Intelligent verification method and system for standard information physical examination table based on data automation

Abstract

The invention discloses a standard information physical examination table intelligent verification method and system based on data automation, and the method comprises the steps: generating standard candidate data of a target field through a data collection step and data standardization processing, and carrying out the screening, and obtaining a standard data set; determining the dependency relationship between the fields of the physical examination table, mapping the standardized data values to the corresponding positions of the fields of the physical examination table through a field mapping function, and generating the physical examination table through data verification and automatic correction; analyzing the relationship between the fields of the physical examination table to predict and generate a filling suggestion value, and generating a filling suggestion list through regularization item correction and verification; inputting the physical examination table data input and modification of the doctor, and generating a final physical examination table draft; and performing consistency verification and medical compliance verification on the final physical examination table draft to generate a formal physical examination table. Through data integration, structured mapping and context reasoning filling, the filling efficiency, data integrity and medical compliance of the physical examination table are improved, and the workload of doctors is relieved.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, specifically to an intelligent verification method and system for standardized information health check forms based on data automation. Background Technology

[0002] With the continuous advancement of the national basic public health service system, annual health checkups for the elderly and patients with chronic diseases have become an important part of primary healthcare. According to current national public health standards, medical personnel are required to complete several standardized forms for this population, including basic information collection, chronic disease follow-up recording, physiological indicator assessment, lifestyle analysis, and medication adherence assessment. These forms not only require complete and accurate information but also strict adherence to the defined field formats, logical relationships, and statistical standards. However, in practice, completing these forms often does not rely on a single, dedicated examination. Instead, medical personnel need to extract relevant information from multiple systems for comprehensive judgment and data entry. This information is scattered across different business systems, with inconsistent formats and data time points, leading to difficulties for doctors in tracing information, unclear field selection, and duplicate data entry, significantly increasing their workload. Furthermore, because the process relies on manual judgment and data entry, issues such as omissions, incorrect field entries, and confusing form structures are prone to occur, affecting the overall quality and effectiveness of public health data. While some systems have attempted to introduce template-based data entry and data synchronization features, existing technologies are primarily limited to field-to-field mapping at the table level. They lack an understanding of the overall structure and semantics of the medical examination form, making it impossible to determine whether certain key items should be filled in, whether there are omissions or errors, and to provide understandable verification criteria and filling suggestions. Therefore, existing technologies still have significant limitations in supporting doctors to efficiently and accurately complete medical examination forms that meet national standards. A more intelligent and structure-aware technological solution is urgently needed to assist in determining the logical completeness of the content and reduce the interactive burden on doctors. Summary of the Invention

[0003] The purpose of this invention is to provide an intelligent verification method and system for standardized information health check forms based on data automation, so as to solve the problems mentioned in the background art.

[0004] In a first aspect, the present invention provides an intelligent verification method for standardized information physical examination forms based on data automation, the method comprising the following steps:

[0005] Extract a list of target fields, generate standardized candidate data for the target fields through data collection steps and data standardization processing, select the standardized candidate data according to a preset standard value selection formula, and obtain a standardized dataset, which includes the standardized data values ​​of the target fields;

[0006] Based on the standardized dataset, a national structure map model is constructed to clarify the dependencies between the fields of the physical examination form and the model. The standardized data values ​​are mapped to the corresponding positions of the fields in the physical examination form through a field mapping function. The physical examination form is then generated through data validation and automatic correction.

[0007] Based on the field data of the physical examination form, logical rules and contextual reasoning are established to analyze the relationship between fields and predict and generate fill suggestion values. The fill suggestion values ​​are modified and verified by regularization terms to generate a fill suggestion list. The fill suggestions include field fill values ​​and fill value verification results.

[0008] The system allows doctors to input and modify data on the physical examination form through a human-computer interaction interface. Based on the medical normal range, it provides real-time prompts and verifies the validity of the input values, records the data modification history and provides real-time feedback on the results of the modified data. After the doctor confirms all fields on the physical examination form, the final draft of the physical examination form is generated.

[0009] The final draft of the physical examination form undergoes consistency verification, which includes: field order check, field dependency check, and value range and unit consistency check. After passing the consistency verification, the final draft of the physical examination form undergoes medical compliance verification. After passing the medical compliance verification, the official physical examination form is generated.

[0010] Furthermore, the steps of data acquisition and data standardization processing to generate standardized candidate data for the target field include: selecting the target field from the field list, collecting candidate data through interfaces with multiple medical systems, including electronic medical record system interfaces, prescription information system interfaces, and public health follow-up system interfaces; the data standardization processing steps include: unit conversion processing and formatting processing, wherein the unit conversion processing converts the candidate data units into a standard format, the formatting processing converts the candidate data into a uniform number of decimal places, outputs standardized data values, and stores the standardized data values ​​in a candidate value set.

[0011] Furthermore, the standardized candidate data screening step includes: calculating a time score based on the proximity of the data collection time to the current time using a time scoring function; calculating the source priority based on the reliability weight of the data source; performing a final standard value selection calculation based on the time score and the source priority; and finally selecting the standardized data value of the target field. Furthermore, the national structure graph model is based on the physical examination form template in the National Public Health Management Standards, and the national graph structure model is constructed using physical examination form fields as nodes and the relationships between these fields as edges.

[0012] Furthermore, the data verification step includes: checking abnormal data according to medical standards and reasonable data ranges by examining the standardized data values ​​corresponding to the fields; the automatic correction step includes: obtaining correction items based on patient historical data or specific rules, and combining the correction items with correction weight factors into the automatic correction formula to obtain the data value corresponding to the corrected field. Furthermore, the steps of establishing logical rules and contextual reasoning calculation include: establishing a reasoning model based on logical rules, identifying logical relationships between fields, generating fill suggestion values ​​based on the logical relationships between fields; obtaining the patient's known medical data fields, combining the contextual reasoning-generated fields with the known medical data fields into the fill suggestion formula to obtain the generated fill suggestion values.

