Document processing method and device, equipment and storage medium

Abstract

The embodiment of the invention provides a document processing method and device, equipment and a storage medium. The method comprises the steps of obtaining a target document including a physical examination package, and determining a document type of the target document; in response to the fact that the document type is determined to be an image document type, format conversion is conducted on the target document through the optical character recognition technology, a document after format conversion is obtained, and the document format after format conversion is a text format; the document obtained after format conversion is analyzed through a natural language processing model, analysis information is obtained, and the analysis information at least comprises a plurality of entities and subordination relation information between the entities; performing matching in a target database based on the analysis information to obtain a matching result, and determining a quoted price of the physical examination package based on the matching result through a preset pricing strategy; wherein the matching result comprises the target physical examination price corresponding to each physical examination item. According to the embodiment of the invention, the offer of the physical examination package can be quickly and accurately provided through the method.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a document processing method, a document processing device, a computer equipment, and a computer-readable storage medium. Background Art

[0002] In the rapidly developing medical and health field, physical examination services, as an important part of preventive medicine, are increasingly valued by people. With the improvement of social and economic levels and the enhancement of health awareness, people's demand for personalized, high-quality physical examination services continues to grow. However, in the procurement and bidding of physical examination services, users often need to customize physical examination packages according to their own needs. In this process, users will provide highly customized demand documents or reference package screenshots, and then the physical examination package needs to be quoted for users to choose.

[0003] In the related art, it is mainly based on manually organizing the demand documents or reference package screenshots given by the above-mentioned users, and then consulting relevant materials to give a quotation. However, this method faces the following problems: First, the efficiency is slow. In the process of manually processing quotations, it often takes a long time from receiving user requirements to finally giving a quotation. Second, it is prone to errors. Manual operations are bound to make mistakes, especially when dealing with large amounts of data and complex requirements. Quotation errors will not only lead to economic losses, but may also damage the company's reputation and customer relationships. Therefore, based on the above reasons, it is necessary to propose a quotation method for physical examination packages that can quickly and accurately provide quotations for physical examination packages. Summary of the invention

[0004] The present application provides a document processing method, a document processing device, a computer device and a computer-readable storage medium, aiming to achieve rapid and accurate provision of quotations for physical examination packages through the above method.

[0005] To achieve the above purpose, the present application also provides a document processing method, comprising:

[0006] Acquire a target document including a physical examination package, and determine a document type of the target document;

[0007] In response to determining that the document type is an image document type, performing format conversion on the target document by using an optical character recognition technology to obtain a format-converted document, wherein the format of the format-converted document is a text format;

[0008] Parsing the format-converted document through a natural language processing model to obtain parsed information, wherein the parsed information at least includes a plurality of entities and subordinate relationship information between each of the entities;

[0009] Based on the parsed information, a match is performed in a target database to obtain a match result, and a quotation for the physical examination package is determined based on the match result through a preset pricing strategy; wherein the match result includes a target physical examination price corresponding to each physical examination item.

[0010] To achieve the above object, the present application also provides a document processing device, comprising:

[0011] An acquisition module, used to acquire a target document including a physical examination package and determine a document type of the target document;

[0012] a format conversion module, configured to, in response to determining that the document type is an image document type, perform format conversion on the target document by using an optical character recognition technology to obtain a document after format conversion, wherein the format of the document after format conversion is a text format;

[0013] A parsing module, used to parse the format-converted document through a natural language processing model to obtain parsing information, wherein the parsing information at least includes a plurality of entities and subordinate relationship information between each of the entities;

[0014] A matching module is used to perform matching in a target database based on the parsed information to obtain a matching result, and determine the quotation of the physical examination package based on the matching result through a preset pricing strategy; wherein the matching result includes a target physical examination price corresponding to each physical examination item.

[0015] In addition, to achieve the above-mentioned purpose, the present application also provides a computer device, which includes a memory and a processor; the memory is used to store a computer program; the processor is used to execute the computer program and implement the steps of any one of the document processing methods provided in the embodiments of the present application when executing the computer program.

[0016] In addition, to achieve the above-mentioned purpose, the present application also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the processor enables the processor to implement the steps of any one of the document processing methods provided in the embodiments of the present application.

