been subjected to the feature labeling processing is input to an element information detection model for model training, and the second page image which has been subjected to the feature labeling processing is input to a trigger area prediction model for model training.

When the test terminal utilizes the AI model to carry out promotion information test, the test terminal can realize the automation of promotion information test by combining the AI model in the process of executing the promotion information test. For example, suppose that a test terminal initiates a hypertext Transfer Protocol (HTTP) request to a YOLO server through a test interface to request to identify a first page image, where the YOLO server may be a functional component disposed in the test terminal or a functional component disposed in a server. When the YOLO server receives the HTTP request, the YOLO server sends a prediction trigger message to the message queue module to subscribe a prediction result, at this time, the Keras neural network library supporting the YOLO network model reads the prediction trigger message from the message queue module, then obtains a corresponding prediction result from a corresponding AI model (such as a promotion information type prediction model) according to the prediction trigger message, and returns the obtained prediction result to the message queue module, at this time, the message queue module may return the prediction result to the YOLO server, and the YOLO server returns the prediction result to the test terminal through the test interface, so that the test terminal can perform promotion information test according to the prediction result.

It should be noted that, the YOLO server sends the prediction trigger message to the message queue module to subscribe to the prediction result, and the specific process may be: the YOLO server reads an AI model (an AI model implemented by a YOLO algorithm) corresponding to the model classification information from a relevant configuration file according to the model classification information carried in the HTTP request, then uses a model name of the AI model as a title name of a prediction trigger message, and sends the prediction trigger message to a message queue module, and meanwhile, the YOLO server monitors a prediction result corresponding to the title name, and when the prediction result corresponding to the title name is monitored, it indicates that the corresponding prediction processing has been completed, at this time, the YOLO server may read the prediction result corresponding to the title name from the message queue module.

It should be noted that the Keras neural network library is an open source artificial neural network library written in Python language, and can provide a high-level application program interface for design, debugging, evaluation, application, visualization and the like of a deep learning model.

Example three:

as shown in fig. 18, fig. 18 is a flowchart of a promotional information testing method provided by another specific example of the present application. In fig. 18, the promotion information test method includes a process of acquiring a training sample of an AI model and a process of performing an automated promotion information test using the AI model.

When the test terminal carries out the process of obtaining the training samples of the AI model, the test terminal intercepts the related page images, and then adds the intercepted page images into the training sample set of the AI model for training the AI model. For example, the test terminal acquires promotion information according to the promotion information identifier, displays the promotion information in a content page entered through a target promotion information bit inlet, then searches the promotion information in the content page by searching for a promotion information character, and when the promotion information is found, the test terminal captures the content page to obtain a first training sample, and adds the first training sample into a training sample set of the AI model for training the AI model. In addition, after the test terminal searches for the promotion information in the content page, the test terminal can determine a click position in the promotion information, then click operation is executed through the click position, at the moment, the content page can jump, after the content page jumps, the test terminal intercepts the screen display content after the jump to obtain a second training sample, and the second training sample is added into a training sample set of the AI model and used for training the AI model.

When the test terminal utilizes the AI model to perform automatic promotion information test, the test terminal firstly obtains promotion information according to a promotion information identifier, displays the promotion information in a content page entering through a target promotion information bit inlet, then searches the promotion information in the content page through the AI model, when the promotion information is found and the promotion information is determined to be the target promotion information, the test terminal determines a click position in the promotion information through the AI model, then executes click operation through the click position, at the moment, the content page skips, after the content page skips, the test terminal intercepts the display content of the skipped screen to obtain a corresponding screenshot image, then, the test terminal predicts the screenshot image through the AI model to obtain a corresponding prediction result, and then determines the correctness of the screenshot image according to the prediction result. In addition, in the process of carrying out the automatic promotion information test by the test terminal, the test terminal also takes the relevant screenshot content and the prediction result of the AI model as training samples, and adds the training samples into a training sample set of the AI model for further training and processing the AI model.

