Clinical nursing form generation method and system

Abstract

The invention relates to the technical field of clinical nursing management, in particular to a clinical nursing form generation method and system. The method comprises the following steps: acquiring historical clinical nursing form data, and performing rule demand analysis and association rule mining analysis on the historical clinical nursing form data to obtain historical form key features; constructing a form specification generation model according to the historical form key features; obtaining to-be-generated clinical nursing data, and performing automatic generation processing on the to-be-generated clinical nursing data by using the form specification generation model to obtain a clinical nursing form; performing real-time monitoring processing on the to-be-generated clinical nursing data to obtain clinical nursing update data; performing update matching processing and personalized customization processing on the clinical nursing form by using the clinical nursing update data to obtain a personalized clinical form; and executing a corresponding clinical nursing form management decision according to the personalized clinical form. The efficiency and quality of clinical nursing form generation can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of clinical nursing management, and in particular to a method and system for generating a clinical nursing form. Background Art

[0002] In clinical nursing work, medical staff often need to promptly and accurately record and manage patients' clinical care information, such as admission assessment forms, nursing record forms, and discharge plans. Traditionally, nursing forms are generated manually using paper forms, which are inefficient, prone to errors, and lack timely information transmission. Summary of the Invention

[0003] Based on this, it is necessary for the present invention to provide a method for generating a clinical nursing form to solve at least one of the above technical problems.

[0004] To achieve the above object, a method for generating a clinical nursing form includes the following steps:

[0005] Step S1: Obtain historical clinical nursing form data, perform rule requirement analysis on the historical clinical nursing form data, and obtain historical form standard data;

[0006] Step S2: Perform association rule mining analysis on the historical form specification data to obtain key features of the historical form; and construct a form specification generation model based on the key features of the historical form;

[0007] Step S3: Acquire the clinical nursing data to be generated, clean the clinical nursing data to be generated, and obtain clinical nursing standard data; use the form standard generation model to automatically generate the clinical nursing standard data to obtain a clinical nursing form;

[0008] Step S4: performing real-time monitoring processing on the clinical nursing data to be generated to obtain clinical nursing update data; performing update matching processing on the clinical nursing form using the clinical nursing update data to obtain a clinical nursing update form;

[0009] Step S5: Perform personalized customization on the clinical nursing update form to obtain a personalized clinical form; and execute corresponding clinical nursing form management decisions based on the personalized clinical form.

[0010] The present invention acquires historical clinical nursing form data to establish a dataset for analysis and processing. Rule requirements analysis of historical data is performed to understand the characteristics and features of the form data, as well as the rules, constraints, and specifications contained therein. Through rule requirements analysis, important data attributes and information can be extracted, resulting in historical form specification data. This specification data will be used for subsequent analysis and model building. Secondly, by performing association rule mining analysis on the historical form specification data, the most representative and important features can be extracted from the historical form specification data for subsequent form specification generation model construction and data analysis. By mining the historical form specification data, key features and patterns can be identified. These key features help understand the interrelationships and dependencies between form data. Based on the key features of the historical forms, a form specification generation model can be constructed to generate clinical nursing forms that meet the specifications. Then, the clinical nursing data to be generated is acquired. This data can come from real-time monitoring, patient records, or other data sources. Cleaning the generated clinical nursing data can remove noise, errors, and inconsistencies, ensuring data accuracy and consistency. After cleaning, clinical nursing standard data is obtained that meets the form specifications. At the same time, utilizing the previously constructed form specification generation model, we can automatically generate and process clinical nursing standard data to produce standardized clinical nursing forms. The generated forms can include key patient information, nursing records, and other content to support nursing work and clinical decision-making. Next, by monitoring and processing the generated clinical nursing data in real time, nursing staff can promptly grasp patient changes and generate clinical nursing update data. This update data can include information such as changes in physiological parameters and evaluations of nursing effectiveness. Furthermore, utilizing the clinical nursing update data, we can update and match the generated clinical nursing forms, correctly mapping the latest clinical nursing data to the corresponding form fields or items, and generating clinical nursing update forms. The updated forms can be used to track patient progress, adjust nursing plans, and more. Finally, by personalizing the clinical nursing update forms, we can adjust the form content and format based on the patient's specific needs, nursing effectiveness, and nursing plans, making them more personalized to nursing requirements. Personalized clinical forms can provide more accurate and targeted nursing guidance and records. Furthermore, based on the personalized clinical forms, corresponding clinical nursing form management decisions can be implemented. This includes managing aspects of form storage, access, updating, and sharing to ensure effective use and management of forms, thereby ensuring timely and accurate delivery of clinical care information.