[0017] The document processing method, document processing device, computer equipment and computer-readable storage medium disclosed in the embodiment of the present application. Among them, the method includes obtaining a target document including a physical examination package and determining the document type of the target document. Further, in response to determining that the document type is an image document type, the target document can be formatted by optical character recognition technology to obtain a document after format conversion, wherein the document format after format conversion is a text format. Thus, the document after format conversion can be parsed by a natural language processing model to obtain parsing information, wherein the parsing information at least includes a number of entities and the subordinate relationship information between each entity. Finally, matching can be performed in the target database based on the parsing information to obtain a matching result, and the quotation of the physical examination package can be determined based on the matching result by a preset pricing strategy; wherein the matching result includes the target physical examination price corresponding to each physical examination item. The present application converts the target document of the image document type into a text format by optical character recognition technology, and then parses the text content by a natural language processing model to extract entities and their subordinate relationship information, which significantly improves the automation and accuracy of the physical examination package document processing. At the same time, based on the analyzed information, physical examination items and prices are matched in the target database, and quotations are generated in combination with the preset pricing strategy. This not only optimizes the pricing process of physical examination packages, but also reduces the need for manual intervention, improving efficiency and service quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0019] Figure 1 It is a scenario schematic diagram of a document processing method provided in an embodiment of the present application;

[0020] Figure 2 It is a flowchart of a document processing method provided by an embodiment of the present application;

[0021] Figure 3 is a schematic block diagram of a document processing device provided in an embodiment of the present application;

[0022] Figure 4 It is a schematic block diagram of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0023] 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 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.

[0024] The flowcharts shown in the accompanying drawings are only examples and do not necessarily include all the contents and operations / steps, nor do they have to be executed in the order described. For example, some operations / steps can also be decomposed, combined or partially merged, so the actual execution order may change according to actual conditions. In addition, although the functional modules are divided in the device schematic, in some cases, the module division can be different from that in the device schematic.

[0025] The term "and / or" as used in this specification and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

[0026] In conjunction with the accompanying drawings, some embodiments of the present application are described in detail below. In the absence of conflict, the following embodiments and features in the embodiments can be combined with each other.

[0027] like Figure 1 As shown, the document processing method provided in the embodiment of the present application can be applied to Figure 1In the application environment shown. The application environment includes a terminal device 110 and a server 120, wherein the terminal device 110 can communicate with the server 120 through a network. Specifically, the server 120 can obtain a target document including a physical examination package and determine the document type of the target document; in response to determining that the document type is an image document type, the target document is formatted by optical character recognition technology to obtain a document after format conversion, wherein the format of the document after format conversion is a text format; the formatted document is parsed by a natural language processing model to obtain parsing information, wherein the parsing information at least includes a number of entities and the subordinate relationship information between each of the entities; matching is performed in the target database based on the parsing information to obtain a matching result, and the quotation of the physical examination package is determined based on the matching result through a preset pricing strategy; wherein the matching result includes the target physical examination price corresponding to each physical examination item, thereby the quotation of the physical examination package can be sent to the terminal device 110. Among them, the server 120 can be an independent server, or it can be a cloud server that provides basic cloud computing services 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 (CDN), and big data and artificial intelligence platforms. The terminal device 110 can be a smart phone, a tablet computer, a laptop computer, a desktop computer, a smart speaker, a smart watch, etc., but is not limited to this. The terminal and the server can be directly or indirectly connected via wired or wireless communication, and this application does not limit this.

[0028] See also Figure 2 , Figure 2 Schematic diagram of a document processing method provided by an embodiment of the present application. Figure 2 As shown, the document processing method can be implemented through steps S11 to S14.

[0029] Step S11: Acquire a target document including a physical examination package, and determine the document type of the target document.

[0030] For example, a target document may be obtained, wherein the target document content includes relevant information of a medical examination package. Further, the present application does not limit the source of the target document, such as a file uploaded by a user (such as a scanned medical examination package receipt or form), an existing storage in a database or system, etc.