[0013] Further, the regularization term correction includes: calculating a regularization adjustment term based on the medical normal range and known medical data; the regularization adjustment term and the regularization correction factor are combined with the imputation suggestion value and input into the regularization formula to output the field imputation value; the verification step includes: checking the imputation suggestion value after correction based on the medical normal range, outputting the imputation value verification result if it conforms to the normal range, and marking it as invalid if it does not conform to the normal range, and further inputting the regularization term correction. Further, the consistency verification includes: field order check, field dependency verification, and value range and unit consistency check, specifically including: the field order check includes checking whether the fields of the physical examination form conform to the requirements of the national public health management standards; the field dependency verification includes checking whether the dependency relationship between fields meets the system's preset field dependency relationship; the value range and unit consistency check includes checking whether the field values ​​of the physical examination form are within the medical standard normal range and whether the field units are consistent, and the final physical examination form draft is input into the medical compliance verification after passing the field order check, field dependency verification, and value range and unit consistency check.

[0014] Furthermore, the medical compliance verification includes: comparing the input field data values ​​with preset medical standards; if the input field data values ​​conform to the preset normal range, an official medical examination form is output; if the input field data values ​​do not conform to the preset range, they are marked as invalid and correction suggestions are output. The official medical examination form includes an archiving process, which includes: storing the official medical examination form in the system database, assigning a unique identifier to the official medical examination form, and generating an electronic copy of the official medical examination form.

[0015] On the other hand, this application also provides an intelligent verification system for standardized information medical examination forms based on data automation. The system includes: a data acquisition module, used to extract a list of target fields, generate standardized candidate data for the target fields through data acquisition steps and data standardization processing, and filter the standardized candidate data according to a preset standard value selection formula to obtain a standardized dataset, the standardized dataset including standardized data values ​​of the target fields; a field mapping and filling module, used to construct a national structure diagram model based on the standardized dataset, clarify the dependencies between the medical examination form fields and the model, map the standardized data values ​​to the corresponding positions of the medical examination form fields through a field mapping function, and generate the medical examination form through data verification and automatic correction; and a field filling generation module, used to establish logical rules and contextual reasoning based on the medical examination form field data. The system analyzes the relationships between fields to predict and generate fill-in suggestions. These suggestions are then corrected and validated using regularization to generate a list of fill-in suggestions, including the field fill-in values ​​and their validation results. An interactive confirmation module allows doctors to input and modify data on the medical examination form through a human-computer interface. Based on medically normal ranges, the module provides real-time prompts and validations of the input values, records the data modification history, and provides real-time feedback on the modification results. After the doctor confirms all fields on the medical examination form, a final draft is generated. A validation and verification module performs consistency verification on the final draft, including field order checks, field dependency verification, and value range and unit consistency checks. After passing consistency verification, the final draft undergoes medical compliance verification, and upon passing this verification, a final medical examination form is generated. By employing the above technical solution, the automated filling, generation, and validation of medical examination forms are achieved.

[0016] Compared with existing technologies, the beneficial effects of this invention are as follows: By establishing a unified data preprocessing and mapping framework, it automatically integrates medical data from multiple sources such as medical records, prescriptions, follow-up records, and auxiliary examinations, solving the problems of inconsistent data sources and duplicate data entry; by introducing mapping logic between the physical examination form structure and national standards, the system can identify the position and function of each field in the overall form, thereby effectively avoiding structural problems such as incorrect columns and forms. Simultaneously, in scenarios where fields are missing or inconsistent, based on existing medical data records and historical data patterns, it uses reasoning and contextual judgment to assist in generating reasonable suggestions for supplementary filling, and expresses prompts in an understandable way, helping medical staff quickly confirm and supplement data, significantly improving data integrity and form compliance. The entire system design balances intelligent automatic processing capabilities with doctor review, reducing the workload of manual labor while improving the quality of physical examination forms and the credibility of medical data, fundamentally solving various problems in the generation and compliant completion of physical examination forms in existing technologies. Attached Figure Description

[0017] Figure 1 This is a flowchart of the method steps of the present invention;

[0018] Figure 2 This is a schematic diagram of the system structure in this invention. Detailed Implementation

[0019] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0020] Please see Figure 1 This invention provides an intelligent verification method for standardized information physical examination forms based on data automation, comprising the following steps:

[0021] S1: Extract the target field list, generate standardized candidate data for the target fields through data acquisition steps and data standardization processing, and filter the standardized candidate data according to a preset standard value selection formula to obtain a standardized dataset. The standardized dataset includes the standardized data values ​​of the target fields. The steps of data acquisition and data standardization processing to generate standardized candidate data for the target fields include: selecting the target fields in the field list, collecting candidate data through interfaces with multiple medical systems, including electronic medical record system interfaces, prescription information system interfaces, and public health follow-up system interfaces; the data standardization processing steps include: unit conversion processing and formatting processing. The unit conversion processing converts the candidate data units to a standard format, and the formatting processing converts the candidate data to a uniform number of decimal places, outputs standardized data values, and stores the standardized data values ​​in a candidate value set.

[0022] Specifically, the standardized candidate data screening steps include: calculating a time score based on the proximity of the data collection time to the current time using a time scoring function; calculating the source priority based on the reliability weight of the data source; performing a final standard value selection calculation based on the time score and the source priority; and finally selecting the standardized data value of the target field.

[0023] In one possible reality, step S1, medical data acquisition and standardized preprocessing, includes:

[0024] Based on national public health management standards and physical examination form requirements, a "whitelist," or field list, is generated containing target fields. This field list includes all fields that need to be filled in on the physical examination form, such as name, gender, date of birth, blood sugar, blood pressure, medication use, dietary habits, and mental state. Only data from these fields will be collected by the system through integration with the hospital's existing electronic medical record system, prescription information system, and public health follow-up system.

