A page generation method, system, storage medium, electronic device and product

Abstract

The embodiment of the application provides a page generation method, system, storage medium, electronic device and product, the method comprises: in the component library knowledge base, the semantic matching of target page text description information is carried out, the page component information related to the target page text description information is determined, the target page text description information, the page component information and the preset target page generation requirement are determined as the first prompt word, and the first prompt word is input into the large language model, and the first code is obtained, wherein the page component information comprises a page component example; the framework language of the first code is obtained by recognizing the framework language of the first code, the first code is parsed according to the framework language, and the second code conforming to the specification of the framework language is generated; the second code is compiled according to the framework language, an executable code is generated, and the target page is generated by running the executable code.

Description

Technical Field

[0001] This application relates to the field of page development, and more specifically, to a page generation method, system, storage medium, electronic device, and product. Background Technology

[0002] In recent years, with the rapid development of artificial intelligence technology, especially the emergence of large-scale pre-trained models (such as GPT), computers have made significant progress in natural language processing, image generation, and other fields. By training large amounts of text data into a general-purpose large language model, high-quality code can be generated under specific conditions, simplifying the development process. Regarding user interface generation, front-end software engineers can develop target pages using their knowledge, and there are many methods in the industry to improve page generation efficiency, but these methods still have considerable room for improvement. Now, based on large-scale model technology, by parsing user input in natural language descriptions or through images and videos, user interface code that meets requirements can be automatically generated, greatly improving development efficiency and reducing human error. Simultaneously, this technology can also provide personalized user interface solutions with a unified design language by building and enriching a knowledge base.

[0003] The page generation methods introduced in related technologies have been found to be unable to adapt to the enterprise's internal design language, regardless of description or adjustment. Research revealed that the implementation methods are limited to specific libraries, and even these libraries may have different design styles. For example, when using the Angular framework, accuracy drops drastically, making it unsuitable for generating and previewing multiple files. Furthermore, these methods cannot identify or modify pages from existing enterprise projects, and their support for complex applications is insufficient. Summary of the Invention

[0004] This application provides a page generation method, system, storage medium, electronic device, and product to at least solve the technical problem in the related art of being unable to accurately generate corresponding pages based on user-input page descriptions.

[0005] According to one embodiment of this application, a page generation method is provided, comprising: semantically matching the text description information of a target page in a component library knowledge base to determine page component information related to the text description information of the target page; determining the text description information of the target page, the page component information, and preset target page generation requirements as first prompt words; inputting the first prompt words into a large language model to obtain first code, wherein the page component information includes page component examples; performing framework language recognition on the first code to obtain the framework language of the first code; parsing the first code according to the framework language to generate second code conforming to the specifications of the framework language; compiling the second code according to the framework language to generate executable code; and generating a target page by running the executable code.

[0006] According to another embodiment of this application, a page generation system is provided, comprising: a page description parsing module, configured to perform semantic matching on the text description information of a target page in a component library knowledge base, determine page component information related to the text description information of the target page, determine the text description information of the target page, the page component information, and preset target page generation requirements as first prompt words, and input the first prompt words into a large language model to obtain first code, wherein the page component information includes page component examples; a code parsing module, configured to perform framework language recognition on the first code, obtain the framework language of the first code, parse the first code according to the framework language, and generate second code that conforms to the specifications of the framework language; a compilation module, configured to compile the second code according to the framework language to generate executable code; and a running module, configured to generate a target page by running the executable code.

[0007] According to yet another embodiment of this application, a computer-readable storage medium is also provided, wherein a computer program is stored in the computer program, and the computer program is configured to execute the steps in the above method embodiments when it is run.

[0008] According to yet another embodiment of this application, an electronic device is also provided, including a memory and a processor, wherein the memory stores a computer program and the processor is configured to run the computer program to perform the steps in the above method embodiments.