[0031] Furthermore, the document type of the target document can be determined by the target document's meta information (e.g., file extension, file header information) or a specific algorithm (e.g., image classifier). The document information includes image documents, such as scanned PDF files, picture format files (JPEG, PNG, etc.), which usually store information in the form of images; and text documents, such as Word documents, TXT files, etc., which directly store information in the form of text.

[0032] Step S12: In response to determining that the document type is an image document type, converting the format of the target document by using optical character recognition technology to obtain a document after the format conversion.

[0033] The document format after format conversion is text format.

[0034] It should be noted that optical character recognition technology is a technology that recognizes and extracts text from images through algorithms. Commonly used optical character recognition technology tools or frameworks include Tesseract OCR, Google Vision API and ABBYYFine Reader, etc. This application is not limited to this.

[0035] For example, the target document can be processed by denoising, contrast enhancement, tilt correction, etc. to improve the recognition accuracy, and then the target document can be scanned line by line through an optical character recognition tool to extract the text and recognize the corresponding characters. Thus, the recognized characters can be output as a structured text format (such as TXT, JSON, etc.), that is, a document with format conversion is obtained, which is convenient for subsequent parsing and processing.

[0036] The above implementation method can start from the target document containing the medical examination package information, automatically determine the document type and use optical character recognition technology to convert the target document format, thereby converting unstructured information (such as image data) into structured text information, laying the foundation for subsequent data analysis, matching and quotation generation. This method greatly reduces the workload of manual input and improves the efficiency and accuracy of the overall processing.

[0037] Step S13: parse the format-converted document using a natural language processing model to obtain parsing information.

[0038] The parsed information at least includes a number of entities and the subordinate relationship information between each entity.

[0039] It should be noted that the main function of the natural language processing model is to perform semantic analysis on the document content after format conversion and extract structured information from it, such as the entity names, prices, descriptions, etc. of the medical examination package, as well as the subordinate relationships between entities. In this way, unstructured text can be converted into structured data that can be used for further analysis and matching.

[0040] For example, the natural language processing model includes deep learning models such as BERT and BiLSTM-CRF, which can perform entity recognition on the format-converted document to obtain several entities. The entities include physical examination items, such as "blood routine", "liver function test", etc.; additional information, such as project description, time limit, applicable population, etc., which are not limited in this application.

[0041] For example, a grammatical structure tree of sentences in the format-converted document can be further established through a natural language processing model to identify modification relationships or dependency relationships between entities. For example, the subordinate relationship includes that the subject of a blood routine examination is a female, and the physical examination package includes a blood routine examination and a liver function test, etc., which is not limited in this application.

[0042] In the above implementation method, the converted document can be parsed by the natural language processing model to effectively extract the key entities in the document (such as physical examination items, gender of the examinee) and their subordinate relationships, and convert them into structured data. This automated semantic parsing method greatly reduces the complexity of manual analysis, improves data processing efficiency and accuracy, and lays the foundation for subsequent physical examination package matching and quotation generation.

[0043] Step S14: matching is performed in the target database based on the parsed information to obtain a matching result, and the quotation of the physical examination package is determined based on the matching result through a preset pricing strategy.

[0044] The matching results include the target physical examination price corresponding to each physical examination item.

[0045] For example, the target database is used to store predefined standard physical examination packages and their corresponding price information, such as a physical examination item table, the name of each physical examination item, the standard price, applicable packages, etc., and a package combination table, the specific items included in each package and their corresponding package prices, etc., which are not limited in this application.

[0046] For example, the names of the physical examination items in the parsed information can be matched with the names of the standard physical examination items already in the target database to determine the most suitable items or package combinations.

[0047] It should be noted that the pricing strategy is the price rules set by the enterprise for different customer groups (such as individual customers, corporate customers) or different scenarios (such as promotional seasons, holidays). This application does not limit the preset pricing strategy. For example, prices are adjusted according to user categories (such as VIPs, first-time customers), or according to project combination discounts. That is, if the user selects multiple projects or packages, discount rules can be applied.

[0048] The above implementation method can reduce manual processing and improve efficiency by matching the target database and pricing strategy, while ensuring that the physical examination items mentioned in the target document accurately correspond to the standard database, and the quotation details of the obtained physical examination package are clear, which enhances user trust.