[0011] Preferably, the present invention further provides a system for generating a clinical nursing form, for executing the method for generating a clinical nursing form as described above, wherein the system for generating a clinical nursing form comprises:

[0012] The form requirement analysis module is used to obtain historical clinical nursing form data, perform rule requirement analysis on the historical clinical nursing form data, and thus obtain historical form standard data;

[0013] The form generation model building module is used to perform association rule mining and analysis on historical form specification data to obtain key features of historical forms; and to build a form specification generation model based on the key features of historical forms;

[0014] The form generation module is used to obtain the clinical nursing data to be generated, clean the clinical nursing data to be generated, and obtain clinical nursing standard data; the form standard generation model is used to automatically generate and process the clinical nursing standard data, thereby obtaining a clinical nursing form;

[0015] The form monitoring and updating module is used to monitor and process the clinical nursing data to be generated in real time to obtain clinical nursing update data; and to update and match the clinical nursing form using the clinical nursing update data to obtain the clinical nursing update form;

[0016] The personalized management module is used to personalize the clinical nursing update form to obtain a personalized clinical form; and to execute corresponding clinical nursing form management decisions based on the personalized clinical form.

[0017] In summary, the present invention provides a system for generating clinical nursing forms. The system comprises a form requirement analysis module, a form generation model construction module, a form generation module, a form monitoring and updating module, and a personalized management module. The system can implement any of the methods for generating clinical nursing forms described in the present invention. The internal structures of the system cooperate with each other and adopt a variety of data processing methods to achieve efficient and personalized generation and customization of clinical nursing forms, thereby improving the efficiency and accuracy of form generation. In addition, by automatically generating clinical nursing forms, the workload of manual filling is reduced, and the efficiency of nursing work is improved. This can greatly reduce repetitive work and manpower input, and can quickly and effectively provide a more accurate and efficient clinical nursing form generation process, thereby simplifying the operating procedures of the system for generating clinical nursing forms. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Other features, objects and advantages of the present invention will become more apparent upon reading the detailed description of non-limiting embodiments thereof made with reference to the following drawings:

[0019] Figure 1 Schematic diagram of the steps of the method for generating a clinical nursing form of the present invention;

[0020] Figure 2 for Figure 1Detailed step flow diagram of step S1;

[0021] Figure 3 for Figure 2 Detailed step flow chart of step S12 in FIG. DETAILED DESCRIPTION

[0022] The following is a clear and complete description of the technical method of the present invention in conjunction with the accompanying drawings. Obviously, the embodiments described are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making any creative work are within the scope of protection of the present invention.

[0023] In addition, the accompanying drawings are merely schematic illustrations of the present invention and are not necessarily drawn to scale. Identical reference numerals in the figures denote identical or similar parts, and thus repetitive descriptions thereof will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities that do not necessarily correspond to physically or logically separate entities. These functional entities may be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor and / or microcontroller approaches.

[0024] It should be understood that although the terms "first," "second," and the like may be used herein to describe various elements, these elements should not be limited by these terms. These terms are used solely to distinguish one element from another. For example, a first element may be referred to as a second element, and similarly, a second element may be referred to as a first element, without departing from the scope of the exemplary embodiments. The term "and / or" as used herein includes any and all combinations of one or more of the listed associated items.

[0025] To achieve this, please refer to Figures 1 to 3 The present invention provides a method for generating a clinical nursing form, the method comprising the following steps:

[0026] Step S1: Obtain historical clinical nursing form data, perform rule requirement analysis on the historical clinical nursing form data, and obtain historical form standard data;

[0027] Step S2: Perform association rule mining analysis on the historical form specification data to obtain key features of the historical form; and construct a form specification generation model based on the key features of the historical form;

[0028] Step S3: Acquire the clinical nursing data to be generated, clean the clinical nursing data to be generated, and obtain clinical nursing standard data; use the form standard generation model to automatically generate the clinical nursing standard data to obtain a clinical nursing form;

[0029] Step S4: performing real-time monitoring processing on the clinical nursing data to be generated to obtain clinical nursing update data; performing update matching processing on the clinical nursing form using the clinical nursing update data to obtain a clinical nursing update form;

[0030] Step S5: Perform personalized customization on the clinical nursing update form to obtain a personalized clinical form; and execute corresponding clinical nursing form management decisions based on the personalized clinical form.

[0031] In the embodiment of the present invention, please refer to Figure 1 FIG. 1 is a flow chart showing the steps of the method for generating a clinical nursing form according to the present invention. In this example, the steps of the method for generating a clinical nursing form include:

[0032] Step S1: Obtain historical clinical nursing form data, perform rule requirement analysis on the historical clinical nursing form data, and obtain historical form standard data;

[0033] The embodiment of the present invention first obtains historical clinical nursing form data from a clinical nursing information system or paper clinical nursing forms. Then, the historical clinical nursing form data is analyzed for fields, data formats, and data associations to understand the structure and content of the fields, data formats, and data associations of the historical clinical nursing form data. The analyzed fields, data formats, and data associations are then combined and analyzed to ultimately obtain standardized historical form data.

