Automatic testing method, device and equipment for intelligent question-answering system and storage medium

Abstract

The invention discloses an automatic testing method and device for an intelligent question-answering system, equipment and a storage medium, and relates to the field of artificial intelligence. Corpus information of a knowledge base platform is adjusted and published; if the corpus publishing result indicates that publishing is successful, the adjusted corpus information is synchronized to a human-computer interaction platform; when the corpus synchronization result indicates that the synchronization succeeds, executing an index construction operation, and executing a corpus recall operation by using the successfully constructed target index under the condition that the execution succeeds; and if the corpus recall result accords with the expected recall result, generating and outputting a test result used for indicating that the full-link process verification of the intelligent question-answering system is successful. Through links of corpus construction, corpus synchronization, index construction, corpus recall and the like in series connection, the method can be applied to the business fields of financial science and technology, medical health, old-age care and the like, automatic verification is realized in an online customer service intelligent question-answering system of related businesses, automatic interruption is realized when nodes are abnormal, error information is thrown out, the manpower analysis cost is reduced, and the test efficiency is improved.

Description

Technical Field

[0001] This application relates to the field of artificial intelligence and can be applied to the fields of medical health and financial technology, and in particular to an automated testing method, device, equipment and storage medium for an intelligent question-and-answer system. Background Art

[0002] With the development of artificial intelligence (AI), intelligent question-answering (FAQ) systems have become a core application in the information exchange field, supporting functions such as financial product consulting, investment and financial planning, intelligent medical consultation, and disease-assisted diagnosis. Frequently Asked Questions (FAQ) is a Q&A platform service built by the architecture team based on an AI-related technology stack. The system includes multiple steps, including knowledge base corpus construction, corpus synchronization, indexing, corpus recall, and ranking.

[0003] In the prior art, manual verification of corpus synchronization data is often performed to verify the success of corpus synchronization. The index is then manually constructed and the accuracy of the entire index construction process is verified. However, the applicant recognizes that index construction is a typically lengthy process, with multiple steps and a lengthy process, from corpus creation to index construction and FAQ recall. Manual operation results in long testing times and low testing efficiency. Summary of the Invention

[0004] In view of this, the present application provides an automated testing method, device, equipment and readable storage medium for an intelligent question-answering system. The main purpose is to solve the problem that there are many links and a long process from creating corpus to building index to FAQ recall, and manual operation will result in long testing time and low testing efficiency.

[0005] According to the first aspect of the present application, there is provided an automated testing method for an intelligent question-answering system, the method comprising:

[0006] Adopting an automated browser operation method to adjust the corpus information of the knowledge base platform, and publishing the adjusted corpus information to obtain a corpus publishing result;

[0007] If the corpus publishing result indicates that the corpus is successfully published, synchronizing the adjusted corpus information in the knowledge base platform to the human-computer interaction platform to obtain a corpus synchronization result;

[0008] When the corpus synchronization result indicates that the corpus synchronization is successful, performing an index building operation, and if the index building operation is successfully executed, obtaining a successfully built target index, performing a corpus recall operation using the target index, and obtaining a corpus recall result;

[0009] If the corpus recall result meets the expected recall result, the intelligent question-answering system in which the knowledge base platform and the human-computer interaction platform are located is determined, a test result indicating that the full-link process verification of the intelligent question-answering system is successful is generated, and the test result is output.

[0010] According to a second aspect of the present application, there is provided an automated testing device for an intelligent question-answering system, the device comprising:

[0011] The corpus adjustment and publishing module is used to adjust the corpus information of the knowledge base platform using an automated browser operation method, and publish the adjusted corpus information to obtain a corpus publishing result;

[0012] A corpus synchronization module is configured to synchronize the adjusted corpus information in the knowledge base platform to the human-computer interaction platform to obtain a corpus synchronization result if the corpus publishing result indicates that the corpus is successfully published;

[0013] An index building and corpus recall module, configured to, when the corpus synchronization result indicates that the corpus synchronization is successful, perform an index building operation, and, if the index building operation is successfully executed, obtain a successfully constructed target index, perform a corpus recall operation using the target index, and obtain a corpus recall result;

[0014] The first output module is used to determine the intelligent question-answering system in which the knowledge base platform and the human-computer interaction platform are located if the corpus recall result meets the expected recall result, generate a test result indicating that the full-link process verification of the intelligent question-answering system is successful, and output the test result.

[0015] According to a third aspect of the present application, a device is provided, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of any one of the methods described in the first aspect when executing the computer program.

[0016] According to a fourth aspect of the present application, a storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of any one of the methods in the first aspect are implemented.

[0017] By means of the above technical solution, the technical solution provided by the embodiment of the present invention has at least the following advantages:

[0018] The present application provides an automated testing method, apparatus, device and storage medium for an intelligent question-and-answer system. The present application adopts an automated browser operation method to adjust the corpus information of a knowledge base platform, and publishes the adjusted corpus information to obtain a corpus publishing result; if the corpus publishing result indicates that the corpus publishing is successful, the adjusted corpus information in the knowledge base platform is synchronized to the human-computer interaction platform to obtain a corpus synchronization result; when the corpus synchronization result indicates that the corpus synchronization is successful, an index construction operation is performed, and when the index construction operation is successfully executed, a successfully constructed target index is obtained, and a corpus recall operation is performed using the target index to obtain a corpus recall result; if the corpus recall result meets the expected recall result, the intelligent question-and-answer system in which the knowledge base platform and the human-computer interaction platform are located is determined, a test result is generated to indicate that the full-link process verification of the intelligent question-and-answer system is successful, and the test result is output. By serially constructing knowledge base corpus, corpus synchronization, index construction, corpus recall, sorting and other links, the entire link can be automatically executed and verified. At the same time, it can automatically interrupt and throw error messages when an exception occurs in each node of the link, timely discover problem links in long process links, reduce human analysis costs, and greatly improve testing efficiency.

