Information processing method, image contrast model training method, device and equipment

Abstract

Embodiments of the present application provide an information processing method, a training method and device of an image comparison model, and the information processing method comprises: obtaining a plurality of first page sequences; the plurality of first page sequences are obtained by performing function testing on an application program, and the first page sequence comprises an image of at least one page, and the page is included in the application program; determining at least one first page set according to the plurality of first page sequences; the similarity between the page sequences included in the first page set is not less than a first threshold. The information processing method, the training method and device of the image comparison model provided by the embodiments of the present application can be used to improve the efficiency of finding a truly abnormal page sequence.

Description

Technical Field

[0001] This application relates to the field of functional testing technology for applications, and more particularly to an information processing method, an image comparison model training method, apparatus, and device. Background Technology

[0002] Before an application goes live, it is usually necessary to perform automated functional testing on the application in order to identify functional defects in a timely manner and then propose targeted fixes.

[0003] In related technologies, to improve the efficiency of automated functional testing, testers typically develop corresponding automated testing strategies to address potential functional defects in applications, and then perform functional testing based on these strategies. During functional testing, a large number of abnormal page sequences (including images of multiple pages) are automatically saved. Testers manually identify the truly abnormal page sequences from this large number of sequences and, based on these sequences, propose targeted repair strategies to ensure that the repaired application can pass the functional tests.

[0004] In the above process, testers manually searched for truly abnormal page sequences among a large number of page sequences, resulting in low efficiency in finding truly abnormal page sequences. Summary of the Invention

[0005] This application provides an information processing method, an image comparison model training method, an apparatus, and a device to improve the efficiency of finding truly abnormal page sequences.

[0006] In a first aspect, embodiments of this application provide an information processing method, including:

[0007] Obtain multiple first page sequences; the multiple first page sequences are obtained by performing functional tests on the application, and each first page sequence includes an image of at least one page, which is a page included in the application;

[0008] Based on multiple first page sequences, at least one first page set is determined; the similarity between the page sequences included in the first page set is not less than a first threshold.

[0009] In one possible design, at least one set of first pages is determined based on multiple first page sequences, including:

[0010] Multiple first-page sequences are processed to remove duplicate images, resulting in multiple second-page sequences.

[0011] Based on multiple second page sequences, at least one first page set is determined; the similarity between the second page sequences included in the first page set is not less than a first threshold.

[0012] In one possible design, at least one set of first pages is determined based on multiple second page sequences, including:

[0013] Multiple second-page sequences are classified according to at least one sequence length to obtain at least one second-page set; the total number of images of each second-page sequence included in the second-page set corresponds to the sequence length of the second-page set.

[0014] Clustering is performed on the second page sequences included in each second page set to obtain at least one first page set corresponding to each second page set.

[0015] In one possible design, the first page sequence is deduplicated to obtain the second page sequence, which includes:

[0016] Get the similarity between the i-th image and the (i+1)-th image in the first page sequence; if the similarity is less than the first threshold, increment the i-th image by 1 and repeat this step until the second page sequence is obtained; if the similarity is not less than the first threshold, delete the i-th image and increment the i-th image by 1, repeat this step until the second page sequence is obtained; initially, i equals 1, and j is the total number of images included in the first page sequence.

[0017] In one possible design, obtaining the similarity between the i-th image and the (i+1)-th image in the first page sequence includes:

[0018] Feature extraction is performed on the i-th image and the (i+1)-th image in the first page sequence to obtain the feature information corresponding to the i-th image and the (i+1)-th image respectively;

[0019] Based on the feature information corresponding to the i-th image and the (i+1)-th image, determine the similarity between the i-th image and the (i+1)-th image.

[0020] In one possible design, feature extraction is performed on the i-th image and the (i+1)-th image in the first page sequence to obtain the feature information corresponding to each of the i-th and (i+1)-th images, including:

[0021] By using a pre-trained image comparison model, feature extraction is performed on the i-th image and the (i+1)-th image to obtain the feature information corresponding to each of the i-th image and the (i+1)-th image.

[0022] The image comparison model is trained using multiple sets of training samples. Each set of training samples includes two sample images and the corresponding label information for the two sample images.

[0023] In one possible design, the similarity between the i-th image and the (i+1)-th image is determined based on the feature information corresponding to each of the i-th and i+1-th images, including:

[0024] Based on the feature information corresponding to the i-th image and the (i+1)-th image, determine the difference information between the i-th feature information and the (i+1)-th feature information;

[0025] The difference information is determined as the similarity between the i-th image and the (i+1)-th image.

[0026] Secondly, embodiments of this application provide a method for training an image contrast model, comprising:

[0027] Obtain multiple sample anomaly sequences; the sample anomaly sequences include multiple sample images;

[0028] Multiple abnormal sequences of samples are classified and labeled to obtain multiple sample image pairs and the corresponding label information for each sample image pair;

[0029] Based on multiple sample image pairs and the corresponding label information for each sample image pair, the model parameters of the initial comparison model are adjusted to obtain the image comparison model.

[0030] In one possible design, multiple abnormal sample sequences are classified and labeled to obtain multiple sample image pairs and corresponding label information for each sample image pair, including:

[0031] For each sample anomaly sequence, identify the target sample anomaly sequence within the sample anomaly sequence;

[0032] Obtain multiple sample image pairs from multiple target sample anomaly sequences;

[0033] Label each sample image pair with its own label information.

[0034] In one possible design, determining the target sample anomaly sequence within the sample anomaly sequence includes:

[0035] Determine whether the number of sample images in the abnormal sample sequence is less than a preset number;

[0036] If the number is less than the preset number, the abnormal sample sequence will be identified as the target abnormal sample sequence.

[0037] If the number is not less than the preset number, then starting from the last sample image in the sample anomaly sequence, the preset number of sample images will be obtained sequentially and continuously from the sample anomaly sequence, and the preset number of sample images will be determined as the target sample anomaly sequence; the last image is the anomaly sample image in the sample anomaly sequence.