[0049] The document processing method disclosed in the embodiment of the present application includes obtaining a target document including a physical examination package and determining the document type of the target document. Further, in response to determining that the document type is an image document type, the target document can be formatted by optical character recognition technology to obtain a document after format conversion, wherein the document format after format conversion is a text format. Thus, the document after format conversion can be parsed by a natural language processing model to obtain parsing information, wherein the parsing information at least includes a number of entities and the subordinate relationship information between each entity. Finally, matching can be performed in a target database based on the parsing information to obtain a matching result, and the quotation of the physical examination package can be determined based on the matching result by a preset pricing strategy; wherein the matching result includes the target physical examination price corresponding to each physical examination item. The present application converts the target document of the image document type into a text format by optical character recognition technology, and then parses the text content by a natural language processing model to extract the entity and its subordinate relationship information, which significantly improves the automation and accuracy of the physical examination package document processing. At the same time, matching the physical examination items and prices in the target database based on the parsing information, and generating a quotation in combination with the preset pricing strategy, not only optimizes the physical examination package pricing process, but also reduces the need for manual intervention, and improves efficiency and service quality.

[0050] Optionally, the format-converted document is parsed through a natural language processing model to obtain parsing information, including: performing layout analysis on the format-converted document through a natural language processing model to obtain document structure information; performing structured analysis on the format-converted document based on the document structure information to obtain a number of entities; and performing entity relationship analysis on the format-converted document through a natural language processing model to obtain subordinate relationship information between each entity; and obtaining parsing information based on the several entities and the subordinate relationship information between each entity.

[0051] For example, the layout analysis of the converted document can be performed through a natural language processing model to obtain the overall structural information of the document. For example, the structure of the converted document can be extracted to identify the basic layout of the document, such as title, paragraph, table, image, page number, footnote, etc.; or, the text block detection of the converted document can be performed to decompose the document content into logical blocks, such as separating the title, body and comments; or, based on the typesetting and layout of the content, the hierarchical structure of the document can be constructed, such as the hierarchical relationship between chapters, sections and paragraphs, which is not limited in this application.

[0052] For example, based on the document structure information, the document content can be further structured analyzed to extract several entities in the document. Among them, the entity is used to represent the core information unit in the document, such as: name of a person, place name, organization name, time and date, etc., which is not limited in this application. Furthermore, the relationship between each entity in the document can be analyzed through a natural language processing model to clarify the subordinate relationship information of these entities.

[0053] The above embodiments can combine layout analysis, structural analysis and relationship analysis to achieve a comprehensive analysis of the document after format conversion.

[0054] On the basis of the above-mentioned embodiment, the layout analysis of the format-converted document is performed through a natural language processing model to obtain document structure information, including: extracting semantic structure information and text position information of the format-converted document through a natural language processing model; based on the text position information, associating the text in the corresponding area to obtain text association information; and obtaining document structure information based on the semantic structure information and text association information.

[0055] For example, the semantic content in the format-converted document can be analyzed by a natural language processing model (such as BERT, GPT, etc.), and information related to the logical structure of the document, such as titles, paragraphs, lists, tables, etc., can be extracted, and elements with specific meanings in the document can be classified, such as chapter titles, text content, footers, page numbers, comments, etc. By analyzing the grammatical features (such as font size, bold, italic, underline, etc.) and markup features (such as number sequences, indents, symbols, etc.) in the document, the hierarchical relationship in the document can be further inferred, thereby obtaining the semantic structure information of the format-converted document.

[0056] For example, text location information refers to the specific spatial location (such as page number, coordinates, etc.) of each text content in a document. By combining this information, the semantic content and the document area where it is located can be more accurately associated. The location information of each text segment can be extracted from the page information, coordinate information, and typesetting information of the document after format conversion, and this application does not limit this.

[0057] For example, based on the position information, the text content in the same logical area can be associated. For example, texts with coordinates in the same horizontal line range belong to the same title; texts with adjacent coordinates in the vertical direction belong to the same paragraph; if the document contains a table or image, the text content can be associated with the table / image element based on the position information. In this way, the mapping relationship between the text and its position information can be obtained, and then the text association information can be obtained, and the document structure information can be obtained based on the semantic structure information and the text association information.

