Document material processing method and device, electronic equipment and storage medium

Abstract

The invention provides a document material processing method and device, electronic equipment and a storage medium. The document material processing method comprises the following steps: firstly, carrying out layout structure division on credit materials of a user; wherein the credit material is a file in an image format; the layout structure comprises a character part and a table part. And then character recognition is carried out on the character part to obtain character recognition content. And performing table identification on the table part to obtain table identification content. Then supplementary information is obtained based on the user information of the user, and supplementary content is obtained; and finally, generating a credit file of the user based on the character recognition content, the table recognition content and the supplementary content. Therefore, by means of the method, the content of each part in the complex credit materials can be automatically processed, the related supplementary information is obtained and finally integrated into the credit file, and the document processing efficiency and accuracy can be effectively improved.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a method, device, electronic device and storage medium for processing document materials. Background Art

[0002] In traditional bank corporate credit business, account managers need to deal with a large amount of complex company materials including company articles of association, credit reports, Qichacha information, etc. Different types of materials are also different, including scanned PDF, electronic PDF, website data, etc. For corporate financial reports, account managers need to compare the data of various items in the financial report files, manually enter them into the system and then proceed to the next step.

[0003] For some companies with complex financial structures, data entry is a heavy, time-consuming, repetitive and error-prone task, which causes great troubles for business personnel. These tedious tasks make it time-consuming and laborious for account managers to process information and are inefficient. Summary of the invention

[0004] In view of this, the present application provides a method, device, electronic device and storage medium for processing document materials to solve the problem of low document processing efficiency in the prior art.

[0005] To achieve the above objectives, this application provides the following technical solutions:

[0006] The first aspect of the present application discloses a method for processing document materials, comprising:

[0007] Divide the user's credit materials into layout structures; wherein the credit materials are files in image format; the layout structure includes a text part and a table part;

[0008] Performing text recognition on the text portion to obtain text recognition content;

[0009] Performing table recognition on the table portion to obtain table recognition content;

[0010] Acquire supplementary information based on the user information of the user to obtain supplementary content;

[0011] A credit file of the user is generated based on the text recognition content, the table recognition content and the supplementary content.

[0012] Optionally, in the above method, performing text recognition on the text portion to obtain text recognition content includes:

[0013] Performing image enhancement processing on the text portion to obtain a processed text portion;

[0014] Recognize the text content in the processed text portion by optical character recognition technology;

[0015] Perform text error correction processing on the text content to obtain the text recognition content.

[0016] Optionally, in the above method, performing table recognition on the table portion to obtain table recognition content includes:

[0017] For each table in the table part, extracting the table structure and text information of the table;

[0018] A table file in a preset format is generated based on the table structure and the text information.

[0019] Optionally, in the above method, the acquiring of supplementary information based on the user information of the user to obtain supplementary content includes:

[0020] Generate a search instruction based on the user information; wherein the search instruction includes a first search instruction and a second search instruction; the first search instruction is used for data from a fixed data source; the second search instruction is used for retrieving data from a non-fixed data source;

[0021] Perform data retrieval based on the retrieval instruction and obtain the retrieved data;

[0022] The retrieved data is structured to obtain the supplementary content.

[0023] Optionally, in the above method, generating the credit file of the user based on the text recognition content, the table recognition content and the supplementary content includes:

[0024] Performing data cleaning on the text recognition content, the table recognition content and the supplementary content to obtain cleaned data;

[0025] The cleaned data is structured to generate the credit file, and the credit file is stored in a database.

[0026] The second aspect of the present application discloses a document material processing device, comprising:

[0027] A division unit is used to divide the user's credit materials into layout structures; wherein the credit materials are files in image format; the layout structure includes a text part and a table part;

[0028] A text recognition unit, used to perform text recognition on the text part to obtain text recognition content;

[0029] A table recognition unit, used for performing table recognition on the table part to obtain table recognition content;

[0030] an acquisition unit, configured to acquire supplementary information based on the user information of the user to obtain supplementary content;

[0031] A generating unit is used to generate a credit file of the user based on the text recognition content, the table recognition content and the supplementary content.

[0032] Optionally, in the above device, the character recognition unit includes:

[0033] A processing subunit, used for performing image enhancement processing on the text portion to obtain a processed text portion;

[0034] A recognition subunit, used for recognizing text content in the processed text portion by optical character recognition technology;

[0035] The error correction subunit is used to perform text error correction processing on the text content to obtain the text recognition content.

[0036] Optionally, in the above device, the table recognition unit includes:

[0037] An extraction subunit, for extracting the table structure and text information of each table in the table part;

[0038] A generating subunit is used to generate a table file in a preset format based on the table structure and the text information.