[0038] Thirdly, embodiments of this application provide an information processing apparatus, including:

[0039] The acquisition module is used to acquire multiple first page sequences; the multiple first page sequences are obtained by performing functional tests on the application, and each first page sequence includes an image of at least one page, which is a page included in the application;

[0040] The processing module determines at least one set of first pages based on multiple first page sequences; the similarity between the page sequences included in the first page set is not less than a first threshold.

[0041] In one possible design, the processing module is specifically used for:

[0042] Multiple first-page sequences are processed to remove duplicate images, resulting in multiple second-page sequences.

[0043] Based on multiple second page sequences, at least one first page set is determined; the similarity between the second page sequences included in the first page set is not less than a first threshold.

[0044] In one possible design, the processing module is specifically used for:

[0045] Multiple second-page sequences are classified according to at least one sequence length to obtain at least one second-page set; the total number of images of each second-page sequence included in the second-page set corresponds to the sequence length of the second-page set.

[0046] Clustering is performed on the second page sequences included in each second page set to obtain at least one first page set corresponding to each second page set.

[0047] In one possible design, the processing module is specifically used for:

[0048] Get the similarity between the i-th image and the (i+1)-th image in the first page sequence; if the similarity is less than the first threshold, increment the i-th image by 1 and repeat this step until the second page sequence is obtained; if the similarity is not less than the first threshold, delete the i-th image and increment the i-th image by 1, repeat this step until the second page sequence is obtained; initially, i equals 1, and j is the total number of images included in the first page sequence.

[0049] In one possible design, the processing module is specifically used for:

[0050] Feature extraction is performed on the i-th image and the (i+1)-th image in the first page sequence to obtain the feature information corresponding to the i-th image and the (i+1)-th image respectively;

[0051] Based on the feature information corresponding to the i-th image and the (i+1)-th image, determine the similarity between the i-th image and the (i+1)-th image.

[0052] In one possible design, the processing module is specifically used for:

[0053] By using a pre-trained image comparison model, feature extraction is performed on the i-th image and the (i+1)-th image to obtain the feature information corresponding to each of the i-th image and the (i+1)-th image.

[0054] The image comparison model is trained using multiple sets of training samples. Each set of training samples includes two sample images and the corresponding label information for the two sample images.

[0055] In one possible design, the processing module is specifically used for:

[0056] Based on the feature information corresponding to the i-th image and the (i+1)-th image, determine the difference information between the i-th feature information and the (i+1)-th feature information;

[0057] The difference information is determined as the similarity between the i-th image and the (i+1)-th image.

[0058] Fourthly, embodiments of this application provide a training apparatus for an image contrast model, comprising:

[0059] The acquisition module is used to acquire multiple abnormal sample sequences; the abnormal sample sequences include multiple sample images.

[0060] The processing module is used to classify and label multiple abnormal sequences of samples to obtain multiple sample image pairs and the corresponding label information for each sample image pair;

[0061] The processing module is also used to adjust the model parameters of the initial comparison model based on multiple sample image pairs and the label information corresponding to each sample image pair, so as to obtain the image comparison model.

[0062] In one possible design, the processing module is specifically used for:

[0063] For each sample anomaly sequence, identify the target sample anomaly sequence within the sample anomaly sequence;

[0064] Obtain multiple sample image pairs from multiple target sample anomaly sequences;

[0065] Label each sample image pair with its own label information.

[0066] In one possible design, the processing module is specifically used for:

[0067] Determine whether the number of sample images in the abnormal sample sequence is less than a preset number;

[0068] If the number is less than the preset number, the abnormal sample sequence will be identified as the target abnormal sample sequence.

[0069] If the number is not less than the preset number, then starting from the last sample image in the sample anomaly sequence, the preset number of sample images will be obtained sequentially and continuously from the sample anomaly sequence, and the preset number of sample images will be determined as the target sample anomaly sequence; the last image is the anomaly sample image in the sample anomaly sequence.

[0070] Fifthly, embodiments of this application provide an electronic device, including: a processor, and a memory communicatively connected to the processor;

[0071] The memory stores instructions that the computer executes;

[0072] The processor executes computer-executable instructions stored in memory to implement the method as described in any of the first aspects.

[0073] Sixthly, embodiments of this application provide a training device for an image contrast model, including: a processor, and a memory communicatively connected to the processor;

[0074] The memory stores instructions that the computer executes;

[0075] The processor executes computer-executable instructions stored in memory to implement the method as described in any of the second aspects.

[0076] In a seventh aspect, embodiments of this application provide a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the method of any one of the first aspects or any one of the second aspects.

[0077] Eighthly, embodiments of this application provide a computer program product, including a computer program, which, when executed by a processor, implements the method of any one of the first aspects or any one of the second aspects.

[0078] This application provides an information processing method, an image comparison model training method, an apparatus, and a device. The information processing method includes: acquiring a plurality of first page sequences; the plurality of first page sequences are obtained by performing functional testing on an application, and each first page sequence includes an image of at least one page, wherein the page is a page included in the application; determining at least one first page set based on the plurality of first page sequences; the similarity between the page sequences included in the first page set is not less than a first threshold. In the above information processing method, at least one set of first pages is determined based on multiple first page sequences. The similarity between the page sequences included in the first page set is not less than a first threshold, meaning that the similarity between the page sequences included in the first page set is relatively high. Therefore, testers only need to check the page sequences in the first page set. For example, after checking any page sequence in the first page set, if the page sequence is determined to be correct, then all page sequences in the entire first page set are considered correct; if the page sequence is determined to be incorrect, then all page sequences in the entire first page set are considered incorrect. At this point, the remaining page sequences in the first page set can be checked one by one to determine the truly abnormal page sequences. This greatly reduces the number of page sequences that need to be manually checked, improves the efficiency of finding truly abnormal page sequences, and thus improves the overall efficiency of automated functional testing. Attached Figure Description