[0019] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Various other advantages and benefits will become apparent to those skilled in the art upon reading the detailed description of the preferred embodiment below. The accompanying drawings are for illustration purposes only and are not to be considered as limiting the present application. The same reference symbols are used throughout the drawings to represent the same components. In the drawings:

[0021] Figure 1 A schematic diagram of an application environment for automated testing of an intelligent question-answering system provided in an embodiment of the present application is shown;

[0022] Figure 2 A schematic diagram of a method flow for automated testing of an intelligent question-answering system provided in an embodiment of the present application is shown;

[0023] Figure 3 A schematic diagram of a method flow chart for automated testing of another intelligent question-answering system provided in an embodiment of the present application is shown;

[0024] Figure 4 A schematic diagram of a process flow for automated testing of the entire FAQ index construction process provided by an embodiment of the present application is shown;

[0025] Figure 5 A schematic diagram of the structure of an automated test of an intelligent question-answering system provided in an embodiment of the present application is shown;

[0026] Figure 6 A schematic diagram showing the structure of an automated test of another intelligent question-answering system provided in an embodiment of the present application is shown;

[0027] Figure 7 A schematic diagram of the device structure of a device provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0028] In the description of the present invention, it should be understood that the terms "first" and "second" are used for descriptive purposes only and should not be understood to indicate or imply relative importance or implicitly specify the number of the technical features indicated. Therefore, a feature specified as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, "plurality" means two or more, unless otherwise specifically defined.

[0029] The following describes exemplary embodiments of the present application in more detail with reference to the accompanying drawings. Although exemplary embodiments of the present application are shown in the accompanying drawings, it should be understood that the present application can be implemented in various forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided to enable a more thorough understanding of the present application and to fully convey the scope of the present application to those skilled in the art.

[0030] The automated testing method for the intelligent question-answering system provided in the embodiment of the present application can be applied in Figure 1In the application environment, the execution subject of this application is an automated testing system. The automated testing system relies on the computing power of the server to provide services to users, and relies on the client to provide service programs for users corresponding to the server. The client communicates with the server through the network. The server uses an automated browser operation method to adjust the corpus information of the knowledge base platform, and publishes the adjusted corpus information to obtain a corpus publishing result; if the corpus publishing result indicates that the corpus is successfully published, the adjusted corpus information in the knowledge base platform is synchronized to the human-computer interaction platform to obtain a corpus synchronization result; when the corpus synchronization result indicates that the corpus synchronization is successful, the index construction operation is performed, and when the index construction operation is successfully executed, the successfully constructed target index is obtained, and the corpus recall operation is performed using the target index to obtain a corpus recall result; if the corpus recall result meets the expected recall result, the intelligent question and answer system in which the knowledge base platform and the human-computer interaction platform are located is determined, and a test result indicating that the full-link process verification of the intelligent question and answer system is successful is generated, and the test result is returned to the client. By serially constructing the knowledge base corpus, corpus synchronization, index construction, corpus recall, sorting and other links, the entire link is automatically executed and automatically verified, reducing labor costs and improving testing efficiency. The client can be, but is not limited to, various personal computers, laptops, smartphones, tablets, and portable wearable devices. The server can be a standalone server or a server that provides basic cloud computing such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms. The present application is described in detail below through specific embodiments.

[0031] The present application embodiment provides an automated testing method for an intelligent question-answering system. Figure 2 As shown, the method includes:

[0032] 101. Use an automated browser operation method to adjust the corpus information of the knowledge base platform, and publish the adjusted corpus information to obtain a corpus publishing result.

[0033] In an embodiment of the present application, in the financial field, the knowledge base platform stores a large amount of corpus information related to financial products, business processes, market dynamics, laws and regulations, etc. Manually adjusting the corpus word by word is time-consuming and labor-intensive, and errors caused by human operation may also occur. The automated browser operation method is to use a program to simulate manual operations on the browser, so as to perform adjustment operations such as addition, deletion, and modification on the corpus in the knowledge base. A large amount of corpus information can be quickly processed in batches, and the consistency and accuracy of the corpus adjustment can be ensured. For example, when a new financial product is launched, relevant information such as the product's features and the method of calculating returns needs to be added to the knowledge base; or when financial laws and regulations are updated, the corpus such as the interpretation of the terms involved needs to be modified. After the adjustment is completed, the updated corpus information is published through automated operations, so that users (such as financial institution employees, customers, etc.) can obtain the latest and accurate knowledge content, which can greatly shorten the time compared to manually searching and modifying one by one.

[0034] In the medical field, medical knowledge bases are vast and constantly updated, making manual, word-by-word revision of these data consuming time and effort. Automated browser operations can rapidly process large amounts of data in batches, such as updating and adjusting symptoms, treatments, and other content across multiple disease entries simultaneously. This significantly reduces data revision time and improves work efficiency. For example, when new medical research indicates a change in treatment options for a particular disease, automated operations can quickly update the relevant data in the knowledge base, enabling timely revision and improvement of knowledge and enabling users to access the latest and most accurate medical information more quickly.

[0035] 102. If the corpus publishing result indicates that the corpus is successfully published, the adjusted corpus information in the knowledge base platform is synchronized to the human-computer interaction platform to obtain a corpus synchronization result.

[0036] In the embodiment of the present application, after the corpus information is adjusted and published automatically, if it is confirmed that the corpus has been successfully published, that is, the adjusted corpus has been correctly displayed on the knowledge base platform, then the latest corpus information is synchronized to the human-computer interaction platform to ensure the consistency of the data between the knowledge base platform and the human-computer interaction platform. In the financial field, the human-computer interaction platform is the interface for financial institutions to interact with customers or employees, such as mobile banking apps, online banking pages, and financial product transaction clients. In the medical field, human-computer interaction platforms include hospital intelligent consultation systems, doctor workstation query terminals, and patient self-service consultation apps.

[0037] The automated testing system can monitor the corpus publishing status in real time. Only when the corpus publishing is confirmed to be successful can the corpus synchronization operation be triggered. There is no need for manual waiting, viewing and manual initiation of the synchronization process, which improves the work efficiency of the entire process testing.

[0038] 103. When the corpus synchronization result indicates that the corpus synchronization is successful, an index building operation is performed. When the index building operation is successfully performed, a successfully built target index is obtained, and a corpus recall operation is performed using the target index to obtain a corpus recall result.

