A medical data structuring method, device, equipment and medium

Abstract

The present invention discloses a medical data structuring method, apparatus, device, and medium. The method comprises: obtaining a target medical data file and a standard structured prompt template; performing text detection and recognition on the target medical data file to obtain text information and corresponding position information in the target medical data file; performing layout extraction on the target medical data file to obtain layout information corresponding to the target medical data file; performing structured processing on the text information, corresponding position information, and layout information in the target medical data file to obtain initial structured data; inputting the initial structured data and the standard structured prompt template into a model that has been trained for standardization processing; and outputting standard structured data. This method not only automatically implements standard structured processing of medical data files, but also improves the accuracy of the obtained standard structured data, providing data support for downstream tasks of medical data.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data processing, and in particular to a medical data structuring method, device, equipment and medium. BACKGROUND

[0002] With the development of medical technology, the quantity and type of medical data are increasing, which covers text data such as medical records, medical orders and examination reports, image data such as X-ray films and CT scans, and physiological data such as electrocardiogram, blood pressure and blood sugar. Medical structuring refers to the arrangement and standardization of medical data for storage, management and analysis. By converting medical data into a structured form, the readability, searchability and analyzability of the data can be improved, thereby providing better support for medical institutions and medical research. For example, in the auxiliary / AI diagnosis scene, the medical report (such as physical examination report, case report, etc.) can be structured and analyzed to mine the patient's medical history and illness information, and establish a disease prediction model to assist doctors in diagnosis and treatment decision-making; in the application scene of statistical analysis and clinical research, structured medical data can also help researchers to count which groups of people, regions, symptoms, diseases and applicable drugs often appear for pathological research; in the field of business risk assessment, structured medical data can help insurance companies to standardize and structure customer medical record information, facilitate analysis and assessment of customer risk costs, etc. However, the existing medical data structuring mostly needs to be processed based on manual work, which is very inefficient, and the long processing process will also cause eye fatigue, so the manual method is not suitable for the current rapid development of computer and other fields.

[0003] Therefore, how to automatically realize the structured processing of medical data to provide support for the downstream tasks of medical data has become a problem to be solved. SUMMARY

[0004] Therefore, a medical data structuring method, device, equipment and medium are provided to solve the problem of how to automatically realize the structured processing of medical data to provide support for the downstream tasks of medical data.

[0005] In a first aspect, an embodiment of the present application provides a medical data structuring method, comprising:

[0006] obtaining a target medical data file and a standard structured prompt template;

[0007] performing text detection and recognition on the target medical data file to obtain text information and corresponding position information in the target medical data file, and performing layout extraction on the target medical data file to obtain layout information corresponding to the target medical data file;

[0008] text information in the target medical data file, corresponding position information and layout information are structured to obtain initial structured data;

[0009] The initial structured data and the standard structured prompt template are input into a model that has been trained for standardization processing to output standard structured data.

[0010] In a second aspect, an embodiment of the present application provides a medical data structuring apparatus, comprising:

[0011] A data acquisition module is configured to acquire a target medical data file and a standard structured prompt template.

[0012] An information extraction module is configured to perform text detection and recognition on the target medical data file to obtain text information and corresponding position information in the target medical data file, and perform layout extraction on the target medical data file to obtain layout information corresponding to the target medical data file.

[0013] A preliminary structuring module is configured to perform structured processing on the text information, corresponding position information and layout information in the target medical data file to obtain initial structured data.

[0014] A standard structuring module is configured to input the initial structured data and the standard structured prompt template into a model that has been trained for standardization processing to output standard structured data.

[0015] In a third aspect, an embodiment of the present application provides a computer device, comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the medical data structuring method of the first aspect when executing the computer program.

[0016] In a fourth aspect, an embodiment of the present application provides a computer readable storage medium, wherein the computer readable storage medium stores a computer program, and the computer program is executable on a processor to implement the medical data structuring method of the first aspect.