[0079] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0080] Figure 1 This is a schematic diagram illustrating an application scenario of the information processing method provided in the embodiments of this application;

[0081] Figure 2 A schematic diagram of the first page sequence provided for an embodiment of this application;

[0082] Figure 3 A flowchart illustrating the information processing method provided in the embodiments of this application;

[0083] Figure 4 A flowchart for obtaining the second page sequence provided in this application embodiment;

[0084] Figure 5 A flowchart for obtaining at least one first page set provided in the embodiments of this application;

[0085] Figure 6A flowchart illustrating the process of obtaining at least one first page set corresponding to a second page set, as provided in this application embodiment;

[0086] Figure 7 A flowchart for obtaining the similarity between two second page sequences provided in an embodiment of this application;

[0087] Figure 8 A flowchart illustrating the training method for the image contrast model provided in this application embodiment;

[0088] Figure 9 This is a schematic diagram of the structure of the initial comparison model provided in the embodiments of this application;

[0089] Figure 10 This is a schematic diagram of the structure of the information processing device provided in the embodiments of this application;

[0090] Figure 11 A schematic diagram of the structure of the training device for the image contrast model provided in the embodiments of this application;

[0091] Figure 12 A schematic diagram of the hardware structure of the electronic device provided in the embodiments of this application;

[0092] Figure 13 This is a schematic diagram of the hardware structure of the training device for the image comparison model provided in the embodiments of this application. Detailed Implementation

[0093] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0094] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a particular order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented, for example, in orders other than those illustrated or described herein. Furthermore, the terms “comprising” and “having,” and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0095] After an application is developed, it is usually necessary to perform automated functional testing on its functional defects. These defects can include, for example, UI display anomalies and UI interaction anomalies related to the user interface (UI). UI display anomalies include the disappearance, missing, or duplicate of UI controls. UI interaction anomalies include UI controls becoming unresponsive, or incorrect page redirection occurring after interacting with a UI control on the page.

[0096] In related technologies, during automated functional testing of applications for potential functional defects, when the testing system detects an alarm anomaly on a page of the application, it traces backward from that page to the page that triggered the problem, saving images of each page involved in the tracing process. Each of these images is then identified as a sequence of pages with an anomaly and saved. After an automated functional test is completed, testers typically manually search through a large number of page sequences to find the truly abnormal page sequence. Based on this sequence, they propose targeted repair strategies to ensure the repaired application passes functional testing. However, in the aforementioned technologies, testers manually search through a large number of page sequences (e.g., 5,000 or 10,000), resulting in low efficiency in finding the truly abnormal page sequence.

[0097] In practical applications, multiple page sequences obtained after automated functional testing often contain a large number of identical images. Therefore, in this application, to improve the efficiency of finding truly abnormal page sequences, the inventors determine at least one first page set based on multiple first page sequences, such that the similarity between page sequences in the first page set is not less than a first threshold. Thus, after checking any page sequence in the first page set, if the page sequence is determined to be correct, then all page sequences in the entire first page set are considered correct, eliminating the need to check each of the remaining second page sequences in the first page set individually. If the page sequence is determined to be incorrect, then all page sequences in the entire first page set are considered incorrect. In this case, each of the remaining second page sequences in the first page set can be checked individually to determine the truly abnormal page sequence, thus narrowing the tester's search scope and improving the efficiency of finding truly abnormal page sequences.

[0098] The following is combined Figure 1 The application scenarios of the information processing method provided in the embodiments of this application are described.

[0099] Figure 1 This is a schematic diagram illustrating an application scenario of the information processing method provided in the embodiments of this application. For example... Figure 1 As shown, this application scenario includes, for example, multiple first page sequences and multiple first page sets.

[0100] For example, when multiple first page sequences include four first page sequences (L1 to L4 respectively), L1 includes image 11, L2 includes image 21 and image 22, L3 includes image 31, image 32 and image 33, and L4 includes image 41, image 42, image 43, image 43 and image 43.

[0101] For example, when multiple first page sets include three first page sets (C1 to C3 respectively), C1 includes image 11, C2 includes image 21 and image 22, and C3 includes image 31, image 32 and image 34, image 41, image 42 and image 43.

[0102] In the first page set, when the first page set includes multiple page sequences, the similarity between the multiple page sequences is not less than a first threshold.

[0103] Figure 2 This is a schematic diagram of the first page sequence provided in an embodiment of this application. Figure 2 As shown, the first page sequence includes: image 21 and image 22.

[0104] For example, both images 21 and 22 include a five-pointed star control (☆).

[0105] The method for obtaining the first page sequence is explained below:

[0106] A correct display method, for example, when the five-pointed star control (colorless) in the page corresponding to image 21 receives a touch operation, the color of the five-pointed star control in the page corresponding to image 22 is, for example, red;

[0107] An incorrect display method, for example, when the five-pointed star control (colorless) in the page corresponding to image 21 receives a touch operation, the color of the five-pointed star control in the page corresponding to image 22 is still colorless. At this time, the test system records images 21 and 22.

[0108] Next, the technical solution of this application will be described in detail with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments.

[0109] Figure 3 A flowchart illustrating the information processing method provided in this application embodiment. For example... Figure 3 As shown, the method includes:

[0110] S301, Obtain multiple first page sequences.

[0111] Optionally, the execution subject of this application embodiment is an electronic device, or it can be an information processing device installed in the electronic device. The information processing device can be implemented by a combination of software and / or hardware.

[0112] The multiple first page sequences were obtained after performing a functional test on the application.

[0113] An application can be an application that can run on an electronic device.

[0114] For example, electronic devices can be mobile phones, PCs, etc.