[0025] In one embodiment, for the "systolic blood pressure" field, data collection includes:

[0026] Electronic Medical Record System Interface: The system sends a request to the electronic medical record system to query the patient's medical records and obtain the recorded "systolic blood pressure" value. If the medical record contains a valid systolic blood pressure record, the system adds it to the candidate value set.

[0027] Prescription Information System Interface: If the electronic medical record system does not record sufficient blood pressure data, the system will query the prescription information system for the patient's chronic disease medication records, especially "antihypertensive" drugs, which can indicate that the patient has a history of hypertension. In this case, the system will extract relevant medication data from the prescription records as an additional data source.

[0028] Public Health Follow-up System Interface: If the first two systems fail to provide sufficient valid data, the system will query the public health follow-up records for blood pressure data. Blood pressure data is typically recorded during regular patient follow-ups and can serve as supplementary information.

[0029] All collected candidate data will be incorporated into a candidate value set by the system, and each value in the candidate value set represents a possible "systolic blood pressure" data point.

[0030] In one embodiment, through the data collection described above, the patient's systolic blood pressure data were obtained from multiple data sources. To ensure data consistency and comparability, all data underwent standardization processing. The standardization processing included:

[0031] Unit conversion: For example, blood glucose data may be expressed in "millimoles per liter" (mmol / L) or "milligrams per deciliter" (mg / dL), and the system will perform a uniform conversion according to the preset conversion rules (e.g., 1 mg / dL = 0.0555 mmol / L).

[0032] Formatting: For example, blood glucose records may be in the form of "5.8mmol / L" and "5.8". The system will convert the data of all fields to a uniform number of decimal places and ensure their comparability in subsequent steps.

[0033] After standardization, the system will convert the values ​​of all fields into a standardized format to obtain standardized candidate data.

[0034] In one embodiment, for the "systolic blood pressure" field, the system may obtain different data from multiple sources, such as "130 mmHg" and "128 mmHg", and the system will select a final standard value according to the set rules.

[0035] The standardized candidate data will be stored in the candidate value set by the system. Then, the standardized candidate data is filtered according to time priority and data source priority. Specifically, if multiple sources provide data for the same field, the system will select the latest valid data as the final value. The optimization process uses the following standard value selection formula to select the final standard value:

[0036]

[0037] In this formula:

[0038] This indicates the final selected standard value (e.g., the final value of systolic blood pressure);

[0039] V iIt is a set of candidate values, containing raw data from multiple data sources (such as medical records, laboratory tests, follow-up records, etc.);

[0040] The time score (v) is a time scoring function used to calculate how close the data collection time is to the current time; the closer the time is to the present, the higher the score. The function is defined as follows:

[0041]

[0042] Where λ is an adjustment parameter, t 现在 It is the current time, t v This refers to the data recording time, where 'e' is the base of the natural logarithm, ensuring a smaller time difference results in a higher score. Source priority (v) is the priority score for the data source; the system assigns different weights based on the reliability of the data source. For example, equipment-recorded data has a higher reliability score than manually entered data, and laboratory test results have a higher priority than follow-up records. The function is defined as follows:

[0043]

[0044] In one embodiment, the hypothetical "systolic blood pressure" field has the following candidate values:

[0045] Equipment measurement: August 28, 2024, value = 128 mmHg;

[0046] Medical record: September 1, 2024, value = 130 mmHg;

[0047] Follow-up record: September 10, 2024, value = 132 mmHg;

[0048] Suppose we set α = 0.7 (time priority), β = 0.3 (source priority), and based on time score and source priority, the final... Selected "128 mmHg" is used as the standard value.

[0049] The standardized dataset D1, after standardization, will serve as input for the next step, ensuring consistent data format, clear source, and time priority. Furthermore, all... Selected value All fields will include metadata such as the source and timestamp of the fields to facilitate the generation of compliant medical examination forms.

[0050] S2: Based on the standardized dataset, construct a national structure graph model, clarify the dependencies between the fields of the physical examination form and the data, map the standardized data values ​​to the corresponding positions of the fields in the physical examination form through a field mapping function, and generate the physical examination form through data validation and automatic correction.

[0051] Specifically, the standardized candidate data screening steps include: calculating a time score based on the proximity of the data collection time to the current time using a time scoring function; calculating the source priority based on the reliability weight of the data source; performing a final standard value selection calculation based on the time score and the source priority; and finally selecting the standardized data value of the target field.

[0052] Specifically, the national structure graph model is based on the physical examination form template in the national public health management standards. The national graph structure model is constructed with physical examination form fields as nodes and the relationships between physical examination form fields as edges.

[0053] In one possible reality, step S2, the mapping and auto-filling of the physical examination field locations, includes:

[0054] Based on national public health management standards, a national structure diagram model is constructed, which defines the position and dependencies of fields in the physical examination form. Using this model, the system can ensure the accuracy of the position and filling order of each field in the form, automatically identify dependencies between fields, ensure that data entry complies with legal requirements, and reduce subsequent corrections and redundant work.

[0055] National Structure Diagram Model G template It was constructed using a physical examination form template extracted from national public health management standards. Each node in the national graph model represents a physical examination field, while the edges between nodes represent the relationships and dependencies between fields.

[0056] In one embodiment, the "blood glucose" field may depend on the "fasting" field, and the system uses the edges of the structure graph to clarify this dependency. Structure graph model G template It can be represented as:

[0057] G template =(V template E template )

[0058] Among them, V template It is a collection of fields in the medical examination form, covering all fields that need to be filled in, such as name, age, blood sugar, blood pressure, etc.; E template It represents the dependencies between fields. For example, the "blood pressure" field in a medical examination table may depend on the "height" or "weight" field, and the structure graph clarifies this data relationship through edges.