Referring to fig. 19, an embodiment of the present application further discloses a promotion information testing apparatus, where the promotion information testing apparatus 400 can serve as the testing terminal 102 in the embodiment shown in fig. 1 to implement the promotion information testing method in the foregoing embodiment, and the promotion information testing apparatus 400 includes:

the interaction module 401 is configured to respond to a test operation instruction and enter a content page through a target promotion information bit entry;

a promotion information judgment module 402, configured to perform promotion information judgment processing on the content page to obtain a promotion information judgment result;

a trigger test module 403, configured to execute a trigger test on the target popularization information when the popularization information determination result indicates that the content page contains the target popularization information, where the trigger test is used to make the content page jump;

a first capture module 404, configured to capture screen display content to obtain a first page image after the trigger test is performed;

a page detection module 405, configured to input the first page image to the promotion information page detection model, and obtain a first detection result of a page element in the first page image, where the page element is an information bearing element in the page for displaying page information;

and the result determining module 406 is configured to determine the correctness of the first page image according to the first detection result and a preset page element of the target popularization information page.

In one embodiment, the result determination module 406 includes:

In one embodiment, the first comparing module comprises at least one of:

alternatively, the first and second electrodes may be,

In one embodiment, the correctness determination module comprises:

the first determining submodule is used for determining that the first page image is correct when the first comparison result is that the first detection result is consistent with the page elements of the target popularization information page;

alternatively, the first and second electrodes may be,

In one embodiment, the promotion information determination module 402 includes:

the type prediction module is used for inputting the second page image into the promotion information type prediction model to obtain a second prediction result;

In an embodiment, in a case that the test operation instruction includes a promotion information identifier and the first promotion information includes a promotion information text, the information determining module includes:

the information identification module is used for carrying out information identification processing on the first promotion information to obtain a promotion information text;

the first sending module is used for sending the popularization information identifier to the server so that the server can obtain the target text information according to the popularization information identifier;

In one embodiment, the information determining sub-module includes:

the element detection module is used for inputting the second page image into the element information detection model to obtain a third detection result;

and the second comparison module is used for comparing the third detection result with preset target element information, and obtaining a promotion information judgment result that the first promotion information is the target promotion information when the third detection result is consistent with the target element information.

In an embodiment, in a case that the second prediction result includes a prediction type and a confidence level of the promotion information, the information determination module includes:

and the promotion information determining module is used for determining that the second page image contains the first promotion information when the second comparison result shows that the confidence coefficient is greater than or equal to the confidence coefficient threshold value, and the promotion information type of the first promotion information is consistent with the promotion information prediction type.

In one embodiment, the trigger test module 403 includes:

the region prediction module is used for inputting the second page image into the trigger region prediction model to obtain trigger region prediction information of the target popularization information;

the area determination module is used for determining a trigger area in the target popularization information according to the trigger area prediction information;

and the trigger test sub-module is used for executing the trigger test according to the trigger area.

In an embodiment, in a case that the test operation instruction includes a promotion information identifier, the interaction module 401 includes:

the second sending module is used for responding to the test operation instruction and sending the promotion information identifier to the server so that the server can obtain target promotion information bit information according to the promotion information identifier;

the entrance determining module is used for determining an entrance of the target promotion information bit according to the target promotion information bit information;

In an embodiment, the trigger test module 403 is further configured to perform a trigger test on the target popularization information again;

the first truncating module 404 is further configured to truncate the screen display content to obtain a new first page image after the trigger test is re-executed;

the page detection module 405 is further configured to input the new first page image to the promotion information page detection model to obtain a new first detection result;

the result determining module 406 is further configured to determine the correctness of the new first page image according to the new first detection result until the number of times of performing the trigger test reaches a preset threshold.

In one embodiment, the promotion information testing apparatus 400 further includes:

and the first model training module is used for taking the first page image subjected to the first characteristic labeling processing as a training sample of the promotion information page detection model and training the promotion information page detection model.

the second feature labeling module is used for performing second feature labeling processing on the second page image according to the second type label;

and the second model training module is used for taking the second page image subjected to the second characteristic labeling processing as a training sample of the popularization information type prediction model and carrying out training processing on the popularization information type prediction model.

It should be noted that, since the promotion information testing apparatus 400 of this embodiment can implement the promotion information testing method using the test terminal as the execution main body in the foregoing embodiment, the promotion information testing apparatus 400 of this embodiment has the same technical principle and the same beneficial effects as the promotion information testing method using the test terminal as the execution main body in the foregoing embodiment, and in order to avoid content duplication, details are not repeated here.