[0115] Each first page sequence includes images of at least one page. The first page sequence may contain normal pages and / or abnormal pages.

[0116] Optionally, in the first page sequence, the images can be arranged in the same order as the tracing order, or in the reverse order.

[0117] For example, when the order of the images is the same as the order of tracing (image 1 ← image 2 ← image 3), the order of the images is image 1, image 2, image 3.

[0118] For example, when the order of the images is different from the order of tracing (image 1 ← image 2 ← image 3), the order of the images is image 3, image 2, image 1.

[0119] In practical applications, the starting image for tracing (such as image 3 above) is usually an image of an abnormal page.

[0120] S302. Based on multiple first page sequences, determine at least one first page set; the similarity between the page sequences included in the first page set is not less than a first threshold.

[0121] Optionally, the number of page sequences included in the first page set can be 1 or at least two.

[0122] When the first page set includes at least two page sequences, the similarity between the page sequences included in the first page set is not less than a first threshold.

[0123] Alternatively, at least one set of first pages can be determined in several ways.

[0124] Method 11: Determine the first page sequences with the same sequence length from multiple first page sequences as the second page set, so as to obtain multiple second page sets;

[0125] Clustering is performed on the first page sequences included in each second page set to obtain at least one first page set corresponding to each second page set; the similarity between the first page sequences included in the first page set is not less than a first threshold.

[0126] Here, the sequence length is the total number of images included in a first page sequence.

[0127] For example, when multiple first page sequences include four first page sequences (L11~L14), and multiple second page sets include two second page sets (C21, C22).

[0128] The first page sequence L11 includes 4 images, the first page sequence L12 includes 6 images, the first page sequence L13 includes 6 images, and the first page sequence L14 includes 4 images. Therefore, C21 includes L11 and L14, and C22 includes L12 and L13.

[0129] Method 12 involves performing image deduplication on multiple first page sequences to obtain multiple second page sequences;

[0130] Multiple second page sequences with the same sequence length are identified as the second page set, thus obtaining multiple second page sets;

[0131] Clustering is performed on the second page sequences included in each second page set to obtain at least one first page set corresponding to each second page set, and the similarity between the second page sequences included in the first page set is not less than a first threshold.

[0132] Specifically, for each first page sequence, image deduplication is performed on the images in the first page sequence to obtain the corresponding second page sequence.

[0133] For example, when the first page sequence includes image 1, image 2, image 3, image 4, image 5, then after deduplication of the images in the first page sequence, the resulting second page sequence includes image 1, image 2, image 3, image 4, and image 5.

[0134] Here, the sequence length is the total number of images included in a second-page sequence.

[0135] Method 13: Perform image deduplication on multiple first page sequences to obtain multiple second page sequences;

[0136] Based on multiple second page sequences, at least one first page set is determined; the similarity between the second page sequences included in the first page set is not less than a first threshold.

[0137] The clustering methods in methods 11 and 12 above are similar to... Figure 6 The method shown is similar; for details, please refer to [link / reference]. Figure 6 Example.

[0138] For an explanation of the image deduplication process in methods 12 and 13 above, please refer to [link to documentation]. Figure 4 Example.

[0139] For an explanation of determining at least one set of first pages based on multiple second page sequences in section 13 above, please refer to [link to section 13]. Figure 5 Example.

[0140] Unlike existing technologies, in related technologies, testers manually search for truly abnormal page sequences among a large number of page sequences, resulting in low efficiency in finding truly abnormal page sequences.

[0141] In the application provided Figure 3 In this embodiment, at least one set of first pages is determined based on multiple first page sequences. The similarity between the page sequences included in the first page set is not less than a first threshold, meaning that the similarity between the page sequences included in the first page set is relatively high. Therefore, testers only need to check the page sequences in the first page set. For example, after checking any one page sequence in the first page set, if the page sequence is determined to be correct, then all page sequences in the entire first page set are considered correct; if the page sequence is determined to be incorrect, then all page sequences in the entire first page set are considered incorrect. At this point, the remaining page sequences in the first page set can be checked one by one to determine the truly abnormal page sequences. This greatly reduces the number of page sequences that need to be manually checked, improves the efficiency of finding truly abnormal page sequences, and thus improves the overall efficiency of automated functional testing.

[0142] Unlike existing technologies, which rely on manual inspection to find truly abnormal page sequences, this method wastes manpower and takes a long time.

[0143] In this application, the number of sequences requiring manual verification is greatly reduced, thus saving manpower and shortening the time required for manual verification.

[0144] Based on the above embodiments, the following is combined with Figure 4 The method of deduplicating the second page sequence through images is explained.

[0145] Figure 4 A flowchart illustrating the process of obtaining a second page sequence, as provided in an embodiment of this application. Figure 4 As shown, the method includes:

[0146] S401. Obtain the similarity between the i-th image and the (i+1)-th image in the first page sequence.

[0147] In one possible implementation, S401 specifically includes: performing feature extraction processing on the i-th image and the (i+1)-th image in the first page sequence to obtain the feature information corresponding to the i-th image and the (i+1)-th image respectively;

[0148] Based on the feature information corresponding to the i-th image and the (i+1)-th image, determine the similarity between the i-th image and the (i+1)-th image.

[0149] In one possible implementation, the feature information corresponding to the i-th image and the (i+1)-th image is obtained by the following method: using a pre-trained image comparison model, feature extraction processing is performed on the i-th image and the (i+1)-th image to obtain the feature information corresponding to the i-th image and the (i+1)-th image respectively; wherein, the image comparison model is trained using multiple sets of training samples, and each set of training samples includes two sample images and the label information corresponding to the two sample images.

[0150] In one possible implementation, the similarity between the i-th image and the (i+1)-th image is obtained by: determining the difference information between the i-th feature information and the (i+1)-th feature information based on the feature information corresponding to the i-th image and the (i+1)-th feature information respectively; and determining the difference information as the similarity between the i-th image and the (i+1)-th image.