[0039] The third aspect of the present application discloses an electronic device, comprising:

[0040] one or more processors;

[0041] a storage device having one or more programs stored thereon;

[0042] When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any one of the first aspects of the present invention.

[0043] A fourth aspect of the present application discloses a computer storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the method described in any one of the first aspects of the present invention is implemented.

[0044] It can be seen from the above technical scheme that the document material processing method provided by the present application first divides the user's credit material into a layout structure; wherein the credit material is a file in image format; the layout structure includes a text part and a table part. Then, the text part is subjected to text recognition to obtain text recognition content. Then, the table part is subjected to table recognition to obtain table recognition content. Then, supplementary information is obtained based on the user's user information to obtain supplementary content. Finally, the user's credit file is generated based on the text recognition content, the table recognition content and the supplementary content. It can be seen that, using the method of the present application, various parts of the content in complex credit materials can be automatically processed, and relevant supplementary information can be obtained, and finally integrated into a credit file, which can effectively improve the efficiency and accuracy of document processing. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0046] Figure 1 A flowchart of a method for processing document materials disclosed in an embodiment of the present application;

[0047] Figure 2 This is a flowchart of an implementation of step S102 disclosed in an embodiment of the present application;

[0048] Figure 3 A flowchart of the search process disclosed in the embodiment of the present application;

[0049] Figure 4 A flowchart of data post-processing disclosed in the embodiments of the present application;

[0050] Figure 5 A schematic diagram of a document material processing device disclosed in an embodiment of the present application;

[0051] Figure 6 A schematic diagram of an electronic device disclosed in an embodiment of the present application. DETAILED DESCRIPTION

[0052] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0053] In this application, the terms "comprises", "comprising" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprising a ..." does not exclude the presence of other identical elements in the process, method, article or device comprising the element.

[0054] Furthermore, in this document, relational terms such as first and second, etc. are used only to distinguish one entity or operation from another entity or operation, but do not necessarily require or imply any such actual relationship or order between these entities or operations.

[0055] As can be seen from the background technology, in the traditional bank's corporate credit business, for some enterprises with complex financial structures, the workload of data entry is large, time-consuming, repetitive and error-prone, which brings great troubles to the work of business personnel. These tedious tasks make it time-consuming and laborious for account managers to process information and are inefficient.

[0056] In view of this, the present application provides a method, device, electronic device and storage medium for processing document materials to solve the problem of low document processing efficiency in the prior art.

[0057] The present application embodiment provides a method for processing document materials, such as Figure 1 As shown, specifically including:

[0058] S101. Divide the user's credit materials into layout structures; wherein the credit materials are files in image format; the layout structure includes a text part and a table part.

[0059] It should be noted that, firstly, the PP-Structure related algorithm is used to divide the layout structure of the user's credit materials, wherein the credit materials are files in image format, and the layout structure includes at least a text part and a table part. In some embodiments, the layout structure may also include five parts, namely, a text part, a title part, a table part, a picture part, and a list part.

[0060] First, divide the image content to be processed into text and table areas, locate and mark the text and table parts, then perform content recognition on each part, and finally restore the recognized parts of each section to the layout of the original image system, which can make content recognition more targeted and improve processing accuracy. In practical applications, layout analysis can help users quickly identify and extract different elements in documents, so as to quickly classify, organize and edit documents. This function is particularly useful when processing a large number of documents, which can greatly improve the efficiency and accuracy of document processing.

[0061] S102: Perform text recognition on the text part to obtain text recognition content.

[0062] It should be noted that for the text part in the document material, text recognition technology is used to perform text recognition on the text part to obtain text recognition content, such as OCR (optical character recognition) technology. OCR technology scans and recognizes the text in the image and converts it into a digital text format that can be edited and processed by a computer. It mainly relies on image processing and pattern recognition algorithms. By capturing character features in the document, such as strokes, shapes, sizes, spacing, etc., and comparing them with the preset character library, the corresponding text information is recognized. The implementation process includes image preprocessing, text area detection, character segmentation, feature extraction, character classification, post-processing and other processes, and finally outputs the recognition result. OCR recognition has the advantages of high efficiency, convenience, cost saving, easy storage and transmission, and strong editability. It is often used in application scenarios such as document digitization, ticket recognition, license plate recognition, and image text extraction.

[0063] Optionally, in another embodiment of the present application, an implementation of the above step S102 is as follows: Figure 2 As shown, it may include:

[0064] S201, performing image enhancement processing on the text portion to obtain a processed text portion.