[0059] After establishing the national structure graph model, the standardized data values ​​for each field will be extracted from the standardized dataset D1. These standardized data values ​​are obtained from the previous stage of data processing, ensuring data consistency and accuracy.

[0060] In one embodiment, the patient's blood glucose levels are first extracted from hospital medical records, prescription information, and follow-up records in a standardized dataset D1. and blood pressure value These data have all been converted into a standardized format and have undergone effective data cleaning and processing.

[0061] Then, the system will use the national structure diagram model G template and data extracted from D1 The medical examination form is automatically populated based on the positional relationship of the fields. Field population is handled by the field mapping function f. mapping Complete. This function maps standardized data values ​​to specific locations on the medical examination form. The system ensures each field is correctly populated using nodes and edges in the graph model. The mapping formula can be expressed as:

[0062]

[0063] in, Represents standardized data The field position f that is accurately mapped to the physical examination form i position(f) i ) represents field f i In the medical examination form, ensure that the data is filled in the correct fields.

[0064] In one embodiment, the standardized dataset D1 contains the patient's blood glucose values. The system will use the field mapping function f mapping Fill in the "blood glucose" field on the medical examination form with this value. Similarly, the blood pressure value... It will be mapped to the "blood pressure" field.

[0065] To ensure the accuracy of the populated data, the system also performs data validation and automatic correction on the standardized data values.

[0066] In one embodiment, the system checks whether the "systolic blood pressure" and "diastolic blood pressure" fields are within reasonable ranges, and whether values ​​such as blood glucose and blood pressure meet medical standards. If the system detects abnormal data, it will automatically adjust it according to preset correction rules, or prompt the user to make corrections. The correction process is based on pre-set standards and rules; for example, if the blood glucose value exceeds a certain range, the system will automatically adjust the data or remind the user to re-enter it.

[0067] Automatic correction can be performed using the following formula:

[0068]

[0069] in: These are the corrected data values; These are the initial field values; λ is the adjustment weight factor used to control the degree of adjustment; adjustment(f i ) is a correction item for a specific field (such as blood glucose or blood pressure), which may be based on the patient's historical data or other specific rules.

[0070] In one example, if the patient's blood glucose level is found If the value exceeds the set standard range, the adjustment item (f) will be used. glucose The system will take into account the patient's medical history and make corresponding adjustments to ensure that the final data conforms to actual medical standards. Finally, the system will generate an automatically filled medical examination form T. output This medical examination form contains all required fields and their standardized values, and each field has been correctly mapped to its corresponding position on the form using a national structural map model. The output form not only conforms to standards but also ensures the completeness and accuracy of the final data based on verification and correction rules. S3: Based on the field data of the medical examination form, logical rules and contextual reasoning are established to analyze the relationships between fields and predict and generate suggested values ​​for filling in gaps. These suggested values ​​are then corrected and verified using regularization terms to generate a list of suggested values ​​for filling in gaps. The suggested values ​​include field filling values ​​and the verification results of those values.

[0071] Specifically, the steps of establishing logical rules and contextual reasoning calculation include: establishing a reasoning model based on logical rules, identifying logical relationships between fields, and generating fill suggestion values ​​based on the logical relationships between the fields; obtaining the patient's known medical data fields, combining the fields generated by contextual reasoning with the known medical data fields, and inputting them into the fill suggestion formula to obtain the generated fill suggestion values.

[0072] Specifically, the regularization term correction includes: calculating a regularization adjustment term based on the medical normal range and known medical data; the regularization adjustment term and the regularization correction factor, combined with the fill suggestion value, are input into the regularization formula to output the field fill value; the verification step includes: checking the corrected fill suggestion value based on the medical normal range, outputting the fill value verification result if it conforms to the normal range, and marking it as invalid if it does not conform to the normal range, and further inputting the regularization term correction. In one possible reality, step S3 generates field fill suggestions based on logical rules and contextual reasoning, including: from the physical examination form T... outputRetrieves all populated field data. This field data is automatically collected from hospital, medical record, electronic prescription, and follow-up records, and has been standardized and validated before being entered into the physical examination form. However, some fields may not be populated due to dependencies or lack of supporting data. For example, blood glucose data may depend on the patient's age, weight, etc., while systolic and diastolic blood pressure usually need to be entered together. If these fields are not fully populated, the system will generate reasonable values ​​to fill in the missing data through inference.

[0073] In this step, the system builds a logical rule-based reasoning model based on the entered data, aiming to identify dependencies between fields. For example, systolic and diastolic blood pressure often appear in pairs, indicating a logical relationship between these two fields. Therefore, if the system detects missing data in one field, it can infer the value of the missing field using the other filled fields.

[0074] In one embodiment, if the "systolic blood pressure" field is filled in but the "diastolic blood pressure" field is missing, the system can infer a reasonable range for diastolic blood pressure based on known systolic blood pressure data and relevant medical knowledge. Similarly, if the "blood glucose" field is missing, the system can also infer a reasonable blood glucose value using other fields (such as weight, age, etc.). At the heart of this process is a logical rule-based reasoning model, which helps the system identify dependencies between fields and generate reasonable suggestions for filling in the missing data based on these dependencies.

[0075] Specifically, the system determines whether a field can be inferred from other filled fields based on whether there are dependencies between each field.

[0076] In one embodiment, the system checks whether systolic blood pressure can help estimate diastolic blood pressure, or whether blood glucose can be estimated using information such as weight and age. If the value of a field cannot be estimated from other fields, the system marks it as "missing" and prompts the doctor for further confirmation. In this way, the system can intelligently fill in missing field data, improving the completeness and accuracy of the medical examination form. The system analyzes the relationships between the filled data using these logical rules, identifies which fields are interrelated, and then generates appropriate suggestions for filling in the missing fields.