[0058] In an embodiment of the present application, a natural language processing model can be used to obtain the logical structure of the document content to ensure the semantic accuracy of the parsing results, and combined with the text position information, the physical layout and logical hierarchy of the document can be more accurate.

[0059] Optionally, based on the document structure information, a structured analysis is performed on the format-converted document to obtain a number of entities, including: performing a preprocessing operation on the format-converted document to obtain a preprocessed document; based on the document structure information, segmenting the preprocessed document according to paragraphs to obtain a segmented document; performing entity recognition on the segmented document to obtain a number of entities.

[0060] Among them, the preprocessing operations include noise removal operations, such as removing irrelevant symbols, blank lines, etc.; word segmentation operations, such as dividing a continuous text stream into independent words or phrases; standardization operations, such as unifying text formats, for example, converting full-width characters to half-width, unifying currency symbols (such as converting ￥ to yuan), etc., which are not limited in this application.

[0061] It should be noted that the present application does not limit the above-mentioned segmentation method. For example, the boundaries of chapters can be identified according to the title (such as "Chapter 1", "Section 1") or style (font size, bold, etc.) in the document, and then the pre-processed document can be segmented to obtain the segmented document; or, paragraphs can be segmented according to the natural segmentation marks of the text layout (such as line breaks, indents, paragraph spacing) to obtain the segmented document.

[0062] Furthermore, the segmented documents may be subjected to entity recognition through a natural language processing model. The specific recognition method is described in the above embodiment and will not be described in detail here.

[0063] The above embodiments can not only accurately locate important content in a document, but also organize it according to semantic information, thus laying a foundation for subsequent semantic analysis and information processing.

[0064] Optionally, the entity includes at least physical examination items and the gender of the examinee, and matching is performed in the target database based on the parsed information to obtain a matching result, including: determining the corresponding target physical examination price in the target database according to the gender of the examinee and the physical examination items, and determining the physical examination items and the corresponding target physical examination price as the matching result; wherein, the target database includes several physical examination items and physical examination prices corresponding to the gender of the examinee.

[0065] For example, after document parsing, at least two key entities, namely, physical examination items and gender of the examinee, can be extracted through entity recognition. Furthermore, corresponding records can be found in the target database based on the entity information to determine the target physical examination price. The matching process is based on a predefined structure in the target database, which contains the corresponding relationship between physical examination items, gender and physical examination prices. Finally, the physical examination items and their prices can be combined to form a matching result.

[0066] In the embodiment of the present application, accurate matching of physical examination items and prices can be achieved, greatly improving the efficiency and accuracy of physical examination services. Through automated parsing and matching, errors that may be caused by manual comparison are avoided, ensuring that price information is highly consistent with user-specific needs (such as gender, items). At the same time, the process supports flexible expansion and can adapt to different database structures and business scenarios, providing strong support for the informatization and intelligence of the physical examination industry.

[0067] Optionally, the quotation of the physical examination package is determined based on the matching result through a preset pricing strategy, including: determining the number of physical examination items based on the matching result, and comparing the number of physical examination items with the preset number of physical examination items to obtain a comparison result; in response to the comparison result that the number of physical examination items is greater than or equal to the preset number of physical examination items, multiplying the total physical examination price by a preset discount to obtain the quotation of the physical examination package, wherein the total physical examination price is obtained by adding up the target physical examination prices of each physical examination item; in response to the comparison result that the number of physical examination items is less than the preset number of physical examination items, determining the total physical examination price as the quotation of the physical examination package.

[0068] For example, based on the matching results, the total physical examination price can be calculated according to the target physical examination price of each physical examination item. If the number of matched physical examination items is greater than or equal to the preset minimum number of items, the total physical examination price can be discounted according to the preset discount strategy to generate a quotation for the physical examination package; if the number of matched physical examination items is less than the preset number, the total physical examination price is directly used as the quotation for the physical examination package.

[0069] The above implementation methods, through the introduction of pricing strategies, effectively realize the automatic generation and optimization of medical examination package quotations, which not only meets the needs of users to flexibly select medical examination items, but also encourages users to select more medical examination items through discount strategies, thereby improving customer experience and order amounts. At the same time, automated quotations avoid the inconsistency and inefficiency of manual pricing, and provide strong support for the standardization and intelligent management of medical examination services.