[0039] In the embodiment of the present application, after the corpus is successfully synchronized to the human-computer interaction platform, it is necessary to index this corpus. By marking and arranging key information in the corpus, such as financial product names and financial terms in the financial field, and disease names, symptoms, drug ingredients, and examination items in the medical field, a target index is generated. With the target index, when a user asks a question or searches on the human-computer interaction platform, the intelligent question-answering system can quickly locate the relevant corpus based on this index, extracting qualified content from the large amount of stored corpus, and improving the accuracy of business processing.

[0040] The automated testing system only builds the index after successful corpus synchronization, ensuring that the data used for index construction is complete and accurately synchronized. Building the index before corpus synchronization contains missing or erroneous data can lead to incorrect results when recalling corpora based on the index, such as recalling irrelevant or incomplete corpora. By testing corpus synchronization results, we can prevent subsequent operations from being affected by data source issues and maintain data accuracy and consistency at all stages.

[0041] Secondly, the automated testing system only performs corpus recall operations after confirming that the index has been successfully built, ensuring that the recall operation is based on a correctly constructed index. If the index construction contains loopholes, such as incorrect index structure or incomplete index information, the required corpus cannot be accurately recalled. This ensures that the corpus recall process uses a valid and correct index, improving the accuracy and effectiveness of corpus recall.

[0042] 104. If the corpus recall result meets the expected recall result, the intelligent question-answering system where the knowledge base platform and the human-computer interaction platform are located is determined, and a test result indicating that the full-link process verification of the intelligent question-answering system is successful is generated, and the test result is output.

[0043] In this embodiment of the present application, after a user asks a question, the intelligent question-answering system will perform a corpus recall operation from the corpus associated with the knowledge base platform and the human-computer interaction platform based on the previously constructed index, and obtain a corpus recall result, which is the relevant information retrieved by the intelligent question-answering system. The expected recall result is the corpus information that is pre-set during the test and is expected to be retrieved by the intelligent question-answering system and is correct and meets the user's question intent.

[0044] When the corpus recall result matches the expected recall result, that is, when the information retrieved by the intelligent question-answering system is exactly what the user needs and meets the correct answer criteria, it can be determined that the intelligent question-answering system, which is composed of a knowledge base platform and a human-computer interaction platform, is operating normally. At this point, the system will generate a test result. This test result is used to indicate that the entire process of the intelligent question-answering system from corpus adjustment, publishing, synchronization, index construction to corpus recall has been successfully verified, which means that the system can accurately and effectively provide users with answers to questions related to the financial field or the medical field. Finally, the system will output this test result so that relevant personnel (such as system developers, operation and maintenance personnel, financial institution managers, medical staff, patient users, etc.) can view it and confirm the reliability and availability of the system.

[0045] Through full-link process verification, the system is considered successful only when the corpus publishing result indicates successful corpus publishing, the corpus synchronization result indicates successful corpus synchronization, the index construction operation is executed successfully, and the corpus recall results meet expectations. This effectively ensures the reliability of intelligent question-answering systems in the financial and medical fields. For example, when a customer inquires about the risk assessment of an investment product, the intelligent question-answering system accurately recalls the expected risk assessment-related corpus and provides the customer with the correct answer, avoiding investment decision-making errors due to incorrect information and ensuring the safety of the customer's funds. For another example, if a patient enters symptoms of persistent abdominal pain, nausea and vomiting for three days, the intelligent question-answering system's expected recall results include differential diagnoses such as acute pancreatitis, intestinal obstruction, and peptic ulcers, as well as corresponding laboratory tests, imaging examinations, and emergency treatment measures. This provides doctors with comprehensive and accurate disease differential diagnosis information and avoids diagnostic errors due to missing information.

[0046] An embodiment of the present application provides an automated testing method for an intelligent question-and-answer system. Compared with the prior art, the embodiment of the present invention adjusts the corpus information of the knowledge base platform by adopting an automated browser operation method, and publishes the adjusted corpus information to obtain a corpus publishing result; if the corpus publishing result indicates that the corpus publishing is successful, the adjusted corpus information in the knowledge base platform is synchronized to the human-computer interaction platform to obtain a corpus synchronization result; when the corpus synchronization result indicates that the corpus synchronization is successful, an index construction operation is performed, and when the index construction operation is successfully executed, a successfully constructed target index is obtained, and a corpus recall operation is performed using the target index to obtain a corpus recall result; if the corpus recall result meets the expected recall result, the intelligent question-and-answer system in which the knowledge base platform and the human-computer interaction platform are located is determined, a test result is generated to indicate that the full-link process verification of the intelligent question-and-answer system is successful, and the test result is output. By serially constructing knowledge base corpus, corpus synchronization, index construction, corpus recall, sorting and other links, the entire link can be automatically executed and verified. At the same time, it can automatically interrupt and throw error messages when an exception occurs in each node of the link, timely discover problem links in long process links, reduce human analysis costs, and greatly improve testing efficiency.

[0047] Furthermore, as a refinement and expansion of the specific implementation of the above embodiment, in order to fully illustrate the specific implementation process of this embodiment, the embodiment of the present application provides another automated testing method for the intelligent question-answering system, such as Figure 3 As shown, the method includes:

[0048] 201. Use an automated browser operation method to adjust the corpus information of the knowledge base platform, and publish the adjusted corpus information to obtain a corpus publishing result. If the corpus publishing result indicates that the corpus is successfully published, execute the following step 203; if the corpus publishing result indicates that the corpus is abnormal, execute the following step 202.