[0017] The technical effects achieved by the present application are different from the prior art solutions: the present application obtains text information and corresponding position information in the target medical data file by text detection and recognition on the target medical data file, extracts the layout of the target medical data file to obtain layout information corresponding to the target medical data file, and performs structured processing on the text information, corresponding position information and layout information in the target medical data file to obtain initial structured data. The initial structured data and the standard structured prompt template are input into a model that has been trained and standardized, and the standard structured data is output. The initial structured data is obtained by initial information extraction on the target medical data file, so that the model that has been trained and standardized can perform standardized processing on the initial structured data based on the standard structured prompt template to obtain the standard structured data, thereby automatically implementing the standard structured processing of the medical data file. In addition, the correction processing of the initial structured data based on the model and the prompt template also improves the accuracy of the obtained standard structured data, thereby providing data support for downstream tasks of medical data. BRIEF DESCRIPTION OF DRAWINGS

[0018] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the description of the embodiments of the present application. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can also be obtained by those skilled in the art without creative labor.

[0019] Figure 1 is an application environment schematic diagram of a medical data structured method provided by the first embodiment of the present application;

[0020] Figure 2 is a flow schematic diagram of a medical data structured method provided by the second embodiment of the present application;

[0021] Figure 3 is a flow schematic diagram of a medical data structured method provided by the third embodiment of the present application;

[0022] Figure 4 is a structural schematic diagram of a medical data structured device provided by the fourth embodiment of the present application;

[0023] Figure 5 is a structural schematic diagram of a computer device provided by the fifth embodiment of the present application. DETAILED DESCRIPTION

[0024] With reference to the accompanying drawings, the technical solutions in the embodiments of the present application will be clearly and completely described below, obviously, the described embodiments are some of the embodiments of the present application, rather than all the embodiments. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without creative work belong to the protection scope of the present application.

[0025] It should be understood that the size of the serial number of each step in the following embodiments does not mean the order of execution, the execution order of each process should be determined according to its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0026] The medical data structuring method provided by the embodiment one of the present application can be applied in the application environment such as Figure 1 , wherein the server and the client communicate, the server provides medical data structuring service, and the client triggers medical data structuring task to the server. The client includes but is not limited to palmtop computer, desktop computer, notebook computer, ultra-mobile personal computer (UMPC), netbook, cloud computer device, personal digital assistant (PDA) and the like. The computer device corresponding to the server can be realized by an independent server or a server cluster composed of multiple servers.

[0027] As shown in Figure 2 , it is a flowchart of a medical data structuring method provided by the embodiment two of the present application, including the following steps:

[0028] Step S201: obtaining target medical data file and standard structured prompt template.

[0029] In the embodiment, the target medical data file can be a file to be structured, for example, the target medical data file can be physical examination report and case report, and the standard structured prompt template can be a standard structured information defined by the target medical data file.

[0030] For example, the standard structured prompt template can be:

[0031] Standardize the initial structured data, please follow the guidelines below:

[0032] 1. Keep all original titles and convert them to appropriate marked title levels (# for main title, ## for sub-level, etc.), ensure that each title is on its own line, and add a blank line before and after each title;

[0033] 2. If the list exists in the original text, set its format correctly (unordered or ordered);

[0034] 3. Preserve all original content and meaning;

[0035] 4. Remove any spurious introductory text such as "This is the corrected text:" that may have been added by the large language model and is clearly not part of the original text;

[0036] 5. Remove any obviously duplicated content that seems to have been accidentally included twice. Follow these strict guidelines:

[0037] - Only remove exactly or nearly exactly duplicated paragraphs or parts within the main block.

[0038] - Consider the context (before and after the main block) to identify duplicates that span block boundaries.

[0039] - Do not remove content that is simply similar but conveys different information.

[0040] - Preserve all unique content, even if it seems redundant.

[0041] - Ensure the text flows smoothly after removal.

[0042] - Do not add any new content or explanations.

[0043] - If no obvious duplicates are found, return the main block unchanged.