[0070] Optionally, after determining the quotation of the physical examination package based on the matching result through a preset pricing strategy, it also includes: displaying the quotation of the physical examination package through a display page, so that the user can query the quotation of the physical examination package based on the display page or export the quotation of the physical examination package.

[0071] For example, after calculating the quote for the physical examination package based on the matching results and the preset pricing strategy, the quote information can be presented to the user through a display page. As a result, the user can intuitively query the specific quote for the physical examination package on the display page. At the same time, the page provides an export function, allowing the user to save the quote information in the form of a file for further reference or sharing. This process realizes the transparency and convenient acquisition of quote information.

[0072] The above implementation method provides quotation query and export functions through the display page, which improves the interaction experience between the user and the system and facilitates the user to quickly understand the detailed information of the physical examination package and make decisions.

[0073] See also Figure 3 , Figure 3 1 is a schematic block diagram of a document processing device provided in an embodiment of the present application. The document processing device can be configured in a server to execute the aforementioned document processing method.

[0074] like Figure 4 As shown, the document processing device 200 includes: an acquisition module 201 , a format conversion module 202 , a parsing module 203 and a matching module 204 .

[0075] An acquisition module 201 is used to acquire a target document including a physical examination package and determine a document type of the target document;

[0076] The format conversion module 202 is used for, in response to determining that the document type is an image document type, performing format conversion on the target document by using optical character recognition technology to obtain a document after format conversion, wherein the format of the document after format conversion is a text format;

[0077] A parsing module 203, configured to parse the format-converted document through a natural language processing model to obtain parsing information, wherein the parsing information at least includes a plurality of entities and subordinate relationship information between each of the entities;

[0078] The matching module 204 is used to perform matching in the target database based on the parsed information to obtain matching results, and determine the quotation of the physical examination package based on the matching results through a preset pricing strategy; wherein the matching results include the target physical examination price corresponding to each physical examination item.

[0079] The parsing module 203 is also used to perform layout analysis on the format-converted document through the natural language processing model to obtain document structure information; based on the document structure information, perform structured analysis on the format-converted document to obtain a plurality of entities; and perform entity relationship analysis on the format-converted document through the natural language processing model to obtain the subordinate relationship information between each of the entities; and obtain the parsing information based on the plurality of entities and the subordinate relationship information between each of the entities.

[0080] The parsing module 203 is also used to extract the semantic structure information and text position information of the format-converted document through the natural language processing model; based on the text position information, the text in the corresponding area is associated to obtain text association information; according to the semantic structure information and the text association information, the document structure information is obtained.

[0081] The parsing module 203 is also used to perform preprocessing operations on the document after format conversion to obtain a preprocessed document; based on the document structure information, segment the preprocessed document according to paragraphs to obtain a segmented document; perform entity recognition on the segmented document to obtain a number of entities.

[0082] The matching module 204 is also used to determine the corresponding target physical examination price in the target database according to the gender of the examinee and the physical examination items, and determine the physical examination items and the corresponding target physical examination price as the matching result; wherein, the target database includes several physical examination prices corresponding to the physical examination items and the gender of the examinee.

[0083] The matching module 204 is also used to determine the number of the physical examination items based on the matching result, and compare the number of the physical examination items with the preset number of physical examination items to obtain a comparison result; in response to the comparison result that the number of the physical examination items is greater than or equal to the preset number of physical examination items, multiply the total physical examination price by the preset discount to obtain the quotation for the physical examination package, wherein the total physical examination price is obtained by adding the target physical examination prices of each of the physical examination items; in response to the comparison result that the number of the physical examination items is less than the preset number of physical examination items, determine the total physical examination price as the quotation for the physical examination package.

[0084] The matching module 204 is further configured to display the quotation of the physical examination package through a display page, so that the user can query the quotation of the physical examination package or export the quotation of the physical examination package based on the display page.

[0085] It should be noted that those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described devices and modules and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0086] The method and apparatus of the present application can be used in many general or special computing system environments or configurations, such as personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer terminal devices, network PCs, minicomputers, mainframe computers, and distributed computing environments including any of the above systems or devices.