[0065] It should be noted that the clarity of credit materials varies. For credit materials with lower clarity, direct OCR text recognition is not ideal. Therefore, the text part is subjected to image enhancement processing to obtain the processed text part to improve the accuracy of OCR recognition. These include sharpening, denoising, adjusting brightness and contrast, adaptive histogram equalization, and conversion to grayscale. Image sharpening can enhance the edges and details of the image to make the text clearer. Denoising can remove noise and impurities in the image to reduce interference, adjust the image brightness and contrast to make the text part more obvious, and adaptive histogram equalization can enhance the local contrast of the image to make the text area more prominent. Through image enhancement operations, the image clarity is improved to facilitate the improvement of the accuracy of subsequent text recognition.

[0066] S202: Recognize text content in the processed text part by using optical character recognition technology.

[0067] It should be noted that after image enhancement processing, OCR technology is used to convert the text in the image into editable text. In this embodiment, PaddleOCR is mainly used for text recognition. PaddleOCR is an open source OCR tool based on the PaddlePaddle deep learning platform, which aims to provide high-performance and accurate text recognition functions, support text recognition in multiple languages, and provide a variety of pre-trained OCR models for selection.

[0068] The OCR recognition process mainly includes character segmentation, feature extraction and character recognition. Character segmentation divides the text area in the image into characters to ensure that each character can be recognized individually. Feature extraction extracts feature information for recognition from each segmented character image. Character recognition uses a pre-trained OCR model to match the extracted character features with the existing character library to generate the corresponding text characters. The text content after the OCR text recognition process is formatted according to the layout structure of the original document, and the recognized text content can be saved as an editable word document.

[0069] Based on this, the scanned document will be recognized and generated into editable document content to facilitate subsequent data processing.

[0070] S203: Perform text error correction processing on the text content to obtain text recognition content.

[0071] It should be noted that after the text content is recognized, in order to correct the possible typos and grammatical errors that may occur during the recognition process, the existing Chinese error correction model is used to perform text error correction on the text content to obtain the text recognition content and improve the accuracy of the recognition results. By performing text error correction on the text content, typos are significantly reduced and the accuracy of text recognition is further improved.

[0072] S103, performing table recognition on the table part to obtain table recognition content.

[0073] It should be noted that, for the table part in the credit materials, table recognition is performed on the table part to obtain the table recognition content, so that the table image is converted into an editable Excel file.

[0074] Optionally, in another embodiment of the present application, an implementation of step S103 may include:

[0075] For each table in the table part, the table structure and text information of the table are extracted.

[0076] Generates a pre-formatted table file based on table structure and text information.

[0077] It should be noted that table recognition is mainly based on the table part analyzed by the layout, and the ppstructure table recognition algorithm is used to detect and recognize text. At the same time, the table structure information is completely extracted, so that the table image becomes an editable Excel file. The image is detected by the single-line text detection model to obtain the coordinates of the single-line text, and then sent to the recognition model to obtain the recognition result; the model obtains the table structure information and cell coordinate information; the single-line text coordinates, recognition results and cell coordinates are combined to obtain the cell recognition result; finally, the contents of all cells are integrated with their positions in the table to form a complete table structure.

[0078] S104: Acquire supplementary information based on the user information of the user to obtain supplementary content.

[0079] It should be noted that in order to obtain more information about the user so as to make a more accurate judgment about the user, supplementary information is obtained based on the user information of the user to obtain supplementary content. For example, information related to the user is detected from the Internet and supplementary content is generated. Among them, user information may include personal information and company information.

[0080] Optionally, in another embodiment of the present application, an implementation of the above step S104 may include:

[0081] Generate a search instruction based on user information; wherein the search instruction includes a first search instruction and a second search instruction; the first search instruction is used for data from a fixed data source; and the second search instruction is used for retrieving data from a non-fixed data source.

[0082] Perform data retrieval based on the retrieval instruction and obtain the retrieved data.

[0083] The retrieved data is structured to obtain supplementary content.

[0084] It should be noted that after the user enters a specific company name, the company name will be automatically embedded in the script question and form a set of instructions for collecting information about the company. For example, if the company name is: Company A, and the script question is: Search for registered capital, they will be combined into: Please search for the registered capital of Company A. There are two types of questions in the script question.

[0085] The search process can be found in Figure 3, Question type 1 is specific company information, such as company registered capital, company address, company business registration number, etc. This type of question is clear and this type of information can be obtained on a specific website, so the first search instruction is generated for this type of question and searched on a specific website. The Internet automatic information search system based on Selenium and BeautifulSoup is used. The system will search the company's first search instruction one by one and save the obtained information.