[0077] After constructing the logical rules, the system enters the contextual reasoning phase. In this phase, the system not only relies on the direct dependencies between fields, but also utilizes the patient's known medical information, such as historical medical records and physical examination records, to infer the values ​​of missing fields.

[0078] In one embodiment, if the blood glucose field is missing, the system considers factors such as the patient's weight, age, and medical history (e.g., diabetes). This information helps the system infer whether the patient's blood glucose level is abnormal and generates reasonable suggestions for filling in the missing value.

[0079] To achieve this contextual reasoning, the system uses the following formula to generate fill-in suggestions:

[0080]

[0081] in, These are the generated suggested values ​​for filling in the missing information; This indicates the field f generated by the system through contextual reasoning. i The suggested values ​​for filling in the missing data are based on known fields. For example, the patient's weight, age, eating habits, and past medical history.

[0082] In one embodiment, assuming a patient's "blood glucose" field is missing, the system can extract relevant data from other patient information. For example, if the system detects that the patient is overweight and has a history of high blood glucose, it will generate a higher-range blood glucose imputed value. This imputed value, based on contextual reasoning and logical rules, improves the accuracy and plausibility of the data.

[0083] To further optimize the quality of the fill-in suggestions, a regularization term was introduced to prevent some fill-in values ​​from deviating too far from the normal medical range.

[0084] In one embodiment, the imputed blood glucose value should generally be within a reasonable range. The system uses a regularization term to control the imputed value within this range. The introduction of the regularization term ensures that the imputed value not only conforms to logical reasoning but also guarantees compliance with medical standards. The regularization formula is as follows:

[0085]

[0086] in, These are the corrected and supplemented values; This is the initially generated fill value; λ is the regularization factor, used to control the degree of fill adjustment; adjustment(f i ) is an adjustment item for a specific field (such as blood sugar or blood pressure).

[0087] In one example, the system inferred a blood glucose value of 10 mmol / L, but due to the patient's age and weight, the system adjusted it to 7.8 mmol / L through regularization, which is a reasonable range based on historical data and medical standards.

[0088] After generating suggested values, the system verifies and validates each value to ensure it conforms to medical standards. Specifically, the system validates suggested values ​​for fields such as blood glucose and blood pressure to ensure they are within medically recognized normal ranges.

[0089] In one embodiment, the normal range for blood glucose is typically 3.9 to 6.1 mmol / L. If the generated supplemented blood glucose value exceeds this range, the system will automatically mark it as invalid data. During the validation process, the system first checks whether each supplemented value conforms to the medical standards for that field. If the supplemented value conforms to the normal range, the system will consider the value valid; if it does not conform, the system will mark it as "invalid" and require further correction. The system not only identifies non-compliant values ​​but also provides corrective suggestions to doctors by comparing them with the patient's health records or estimated values. Through this validation process, the system ensures that all supplemented data meets medical requirements, avoids erroneous data, and thus guarantees the accuracy and reliability of the medical examination form. This process is crucial because every piece of data on the medical examination form is directly related to the patient's health information, and any unqualified data may affect subsequent diagnosis or health management. Therefore, when supplementing data, the system must not only ensure its logical rationality but also strictly adhere to medical standards and normal ranges to minimize errors and ensure that the final output data is medically reasonable and reliable.

[0090] The final output list of fill suggestions S fill Includes suggestions for completing all missing fields, indicating whether each completed value meets medical standards. The list of suggestions includes the following:

[0091] Fill in the missing values ​​for each field;

[0092] The verification result of each filler value indicates whether it conforms to the standard medical range.

[0093] These suggestions for supplementing the data will serve as the basis for further optimizing the medical examination form data, ensuring the completeness and accuracy of the form.

[0094] S4: Doctors input and modify data on the physical examination form through the human-computer interaction interface. The system provides real-time prompts and verifies the validity of input values ​​based on medically normal ranges, records the data modification history and provides real-time feedback on the results of data modifications. After the doctor confirms all fields on the physical examination form, a final draft of the physical examination form is generated.

[0095] In one possible scenario, step S4 involves the doctor interactively confirming and generating a final draft of the medical examination form, including:

[0096] Based on the output suggestions for filling in the blanks and the automatically populated data in the medical examination form, an interactive interface is generated for doctors to confirm the data. Doctors can view the suggestions for filling in each field and the data that has already been automatically populated. The system will dynamically update the draft medical examination form based on the doctor's actions, including:

[0097] User Interface Design: The system provides doctors with a graphical interface displaying all filled fields and their suggested values. Each field is labeled "Confirmed" or "Pending Confirmation," and the suggested values ​​are clearly indicated alongside the filled data to help doctors quickly identify whether modifications or confirmations are needed. The system also provides hints about dependencies between fields. In one embodiment, if blood glucose data is missing, the system prompts the doctor to check if it needs to be added and displays relevant historical data for reference. Doctors can confirm or modify each field within this interface. For automatically inferred values ​​based on patient health information, doctors can adjust them according to their own judgment. For example, if the system suggests setting the blood glucose value to 7.8 mmol / L, the doctor can correct it based on the patient's physical examination history, past medical history, etc. The modified data will be saved and updated in real time.

[0098] Real-time prompts and verification: The system provides real-time prompts and verification results as doctors confirm or modify data on the medical examination form. In one embodiment, when a doctor enters or modifies a blood glucose value, the system immediately verifies whether the input value conforms to medical standards and checks whether it is within the normal range. If the blood glucose value entered by the doctor exceeds the medically prescribed reasonable range (e.g., blood glucose exceeding 3.9-6.1 mmol / L), the system displays a warning message and prompts the doctor to reconfirm the data. The system automatically marks these potential errors as "suspected errors" and provides relevant suggestions or modification prompts to help doctors make the correct decisions. Through this real-time verification mechanism, doctors can quickly identify and correct non-compliant data, thereby reducing errors and improving data accuracy.