[0009] According to yet another embodiment of this application, a computer program product is also provided, including a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0010] Through the embodiments described above in this application, semantic matching in the component library knowledge base allows for a more accurate understanding of the target page requirements described by the user, thereby generating more accurate first code. Identifying and parsing the framework language in the first code ensures that the generated second code not only conforms to the syntax characteristics of the framework but also has a clear and standardized structure, improving code quality and maintainability. Compiling and running the generated second code allows for an instant preview of the page effect, rapid verification of whether the code meets the requirements, and accelerated development and iteration processes. Therefore, this solves the technical problem in related technologies where it is impossible to accurately generate a corresponding page based on the page description input by the user. Attached Figure Description

[0011] Figure 1 This is a hardware structure block diagram of a computer terminal according to the page generation method of the present application embodiment;

[0012] Figure 2 This is a flowchart of a page generation method according to an embodiment of this application;

[0013] Figure 3 This is a schematic diagram of the first code generation according to an embodiment of this application;

[0014] Figure 4 This is a schematic diagram illustrating the generation of target page text description information according to an embodiment of this application;

[0015] Figure 5 This is a schematic diagram of the second code generation according to an embodiment of this application;

[0016] Figure 6 This is a schematic diagram illustrating the generation of executable code according to an embodiment of this application;

[0017] Figure 7 This is a schematic diagram illustrating code modifications according to an embodiment of this application;

[0018] Figure 8 This is a schematic diagram illustrating the description information of page components according to an embodiment of this application;

[0019] Figure 9 This is a structural block diagram of a page generation system according to an embodiment of this application;

[0020] Figure 10 This is a structural block diagram of a page generation system according to another embodiment of the present application. Detailed Implementation

[0021] The embodiments of this application will be described in detail below with reference to the accompanying drawings and examples.

[0022] It should be noted that the terms "first," "second," etc., in the specification, claims, and drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence.

[0023] The methods and embodiments provided in this application can be executed on a mobile terminal, a computer terminal, or a similar computing device. Taking running on a mobile terminal as an example, Figure 1 This is a hardware structure block diagram of the mobile terminal used in the embodiments of the method of this application. For example... Figure 1 As shown, a mobile terminal may include one or more ( Figure 1 Only one is shown in the diagram. A processor 102 (which may include, but is not limited to, a microprocessor MCU or a programmable logic device FPGA, etc.) and a memory 104 for storing data are also shown. The mobile terminal may further include a transmission device 106 for communication functions and an input / output device 108. Those skilled in the art will understand that... Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the mobile terminal described above. For example, the mobile terminal may also include components that are more... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown.

[0024] The memory 104 can be used to store computer programs, such as application software programs and modules, like the computer program corresponding to the page generation method in this embodiment. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, thus implementing the above-described method. The memory 104 may include high-speed random access memory and non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor 102, and these remote memories can be connected to the mobile terminal via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0025] The transmission device 106 is used to receive or send data via a network. Specific examples of the network described above may include a wireless network provided by the mobile terminal's communication provider. In one example, the transmission device 106 includes a Network Interface Controller (NIC), which can connect to other network devices via a base station to communicate with the Internet. In another example, the transmission device 106 may be a Radio Frequency (RF) module, used for wireless communication with the Internet.

[0026] Figure 2 This is a flowchart of a page generation method according to an embodiment of this application, such as... Figure 2 As shown, the process includes the following steps:

[0027] Step S202: Semantically match the text description information of the target page in the component library knowledge base to determine the page component information related to the text description information of the target page. Determine the text description information of the target page, the page component information, and the preset target page generation requirements as the first prompt words. Input the first prompt words into the large language model to obtain the first code. The page component information includes page component examples.

[0028] In an exemplary embodiment of this application, the text description information of the target page includes at least one of the following: the text content of the target page, the page layout of the target page, and the page components of the target page.

[0029] In one embodiment, if the target page's layout is not specified in the target page's text description, the default layout of the components will be adopted. The target page's page components may take various forms; for example, the page may consist of a table and a form.

[0030] In an exemplary embodiment of this application, the component library knowledge base includes page component specifications, page component examples, and page component attributes.