[0151] Optionally, the difference information can be the Euclidean distance, Manhattan distance, Minkowski distance, etc., between the i-th feature information and the (i+1)-th feature information.

[0152] S402. Determine whether the similarity is not less than the first threshold.

[0153] If not, execute S403 to S405; otherwise, execute S406.

[0154] S403. Determine if i is greater than I.

[0155] If yes, then execute S404; otherwise, execute S405.

[0156] I equals the total number of images in the first page sequence.

[0157] In this application, since it is necessary to remove the repeated identical images included in the first page sequence, I can be a variable integer.

[0158] S404, Obtain the second page sequence.

[0159] S405. Increase i by 1 and repeat S401 to S402.

[0160] S406. Delete the i-th image and repeat S405.

[0161] Optionally, 406 can also be: delete the (i+1)th image, update the indices (i+2 to j) of the (i+2 to j)th images in the first page sequence to (i-1 to j-1), and repeat S401 to S402.

[0162] Initially, i equals 1, and j is the total number of images included in the first page sequence.

[0163] The value of i can be an integer between 1 and j.

[0164] In this application, since duplicate images in the first page sequence need to be removed, j is a variable integer.

[0165] Unlike existing technologies, where testers manually search for truly anomalous page sequences among a large number of page sequences, this process involves checking the correctness of each image within the page sequence to determine if an anomaly truly exists. Since page sequences often contain repeated images, checking the correctness of each image in a page sequence in these technologies leads to low efficiency in finding truly anomalous page sequences.

[0166] In this application, repeating the above S401 to S406 and deleting the repeated identical images included in the first page sequence can reduce the number of images that testers need to check, save manpower, shorten the time for manual inspection, improve the efficiency of finding the page sequence that is truly abnormal, and thus improve the overall efficiency of automated functional testing.

[0167] Based on the above embodiments, the following is combined with Figure 5 The execution process of determining at least one set of first pages based on multiple second page sequences in method 13 above will be explained.

[0168] Figure 5 A flowchart illustrating the process of obtaining at least one set of first pages, as provided in embodiments of this application. Figure 5 As shown, the method includes:

[0169] S501. Based on at least one sequence length, perform sequence classification processing on multiple second page sequences to obtain at least one set of second pages.

[0170] Optionally, at least one sequence length may include: 1, 2, ..., X-1, X.

[0171] Where X is a positive integer, for example, X can be equal to 3.

[0172] Each set of second pages corresponds to a sequence length.

[0173] The second page set includes the second page sequence. The number of images included in the second page sequence in the second page set corresponds to the sequence length of the second page set.

[0174] For example, when the sequence length is X-1, the second page sequence in the second page set includes the same number of images, all equal to X-1.

[0175] For example, when the sequence length is X, the number of images included in the second page sequence in the second page set can be the same or different.

[0176] When the sequence length is X, if the number of images included in the second page sequence in the second page set is not the same, the second page set can simultaneously contain second page sequences with a number of images greater than or equal to X.

[0177] The number of images included in the second page sequence of the second page set can be the same and equal to X, or they can be different and greater than or equal to X.

[0178] S502. Perform sequence clustering on the second page sequences in each second page set to obtain at least one first page set corresponding to each second page set.

[0179] The following example uses a collection of second-page pages, combined with... Figure 6 The execution process of S502 is explained.

[0180] Figure 6 A flowchart illustrating the process of obtaining at least one first page set corresponding to a second page set, as provided in this application embodiment. Figure 6 As shown, the method includes:

[0181] S601. Obtain the nth second page sequence and the mth second page sequence from the second page set.

[0182] Initially, n equals 1 and m equals 2.

[0183] Optionally, before S601, it may also include: determining whether the second page set includes multiple second page sequences; if it includes multiple second page sequences, then obtaining the nth second page sequence and the mth second page sequence from the second page set.

[0184] S602. Determine whether the nth second page sequence and the mth second page sequence are similar.

[0185] If not, execute S603 to S607; otherwise, execute S605.

[0186] S603. Store the m-th second page sequence into the i-th first page set.

[0187] S604. Determine if m is greater than Q1.

[0188] If yes, then execute S605; otherwise, execute S606.

[0189] Q1 represents the total number of second-page sequences included in the second-page set.

[0190] In this application, Q1 is a variable integer value because the second page sequence needs to be removed from the second page set.

[0191] S605. Increase m by 1, and repeat S601 to S607.

[0192] S606. Store the nth second page sequence into the i-th first page set.

[0193] Specifically, after storing the nth second page sequence into the ith first page set, a second page sequence corresponding to the second page set is obtained.

[0194] S607. Delete the second page sequence that overlaps with the i-th first page set from the second page set to obtain a new second page set. Increment i by 1, update n and m to their initial values, and repeat S601 to S607 for the new second page set until there is no second page sequence in the new second page set, thus achieving the goal of obtaining at least one second page sequence corresponding to the second page set.

[0195] Based on the above embodiments, the following example illustrates how the image arrangement order of at least one page is the same as the tracing order. Figure 7 The specific implementation method of S602 will be explained.

[0196] Figure 7 A flowchart for obtaining the similarity of two second page sequences provided in an embodiment of this application.

[0197] like Figure 7 As shown, the method includes:

[0198] S701. From the second page set, obtain the similarity between the i-th image in the n-th second page sequence and the j-th image in the m-th second page sequence.

[0199] The number of images included in the nth second page sequence and the mth second page sequence can be the same or different.

[0200] When the second page set has sequence lengths of 1, 2, ..., X-1, the nth second page sequence and the mth second page sequence contain the same number of images.

[0201] When the second page set is of sequence length X, the number of images included in the nth second page sequence and the mth second page sequence may be different.