[0099] This real-time verification mechanism not only helps doctors quickly identify and correct potential errors, but also ensures that all data in the medical examination form meets medical standards, avoiding medical decision-making biases caused by input errors or unreasonable data.

[0100] In one embodiment, during the blood glucose data verification process, the system performs real-time comparisons against a preset medical standard range (e.g., a normal range of 3.9-6.1 mmol / L) to ensure that the input value conforms to this standard. If the data exceeds the range, the system automatically marks it and prompts the doctor to make appropriate corrections. In this way, the system ensures the validity and medical rationality of the data, helping doctors make more accurate health management decisions.

[0101] Dynamic modification records and feedback: Every time a doctor confirms or modifies field data, the system records the modification history, including the values ​​before and after the modification, the reason for the modification, and the modification time. The system saves a "modification log" for each field to ensure data transparency and traceability. Modification records are crucial for subsequent review and data analysis, especially in medical decision-making, where every judgment made by a doctor needs to be clearly recorded.

[0102] In one embodiment, the system automatically provides feedback when a doctor modifies data. For example, if a doctor modifies a blood glucose value, the system will prompt: "You have modified your blood glucose value to 7.8 mmol / L, which is within the normal range." Simultaneously, the system will suggest that the doctor verify whether this data is consistent with the patient's long-term medical history to avoid invalid data or outliers.

[0103] Generating a final draft medical examination form: After the doctor confirms all fields, the system will generate a final draft medical examination form (T). draft This draft contains all confirmed field data and the doctor's modification history. The physical examination form draft will include all necessary fields (such as blood glucose, blood pressure, etc.), and the confirmation status and modification history of each field will be recorded. The draft generation process is based on interactive confirmation by the doctor and real-time verification results to ensure the accuracy, completeness, and compliance of the data with medical requirements.

[0104] The final draft will be stored in the system and can be exported, printed, or submitted by the doctor. The draft medical examination form can be used in subsequent treatment processes to ensure accurate recording of the patient's health information and provide a reliable basis for medical decisions. Output: Draft medical examination form (T) after doctor confirmation. draft It contains complete data for all fields, including doctors' confirmation records and modification history for fields to be filled in.

[0105] S5: Perform consistency verification on the final draft of the physical examination form. The consistency verification includes: field order check, field dependency verification, and value range and unit consistency check. After passing the consistency verification, perform medical compliance verification on the final draft of the physical examination form. After passing the medical compliance verification, generate the official physical examination form.

[0106] Specifically, the consistency verification includes: field order check, field dependency verification, and value range and unit consistency check. Specifically, the field order check includes checking whether the fields on the medical examination form comply with national public health management standards; the field dependency verification includes checking whether the dependencies between fields meet the system's preset field dependency relationships; and the value range and unit consistency check includes checking whether the field values ​​on the medical examination form are within the normal range of medical standards and whether the field units are consistent. The final draft medical examination form, after passing the field order check, field dependency verification, and value range and unit consistency check, has its verification results input into the medical compliance verification.

[0107] Specifically, the medical compliance verification includes: comparing the input field data values ​​with preset medical standards; if the input field data values ​​conform to the preset normal range, an official medical examination form is output; if the input field data values ​​do not conform to the preset range, they are marked as invalid and correction suggestions are output. The official medical examination form includes an archiving process, which includes: storing the official medical examination form in the system database, assigning a unique identifier to the official medical examination form, and generating an electronic copy of the official medical examination form.

[0108] In one possible scenario, step S5 involves verifying the structural consistency of the formal medical examination form and archiving it, including:

[0109] Structural consistency verification includes checking field order, field dependencies, value range, and unit consistency. Additionally, it is responsible for generating the final medical examination form, transforming the confirmed draft into the final official medical examination form T. final The medical examination form is then archived for future use and storage. The entire process ensures the data on the medical examination form is complete, accurate, and legal, providing a reliable basis for subsequent diagnosis, health management, and data analysis.

[0110] First, regarding T draft Perform structural consistency verification to ensure that the field order, format, and field dependencies of the medical examination form conform to the predetermined structural standards. Structural consistency verification includes the following aspects:

[0111] Field order check: Check whether the order of fields in the physical examination form complies with the requirements of national public health management standards.

[0112] In one embodiment, the "Name" and "Gender" fields in the physical examination form should appear before the health data fields (such as blood sugar, blood pressure, etc.). The system will automatically check the field order to ensure that it meets the requirements.

[0113] Field dependency validation: Check whether the dependencies between fields in the physical examination table are satisfied.

[0114] In one embodiment, the system ensures that the "systolic blood pressure" and "diastolic blood pressure" fields are filled together, rather than one of them being filled in isolation. Dependencies can be validated using pre-defined system rules.

[0115] Value range and unit consistency check: The system verifies that the value of each field is within a reasonable range. For example, blood glucose values ​​should be within the normal range, and blood pressure values ​​should conform to medical standards. If the value of a field exceeds the expected range, the system will automatically mark it as "abnormal" and prompt the doctor or administrator to make corrections. The system also ensures that the units of each field are consistent; blood glucose values ​​should be "mmol / L" or "mg / dL", while blood pressure values ​​should be "mmHg".

[0116] Structural consistency verification is expressed by the following formula:

[0117]

[0118] Among them, C valid (T draft () indicates the draft of the medical examination form. draft Does it conform to structural consistency specifications?

[0119] If the medical examination form conforms to the predetermined structure, format, and field dependency rules, the return value is 1; otherwise, it is 0.

[0120] If the validation result is 0, the system will mark it as "structural inconsistency" and generate a detailed report indicating which fields violated the rules. At this point, the medical examination form will be returned to the doctor or administrator for correction.