[0086] Question type 2 is open-ended information, such as resumes of company leaders, honors obtained by the company, and company reputation. This type of information is relatively complex and has many sources, so it cannot be obtained through a single website. It is necessary to retrieve and integrate comprehensive information to finally obtain this type of question information. Therefore, a second search instruction is generated for this type of question, and searches are performed on multiple different websites. The Internet RAG system based on Bing search is used. The system will conduct a comprehensive search for this type of question in the Bing search system, extract the relevant web page content retrieved, and then perform data processing on the extracted content to finally generate the corresponding information.

[0087] After the data is retrieved, the retrieved data is processed and output in a structured format as a Json format file containing complete information about the company.

[0088] S105: Generate a credit file for the user based on the text recognition content, the table recognition content and the supplementary content.

[0089] It should be noted that after obtaining the text recognition content, table recognition content and supplementary content, the text recognition content, table recognition content and supplementary content are post-processed to generate the user's credit file and save it in the database.

[0090] Optionally, in another embodiment of the present application, an implementation of the above step S105 may include:

[0091] Data cleaning is performed on the text recognition content, table recognition content and supplementary content to obtain cleaned data.

[0092] The cleaned data is structured to generate credit files, which are then stored in the database.

[0093] It should be noted that text data belongs to the category of natural language and contains a lot of irrelevant information and noise, such as redundant punctuation, spaces, and useless blank lines. Data cleaning is responsible for removing redundant information and noise to ensure the accuracy and consistency of the data.

[0094] The cleaned text data is then converted into a structured data format for subsequent analysis and use, including field extraction, data annotation, and format conversion. First, key fields such as document title, company name, etc. are extracted from the text; then, the extracted fields are annotated, and necessary tags and metadata are added; finally, the text data is converted into a structured data format, such as a JSON file.

[0095] The structured data is stored in the vector database Elasticsearch to ensure data persistence and availability. By establishing a connection with the Elasticsearch database, ensure that the data can be correctly transmitted and stored, then create the corresponding index in Elasticsearch, define the data structure and field type for efficient storage and retrieval, and finally insert the structured data into the Elasticsearch index one by one to ensure data integrity and consistency. When inserting, the data needs to be converted to the JSON format supported by Elasticsearch. The specific process of data post-processing is as follows: Figure 4 shown.

[0096] The embodiment of the present application provides a method for processing document materials, which first divides the user's credit materials into layout structures; wherein the credit materials are files in image format; and the layout structure includes a text part and a table part. Then, text recognition is performed on the text part to obtain text recognition content. Then, table recognition is performed on the table part to obtain table recognition content. Then, supplementary information is acquired based on the user's user information to obtain supplementary content. Finally, the user's credit file is generated based on the text recognition content, the table recognition content and the supplementary content. It can be seen that by using the method of the present application, various parts of the content in complex credit materials can be automatically processed, and relevant supplementary information can be acquired, and finally integrated into a credit file, which can effectively improve the efficiency and accuracy of document processing.

[0097] Another embodiment of the present application also discloses a document material processing device, such as Figure 5 As shown, specifically including:

[0098] The division unit 501 is used to divide the user's credit materials into layout structures; wherein the credit materials are files in image format; the layout structure includes a text part and a table part.

[0099] The text recognition unit 502 is used to perform text recognition on the text part to obtain text recognition content.

[0100] The table recognition unit 503 is used to perform table recognition on the table part to obtain table recognition content.

[0101] The acquisition unit 504 is used to acquire supplementary information based on the user information of the user to obtain supplementary content.

[0102] The generating unit 505 is used to generate a credit file of the user based on the text recognition content, the table recognition content and the supplementary content.

[0103] In this embodiment, the specific execution process of the division unit 501, the text recognition unit 502, the table recognition unit 503, the acquisition unit 504 and the generation unit 505 can be referred to the corresponding Figure 1 The content of the method embodiment will not be repeated here.

[0104] The embodiment of the present application provides a device for processing document materials. First, the division unit 501 divides the layout structure of the user's credit materials; wherein the credit materials are files in image format; the layout structure includes a text part and a table part. Then the text recognition unit 502 performs text recognition on the text part to obtain text recognition content. The table recognition unit 503 then performs table recognition on the table part to obtain table recognition content. Then the acquisition unit 504 acquires supplementary information based on the user's user information to obtain supplementary content. Finally, the generation unit 505 generates the user's credit file based on the text recognition content, the table recognition content and the supplementary content. It can be seen that by using the method of the present application, it is possible to automatically process various parts of the content in complex credit materials, obtain relevant supplementary information, and finally integrate them into a credit file, which can effectively improve the efficiency and accuracy of document processing.