The above described embodiments of the apparatus are merely illustrative, wherein the units illustrated as separate components may or may not be physically separate, may be located in one place, or may be distributed over a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment.

Referring to fig. 20, an embodiment of the present application further discloses a promotion information testing apparatus, where the promotion information testing apparatus 500 includes:

at least one processor 501;

at least one memory 502 for storing at least one program;

when the at least one program is executed by the at least one processor 501, a promotional information testing method as described in any of the previous embodiments is implemented.

The embodiment of the application also discloses a computer readable storage medium, wherein a program executable by a processor is stored, and when the program executable by the processor is executed by the processor, the program is used for realizing the popularization information testing method as described in any of the foregoing embodiments.

The embodiment of the application also discloses a computer program product, which comprises a computer program or a computer instruction, wherein the computer program or the computer instruction is stored in a computer readable storage medium, a processor of the computer device reads the computer program or the computer instruction from the computer readable storage medium, and the processor executes the computer program or the computer instruction, so that the computer device executes the popularization information testing method according to any embodiment of the foregoing embodiment.

The terms "first," "second," "third," "fourth," and the like in the description of the application and the above-described figures, if any, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the application described herein are, for example, capable of operation in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

It should be understood that in the present application, "at least one" means one or more, "a plurality" means two or more. "and/or" for describing an association relationship of associated objects, indicating that there may be three relationships, e.g., "a and/or B" may indicate: only A, only B and both A and B are present, wherein A and B may be singular or plural. The character "/" generally indicates that the former and latter associated objects are in an "or" relationship. "at least one of the following" or similar expressions refer to any combination of these items, including any combination of single item(s) or plural items. For example, at least one (one) of a, b, or c, may represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", wherein a, b and c may be single or plural.

In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.

The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.

The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application may be substantially implemented or contributed to by the prior art, or all or part of the technical solution may be embodied in a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.

For the step numbers in the above method embodiments, they are set for convenience of illustration only, the order between the steps is not limited at all, and the execution order of each step in the embodiments can be adapted according to the understanding of those skilled in the art.

Claims

1. A promotion information testing method is characterized by comprising the following steps:

when the promotion information judgment result shows that the content page contains target promotion information, executing a trigger test on the target promotion information, wherein the trigger test is used for skipping the content page;

2. The promotion information testing method according to claim 1, wherein the determining the correctness of the first page image according to the first detection result and a preset page element of the target promotion information page includes:

comparing the first detection result with page elements of a preset target promotion information page to obtain a first comparison result;

and determining the correctness of the first page image according to the first comparison result.

3. The promotion information testing method according to claim 2, wherein the comparing the first detection result with page elements of a preset target promotion information page includes at least one of the following steps:

when the first detection result comprises page element type detection information, comparing the page element type detection information with page element type information of a preset target promotion information page;

alternatively, the first and second electrodes may be,

and when the first detection result comprises page element layout detection information, comparing the page element layout detection information with page element layout information of a preset target promotion information page.

4. The promotion information testing method according to claim 2, wherein the determining the correctness of the first page image according to the first comparison result includes:

when the first comparison result is that the first detection result is consistent with the page elements of the target promotion information page, determining that the first page image is correct;

alternatively, the first and second electrodes may be,

and when the first comparison result is that the first detection result is inconsistent with the page elements of the target promotion information page, determining that the first page image is wrong.

5. The promotion information testing method according to claim 1, wherein the performing promotion information judgment processing on the content page to obtain a promotion information judgment result includes:

intercepting the content page to obtain a second page image;

inputting the second page image into a promotion information type prediction model to obtain a second prediction result;

and when the second page image is determined to contain the first promotion information according to the second prediction result, performing information judgment processing on the first promotion information to obtain a promotion information judgment result.