[0031] In one embodiment, such as Figure 3 As shown, the first code is obtained through the business parsing module. The component knowledge base is stored in the vector database. In the construction of the vector database, referring to the modeling in Table 1, missing information will cause a decrease in the generation rate or failure of the function. The component knowledge base includes page component specifications, page component examples, page component attributes, and overall page examples (optional). The component knowledge base can semantically match relevant page component information based on the text description information of the target page. The page component information includes page component examples. After retrieving the page component information, the text description information of the target page, the page component information, and the preset target page generation requirements are determined as the first prompt words for use by the large language model.

[0032] Table 1

[0033]

[0034] It's important to note that the preset target page generation requirements include the framework language used, project-specific coding standards, and other considerations. For example, when using new component modules, an `import` statement needs to be added to the top of the code file. These requirements can be fixed and not changed, or they can be modified according to different generation scenarios, such as different coding languages. Multiple framework languages ​​can be prepared for this part, and can be switched during the task. Framework languages ​​may include Angular, Vue, and React.

[0035] In one embodiment, the output of the business parsing module may include, in addition to the necessary initial code, explanations of some of the code, depending on the preparation of the corpus, and may also include some human-like statements.

[0036] In an exemplary embodiment of this application, before semantic matching of the target page text description information in the component library knowledge base, the method further includes: converting multimodal data into target page text description information, wherein the multimodal data includes at least one of the following: images, videos, and audio.

[0037] In an exemplary embodiment of this application, converting multimodal data into textual description information of a target page includes: inputting a second prompt word into a multimodal large model to obtain textual description information of the target page; wherein, the second prompt word includes multimodal data, thought patterns, component functions, and output styles, and the thought patterns include thought order, which is to observe the main functions implemented by the target page, identify page components, and identify page combination components.

[0038] In one embodiment, the multimodal data is converted into textual description information for the target page using a multimodal parsing module, such as... Figure 4 As shown, images, videos, and audio are input into the multimodal parsing module, which converts them into text descriptions of the target page. These text descriptions are in natural language, describing the page's functions, including but not limited to page content and the business it represents. The key to converting multimodal data into text descriptions of the target page lies in determining the second prompt word and the capabilities of the multimodal large-scale model. The multimodal large-scale model needs certain command capabilities and multimodal recognition capabilities. The requirements for the second prompt word are as shown in Table 2 below, ensuring that the multimodal output page description accurately describes the page content. The thought process in Table 2 should include the following sequence: observe the main functions implemented by the target page; identify page components, as different main functions have different component scenarios; combining functional scenarios and the page allows for more accurate confirmation of the components present and used on the page; identify page composite components, as some complex components are combined with smaller basic components to avoid redundant component identification and output; and the identification method and order, which provides a general layout pattern.

[0039] By implementing the above thought process, the multimodal large model can effectively output useful information for subsequent steps, namely, the text description information of the target page. Because the multimodal parsing module converts the text into a natural language description of the page, some stylistic elements are effectively removed, facilitating the generation of uniformly styled code later.

[0040] Table 2

[0041]

[0042] Without a multimodal parsing module to convert multimodal data into text descriptions on the target page, users would need to convert the multimodal data, such as images, into text descriptions on the target page. The multimodal parsing module eliminates the need for manual recognition and input by users.

[0043] Step S204: Perform framework language recognition on the first code, obtain the framework language of the first code, parse the first code according to the framework language, and generate second code that conforms to the specifications of the framework language.

[0044] In one embodiment, the code parsing module parses the first code output by the business function parsing module to obtain new second code. The business function parsing module contains preset target page generation requirements, which include a framework language (or a default framework language if none is specified). Therefore, the goal of the business function parsing module is to output first code that conforms to the characteristics of the framework language, but this may not be a perfect fit. Figure 5 As shown, the code parsing module first needs to identify the framework language of the first code based on its language characteristics and save it to a variable. Then, based on the language characteristics, it performs regular expression matching / AST (Abstract Syntax Tree) matching or other convention-based matching to finally obtain the second code.