[0049] In an embodiment of the present application, an automated testing system uses an automated browser operation method to launch a browser and precisely control the browser to display the first platform login page of a knowledge base platform. The automated browser operation method can be a playwright method. In the financial sector, data volumes are vast, including numerous corpora such as customer consultation records and financial product introduction documents. Automated browser operation can quickly launch the browser, log in to the knowledge base platform, and process the corpora, ensuring the accuracy and reliability of financial corpus data and maintaining the stable operation of financial services. In the medical sector, knowledge is rapidly updated, with new diseases, new therapies, and new drugs constantly emerging. Automated browser operation can quickly process large amounts of corpora, such as simultaneously updating the latest diagnostic criteria and therapeutic drug information for multiple diseases. Compared to manual operation, automated browser operation can complete adjustments such as adding, modifying, and deleting large amounts of corpora in a short period of time, greatly improving knowledge base update efficiency. Next, the automated testing system obtains pre-set first access information for logging into the knowledge base platform, including security credentials such as username, password, and dynamic verification code. On the first platform login page, the system automatically fills in and submits the first access information to log in to the knowledge base platform. Furthermore, the automated browser operation method uses element location strategies to precisely locate the corpus management page of the knowledge base platform. Then, based on the corpus management page, the automated testing system adjusts the corpus information of the knowledge base platform to obtain the adjusted corpus information, where corpus adjustment includes at least one of corpus addition, corpus modification, and corpus deletion, which can timely update the relevant information in the knowledge base. For example, in the financial field, if it is found that the introduction of a certain financial product is ambiguous, it can be modified in time; for expired product information, the deletion operation can be performed. For another example, in the medical field, when new disease diagnosis and treatment guidelines are released, such as new targeted treatment plans for cancer, relevant corpus can be added to the knowledge base through automated operations; if it is found that the adverse reaction information of a certain drug is updated, the corresponding corpus can be modified in time; for information related to obsolete medical technologies, the deletion operation can be performed.

[0050] After completing the corpus adjustment, the automated testing system uses automated browser operations to publish the adjusted corpus information and employs an element location strategy to locate the corpus release list page on the knowledge base platform. This page details information such as the time, operator, and corpus type of each corpus release. The element location strategy accurately locates the target page based on the characteristics of page elements. Even if the knowledge base platform's page layout changes, as long as the key characteristics of the elements remain unchanged, the corpus release list page can be quickly located, demonstrating its strong adaptability and flexibility. The latest release record corresponding to this corpus release is then obtained from the corpus release list page, and the status display parameters are read from the latest release record. Then, the automated testing system obtains a preset expected value, compares the preset expected value with the status display parameter, and generates a corpus publishing result based on the comparison result. If the comparison determines that the status display parameter meets the preset expected value, a corpus publishing result is generated to indicate that the corpus publishing is successful; and if the comparison determines that the status display parameter does not meet the preset expected value, a corpus publishing result is generated to indicate that the corpus publishing is abnormal. By automatically comparing the preset expected value and the status display parameter, an intelligent judgment of the corpus publishing result is achieved, reducing the subjectivity and uncertainty of manual judgment. If the corpus publishing result indicates that the corpus publishing is successful, the following step 203 is executed; if the corpus publishing result indicates that the corpus publishing is abnormal, the following step 202 is executed. Therefore, by verifying the reliability of the knowledge base corpus publishing link, corpus publishing problems of the knowledge base platform can be discovered in a timely manner, the process can be interrupted, and the use case execution results can be fed back.

[0051] 202. If the corpus publishing result indicates that the corpus publishing is abnormal, a test result indicating that the knowledge base platform corpus publishing is abnormal is generated, and the test result is output.

[0052] In an embodiment of the present application, if the corpus publishing result indicates that the corpus publishing is abnormal, it means that the corpus publishing operation has failed, and a test result is generated to indicate that the corpus publishing on the knowledge base platform is abnormal, and the test result is output to more intuitively feedback the abnormal situation in the long link process test.

[0053] 203. If the corpus publishing result indicates that the corpus is successfully published, the adjusted corpus information in the knowledge base platform is synchronized to the human-computer interaction platform to obtain the corpus synchronization result. When the corpus synchronization result indicates that the corpus synchronization is successful, the following step 205 is executed; when the corpus synchronization result indicates that the corpus synchronization is abnormal, the following step 204 is executed.

[0054] In an embodiment of the present application, the automated testing system uses an automated browser operation method to start the browser, control the browser to display the second platform login page of the human-computer interaction platform, and obtain the preset second access information for logging into the human-computer interaction platform, including user name, password, dynamic verification code and other security credentials. On the second platform login page, the second access information is used to log in to the human-computer interaction platform.

[0055] An element positioning strategy using an automated browser operation method is used to locate the corpus synchronization page of the human-computer interaction platform, and based on the corpus synchronization page, a resource interaction method is used to synchronize the adjusted corpus information in the knowledge base platform, wherein the resource interaction method can be a request method.

[0056] The corpus synchronization interface, invoked based on the resource interaction method, serves as a bridge between the knowledge base platform and the human-computer interaction platform for data transmission and status feedback. Through this interface, the automated testing system can obtain the task status of the corpus synchronization in real time and generate a corpus synchronization result based on the task status. If the task status indicates success, it indicates that the human-computer interaction platform has successfully acquired and updated the adjusted corpus from the knowledge base platform, generating a corpus synchronization result indicating successful corpus synchronization. If the task status indicates failure, a corpus synchronization result is generated indicating a corpus synchronization anomaly. In financial scenarios, when launching new financial products or services, synchronization testing of the relevant corpus can be performed quickly to promptly identify corpus data synchronization anomalies, interrupt the process, and provide feedback on the use case execution results. In medical scenarios, information accuracy is crucial. For example, synchronization errors in corpus information such as drug usage, dosage, and contraindications can lead to medication errors by medical staff, endangering the patient's health. The corpus synchronization testing process ensures that corpus data is accurately synchronized from the knowledge base platform to the human-computer interaction platform, safeguarding the reliability of medical information. Finally, when the corpus synchronization result indicates that the corpus synchronization is successful, the following step 205 is executed; when the corpus synchronization result indicates that the corpus synchronization is abnormal, the following step 204 is executed.

[0057] 204. When the corpus synchronization result indicates that the corpus synchronization is abnormal, a test result indicating that the corpus synchronization of the human-computer interaction platform is abnormal is generated, and the test result is output.

[0058] In the embodiment of the present application, when the corpus synchronization result indicates a corpus synchronization anomaly, it indicates that the corpus synchronization operation has failed, and a test result indicating a corpus synchronization anomaly on the human-computer interaction platform is generated and output. Automatically generating an abnormality test result can help technicians quickly identify problems with the corpus synchronization operation.