[0202] Initially, i equals the total number of images included in the nth second page sequence, and j equals the total number of images included in the mth second page sequence.

[0203] S702. Determine whether the similarity is not less than the first threshold.

[0204] If so, execute S703 to S705; otherwise, execute S706.

[0205] S703. Determine whether i is not greater than the first preset value and whether j is not greater than the second preset value.

[0206] If yes, then execute S704; otherwise, execute S705.

[0207] When the number of images included in the nth second page sequence and the mth second page sequence is the same, the first preset value and the second preset value are the same and both take the value of 1.

[0208] When the number of images included in the nth second page sequence and the mth second page sequence are not the same, the first preset value is equal to the difference between the number of images included in the nth second page sequence and A-1, and the second preset value is equal to the difference between the number of images included in the mth second page sequence and A-1. Here, A is a pre-set fixed value, for example, A can be equal to 3.

[0209] S704. Determine if the nth second page sequence is similar to the mth second page sequence.

[0210] S705, Repeat S701 to S703 for i-1 and j-1.

[0211] S706. Determine that the nth second page sequence is not similar to the mth second page sequence.

[0212] Figure 8 A flowchart illustrating the training method for the image contrast model provided in this application embodiment. Figure 8 As shown, the method includes:

[0213] S801: Obtain multiple abnormal sequences from samples.

[0214] Among them, multiple sample abnormal sequences were obtained after functional testing of multiple sample applications.

[0215] Each sample anomalous sequence includes multiple sample images.

[0216] S802: Perform classification and labeling processing on multiple abnormal sample sequences to obtain multiple sample image pairs and the corresponding label information for each sample image pair.

[0217] In one possible implementation, for each sample anomaly sequence, a target sample anomaly sequence is determined within the sample anomaly sequence; multiple sample image pairs are obtained from multiple target sample anomaly sequences; and label information is assigned to each sample image pair.

[0218] Optionally, multiple sample image pairs can be randomly obtained from multiple target sample anomaly sequences.

[0219] When the sample image pair is a positive sample pair, the label information is 1; when the sample image pair is a negative sample pair, the label information is 0.

[0220] In one possible implementation, determining the target sample anomaly sequence within the sample anomaly sequence includes:

[0221] Determine whether the number of sample images in the abnormal sample sequence is less than a preset number;

[0222] If the number is less than the preset number, the abnormal sample sequence will be identified as the target abnormal sample sequence.

[0223] If the number is not less than a preset number, then starting from the last sample image in the sample anomaly sequence, a preset number of sample images are sequentially and continuously obtained from the sample anomaly sequence, and the preset number of sample images are determined as the target sample anomaly sequence. Among them, the last image is the anomaly sample image in the sample anomaly sequence.

[0224] Optionally, the preset quantity can be equal to 4, 5, 6, 7, etc., and the value of the preset quantity is not limited here.

[0225] S803: Based on multiple sample image pairs and the corresponding label information of each sample image pair, adjust the model parameters of the initial comparison model to obtain the image comparison model.

[0226] Optionally, the initial comparison model can be a model based on the MobileNet-V2 Convolutional Neural Network (CNN) (e.g., block 1 and block 2 modules). Explanations of block 1 and block 2 modules can be found in existing technologies and will not be repeated here.

[0227] Specifically, the sample images can be input into the initial comparison model to obtain the feature vectors corresponding to the sample images;

[0228] Based on the label information corresponding to the sample images and the feature vectors corresponding to the sample images, the contrastive loss function is determined; based on the contrastive loss function, the model parameters of the initial contrast model are adjusted to obtain the image contrast model.

[0229] exist Figure 8 In the training method of the image comparison model provided in the embodiment, multiple abnormal sample sequences are obtained; the multiple abnormal sample sequences are classified and labeled to obtain multiple sample image pairs and the label information corresponding to each sample image pair; the model parameters of the initial comparison model are adjusted according to the multiple sample image pairs and the label information corresponding to each sample image pair to obtain the image comparison model. The image comparison model can be obtained quickly, so that the image comparison model can be used to perform image deduplication processing on multiple first page sequences to obtain multiple second page sequences, and to perform sequence clustering processing on the second page sequences in the second page set to obtain at least one first page set corresponding to the second page set, thereby improving the efficiency of finding the truly abnormal page sequences.

[0230] Figure 9 This is a schematic diagram of the structure of the initial comparative model provided in the embodiments of this application. For example... Figure 9 As shown, for example, the initial comparison model structure includes 11 processing layers. The 11 processing layers are: the first processing layer to the eleventh processing layer.

[0231] The first processing layer consists of a 3x3 convolutional layer (Conv2d).

[0232] The second processing layer consists of one block1 module.

[0233] The third processing layer consists of two block2 modules.

[0234] The fourth processing layer consists of three block2 modules.

[0235] The fifth processing layer consists of four block2 modules.

[0236] The sixth processing layer consists of three block1 modules.

[0237] The seventh processing layer consists of three block2 modules.

[0238] The eighth processing layer consists of one block1 module.

[0239] The ninth processing layer consists of a 1*1 convolutional layer.

[0240] The tenth processing layer consists of a pooling layer (AvgPooling) with a size of 7*7.

[0241] The eleventh processing layer consists of a 1*1 convolutional layer.

[0242] Figure 10 This is a schematic diagram of the structure of the information processing apparatus provided in an embodiment of this application. Figure 10 As shown, the information processing device 10 includes:

[0243] The acquisition module 101 is used to acquire multiple first page sequences; the multiple first page sequences are obtained by performing functional tests on the application, and each first page sequence includes an image of at least one page, which is a page included in the application;

[0244] The processing module 102 determines at least one set of first pages based on multiple first page sequences; the similarity between the page sequences included in the first page set is not less than a first threshold.

[0245] The information processing device 10 provided in this application embodiment can execute the above-described information processing method. Its implementation principle and beneficial effects are similar, and will not be described again here.