[0045] To identify a framework language, a multi-dimensional analysis is possible. When the business function parsing module explicitly specifies the framework language (user, project, default), its output will inevitably include framework language information; therefore, this can be easily obtained by reading the framework language information. Furthermore, to ensure functional robustness, identification can be achieved by analyzing the characteristics of different framework languages. Framework languages ​​may include Angular, Vue, and React.

[0046] Angular: The main output modules are .ts / .js files, .html files, and .css / .less / .scss files, etc., and the .ts / js files usually contain @Component decorators, @NgModuLe, etc.

[0047] Vue: Typically, output files include Vue information and use <template>, and the file extension is usually .vue.

[0048] React: Files often have extensions like .tsx / .jsx, and JavaScript logic code and HTML code are deeply intertwined.

[0049] Step S206: Compile the second code according to the framework language to generate executable code, and generate the target page by running the executable code.

[0050] In an exemplary embodiment of this application, compiling the second code according to the framework language to generate executable code includes: determining a scaffold corresponding to the framework language, compiling the second code according to the scaffold, and generating executable code.

[0051] After determining the framework language and obtaining the second code, such as Figure 6 As shown, if the code is not modified from the existing project code but is generated entirely new, the compiler will select the scaffolding for the specified framework language based on the obtained framework language. If the code is modified based on the existing project code, the compiler will directly use the scaffolding language configured in the existing project code and compile it using the corresponding framework language scaffolding. After compilation, an executable code will be obtained.

[0052] In one embodiment, a loading module can run executable code and preview it for the user, allowing the user to verify the correctness of the results. The loading module can be a common browser, a browser-like application, or software with an engine such as V8.

[0053] The loading module, consisting of a compilation module and a loading module, supports language replacement within the language framework. It then receives the outputs from the business function parsing module and the code parsing module, ultimately transforming them into a runnable functional page.

[0054] In an exemplary embodiment of this application, semantic matching is performed on the target page modification instruction in the component library knowledge base to determine the page component information corresponding to the target page modification instruction; semantic matching is also performed on the target page modification instruction in the project code knowledge base to determine the code function description corresponding to the target page modification instruction; and the third code corresponding to the code function description is obtained. The page component information and the third code are determined as a third prompt word, and the third prompt word is input into a large language model to obtain a fourth code. The third code in the project code knowledge base is replaced with the fourth code. The component library knowledge base includes project component code files, component code fragments, and code function descriptions.

[0055] In one embodiment, modifying code in the engineering code knowledge base requires the user to submit modification instructions for the target page, such as, "I need to add a chart below table XX, with the chart content derived from the table. Please draw a line chart using data from column XX as values." Figure 7 As shown, if there is no user-input natural language description of the target page modification instructions, the prototype / hand-drawn illustration needs to be converted into natural language descriptions of the target page modification instructions through a multimodal large model. Semantic matching of the target page modification instructions is performed in the component library knowledge base to determine the corresponding page component information. Semantic matching of the target page modification instructions is also performed in the engineering code knowledge base to determine the corresponding code function description, thereby obtaining the third code. The page component information and the third code are used together as input prompt words into the large language model. Based on the provided prompt words, a new fourth code can be obtained. The fourth code replaces the third code to complete the code modification task. Finally, manual verification is performed.

[0056] In exemplary embodiments of this application, as Figure 8 As shown, the code files of the project components are traversed to obtain the page components and the list of objects related to the page components. The list of objects related to the page components includes: the name of the upstream component of the page component, the name of the downstream component of the page component, and the code of the page component. The fourth prompt word is input into the large language model to obtain the description information of the page components. The fourth prompt word includes the page components and the list of objects related to the page components. The upstream and downstream relationships of the page components, the code of the page components, and the description information of the page components are added to the code function description in the component library knowledge base.