[0059] 205. When the corpus synchronization result indicates that the corpus synchronization is successful, perform the index construction operation. If the index construction operation is successfully executed, obtain the successfully constructed target index, use the target index to perform the corpus recall operation, and obtain the corpus recall result. If the corpus recall result meets the expected recall result, execute the following step 207; if the corpus recall result does not meet the expected recall result, execute the following step 206.

[0060] In the embodiment of the present application, the intelligent question-answering system is crucial for providing financial information to customers and employees in a timely and accurate manner. In order to achieve efficient operation of the system, it is necessary to index and construct a large amount of financial corpus. The financial corpus covers various financial product information (such as the characteristics and returns of stocks, funds, bonds, etc.), interpretation of industry laws and policies, market dynamics analysis, etc. Therefore, the index construction operation is triggered by calling the operation interface based on the resource interaction method. The operation interface will process these corpora and construct an index structure that is convenient for rapid retrieval. In the medical scenario, the medical knowledge base contains a large amount of information, such as disease diagnosis standards, treatment plans, drug characteristics, medical research results, etc. Index construction is like establishing an efficient directory system for this information. The corpus is processed by calling the operation interface through the resource interaction method to form an index structure that is convenient for rapid retrieval. During the construction process, each index construction will get two results, either a successful construction or a failed construction. In order to increase the possibility of successful index construction, three retry operations are set. If the construction fails in the end, an abnormal result is generated and output.

[0061] When the first index building status indicates that the index building operation is successfully executed, the automated testing system obtains the successfully built target index and stores the target index in the database;

[0062] If the initial index build status indicates a failure, the automated testing system will call the operation interface to re-run the index build and retrieve the second index build status returned by the operation interface. For example, a server might experience a brief response delay due to a large number of data requests, causing the initial index build to fail. Retrying the operation might resolve the issue.

[0063] If the second index building status indicates that the index building operation is successfully re-executed, the automated testing system will obtain the successfully built target index and store the target index in the database;

[0064] If the second index building status indicates that the index building operation fails to be re-executed, the automated testing system will call the operation interface to execute the index building operation again and obtain the third index building status returned by the operation interface, which further increases the possibility of successful index building and reduces the impact of failures caused by accidental factors on the system.

[0065] When the third index building status indicates that the index building operation is successfully executed again, the automated testing system obtains the successfully built target index and stores the target index in the database;

[0066] If the third index building status indicates that the index building operation has failed again, the automated testing system will generate a test result indicating an abnormality in the intelligent question-answering system's index building, and output the test result. This can verify the abnormality in the index building process and actively initiate a retry. If the retry fails, the process will be interrupted and the use case execution result will be fed back, allowing technical personnel to conduct in-depth investigation and repair based on this result to ensure the normal operation of the system. Optionally, the successfully built target index can be stored in the database in the form of questions and answers, so that the intelligent question-answering system can quickly filter the corpus and return the corresponding information.

[0067] Whether in finance or healthcare, intelligent question-answering systems must maintain stable operation to meet user information needs. By performing index build operations multiple times, the probability of successful index builds is greatly increased, reducing system failures caused by accidental factors, ensuring that the index builds properly, and thus safeguarding system stability. If multiple attempts still fail, the system generates and outputs exception test results in a timely manner, allowing technicians to quickly locate and resolve the issue, helping to reduce the duration of system failures and minimize the impact on business operations.

[0068] After successfully acquiring the target index, the automated testing system calls the Q&A interface based on the resource interaction method. The Q&A interface then performs a corpus recall operation on the target index, verifying whether the updated corpus data is valid for index construction and whether newly added, modified, or deleted corpora are correctly recalled, ultimately obtaining a corpus recall result. In medical scenarios, for example, when a patient asks about treatment options for advanced lung cancer or a doctor inquires about the latest diagnostic criteria for a rare disease, the Q&A interface will quickly filter relevant information from a vast amount of medical corpus (including disease diagnosis and treatment guidelines, medical research literature, clinical cases, etc.) based on the target index, obtaining a corpus recall result. This verifies whether the index is valid and whether newly added, modified, or deleted corpora are correctly recalled. In this way, through rapid retrieval of the index, relevant information can be filtered out from a vast amount of financial corpus. For example, when a customer asks questions about the risk assessment of a particular stock or the return calculation of a particular financial product, the Q&A interface will use the target index to recall the corpus, ultimately obtaining a corpus recall result and providing the user with an accurate answer.

[0069] 206. If the corpus recall result does not meet the expected recall result, a test result indicating that the corpus recall of the intelligent question answering system is abnormal is generated, and the test result is output.

[0070] In an embodiment of the present application, if the corpus recall result does not meet the expected recall result, it indicates that the corpus recall is abnormal, and a test result is generated to indicate that the corpus recall of the intelligent question-answering system is abnormal, and the test result is output, so as to quickly troubleshoot the problem, restore accurate corpus recall, ensure that users obtain reliable information, and thereby improve user satisfaction.

[0071] 207. If the corpus recall result meets the expected recall result, the intelligent question-answering system where the knowledge base platform and the human-computer interaction platform are located is determined, a test result indicating that the full-link process verification of the intelligent question-answering system is successful is generated, and the test result is output.

[0072] In this embodiment of the application, customers rely on the intelligent question-and-answer system to obtain key information such as financial product information and market dynamics analysis. When the full-link process is successfully verified, it means that the information obtained by customers on the human-computer interaction platform is accurate, which can effectively prevent customers from making investment decisions due to incorrect information. For example, when a customer inquires about the risk rating of a fund product, the intelligent question-and-answer system can provide the correct answer based on the accurately recalled corpus.

[0073] In the healthcare field, medical decisions rely on accurate information. Successful full-link process verification ensures that the medical knowledge, diagnosis and treatment plans, and other information obtained by patients and medical staff are accurate and correct. For example, the latest disease diagnosis and treatment guidelines provided by the doctor reference system can help patients develop treatment plans, avoid misdiagnosis and mistreatment due to erroneous information, and ensure medical quality and patient safety. Furthermore, medical knowledge is constantly updated. Successful full-link process verification means that new medical research results, diagnosis and treatment standards, and so on can be promptly and accurately communicated to medical staff and patients. For example, after the release of new diagnostic criteria for rare diseases, they can be quickly updated to the knowledge base and accurately recalled, allowing doctors to grasp them in a timely manner and apply them in clinical practice.