[0044] 6. Identify but do not remove headers, footers, or page numbers. Instead, format them explicitly;

[0045] 7. Attempt to reconstruct tables or correct table reconstruction content from images, if any.

[0046] Step S202: text detection and recognition are performed on the target medical data file to obtain text information and corresponding position information in the target medical data file, and layout extraction is performed on the target medical data file to obtain layout information corresponding to the target medical data file.

[0047] Step S203: the text information, corresponding position information, and layout information in the target medical data file are structured to obtain initial structured data.

[0048] In this embodiment, the initial structured data can refer to structured data obtained by performing preliminary structured processing on the target medical data file.

[0049] Specifically, in the process of text detection and recognition on the target medical data file to obtain the text information and the corresponding position information in the target medical data file. First, the text area in the target medical data file is determined through the text area detection technology, and the detected text area is segmented into single characters. Then, the feature information of each character is extracted, and the text information in the text area is determined through the character recognition technology according to the extracted character features, and the specific position information of the text in the target medical data file is determined in the process of recognition.

[0050] In the process of layout extraction on the target medical data file to obtain the layout information corresponding to the target medical data file. First, the target medical data file is input into the model that has been trained for layout analysis, and the layout format information corresponding to the target medical data file is output, such as double-column and three-column, etc. Then, the target medical data file is input into the model that has been trained for table extraction, and the table information is output, such as bordered table / non-bordered table, etc. Finally, the layout format information and the table information are combined to obtain the layout information.

[0051] And according to the extracted text information, position information and layout information, preliminary structured processing is performed to obtain initial structured data.

[0052] Step S204: input the initial structured data and the standard structured prompt template into the model that has been trained for standardization processing, and output the standard structured data.

[0053] In this embodiment, the standard structured data can refer to the structured data obtained by standardizing the initial structured data according to the standard structured prompt template, and the model that has been trained for standardization processing can refer to a deep learning model for multi-modal tasks that has been trained for standardization processing. This model can fuse multiple modalities such as vision and text, and can process and understand multiple types of data input such as images and texts.

[0054] Specifically, the text information, position information and layout information in the initial structured data are adjusted according to the standard structured prompt template through the model that has been trained for standardization processing, to obtain adjusted text information, adjusted position information, adjusted layout information and corresponding adjustment scores. The adjusted text information, adjusted position information and adjusted layout information form candidate structured data, and the adjustment scores are candidate scores of the candidate structured data. According to the candidate scores, all candidate structured data are sorted, and the candidate structured data with the highest candidate score is output as the standard structured data.

[0055] In the embodiment, the initial structured data is obtained by performing initial information extraction on the target medical data file, the model trained by the standardization processing is used to perform standardization processing on the initial structured data based on the standard structured prompt template, the standard structured data is obtained, the standard structured processing of the medical data file is automatically realized, the correction processing of the initial structured data based on the model and the prompt template also improves the accuracy of the obtained standard structured data, thereby providing data support for downstream tasks of medical data.

[0056] As shown in Figure 3 FIG. 3 is a flowchart of a medical data structuring method according to an embodiment of the present application. After the step S204 of outputting the standard structured data, the method can further include the following steps:

[0057] Step S301: performing redundancy checking on the standard structured data to obtain a checking result.

[0058] Step S302: performing parameter optimization on the model trained by the standardization processing according to the checking result to obtain an updated model.

[0059] Step S303: inputting the initial structured data and the standard structured prompt template into the updated model to output updated structured data.

[0060] Specifically, after the initial structured data and the standard structured prompt template are input into the model trained by the standardization processing to output the standard structured data, content checking can be performed on the standard structured data. Whether there is redundancy in the standard structured data is determined by logical judgment. If there is redundancy, the model trained by the standardization processing is optimized in parameters to obtain an updated model. The initial structured data and the standard structured prompt template are input into the updated model for re-pushing to output updated structured data.

[0061] Optionally, after the updated structured data is output, similarity matching technology can be used to perform similarity matching on the text information in the standard structured data and the text information in the target medical data file to obtain a similarity score. If the similarity score meets a preset threshold, it is determined that the similarity verification of the standard structured data is passed. If the similarity score does not meet the preset threshold, the standard structured data can be marked for subsequent manual verification.