[0121] Then, a medical compliance verification is performed:

[0122] In addition to structural consistency verification, the system also performs medical compliance verification on the medical examination form, checking whether the data filled in each field of the medical examination form conforms to medical standards.

[0123] In one embodiment, the medical validity of blood glucose values ​​is assessed by checking whether the blood glucose level is within a reasonable range (e.g., the normal range is 3.9-6.1 mmol / L). If it exceeds the range, the system marks it as abnormal data.

[0124] Compliance of blood pressure values: The system checks the reasonable relationship between "systolic blood pressure" and "diastolic blood pressure." For example, systolic blood pressure should be greater than diastolic blood pressure. If non-compliant data is found, the system will automatically flag it and request the doctor to correct it.

[0125] During the data validation process, the system checks whether the value of each field conforms to medical standards.

[0126] In one embodiment, for the blood glucose field, the system verifies whether the entered blood glucose value is within the medically prescribed normal range. If the entered blood glucose value is within the normal range, the system considers the data valid. If the blood glucose value exceeds the medical standard range, for example, a blood glucose value of 12 mmol / L (exceeding the normal range of 3.9 to 6.1 mmol / L), the system determines the data to be invalid and automatically prompts the doctor that the data does not meet medical standards.

[0127] The purpose of this verification mechanism is to ensure that every data value in the medical examination form conforms to the pre-defined normal range in medicine. The system will check each field independently, comparing it according to the field type and predetermined medical standards.

[0128] In one embodiment, for fields such as blood glucose and blood pressure, the system validates them against standard ranges and marks data outside these ranges as invalid. This mechanism automatically identifies and eliminates potentially erroneous data, ensuring data accuracy and medical validity. The system also provides doctors with corrective suggestions to ensure that every data point on the medical examination form meets medical standards, ultimately improving data reliability and quality.

[0129] Generation and archiving of official medical examination forms:

[0130] After completing all structural consistency verification and medical compliance checks, the system will generate an official medical examination form T. final At this point, all verified data will be marked as final confirmation, and an official medical examination form will be generated according to a predetermined format.

[0131] The system will generate the official medical examination form T final Archiving is then performed. The archiving process includes: storing the medical examination forms in the system's database to ensure data security and accessibility; assigning a unique identifier to each medical examination form for easy subsequent querying, analysis, and review; and generating an electronic copy of the medical examination form for patients, doctors, and administrators to view and download. The output of step S5 is the official medical examination form T. final This medical examination form has undergone structural consistency verification and medical compliance checks, and meets all regulatory requirements. The official medical examination form will include:

[0132] T final A verified, official medical examination form containing the final data for all fields;

[0133] Archived records: Archived information of the medical examination form, including archive location, timestamp, medical examination form identifier, etc.

[0134] The technical solutions described in the embodiments of this application have at least the following technical effects or advantages:

[0135] It balances intelligent automated processing capabilities with doctors' review authority, ensuring that the quality of medical examination forms and the credibility of medical data are improved while reducing workload.

[0136] This application also provides an intelligent verification system for standardized information physical examination forms based on data automation, such as... Figure 2 As shown, the system includes:

[0137] The data acquisition module is used to extract a list of target fields, generate standardized candidate data for the target fields through data acquisition steps and data standardization processing, and filter the standardized candidate data according to a preset standard value selection formula to obtain a standardized dataset, which includes standardized data values ​​of the target fields. The field mapping and filling module is used to construct a national structure map model based on the standardized dataset, clarify the dependencies between the fields of the medical examination form, map the standardized data values ​​to the corresponding positions of the fields in the medical examination form through a field mapping function, and generate the medical examination form through data verification and automatic correction. The field filling generation module is used to establish logical rules and contextual reasoning based on the field data of the medical examination form, analyze the relationships between fields, predict and generate suggested filling values. The system generates a list of suggested values ​​for filling in fields through regularization and validation. These suggestions include the field filling values ​​and their validation results. An interactive confirmation module allows doctors to input and modify data on the medical examination form via a human-computer interface. It provides real-time feedback and validation of input values ​​based on medically normal ranges, records data modification history, and provides real-time feedback on the results. After the doctor confirms all fields on the medical examination form, a final draft is generated. A validation and verification module performs consistency verification on the final draft, including field order checks, field dependency verification, and value range and unit consistency checks. After passing consistency verification, the final draft undergoes medical compliance verification, and a formal medical examination form is generated upon passing this verification. This embodiment provides an intelligent verification system for standardized medical examination forms based on data automation, which implements the steps of the aforementioned intelligent verification method for standardized medical examination forms based on data automation, achieving the same results.

[0138] The above description is only a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any equivalent substitutions or modifications made by those skilled in the art within the scope of the technology disclosed in the present invention, based on the technical solution and inventive concept of the present invention, should be covered within the scope of protection of the present invention.

Claims

1. A method for intelligently verifying standardized information health check forms based on data automation, characterized in that, The method includes the following steps: Extract a list of target fields, generate standardized candidate data for the target fields through data collection steps and data standardization processing, select the standardized candidate data according to a preset standard value selection formula, and obtain a standardized dataset, which includes the standardized data values ​​of the target fields; Based on the standardized dataset, a national structure map model is constructed to clarify the dependencies between the fields of the physical examination form and the model. The standardized data values ​​are mapped to the corresponding positions of the fields in the physical examination form through a field mapping function. The physical examination form is then generated through data validation and automatic correction. Based on the field data of the physical examination form, logical rules and contextual reasoning are established to analyze the relationship between fields and predict and generate fill suggestion values. The fill suggestion values ​​are modified and verified by regularization terms to generate a fill suggestion list. The fill suggestions include field fill values ​​and fill value verification results. The system allows doctors to input and modify data on the physical examination form through a human-computer interaction interface. Based on the medical normal range, it provides real-time prompts and verifies the validity of the input values, records the data modification history and provides real-time feedback on the results of the modified data. After the doctor confirms all fields on the physical examination form, the final draft of the physical examination form is generated. The final draft of the physical examination form undergoes consistency verification, which includes: field order check, field dependency check, and value range and unit consistency check. After passing the consistency verification, the final draft of the physical examination form undergoes medical compliance verification. After passing the medical compliance verification, the official physical examination form is generated.