[0074] In summary, the automated testing system uses automated scripts to connect the knowledge base corpus construction - corpus synchronization - index construction - corpus recall - sorting and other links in series, and the entire link is automatically executed and automatically verified. At the same time, it can automatically interrupt and throw error messages when an exception occurs in each link of the long process, and promptly discover the problem links in the long process link, greatly improving the testing efficiency. The automated testing method for the intelligent question-and-answer system proposed in this application can automatically verify after the use case execution is triggered, and automatically send an email to the user after the use case execution is completed or interrupted. It can more intuitively feedback the abnormal conditions of each link in the long link process test, and greatly reduce the cost of human analysis.

[0075] Furthermore, successfully verified test results serve as a benchmark for the normal operation of the intelligent question-answering system. If a problem arises later, comparison can quickly identify the abnormal link and narrow the scope of investigation. For example, if the intelligent question-answering system encounters an abnormality in corpus recall, it can quickly determine whether it is a new fault rather than an inherent problem in the entire process, improving problem location efficiency.

[0076] Based on the above process, a flowchart of an automated test of the entire FAQ index construction process proposed in an embodiment of the present application is as follows:

[0077] like Figure 4 As shown, the system automatically logs in to the knowledge base platform through UI automation, adds, modifies, deletes, and publishes corpus information. It then automatically determines whether the corpus has been published successfully. If the publication fails, execution is aborted, and a knowledge base corpus publication exception is returned and emailed. If the publication is successful, the system automatically logs in to the human-computer interaction platform through UI automation. It then obtains synchronized corpus data and automatically confirms whether the synchronization is successful. If synchronization fails, execution is aborted, and a synchronization exception is returned and emailed. If synchronization succeeds, it automatically initiates the index build process and automatically determines whether the build is successful. If the build fails, a retry is initiated. If the retry fails, execution is aborted, and a index build exception is returned and emailed. If the build succeeds or the retry succeeds, the results of the added, modified, or deleted corpus are verified through the interface. Specifically, by calling the Q&A engine's interface to input a question, the interface returns the correct answer. For example, if a question about a modified corpus is input, the interface returns the latest modified answer. If a corpus containing a currently deleted corpus is input, the interface does not return the deleted answer, indicating that the recall results meet expectations. If the recall result does not meet expectations, the abnormal result of taq index recall exception is returned and sent by email; if the recall result meets expectations, the return result of full-link process verification is returned and the full-link process verification result is sent by email.

[0078] An embodiment of the present application provides an automated testing method for an intelligent question-and-answer system. Compared with the prior art, the embodiment of the present invention adjusts the corpus information of the knowledge base platform by adopting an automated browser operation method, and publishes the adjusted corpus information to obtain a corpus publishing result; if the corpus publishing result indicates that the corpus publishing is successful, the adjusted corpus information in the knowledge base platform is synchronized to the human-computer interaction platform to obtain a corpus synchronization result; when the corpus synchronization result indicates that the corpus synchronization is successful, an index construction operation is performed, and when the index construction operation is successfully executed, a successfully constructed target index is obtained, and a corpus recall operation is performed using the target index to obtain a corpus recall result; if the corpus recall result meets the expected recall result, the intelligent question-and-answer system in which the knowledge base platform and the human-computer interaction platform are located is determined, a test result is generated to indicate that the full-link process verification of the intelligent question-and-answer system is successful, and the test result is output. By serially constructing knowledge base corpus, corpus synchronization, index construction, corpus recall, sorting and other links, the entire link can be automatically executed and verified. At the same time, it can automatically interrupt and throw error messages when an exception occurs in each node of the link, timely discover problem links in long process links, reduce human analysis costs, and greatly improve testing efficiency.

[0079] Further, as Figure 2 The specific implementation of the method, the embodiment of the present application provides an automated testing device for an intelligent question-answering system, such as Figure 5 As shown, the apparatus includes: a corpus adjustment and publishing module 301 , a corpus synchronization module 302 , an index construction and corpus recall module 303 and a first output module 304 .

[0080] The corpus adjustment and publishing module 301 is used to adjust the corpus information of the knowledge base platform using an automated browser operation method, and publish the adjusted corpus information to obtain a corpus publishing result;

[0081] A corpus synchronization module 302 is configured to synchronize the adjusted corpus information in the knowledge base platform to the human-computer interaction platform to obtain a corpus synchronization result if the corpus publishing result indicates that the corpus is successfully published;

[0082] The index building and corpus recall module 303 is configured to, when the corpus synchronization result indicates that the corpus synchronization is successful, perform an index building operation, and, if the index building operation is successful, obtain a successfully built target index, perform a corpus recall operation using the target index, and obtain a corpus recall result;

[0083] The first output module 304 is used to determine the intelligent question-answering system where the knowledge base platform and the human-computer interaction platform are located if the corpus recall result meets the expected recall result, generate a test result indicating that the full-link process verification of the intelligent question-answering system is successful, and output the test result.

[0084] In a specific application scenario, the corpus adjustment and publishing module 301 is used to start the browser using the automated browser operation method, control the browser to display the first platform login page of the knowledge base platform; obtain the preset first access information for logging into the knowledge base platform, and use the first access information to log in to the knowledge base platform on the first platform login page; use the element positioning strategy of the automated browser operation method to locate the corpus management page of the knowledge base platform, and based on the corpus management page, perform corpus adjustment on the corpus information of the knowledge base platform to obtain the adjusted corpus information, wherein the corpus adjustment includes at least one of corpus addition, corpus modification, and corpus deletion; use the automated browser operation method to start the browser, control the browser to display the first platform login page of the knowledge base platform ... The device operation method publishes the corpus information after adjustment, and adopts the element positioning strategy to locate the corpus publishing list page of the knowledge base platform, obtains the latest publishing record corresponding to this corpus publishing in the corpus publishing list page, and reads the status display parameter in the latest publishing record; obtains the preset expected value, compares the preset expected value with the status display parameter, and generates the corpus publishing result according to the comparison result, wherein, if the comparison determines that the status display parameter meets the preset expected value, the corpus publishing result indicating that the corpus publishing is successful is generated; and if the comparison determines that the status display parameter does not meet the preset expected value, the corpus publishing result indicating that the corpus publishing is abnormal is generated.