[0246] In one possible design, the processing module 102 is specifically used for:

[0247] Multiple first-page sequences are processed to remove duplicate images, resulting in multiple second-page sequences.

[0248] Based on multiple second page sequences, at least one first page set is determined; the similarity between the second page sequences included in the first page set is not less than a first threshold.

[0249] In one possible design, the processing module 102 is specifically used for:

[0250] Multiple second-page sequences are classified according to at least one sequence length to obtain at least one second-page set; the total number of images of each second-page sequence included in the second-page set corresponds to the sequence length of the second-page set.

[0251] Clustering is performed on the second page sequences included in each second page set to obtain at least one first page set corresponding to each second page set.

[0252] In one possible design, the processing module 102 is specifically used for:

[0253] Get the similarity between the i-th image and the (i+1)-th image in the first page sequence; if the similarity is less than the first threshold, increment the i-th image by 1 and repeat this step until the second page sequence is obtained; if the similarity is not less than the first threshold, delete the i-th image and increment the i-th image by 1, repeat this step until the second page sequence is obtained; initially, i equals 1, and j is the total number of images included in the first page sequence.

[0254] In one possible design, the processing module 102 is specifically used for:

[0255] Feature extraction is performed on the i-th image and the (i+1)-th image in the first page sequence to obtain the feature information corresponding to the i-th image and the (i+1)-th image respectively;

[0256] Based on the feature information corresponding to the i-th image and the (i+1)-th image, determine the similarity between the i-th image and the (i+1)-th image.

[0257] In one possible design, the processing module 102 is specifically used for:

[0258] By using a pre-trained image comparison model, feature extraction is performed on the i-th image and the (i+1)-th image to obtain the feature information corresponding to each of the i-th image and the (i+1)-th image.

[0259] The image comparison model is trained using multiple sets of training samples. Each set of training samples includes two sample images and the corresponding label information for the two sample images.

[0260] In one possible design, the processing module 102 is specifically used for:

[0261] Based on the feature information corresponding to the i-th image and the (i+1)-th image, determine the difference information between the i-th feature information and the (i+1)-th feature information;

[0262] The difference information is determined as the similarity between the i-th image and the (i+1)-th image.

[0263] The information processing apparatus provided in this application embodiment can execute the above-described information processing method. Its implementation principle and beneficial effects are similar, and will not be described again here.

[0264] Figure 11 This is a schematic diagram of the structure of the training device for the image contrast model provided in an embodiment of this application. Figure 11 As shown, the training device 20 for the image contrast model includes:

[0265] The acquisition module 201 is used to acquire multiple sample anomaly sequences; the sample anomaly sequence includes multiple sample images;

[0266] Processing module 202 is used to classify and label multiple abnormal sample sequences to obtain multiple sample image pairs and label information corresponding to each sample image pair;

[0267] The processing module 202 is also used to adjust the model parameters of the initial comparison model based on multiple sample image pairs and the label information corresponding to each sample image pair, so as to obtain an image comparison model.

[0268] The image comparison model training device 20 provided in this application embodiment can execute the above-described image comparison model training method. Its implementation principle and beneficial effects are similar, and will not be described again here.

[0269] In one possible design, the processing module 202 is specifically used for:

[0270] For each sample anomaly sequence, identify the target sample anomaly sequence within the sample anomaly sequence;

[0271] Obtain multiple sample image pairs from multiple target sample anomaly sequences;

[0272] Label each sample image pair with its own label information.

[0273] In one possible design, the processing module 202 is specifically used for:

[0274] Determine whether the number of sample images in the abnormal sample sequence is less than a preset number;

[0275] If the number is less than the preset number, the abnormal sample sequence will be identified as the target abnormal sample sequence.

[0276] If the number is not less than the preset number, then starting from the last sample image in the sample anomaly sequence, the preset number of sample images are obtained sequentially from the sample anomaly sequence, and the preset number of sample images are determined as the target sample anomaly sequence; the last image is the anomaly sample image in the sample anomaly sequence.

[0277] The image comparison model training device provided in this application embodiment can execute the above-described image comparison model training method. Its implementation principle and beneficial effects are similar, and will not be described again here.

[0278] Figure 12 This is a schematic diagram of the hardware structure of the electronic device provided in an embodiment of this application. Figure 12 As shown, the electronic device 30 includes a processor 301 and a memory 302 communicatively connected to the processor 301.

[0279] The processor 301 and the memory 302 are connected via a bus 303.

[0280] In the specific implementation process, the processor 301 executes the computer execution instructions stored in the memory 302, causing the processor 301 to perform the information processing method described above.

[0281] The specific implementation process of processor 301 can be found in the above information processing method. Its implementation principle and technical effect are similar, and will not be repeated here in this embodiment.

[0282] Figure 13 This is a schematic diagram of the hardware structure of the training device for the image contrast model provided in an embodiment of this application. Figure 13 As shown, the training device 40 for the image contrast model includes: a processor 401 and a memory 402 communicatively connected to the processor 401;

[0283] The processor 401 and the memory 402 are connected via a bus 403.

[0284] In the specific implementation process, the processor 401 executes the computer execution instructions stored in the memory 402, causing the processor 401 to perform the information processing method described above.

[0285] The specific implementation process of processor 401 can be found in the training method of the image comparison model described above. Its implementation principle and technical effect are similar, and will not be repeated here in this embodiment.

[0286] In this application, the electronic device and the training device for the image contrast model can be the same device or different devices.

[0287] In the above Figure 12 and Figure 13 In the illustrated embodiments, it should be understood that the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in the application can be directly manifested as being executed by a hardware processor, or executed by a combination of hardware and software modules within the processor.

[0288] The memory may include high-speed RAM, or it may also include non-volatile memory (NVM), such as disk storage.