[0087] Exemplarily, the above method and apparatus may be implemented in the form of a computer program. The computer program may be implemented in the form of a computer program. Figure 4 Runs on the computer device shown.

[0088] See also Figure 4 , Figure 4 1 is a schematic diagram of a computer device provided in an embodiment of the present application. The computer device may be a server.

[0089] like Figure 4 As shown, the computer device includes a processor, a memory and a network interface connected through a system bus, wherein the memory may include a volatile storage medium, a non-volatile storage medium and an internal memory.

[0090] The non-volatile storage medium can store an operating system and a computer program. The computer program includes program instructions, and when the program instructions are executed, the processor can execute any document processing method.

[0091] The processor is used to provide computing and control capabilities and support the operation of the entire computer equipment.

[0092] The internal memory provides an environment for the operation of the computer program in the non-volatile storage medium. When the computer program is executed by the processor, the processor can execute any document processing method.

[0093] The network interface is used for network communication, such as sending assigned tasks, etc. Those skilled in the art can understand that the structure of the computer device is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0094] It should be understood that the processor may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0095] Among them, in some embodiments, the processor is used to obtain a target document including a physical examination package, and determine the document type of the target document; in response to determining that the document type is an image document type, the target document is formatted through optical character recognition technology to obtain a document after format conversion, wherein the format of the document after format conversion is a text format; the formatted document is parsed through a natural language processing model to obtain parsing information, wherein the parsing information at least includes a number of entities and the subordinate relationship information between each of the entities; matching is performed in a target database based on the parsing information to obtain a matching result, and the quotation of the physical examination package is determined based on the matching result through a preset pricing strategy; wherein the matching result includes a target physical examination price corresponding to each physical examination item.

[0096] In some embodiments, the processor is also used to perform layout analysis on the format-converted document through the natural language processing model to obtain document structure information; based on the document structure information, perform structured analysis on the format-converted document to obtain several entities; and perform entity relationship analysis on the format-converted document through the natural language processing model to obtain subordinate relationship information between each entity; and obtain the parsed information based on the several entities and the subordinate relationship information between each entity.

[0097] In some embodiments, the processor is also used to extract semantic structure information and text position information of the format-converted document through the natural language processing model; based on the text position information, associate the text in the corresponding area to obtain text association information; and obtain the document structure information based on the semantic structure information and the text association information.

[0098] In some embodiments, the processor is further used to perform preprocessing operations on the document after format conversion to obtain a preprocessed document; based on the document structure information, segment the preprocessed document according to paragraphs to obtain a segmented document; perform entity recognition on the segmented document to obtain a number of entities.

[0099] In some embodiments, the processor is also used to determine the corresponding target physical examination price in the target database based on the gender of the examinee and the physical examination items, and determine the physical examination items and the corresponding target physical examination price as the matching results; wherein the target database includes several physical examination prices corresponding to the physical examination items and the gender of the examinee.

[0100] In some embodiments, the processor is also used to determine the number of physical examination items based on the matching result, and compare the number of physical examination items with the preset number of physical examination items to obtain a comparison result; in response to the comparison result that the number of physical examination items is greater than or equal to the preset number of physical examination items, multiply the total physical examination price by a preset discount to obtain a quotation for the physical examination package, wherein the total physical examination price is obtained by adding up the target physical examination prices of each of the physical examination items; in response to the comparison result that the number of physical examination items is less than the preset number of physical examination items, the total physical examination price is determined as the quotation for the physical examination package.

[0101] In some implementations, the processor is further configured to display the quotation of the physical examination package through a display page, so that the user can query the quotation of the physical examination package or export the quotation of the physical examination package based on the display page.

[0102] The computer-readable storage medium may be an internal storage unit of the computer device described in the foregoing embodiment, such as a hard disk or memory of the computer device. The computer-readable storage medium may also be an external storage device of the computer device, such as a plug-in hard disk, a smart memory card (SmartMedia Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc., equipped on the computer device.

[0103] Furthermore, the computer-readable storage medium may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application program required for at least one function, and the like.

[0104] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in the present application, and these modifications or replacements should be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.