[0057] Through the above embodiments, multimodal data is converted into natural language descriptions using a multimodal large model, removing the original multimodal data style. Normally, designers and similar page specifications would be consistent. This application embodiment adds an extra layer of protection by retrieving relevant components in the business parsing module to obtain component specifications, component code examples, etc., further providing unified design language style output conditions. This enables the generation of the final front-end page and page code from multimodal content such as images, videos, audio, and text, while ensuring a consistent style output.

[0058] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods according to the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0059] This embodiment also provides a page generation system for implementing the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the apparatus described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0060] Figure 9 This is a structural block diagram of a page generation system according to an embodiment of this application, such as... Figure 9 As shown, the device includes a page description parsing module 20, a code parsing module 30, a compilation module 40, and a runtime module 50.

[0061] The page description parsing module 20 is used to perform semantic matching on the text description information of the target page in the component library knowledge base, determine the page component information related to the text description information of the target page, determine the text description information of the target page, the page component information and the preset target page generation requirements as the first prompt words, and input the first prompt words into the large language model to obtain the first code, wherein the page component information includes page component examples.

[0062] The code parsing module 30 is used to identify the framework language of the first code, obtain the framework language of the first code, parse the first code according to the framework language, and generate second code that conforms to the specifications of the framework language.

[0063] Compiler module 40 is used to compile the second code according to the framework language to generate executable code.

[0064] Module 50 is used to generate the target page by running executable code.

[0065] Figure 10 This is a structural block diagram of a page generation system according to another embodiment of the present application, such as... Figure 10 As shown, the modules in this system, besides Figure 9 In addition to the modules shown, a multimodal module 10 is also included.

[0066] The multimodal module 10 is used to convert multimodal data into text description information of the target page, wherein the multimodal data includes at least one of the following: images, videos, and audio.

[0067] It should be noted that the above modules can be implemented by software or hardware. For the latter, they can be implemented in the following ways, but are not limited to: all the above modules are located in the same processor; or, the above modules are located in different processors in any combination.

[0068] A multimodal large model can receive multimodal data such as images and videos and convert them into natural language. A large language model can then receive natural language input. Furthermore, by retrieving a pre-defined, customizable knowledge base, code generation requirements and minimum code examples are obtained. Combined with user input, the page implementation code is derived. A replaceable code loading module enables real-time page execution. By scanning the entire front-end project and employing the project dimensionality reduction method proposed in this application, necessary component relationships and descriptions are preserved. A knowledge base built upon this content retrieves valid target modification locations, avoiding potential large model token overruns, thereby enabling the modification of page code for complex projects.

[0069] Through the embodiments of this application, front-end pages in the same design language can be dynamically generated in a runtime system or development environment using multimodal information such as natural language or images. At the same time, related front-end code can be provided, and modifications to the front-end page code project output by humans / AI can be supported without relying on previous generation tasks.

[0070] Applying the embodiments of this application in the research and development field can accelerate the production efficiency of front-end pages and the consistency of generated code, support code modifications in complex systems, and accelerate the iteration speed of code development. Applying the embodiments of this application in the internet field can expand the capabilities of a system with low research and development costs, enabling users to instantly access personalized functional pages.

[0071] Embodiments of this application also provide a computer-readable storage medium storing a computer program, wherein the computer program is configured to execute the steps in any of the above method embodiments when run.

[0072] In one exemplary embodiment, the aforementioned computer-readable storage medium may include, but is not limited to, various media capable of storing computer programs, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), portable hard disk, magnetic disk, or optical disk.

[0073] Embodiments of this application also provide an electronic device including a memory and a processor, wherein the memory stores a computer program and the processor is configured to run the computer program to perform the steps in any of the above method embodiments.

[0074] In one exemplary embodiment, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor and the input / output device is connected to the processor.

[0075] Specific examples in this embodiment can be found in the examples described in the above embodiments and exemplary implementations, and will not be repeated here.

[0076] Obviously, those skilled in the art should understand that the modules or steps of this application described above can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a network of multiple computing devices. They can be implemented using computer-executable program code, and thus can be stored in a storage device for execution by a computing device. In some cases, the steps shown or described can be performed in a different order than those presented here, or they can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, this application is not limited to any particular combination of hardware and software.