[0289] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of illustration, the buses shown in the accompanying drawings are not limited to a single bus or a single type of bus.

[0290] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement an information processing method and an image comparison model training method.

[0291] This application provides a computer program product, including a computer program that, when executed by a processor, implements an information processing method and an image comparison model training method.

[0292] The aforementioned computer-readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The readable storage medium can be any available medium accessible to a general-purpose or special-purpose computer.

[0293] An exemplary readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can reside in an Application Specific Integrated Circuit (ASIC). Alternatively, the processor and the readable storage medium can exist as discrete components in the device.

[0294] The division of units is merely a logical functional division; in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0295] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0296] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0297] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0298] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0299] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features therein. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application.

Claims

1. An information processing method, characterized in that, include: Obtain multiple first page sequences; the multiple first page sequences are obtained by performing functional tests on the application, and each first page sequence includes an image of at least one page, the page being a page included in the application; The plurality of first page sequences are subjected to image deduplication processing to obtain a plurality of second page sequences; the plurality of second page sequences are classified according to at least one sequence length to obtain at least one second page set; the total number of images of each second page sequence included in the second page set corresponds to the sequence length corresponding to the second page set; the second page sequences included in each second page set are clustered to obtain at least one first page set corresponding to each second page set; the similarity between the second page sequences included in the first page set is not less than a first threshold.

2. The method according to claim 1, characterized in that, The first page sequence is deduplicated to obtain the second page sequence, which includes: Obtain the similarity between the i-th image and the (i+1)-th image in the first page sequence; if the similarity is less than a first threshold, increment the i-th image by 1 and repeat this step until the second page sequence is obtained; if the similarity is not less than the first threshold, delete the i-th image, increment the i-th image by 1, and repeat this step until the second page sequence is obtained; initially, i equals 1, and j is the total number of images included in the first page sequence.

3. The method according to claim 2, characterized in that, Obtaining the similarity between the i-th image and the (i+1)-th image in the first page sequence includes: Feature extraction processing is performed on the i-th image and the (i+1)-th image in the first page sequence to obtain the feature information corresponding to the i-th image and the (i+1)-th image respectively; The similarity between the i-th image and the (i+1)-th image is determined based on the feature information corresponding to each of the i-th image and the (i+1)-th image.

4. The method according to claim 3, characterized in that, The step of performing feature extraction processing on the i-th image and the (i+1)-th image in the first page sequence to obtain the feature information corresponding to the i-th image and the (i+1)-th image respectively includes: By using a pre-trained image comparison model, feature extraction processing is performed on the i-th image and the (i+1)-th image to obtain the feature information corresponding to each of the i-th image and the (i+1)-th image. The image comparison model is trained using multiple sets of training samples. Each set of training samples includes two sample images and the corresponding label information for the two sample images.

5. The method according to claim 3, characterized in that, The step of determining the similarity between the i-th image and the (i+1)-th image based on the feature information corresponding to the i-th image and the (i+1)-th image respectively includes: Based on the feature information corresponding to the i-th image and the (i+1)-th image respectively, determine the difference information between the i-th feature information and the (i+1)-th feature information; The difference information is determined as the similarity between the i-th image and the (i+1)-th image.

6. The method according to claim 4, characterized in that, The image comparison model was trained in the following manner: Obtain multiple abnormal sample sequences; the abnormal sample sequences include multiple sample images; The multiple abnormal sample sequences are classified and labeled to obtain multiple sample image pairs and label information corresponding to each sample image pair; Based on the multiple sample image pairs and the corresponding label information of each sample image pair, the model parameters of the initial comparison model are adjusted to obtain the image comparison model.

7. The method according to claim 6, characterized in that, The classification and labeling process of the multiple abnormal sample sequences yields multiple sample image pairs and corresponding label information for each sample image pair, including: For each sample anomaly sequence, determine the target sample anomaly sequence within the sample anomaly sequence; Obtain multiple sample image pairs from multiple target sample anomaly sequences; Each of the sample image pairs is labeled with the tag information.

8. The method according to claim 7, characterized in that, Determining the target sample anomaly sequence in the sample anomaly sequence includes: Determine whether the number of sample images in the abnormal sample sequence is less than a preset number; If the number is less than the preset number, then the abnormal sample sequence is determined as the target abnormal sample sequence; If the number is not less than the preset number, then starting from the last sample image in the sample anomaly sequence, the preset number of sample images are obtained sequentially and continuously from the sample anomaly sequence, and the preset number of sample images are determined as the target sample anomaly sequence; the last image is the anomaly sample image in the sample anomaly sequence.

9. An information processing device, characterized in that, include: An acquisition module is used to acquire multiple first page sequences; the multiple first page sequences are obtained by performing functional tests on the application, and each first page sequence includes an image of at least one page, which is a page included in the application; The processing module performs image deduplication on the plurality of first page sequences to obtain a plurality of second page sequences; classifies the plurality of second page sequences according to at least one sequence length to obtain at least one second page set; the total number of images of each second page sequence included in the second page set corresponds to the sequence length corresponding to the second page set; clusters the second page sequences included in each second page set to obtain at least one first page set corresponding to each second page set; the similarity between the page sequences included in the first page set is not less than a first threshold.

10. The apparatus according to claim 9, characterized in that, include: The acquisition module is also used to acquire multiple sample anomaly sequences; the sample anomaly sequences include multiple sample images; The processing module is used to classify and label the multiple abnormal sample sequences to obtain multiple sample image pairs and label information corresponding to each sample image pair; The processing module is further configured to adjust the model parameters of the initial comparison model based on the plurality of sample image pairs and the label information corresponding to each sample image pair, so as to obtain an image comparison model.

11. An electronic device, characterized in that, include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory to implement the method as described in any one of claims 1 to 6.

12. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, implement the method described in any one of claims 1 to 8.

13. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the method according to any one of claims 1 to 8.

Images