Claims

1. A document processing method, characterized in that: The method comprises: Acquire a target document including a physical examination package, and determine a document type of the target document; In response to determining that the document type is an image document type, performing format conversion on the target document by using an optical character recognition technology to obtain a format-converted document, wherein the format of the format-converted document is a text format; Parsing the format-converted document through a natural language processing model to obtain parsed information, wherein the parsed information at least includes a plurality of entities and subordinate relationship information between each of the entities; A match is performed in a target database based on the parsed information to obtain a match result, and a quotation for the physical examination package is determined based on the match result through a preset pricing strategy; wherein the match result includes a target physical examination price corresponding to each physical examination item.

2. The method according to claim 1, characterized in that: The document after the format conversion is parsed by a natural language processing model to obtain parsing information, including: Performing layout analysis on the format-converted document using the natural language processing model to obtain document structure information; Based on the document structure information, a structural analysis is performed on the document after the format conversion to obtain a plurality of entities; and Performing entity relationship analysis on the format-converted document by using the natural language processing model to obtain subordinate relationship information between each of the entities; The parsing information is obtained according to the entities and the subordinate relationship information between each of the entities.

3. The method according to claim 2, characterized in that The process of performing layout analysis on the format-converted document by the natural language processing model to obtain document structure information includes: Extracting semantic structure information and text position information of the format-converted document through the natural language processing model; Based on the text position information, associating the text in the corresponding area to obtain text association information; The document structure information is obtained according to the semantic structure information and the text association information.

4. The method according to claim 2, characterized in that: The document after the format conversion is structurally analyzed based on the document structure information to obtain a plurality of entities, including: Performing a preprocessing operation on the document after the format conversion to obtain a preprocessed document; Based on the document structure information, segmenting the preprocessed document according to paragraphs to obtain segmented documents; Entity recognition is performed on the segmented documents to obtain a number of entities.

5. The method according to claim 1, characterized in that The entity at least includes the physical examination items and the gender of the examinee, and the matching is performed in the target database based on the parsed information to obtain the matching result, including: The corresponding target physical examination price is determined in the target database according to the gender of the examinee and the physical examination items, and the physical examination items and the corresponding target physical examination price are determined as the matching results; wherein the target database includes several physical examination prices corresponding to the physical examination items and the gender of the examinee.

6. The method according to claim 1, characterized in that The determining the quotation of the physical examination package based on the matching result by using a preset pricing strategy includes: Determine the number of the physical examination items based on the matching result, and compare the number of the physical examination items with the preset number of physical examination items to obtain a comparison result; In response to the comparison result that the number of the physical examination items is greater than or equal to the preset number of physical examination items, the total physical examination price is multiplied by the preset discount to obtain a quotation for the physical examination package, wherein the total physical examination price is obtained by adding the target physical examination prices of each of the physical examination items; In response to the comparison result being that the number of the physical examination items is less than the preset number of physical examination items, the total physical examination price is determined as the quotation of the physical examination package.

7. The method according to claim 1, characterized in that After determining the quotation of the physical examination package based on the matching result by using a preset pricing strategy, the method further includes: The quotation of the physical examination package is displayed through a display page, so that the user can query the quotation of the physical examination package or export the quotation of the physical examination package based on the display page.

8. A document processing device, characterized in that: The document processing device comprises: An acquisition module, used to acquire a target document including a physical examination package and determine a document type of the target document; a format conversion module, configured to, in response to determining that the document type is an image document type, perform format conversion on the target document by using an optical character recognition technology to obtain a document after format conversion, wherein the format of the document after format conversion is a text format; A parsing module, used to parse the format-converted document through a natural language processing model to obtain parsing information, wherein the parsing information at least includes a plurality of entities and subordinate relationship information between each of the entities; A matching module is used to match in a target database based on the parsed information to obtain a matching result, and determine the quotation of the physical examination package based on the matching result through a preset pricing strategy; wherein the matching result includes a target physical examination price corresponding to each physical examination item.

9. A computer device, characterized in that: include: A memory and a processor; wherein the memory is connected to the processor and is used to store a program; the processor is used to implement the steps of the document processing method as described in any one of claims 1 to 7 by running the program stored in the memory.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the processor implements the steps of the document processing method according to any one of claims 1 to 7.

Images