[0077] The above description is merely a preferred embodiment of this application and is not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the principles of this application should be included within the protection scope of this application.

Claims

1. A page generation method, characterized in that, include: Semantic matching is performed on the text description information of the target page in the component library knowledge base to determine the page component information related to the text description information of the target page. The text description information of the target page, the page component information and the preset target page generation requirements are determined as the first prompt word. The first prompt word is input into the large language model to obtain the first code. The page component information includes page component examples. The first code is subjected to framework language recognition to obtain the framework language of the first code, and the first code is parsed according to the framework language to generate second code that conforms to the specifications of the framework language. The second code is compiled according to the framework language to generate executable code, and the target page is generated by running the executable code.

2. The method according to claim 1, characterized in that, Before performing semantic matching of the target page's text description information in the component library knowledge base, the following is also included: The multimodal data is converted into text description information for the target page, wherein the multimodal data includes at least one of the following: images, videos, and audio.

3. The method according to claim 2, characterized in that, The process of converting multimodal data into text description information for the target page includes: Input the second prompt word into the multimodal large model to obtain the text description information of the target page; The second prompt includes multimodal data, thinking patterns, component functions, and output styles. The thinking patterns include thinking order, which is to observe the main functions implemented by the target page, identify page components, and identify page combination components.

4. The method according to claim 1, characterized in that, The target page text description information includes at least one of the following: the text content of the target page, the page layout of the target page, and the page components of the target page.

5. The method according to claim 1, characterized in that, The component library knowledge base includes page component specifications, page component examples, and page component attributes.

6. The method according to claim 1, characterized in that, The method further includes: Semantic matching is performed on the target page modification instruction in the component library knowledge base to determine the page component information corresponding to the target page modification instruction. Semantic matching is performed on the target page modification instruction in the project code knowledge base to determine the code function description corresponding to the target page modification instruction. The third code corresponding to the code function description is then obtained. The page component information and the third code are determined as the third prompt word, and the third prompt word is input into the large language model to obtain the fourth code; Replace the third code in the engineering code knowledge base with the fourth code; The component library knowledge base includes project component code files, component code snippets, and code function descriptions.

7. The method according to claim 6, characterized in that, The method further includes: Traverse the project component code files to obtain the page component and a list of page component-related objects. The list of page component-related objects includes: the upstream component name, the downstream component name, and the page component code. The fourth prompt word is input into the large language model to obtain page component description information, wherein the fourth prompt word includes page components and a list of objects related to page components; The upstream and downstream relationships of the page components, the page component code, and the page component description information are added to the code function description in the component library knowledge base.

8. The method according to claim 1, characterized in that, The step of compiling the second code according to the framework language to generate executable code includes: A scaffold corresponding to the framework language is determined, and the second code is compiled according to the scaffold to generate the executable code.

9. A page generation system, characterized in that, include: The page description parsing module is used to perform semantic matching on the text description information of the target page in the component library knowledge base, determine the page component information related to the text description information of the target page, determine the text description information of the target page, the page component information and the preset target page generation requirements as the first prompt word, and input the first prompt word into the large language model to obtain the first code, wherein the page component information includes page component examples; The code parsing module is used to identify the framework language of the first code, obtain the framework language of the first code, parse the first code according to the framework language, and generate second code that conforms to the specifications of the framework language. A compilation module is used to compile the second code according to the framework language to generate executable code; The runtime module is used to generate the target page by running the executable code.

10. The system according to claim 9, characterized in that, The page generation system also includes: A multimodal module is used to convert multimodal data into text description information for a target page, wherein the multimodal data includes at least one of the following: images, videos, and audio.

11. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, wherein the computer program, when executed by a processor, implements the steps of the method described in any one of claims 1 to 8.

12. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method described in any one of claims 1 to 8.

13. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method described in any one of claims 1 to 8.

Images