6. The promotion information testing method according to claim 5, wherein the test operation instruction includes a promotion information identifier, and the first promotion information includes a promotion information text;

the information judgment processing is carried out on the first popularization information to obtain a popularization information judgment result, and the method comprises the following steps:

performing information identification processing on the first promotion information to obtain a promotion information text;

sending the promotion information identification to a server, so that the server acquires target text information according to the promotion information identification;

receiving the target text information sent by the server;

and comparing the promotion information text with the target text information, and when the promotion information text is consistent with the target text information, performing element information judgment processing on the first promotion information to obtain a promotion information judgment result.

7. The method for testing popularization information according to claim 6, wherein the performing element information determination processing on the first popularization information to obtain a popularization information determination result includes:

inputting the second page image into an element information detection model to obtain a third detection result;

and comparing the third detection result with preset target element information, and obtaining a promotion information judgment result that the first promotion information is the target promotion information when the third detection result is consistent with the target element information.

8. The promotional information testing method of claim 5 wherein said second prediction result comprises a promotional information prediction type and a confidence level;

the determining that the second page image contains first promotion information according to the second prediction result includes:

comparing the confidence with a confidence threshold to obtain a second comparison result;

and when the second comparison result shows that the confidence coefficient is greater than or equal to the confidence coefficient threshold value, determining that the second page image contains first promotion information, and the promotion information type of the first promotion information is consistent with the promotion information prediction type.

9. The promotion information testing method according to claim 5, wherein the performing of the trigger test on the target promotion information includes:

inputting the second page image into a trigger area prediction model to obtain trigger area prediction information of the target popularization information;

determining a trigger area in the target promotion information according to the trigger area prediction information;

and executing a trigger test according to the trigger area.

10. The promotion information testing method according to claim 1, wherein the test operation instruction includes a promotion information identifier;

the responding to the test operation instruction and entering the content page through the target promotion information bit entry comprises the following steps:

responding to a test operation instruction, sending the promotion information identification to a server, and enabling the server to obtain target promotion information bit information according to the promotion information identification;

receiving the target promotion information bit information sent by the server;

determining a target promotion information bit entry according to the target promotion information bit information;

and entering a content page through the target promotion information bit entry.

11. The popularization information testing method according to claim 1, wherein after the determining of the correctness of the first page image according to the first detection result, the popularization information testing method further includes:

executing the trigger test on the target promotion information again;

inputting the new first page image into the promotion information page detection model to obtain a new first detection result;

12. The promotional information testing method according to claim 1, wherein said promotional information testing method further comprises:

adding a first type label to the first page image;

performing first feature labeling processing on the first page image according to the first type label;

and taking the first page image subjected to the first feature labeling processing as a training sample of the promotion information page detection model, and training the promotion information page detection model.

13. The promotional information testing method according to claim 5, wherein said promotional information testing method further comprises:

adding a second type label to the second page image;

performing second feature labeling processing on the second page image according to the second type tag;

and taking the second page image subjected to the second feature labeling processing as a training sample of the popularization information type prediction model, and training the popularization information type prediction model.

14. The promotional information testing method according to claim 7, wherein said promotional information testing method further comprises:

adding a third type label to the second page image;

performing third feature labeling processing on the second page image according to the third type tag;

and taking the second page image subjected to the third feature labeling processing as a training sample of the element information detection model, and training the element information detection model.

15. The promotional information testing method according to claim 9, wherein said promotional information testing method further comprises:

adding a fourth type label to the second page image;

performing fourth feature labeling processing on the second page image according to the fourth type tag;

and taking the second page image subjected to the fourth feature labeling processing as a training sample of the trigger area prediction model, and training the trigger area prediction model.

16. The utility model provides a promote information testing arrangement which characterized in that includes:

17. The utility model provides a promote information testing arrangement which characterized in that includes:

at least one processor;

at least one memory for storing at least one program;

the promotional information testing method of any of claims 1 to 15 is implemented when at least one of said programs is executed by at least one of said processors.

18. A computer-readable storage medium, in which a processor-executable program is stored, the processor-executable program being configured to implement the promotional information testing method of any of claims 1 to 15 when executed by a processor.

19. A computer program product comprising a computer program or computer instructions stored in a computer readable storage medium, the computer program or computer instructions being read from the computer readable storage medium by a processor of a computer device, the computer program or computer instructions being executed by the processor to cause the computer device to perform the promotional information testing method of any of claims 1 to 15.