[0105] Optionally, in another embodiment of the present application, an implementation of the text recognition unit 502 includes:

[0106] The processing subunit is used to perform image enhancement processing on the text part to obtain the processed text part.

[0107] The recognition subunit is used to recognize the text content in the processed text part by using optical character recognition technology.

[0108] The error correction subunit is used to perform text error correction processing on the text content to obtain text recognition content.

[0109] In this embodiment, the specific execution process of the processing subunit, the identification subunit and the error correction subunit can be found in the corresponding Figure 2 The content of the method embodiment will not be repeated here.

[0110] Optionally, in another embodiment of the present application, an implementation of the table identification unit 503 includes:

[0111] The extraction subunit is used to extract the table structure and text information of each table in the table part.

[0112] The generating subunit is used to generate a table file in a preset format based on the table structure and text information.

[0113] In this embodiment, the specific execution process of the extraction subunit and the generation subunit can be found in the corresponding method embodiment described above, and will not be repeated here.

[0114] Another embodiment of the present application further provides an electronic device, such as Figure 6 As shown, specifically including:

[0115] One or more processors 601 .

[0116] The storage device 602 stores one or more programs.

[0117] When one or more programs are executed by one or more processors 601 , the one or more processors 601 implement any one of the methods in the above embodiments.

[0118] Another embodiment of the present application further provides a computer storage medium on which a computer program is stored, wherein when the computer program is executed by a processor, any one of the methods in the above embodiments is implemented.

[0119] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can refer to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system or system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can refer to the partial description of the method embodiment. The system and system embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without creative work.

[0120] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0121] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for processing document materials, characterized in that: include: Divide the user's credit materials into layout structures; wherein the credit materials are files in image format; the layout structure includes a text part and a table part; Performing text recognition on the text portion to obtain text recognition content; Performing table recognition on the table portion to obtain table recognition content; Acquire supplementary information based on the user information of the user to obtain supplementary content; A credit file of the user is generated based on the text recognition content, the table recognition content and the supplementary content.

2. The method according to claim 1, characterized in that The performing text recognition on the text portion to obtain text recognition content includes: Performing image enhancement processing on the text portion to obtain a processed text portion; Recognize the text content in the processed text portion by optical character recognition technology; Perform text error correction processing on the text content to obtain the text recognition content.

3. The method according to claim 1, characterized in that The step of performing table recognition on the table portion to obtain table recognition content includes: For each table in the table part, extracting the table structure and text information of the table; A table file in a preset format is generated based on the table structure and the text information.

4. The method according to claim 1, characterized in that: The acquiring of supplementary information based on the user information of the user to obtain supplementary content includes: Generate a search instruction based on the user information; wherein the search instruction includes a first search instruction and a second search instruction; the first search instruction is used for data from a fixed data source; the second search instruction is used for retrieving data from a non-fixed data source; Perform data retrieval based on the retrieval instruction and obtain the retrieved data; The retrieved data is structured to obtain the supplementary content.

5. The method according to claim 1, characterized in that: The step of generating the user's credit file based on the text recognition content, the table recognition content and the supplementary content includes: Performing data cleaning on the text recognition content, the table recognition content and the supplementary content to obtain cleaned data; The cleaned data is structured to generate the credit file, and the credit file is stored in a database.

6. A document material processing device, characterized in that: include: A division unit is used to divide the user's credit materials into layout structures; wherein the credit materials are files in image format; the layout structure includes a text part and a table part; A text recognition unit, used to perform text recognition on the text portion to obtain text recognition content; A table recognition unit, used for performing table recognition on the table part to obtain table recognition content; an acquisition unit, configured to acquire supplementary information based on the user information of the user to obtain supplementary content; A generating unit is used to generate a credit file of the user based on the text recognition content, the table recognition content and the supplementary content.

7. The device according to claim 6, characterized in that The character recognition unit comprises: A processing subunit, used for performing image enhancement processing on the text portion to obtain a processed text portion; A recognition subunit, used for recognizing text content in the processed text portion by optical character recognition technology; The error correction subunit is used to perform text error correction processing on the text content to obtain the text recognition content.

8. The device according to claim 6, characterized in that The table recognition unit comprises: An extraction subunit, for extracting the table structure and text information of each table in the table part; A generating subunit is used to generate a table file in a preset format based on the table structure and the text information.

9. An electronic device, characterized in that: include: one or more processors; a storage device having one or more programs stored thereon; When the one or more programs are executed by the one or more processors, the one or more processors are enabled to implement the method according to any one of claims 1 to 5.

10. A computer storage medium, characterized in that: A computer program is stored thereon, wherein when the computer program is executed by a processor, the method according to any one of claims 1 to 5 is implemented.

Images