2. The intelligent verification method for standardized information physical examination forms based on data automation according to claim 1, characterized in that, The steps of data acquisition and data standardization processing to generate standardized candidate data for the target field include: selecting the target field from the field list, collecting candidate data through interfaces with multiple medical systems, including electronic medical record system interfaces, prescription information system interfaces, and public health follow-up system interfaces; the data standardization processing steps include: unit conversion processing and formatting processing, wherein the unit conversion processing converts the candidate data units into a standard format, the formatting processing converts the candidate data into a uniform number of decimal places, outputs standardized data values, and stores the standardized data values ​​into a candidate value set.

3. The intelligent verification method for standardized information physical examination forms based on data automation according to claim 1, characterized in that... The standardized candidate data screening steps include: calculating a time score based on the proximity of the data collection time to the current time using a time scoring function; calculating the source priority based on the reliability weight of the data source; performing a final standard value selection calculation based on the time score and the source priority; and finally selecting the standardized data value of the target field.

4. The intelligent verification method for standardized information physical examination forms based on data automation according to claim 1, characterized in that... The national structure graph model is based on the physical examination form template in the national public health management standards. The national graph structure model is constructed with physical examination form fields as nodes and the relationships between physical examination form fields as edges.

5. The intelligent verification method for standardized information physical examination forms based on data automation according to claim 1, characterized in that... The data verification step includes: checking abnormal data by examining the standardized data values ​​corresponding to the fields, and checking for abnormal data according to medical standards and reasonable data ranges; the automatic correction step includes: obtaining correction items based on patient historical data or specific rules, and combining the correction items with correction weight factors into the automatic correction formula to obtain the data values ​​corresponding to the correction fields.

6. The intelligent verification method for standardized information physical examination forms based on data automation according to claim 1, characterized in that... The steps of establishing logical rules and contextual reasoning calculation include: establishing a reasoning model based on logical rules, identifying logical relationships between fields, generating fill suggestion values ​​based on the logical relationships between fields; obtaining the patient's known medical data fields, combining the fields generated by contextual reasoning with the known medical data fields and inputting them into the fill suggestion formula to obtain the generated fill suggestion values.

7. The intelligent verification method for standardized information physical examination forms based on data automation according to claim 1, characterized in that... The regularization term correction includes: calculating a regularization adjustment term based on the medical normal range and known medical data; inputting the regularization adjustment term and the regularization correction factor into the fill suggestion value in the regularization formula; and outputting the field fill value. The verification step includes: checking the corrected fill suggestion value based on the medical normal range; outputting the fill value verification result if it conforms to the normal range; marking the value that does not conform to the normal range as invalid; and further inputting the regularization term correction.

8. The intelligent verification method for standardized information physical examination forms based on data automation according to claim 1, characterized in that... The consistency verification includes: field order check, field dependency verification, and value range and unit consistency check. Specifically, the field order check includes checking whether the fields of the physical examination form comply with the requirements of national public health management standards; the field dependency verification includes checking whether the dependencies between fields meet the system's preset field dependency relationships; and the value range and unit consistency check includes checking whether the field values ​​of the physical examination form are within the normal range of medical standards and whether the field units are consistent. The final draft physical examination form, after passing the field order check, field dependency verification, and value range and unit consistency check, has its verification results input into the medical compliance verification.

9. The intelligent verification method for standardized information physical examination forms based on data automation according to claim 1, characterized in that... The medical compliance verification includes: comparing the input field data values ​​with preset medical standards; if the input field data values ​​meet the preset normal range, an official medical examination form is output; if the input field data values ​​do not meet the preset range, they are marked as invalid and correction suggestions are output. The official medical examination form includes an archiving process, which includes: storing the official medical examination form in the system database, assigning a unique identifier to the official medical examination form, and generating an electronic copy of the official medical examination form.

10. An intelligent verification system for standardized information physical examination forms based on data automation, characterized in that, The system includes: a data acquisition module, used to extract a list of target fields, generate standardized candidate data for the target fields through data acquisition steps and data standardization processing, and filter the standardized candidate data according to a preset standard value selection formula to obtain a standardized dataset, the standardized dataset including standardized data values ​​of the target fields; a field mapping and filling module, used to construct a national structure map model based on the standardized dataset, clarify the dependencies between the fields of the medical examination form and the model, map the standardized data values ​​to the corresponding positions of the fields in the medical examination form through a field mapping function, and generate the medical examination form through data verification and automatic correction; and a field filling generation module, used to establish logical rules and contextual reasoning based on the field data of the medical examination form, analyze the relationships between fields, and predict and generate filling suggestion values. The imputation suggestion value is generated by regularization and verification to form an imputation suggestion list. The imputation suggestion includes field imputation values ​​and imputation value verification results. The interactive confirmation module is used to input and modify the physical examination form data through the human-computer interaction interface. Based on the medical normal range, it provides real-time prompts and verifies the validity of the input values, records the data modification history and provides real-time feedback on the data modification results. After the doctor confirms all fields of the physical examination form, a final draft physical examination form is generated. The verification and validation module is used to perform consistency verification on the final draft physical examination form. The consistency verification includes: field order check, field dependency verification, and value range and unit consistency check. After passing the consistency verification, the final draft physical examination form is subjected to medical compliance verification. After passing the medical compliance verification, a formal physical examination form is generated.

Images