[0062] Optionally, after outputting the structured data, the medical data item in the standard structured data can be determined, the medical data item is matched with the standard medical data item in the preset medical database, if the matching passes, it is determined that the medical data item in the standard structured data passes the verification, and if the matching fails, the standard structured data can be marked for subsequent manual verification.

[0063] In the embodiment, after the initial structured data and the standard structured prompt template are input into the model trained by the standardization processing, the standard structured data is output, the standard structured data is subjected to redundancy checking, similarity matching and medical data item matching, and the accuracy of the obtained standard structured data is improved.

[0064] As shown in Figure 4 Fig. 4 is a medical data structuring device provided by the fourth embodiment of the present application, which corresponds to the medical data structuring method in the above embodiments. The medical data structuring device comprises a data acquisition module 41, an information extraction module 42, a preliminary structuring module 43 and a standard structuring module 44. The functions of the modules are described in detail as follows.

[0065] The data acquisition module 41 is configured to acquire a target medical data file and a standard structured prompt template.

[0066] The information extraction module 42 is configured to perform text detection and recognition on the target medical data file to obtain text information and corresponding position information in the target medical data file, and perform layout extraction on the target medical data file to obtain layout information corresponding to the target medical data file.

[0067] The preliminary structuring module 43 is configured to perform structured processing on the text information, the corresponding position information and the layout information in the target medical data file to obtain initial structured data.

[0068] The standard structuring module 44 is configured to input the initial structured data and the standard structured prompt template into a model trained by standardization processing to output standard structured data.

[0069] Optionally, the information extraction module 42 comprises:

[0070] A text region detection unit is configured to determine a text region in the target medical data file by using a text region detection technology.

[0071] A character recognition unit is configured to perform text detection and recognition on the text region by using a character recognition technology to obtain the text information and the position information.

[0072] Optionally, the information extraction module 42 comprises:

[0073] a layout extraction unit configured to input the target medical data file into a model trained for layout analysis, and output layout format information corresponding to the target medical data file;

[0074] a table extraction unit configured to input the target medical data file into a model trained for table extraction, and output table information;

[0075] a combination unit configured to combine the layout format information and the table information to obtain the layout information.

[0076] Optionally, the standard structured module 44 comprises:

[0077] an adjustment unit configured to adjust text information, position information, and layout information in the initial structured data according to the standard structured prompt template by using the model trained for standardization, to obtain adjusted text information, adjusted position information, adjusted layout information, and a corresponding adjusted score;

[0078] a candidate unit configured to form candidate structured data from the adjusted text information, the adjusted position information, and the adjusted layout information, and to set the adjusted score as a candidate score of the candidate structured data;

[0079] a sorting unit configured to sort all candidate structured data according to the candidate score, and output a candidate structured data with the highest candidate score as the standard structured data.

[0080] Optionally, the medical data structured device further comprises:

[0081] a redundancy checking module configured to perform redundancy checking on the standard structured data, to obtain a checking result;

[0082] a model optimization module configured to perform parameter optimization on the model trained for standardization according to the checking result, to obtain an updated model;

[0083] an updating module configured to input the initial structured data and the standard structured prompt template into the updated model, and output updated structured data.

[0084] Optionally, the medical data structured device further comprises:

[0085] a similarity matching module configured to perform similarity matching on text information in the standard structured data and text information in the target medical data file by using a similarity matching technique, to obtain a similarity score;

[0086] The similarity verification module is configured to determine that the similarity verification of the standard structured data has passed if the similarity score meets a preset threshold.

[0087] Optionally, the medical data structuring device further includes:

[0088] The data item verification module is used to determine the medical data item in the standard structured data, match the medical data item with the standard medical data item, and if the match is successful, determine that the medical data item of the standard structured data has passed the verification.