[0085] In a specific application scenario, the corpus synchronization module 302 is used to start a browser using the automated browser operation method, control the browser to display the second platform login page of the human-computer interaction platform; obtain preset second access information for logging into the human-computer interaction platform, and use the second access information to log in to the human-computer interaction platform on the second platform login page; use the element positioning strategy of the automated browser operation method to locate the corpus synchronization page of the human-computer interaction platform, and based on the corpus synchronization page, use the resource interaction method to synchronize the corpus information adjusted in the knowledge base platform; call the corpus synchronization interface based on the resource interaction method, obtain the task status of this corpus synchronization through the corpus synchronization interface, and generate the corpus synchronization result according to the task status, wherein, if the task status indicates successful execution, the corpus synchronization result indicating successful corpus synchronization is generated; and if the task status indicates failure, the corpus synchronization result indicating a corpus synchronization exception is generated.

[0086] In a specific application scenario, the index construction and corpus recall module 303 is used to call the operation interface based on the resource interaction method, perform the index construction operation through the operation interface, and obtain the first index construction status returned by the operation interface; when the first index construction status indicates that the index construction operation is successfully executed, obtain the successfully constructed target index; call the question and answer interface based on the resource interaction method, perform the corpus recall operation on the target index through the question and answer interface, and obtain the corpus recall result.

[0087] In a specific application scenario, the index construction and corpus recall module 303 is used to call the operation interface to re-execute the index construction operation when the first index construction status indicates that the index construction operation has failed to execute, and obtain the second index construction status returned by the operation interface; if the second index construction status indicates that the index construction operation has failed to re-execute, then call the operation interface to execute the index construction operation again, and obtain the third index construction status returned by the operation interface; when the third index construction status indicates that the index construction operation has failed to execute again, generate a test result indicating that the index construction of the intelligent question and answer system is abnormal, and output the test result.

[0088] In a specific application scenario, the index construction and corpus recall module 303 is used to obtain the successfully constructed target index if the second index construction status indicates that the index construction operation is successfully re-executed; or, if the third index construction status indicates that the index construction operation is successfully re-executed, obtain the successfully constructed target index.

[0089] In specific application scenarios, such as Figure 6 As shown, the device further includes: a second output module 305.

[0090] The second output module 305 is used to generate a test result indicating that the corpus publishing is abnormal on the knowledge base platform, and output the test result if the corpus publishing result indicates that the corpus publishing is abnormal; or, if the corpus synchronization result indicates that the corpus synchronization is abnormal, generate a test result indicating that the corpus synchronization is abnormal on the human-computer interaction platform, and output the test result; or, if the corpus recall result does not meet the expected recall result, generate a test result indicating that the corpus recall of the intelligent question and answer system is abnormal, and output the test result.

[0091] An embodiment of the present application provides a device. Compared with the prior art, the embodiment of the present invention adjusts the corpus information of the knowledge base platform by adopting an automated browser operation method, and publishes the adjusted corpus information to obtain a corpus publishing result; if the corpus publishing result indicates that the corpus publishing is successful, the adjusted corpus information in the knowledge base platform is synchronized to the human-computer interaction platform to obtain a corpus synchronization result; when the corpus synchronization result indicates that the corpus synchronization is successful, an index construction operation is performed, and when the index construction operation is successfully executed, a successfully constructed target index is obtained, and a corpus recall operation is performed using the target index to obtain a corpus recall result; if the corpus recall result meets the expected recall result, the intelligent question and answer system in which the knowledge base platform and the human-computer interaction platform are located is determined, a test result is generated to indicate that the full-link process verification of the intelligent question and answer system is successful, and the test result is output. By serially constructing knowledge base corpus, corpus synchronization, index construction, corpus recall, sorting and other links, the entire link can be automatically executed and verified. At the same time, it can automatically interrupt and throw error messages when an exception occurs in each node of the link, timely discover problem links in long process links, reduce human analysis costs, and greatly improve testing efficiency.

[0092] It should be noted that for other corresponding descriptions of the functional units involved in the automated testing device for an intelligent question-answering system provided in the embodiment of the present application, please refer to Figures 1 to 4 The corresponding description in will not be repeated here.

[0093] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0094] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0095] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present application. It should be noted that a person of ordinary skill in the art may make various modifications and improvements without departing from the spirit of the present application, and these modifications and improvements fall within the scope of protection of the present application. Therefore, the scope of protection of the present application shall be determined by the appended claims.

[0096] In an exemplary embodiment, see Figure 7A device is also provided, comprising a bus, a processor, a memory, and a communication interface. The device may also include an input / output interface and a display device, wherein the various functional units can communicate with each other via the bus. The memory stores a computer program, and the processor is configured to execute the program stored in the memory and perform the automated testing method for the intelligent question-answering system described in the above embodiment.

[0097] A storage medium stores a computer program, which, when executed by a processor, implements the steps of the automated testing method for an intelligent question-answering system.

[0098] Through the description of the above implementation methods, those skilled in the art can clearly understand that the present application can be implemented through hardware or by means of software plus a necessary general hardware platform. Based on this understanding, the technical solution of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.), including a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each implementation scenario of the present application.

[0099] Those skilled in the art will understand that the accompanying drawings are only schematic diagrams of a preferred implementation scenario, and the modules or processes in the accompanying drawings are not necessarily required to implement the present application.

[0100] Those skilled in the art will appreciate that the modules in the devices in the implementation scenario can be distributed in the devices of the implementation scenario according to the implementation scenario description, or can be modified accordingly and located in one or more devices different from the implementation scenario. The modules in the above implementation scenario can be combined into one module or further split into multiple submodules.

[0101] The above application serial numbers are for description only and do not represent the advantages or disadvantages of the implementation scenarios.

[0102] The above disclosure only describes several specific implementation scenarios of the present application. However, the present application is not limited thereto, and any changes that can be conceived by those skilled in the art should fall within the scope of protection of the present application.