[0089] The specific definition of the medical data structuring device can be found in the definition of the medical data structuring method above and will not be repeated here. The various modules in the above-mentioned medical data structuring device can be implemented in whole or in part through software, hardware, or a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in hardware form, or can be stored in the memory of the computer device in software form, so that the processor can call and execute the corresponding operations of the above-mentioned modules.

[0090] Figure 5 This is a schematic diagram of the structure of a computer device provided in the fifth embodiment of the present invention. Figure 5 As shown, the computer device of this embodiment includes: at least one processor ( Figure 5 Only one is shown), a memory, and a computer program stored in the memory and executable on at least one processor, wherein when the processor executes the computer program, the steps of any of the above-mentioned medical data structuring method embodiments are implemented.

[0091] The computer device may include, but is not limited to, a processor and a memory. It will be understood by those skilled in the art that Figure 5 The above is merely an example of a computer device and does not constitute a limitation on the computer device. The computer device may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, it may also include a network interface, a display screen, and an input device.

[0092] The processor can be a central processing unit (CPU), the processor can also be other general-purpose processors, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor.

[0093] The memory includes a readable storage medium, an internal memory, etc., where the internal memory can be the memory of the computer device, and the internal memory provides an environment for the operation of the operating system and the computer-readable instructions in the readable storage medium. The readable storage medium can be the hard disk of the computer device, and in other embodiments, can also be the external storage device of the computer device, for example, the plug-in hard disk, the smart media card (SMC), the secure digital (SD) card, the flash card, etc. equipped on the computer device. Further, the memory can include both the internal storage unit of the computer device and the external storage device. The memory is used to store the operating system, the application program, the boot loader, the data, and other programs, such as the program code of the computer program, etc. The memory can also be used to temporarily store the data that has been output or will be output.

[0094] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the above-mentioned division of each functional unit and module is exemplified, and in actual application, the above-mentioned functions can be completed by different functional units and modules according to needs, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiment can be integrated in one processing unit, or each unit can be physically present separately, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of software functional unit. In addition, the specific names of each functional unit and module are only for easy distinction, and do not limit the protection scope of the present application. The specific working process of the unit and module in the above device can refer to the corresponding process in the foregoing method embodiment, which will not be repeated here. If the integrated unit is realized in the form of software functional unit and sold or used as an independent product, it can be stored in a computer readable storage medium. Based on this understanding, the present application realizes all or part of the processes in the above-mentioned embodiment methods, which can be completed by a computer program to instruct related hardware. The computer program can be stored in a computer readable storage medium, and when the processor executes the computer program, the steps of the above-mentioned method embodiment can be realized. The computer program includes computer program code, which can be in the form of source code, object code, executable file or some intermediate form, etc. The computer readable medium can at least include any entity or device capable of carrying computer program code, recording medium, computer memory, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), electric carrier signal, telecommunication signal and software distribution medium. For example, U disk, mobile hard disk, magnetic disk or optical disk, etc. In some jurisdictions, according to legislation and patent practice, computer readable medium cannot be electric carrier signal and telecommunication signal.

[0095] The present application realizes all or part of the processes in the above-mentioned embodiment methods, which can also be completed by a computer program product. When the computer program product runs on the computer device, it makes the computer device execute the steps in the above-mentioned method embodiment.

[0096] In the above-mentioned embodiments, the description of each embodiment has its own emphasis, and the parts not described or recorded in detail in a certain embodiment can be referred to the relevant description of other embodiments.

[0097] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present invention.

[0098] In the embodiments provided by the present invention, it should be understood that the disclosed apparatus / computer equipment and methods can be implemented in other ways. For example, the apparatus / computer equipment embodiments described above are merely illustrative. For example, the division of modules or units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0099] Units described as separate components may or may not be physically separate, and components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0100] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention, and should all be included in the scope of protection of the present invention.

Claims

1. A medical data structuring method, characterized in that: include: Obtain target medical data files and standard structured prompt templates; Performing text detection and recognition on the target medical data file to obtain text information and corresponding position information in the target medical data file, and performing layout extraction on the target medical data file to obtain layout information corresponding to the target medical data file; Performing structural processing on the text information, corresponding position information, and format information in the target medical data file to obtain initial structured data; Inputting the initial structured data and the standard structured prompt template into a model that has been trained for standardization, and outputting the standard structured data; The performing layout extraction on the target medical data file to obtain layout information corresponding to the target medical data file includes: Inputting the target medical data file into a model that has been trained for layout analysis, and outputting layout format information corresponding to the target medical data file; Input the target medical data file into a model that has been trained for table extraction, and output table information; Combining the layout format information and the table information to obtain the format information; The step of inputting the initial structured data and the standard structured prompt template into a model that has been trained and standardized, and outputting the standard structured data, includes: Adjusting the text information, position information, and layout information in the initial structured data according to the standard structured prompt template using the standardized trained model to obtain adjusted text information, adjusted position information, adjusted layout information, and corresponding adjustment scores; forming candidate structured data from the adjusted text information, the adjusted position information, and the adjusted layout information, and using the adjusted score as a candidate score of the candidate structured data; All candidate structured data are sorted according to the candidate scores, and the candidate structured data with the highest candidate score is output as the standard structured data.

2. The medical data structuring method according to claim 1, wherein: The performing text detection and recognition on the target medical data file to obtain text information and corresponding position information in the target medical data file includes: Determining the text region in the target medical data file by using text region detection technology; The text area is subjected to text detection and recognition by using character recognition technology to obtain the text information and the position information.

3. The medical data structuring method according to claim 1, wherein: After outputting the standard structured data, the following is also included: Performing a redundancy check on the standard structured data to obtain a check result; Optimizing parameters of the standardized and trained model according to the inspection results to obtain an updated model; The initial structured data and the standard structured prompt template are input into the updated model, and updated structured data is output.

4. The medical data structuring method according to claim 1, wherein: After outputting the standard structured data, the following is also included: Performing similarity matching on the text information in the standard structured data and the text information in the target medical data file using similarity matching technology to obtain a similarity score; If the similarity score meets a preset threshold, it is determined that the similarity verification of the standard structured data has passed.

5. The medical data structuring method according to claim 1, wherein: After outputting the standard structured data, the following is also included: A medical data item in the standard structured data is determined, and the medical data item is matched with a standard medical data item. If the match succeeds, it is determined that the medical data item of the standard structured data has passed verification.

6. A medical data structuring device, characterized in that: include: A data acquisition module, used to acquire target medical data files and standard structured prompt templates; an information extraction module, configured to perform text detection and recognition on the target medical data file to obtain text information and corresponding position information in the target medical data file, and perform layout extraction on the target medical data file to obtain layout information corresponding to the target medical data file; A preliminary structuring module, configured to perform structural processing on the text information, corresponding position information and format information in the target medical data file to obtain initial structured data; A standard structured module, configured to input the initial structured data and the standard structured prompt template into a model that has been trained for standardization processing, and output standard structured data; The information extraction module includes: a layout extraction unit, configured to input the target medical data file into a model that has been trained for layout analysis, and output layout format information corresponding to the target medical data file; a table extraction unit, configured to input the target medical data file into a model that has been trained for table extraction and output table information; a combining unit, configured to combine the layout format information and the table information to obtain the format information; The standard structured module includes: an adjustment unit, configured to adjust the text information, position information, and layout information in the initial structured data according to the standard structured prompt template using the standardized and trained model to obtain adjusted text information, adjusted position information, adjusted layout information, and a corresponding adjustment score; a candidate unit, configured to form candidate structured data from the adjusted text information, the adjusted position information, and the adjusted layout information, and use the adjustment score as a candidate score of the candidate structured data; The sorting unit is configured to sort all the candidate structured data according to the candidate scores, and output the candidate structured data with the highest candidate score as the standard structured data.

7. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the medical data structuring method according to any one of claims 1 to 5 is implemented.

8. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the medical data structuring method according to any one of claims 1 to 5 is implemented.

Images