Claims

1. An automated testing method for an intelligent question-answering system, characterized in that: include: Adopting an automated browser operation method to adjust the corpus information of the knowledge base platform, and publishing the adjusted corpus information to obtain a corpus publishing result; If the corpus publishing result indicates that the corpus is successfully published, synchronizing the adjusted corpus information in the knowledge base platform to the human-computer interaction platform to obtain a corpus synchronization result; When the corpus synchronization result indicates that the corpus synchronization is successful, performing an index building operation, and if the index building operation is successfully executed, obtaining a successfully built target index, performing a corpus recall operation using the target index, and obtaining a corpus recall result; If the corpus recall result meets the expected recall result, the intelligent question-answering system in which the knowledge base platform and the human-computer interaction platform are located is determined, a test result indicating that the full-link process verification of the intelligent question-answering system is successful is generated, and the test result is output.

2. The method according to claim 1, characterized in that The method of using the automated browser operation method to adjust the corpus information of the knowledge base platform and publishing the adjusted corpus information to obtain the corpus publishing result includes: Using the automated browser operation method to start a browser, and controlling the browser to display a first platform login page of the knowledge base platform; Obtaining preset first access information for logging into the knowledge base platform, and logging into the knowledge base platform using the first access information on the first platform login page; Using the element location strategy of the automated browser operation method, locate the corpus management page of the knowledge base platform, and based on the corpus management page, perform corpus adjustment on the corpus information of the knowledge base platform to obtain the adjusted corpus information, wherein the corpus adjustment includes at least one of corpus addition, corpus modification, and corpus deletion; Using the automated browser operation method to publish the adjusted corpus information, and using the element positioning strategy to locate the corpus publishing list page of the knowledge base platform, obtaining the latest publishing record corresponding to this corpus publishing on the corpus publishing list page, and reading the status display parameter in the latest publishing record; Obtain a preset expected value, compare the preset expected value with the status display parameter, and generate the corpus publishing result according to the comparison result, wherein if the comparison determines that the status display parameter meets the preset expected value, then generate the corpus publishing result indicating that the corpus publishing is successful; and if the comparison determines that the status display parameter does not meet the preset expected value, then generate the corpus publishing result indicating that the corpus publishing is abnormal.

3. The method according to claim 1, characterized in that The step of synchronizing the adjusted corpus information in the knowledge base platform to the human-computer interaction platform to obtain a corpus synchronization result includes: Using the automated browser operation method to start a browser, and controlling the browser to display a second platform login page of the human-computer interaction platform; Obtaining preset second access information for logging into the human-computer interaction platform, and logging into the human-computer interaction platform using the second access information on the second platform login page; Using the element location strategy of the automated browser operation method to locate the corpus synchronization page of the human-computer interaction platform, and based on the corpus synchronization page, using the resource interaction method to synchronize the adjusted corpus information in the knowledge base platform; Based on the resource interaction method, a corpus synchronization interface is called, the task status of this corpus synchronization is obtained through the corpus synchronization interface, and the corpus synchronization result is generated according to the task status, wherein if the task status indicates successful execution, the corpus synchronization result indicating successful corpus synchronization is generated; and if the task status indicates failed execution, the corpus synchronization result indicating an abnormal corpus synchronization is generated.

4. The method according to claim 1, wherein The performing of the index building operation, and if the index building operation is successfully performed, obtaining a successfully built target index, and performing a corpus recall operation using the target index to obtain a corpus recall result, includes: Calling an operation interface based on a resource interaction method, executing the index building operation through the operation interface, and obtaining a first index building status returned by the operation interface; When the first index building status indicates that the index building operation is successfully executed, obtaining the successfully built target index; A question-and-answer interface is called based on the resource interaction method, and a corpus recall operation is performed on the target index through the question-and-answer interface to obtain the corpus recall result.

5. The method according to claim 4, characterized in that After obtaining the first index building status returned by the operation interface, the method further includes: When the first index building status indicates that the index building operation fails, calling the operation interface to re-execute the index building operation, and obtaining a second index building status returned by the operation interface; If the second index building status indicates that the re-execution of the index building operation has failed, calling the operation interface to execute the index building operation again, and obtaining a third index building status returned by the operation interface; In a case where the third index building status indicates that the index building operation fails to be executed again, a test result indicating that the index building of the intelligent question-answering system is abnormal is generated, and the test result is output.

6. The method according to claim 5, characterized in that The method further comprises: If the second index building status indicates that the index building operation is successfully re-executed, then obtaining the successfully built target index; or In a case where the third index building status indicates that the index building operation is successfully executed again, a successfully built target index is obtained.

7. The method according to claim 1, characterized in that The method further comprises: If the corpus publishing result indicates that the corpus publishing is abnormal, generating a test result indicating that the corpus publishing on the knowledge base platform is abnormal, and outputting the test result; or If the corpus synchronization result indicates that the corpus synchronization is abnormal, generating a test result indicating that the corpus synchronization of the human-computer interaction platform is abnormal, and outputting the test result; or If the corpus recall result does not meet the expected recall result, a test result indicating that the corpus recall of the intelligent question-answering system is abnormal is generated, and the test result is output.

8. An automated testing device for an intelligent question-answering system, characterized in that: include: The corpus adjustment and publishing module is used to adjust the corpus information of the knowledge base platform using an automated browser operation method, and publish the adjusted corpus information to obtain a corpus publishing result; A corpus synchronization module is configured to synchronize the adjusted corpus information in the knowledge base platform to the human-computer interaction platform to obtain a corpus synchronization result if the corpus publishing result indicates that the corpus is successfully published; An index building and corpus recall module, configured to, when the corpus synchronization result indicates that the corpus synchronization is successful, perform an index building operation, and, if the index building operation is successfully executed, obtain a successfully constructed target index, perform a corpus recall operation using the target index, and obtain a corpus recall result; The first output module is used to determine the intelligent question-answering system in which the knowledge base platform and the human-computer interaction platform are located if the corpus recall result meets the expected recall result, generate a test result indicating that the full-link process verification of the intelligent question-answering system is successful, and output the test result.

9. A device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images