[0034] Step S2: Perform association rule mining analysis on the historical form specification data to obtain key features of the historical form; and construct a form specification generation model based on the key features of the historical form;

[0035] This embodiment of the present invention uses methods such as association rule mining and cluster analysis to extract the most representative and discriminative features from historical form specification data to obtain key features of historical forms. Then, by partitioning these key features into training, validation, and test sets according to a preset ratio of 7:2:1, a decision tree algorithm is used for model training, validation, and testing based on the partitioning results to construct a model capable of accurately generating clinical nursing forms, ultimately resulting in a form specification generation model.

[0036] Step S3: Acquire the clinical nursing data to be generated, clean the clinical nursing data to be generated, and obtain clinical nursing standard data; use the form standard generation model to automatically generate the clinical nursing standard data to obtain a clinical nursing form;

[0037] The embodiment of the present invention obtains clinical nursing data to be generated by real-time monitoring of patient information, medical order information, vital signs, and nursing records during the clinical nursing process, and then merges and organizes these data in a time-series manner. The clinical nursing data to be generated is then subjected to abnormal peak filtering, interpolation, and structured transformation to ensure that the data meets the standards and requirements of clinical nursing forms, thereby obtaining clinical nursing standard data. Finally, the clinical nursing standard data is automatically generated using a pre-established form standard generation model to automatically generate a standard nursing form, ultimately obtaining a clinical nursing form.

[0038] Step S4: performing real-time monitoring processing on the clinical nursing data to be generated to obtain clinical nursing update data; performing update matching processing on the clinical nursing form using the clinical nursing update data to obtain a clinical nursing update form;

[0039] The embodiment of the present invention uses sensors, monitoring equipment and other technical means to monitor the generated clinical nursing data in real time to monitor the changes in the patient's physiological parameters, vital signs and other relevant data to obtain clinical nursing update data. Then, by calculating the form update matching relationship, the corresponding changes in the clinical nursing update data are updated to the corresponding clinical nursing form to ensure that the form is consistent with the latest clinical nursing data, and finally a clinical nursing update form is obtained.

[0040] Step S5: Perform personalized customization on the clinical nursing update form to obtain a personalized clinical form; and execute corresponding clinical nursing form management decisions based on the personalized clinical form.

[0041] The embodiment of the present invention personalizes the clinical care update form according to the actual needs of clinical care to ensure that the clinical care update form can meet specific clinical care scenarios and requirements. Then, based on the generated personalized clinical form, corresponding clinical care form management decisions are executed, such as use, review, archiving and other management decisions.

[0042] The present invention acquires historical clinical nursing form data to establish a dataset for analysis and processing. Rule requirements analysis of historical data is performed to understand the characteristics and features of the form data, as well as the rules, constraints, and specifications contained therein. Through rule requirements analysis, important data attributes and information can be extracted, resulting in historical form specification data. This specification data will be used for subsequent analysis and model building. Secondly, by performing association rule mining analysis on the historical form specification data, the most representative and important features can be extracted from the historical form specification data for subsequent form specification generation model construction and data analysis. By mining the historical form specification data, key features and patterns can be identified. These key features help understand the interrelationships and dependencies between form data. Based on the key features of the historical forms, a form specification generation model can be constructed to generate clinical nursing forms that meet the specifications. Then, the clinical nursing data to be generated is acquired. This data can come from real-time monitoring, patient records, or other data sources. Cleaning the generated clinical nursing data can remove noise, errors, and inconsistencies, ensuring data accuracy and consistency. After cleaning, clinical nursing standard data is obtained that meets the form specifications. At the same time, utilizing the previously constructed form specification generation model, we can automatically generate and process clinical nursing standard data to produce standardized clinical nursing forms. The generated forms can include key patient information, nursing records, and other content to support nursing work and clinical decision-making. Next, by monitoring and processing the generated clinical nursing data in real time, nursing staff can promptly grasp patient changes and generate clinical nursing update data. This update data can include information such as changes in physiological parameters and evaluations of nursing effectiveness. Furthermore, utilizing the clinical nursing update data, we can update and match the generated clinical nursing forms, correctly mapping the latest clinical nursing data to the corresponding form fields or items, and generating clinical nursing update forms. The updated forms can be used to track patient progress, adjust nursing plans, and more. Finally, by personalizing the clinical nursing update forms, we can adjust the form content and format based on the patient's specific needs, nursing effectiveness, and nursing plans, making them more personalized to nursing requirements. Personalized clinical forms can provide more accurate and targeted nursing guidance and records. Furthermore, based on the personalized clinical forms, corresponding clinical nursing form management decisions can be implemented. This includes managing aspects of form storage, access, updating, and sharing to ensure effective use and management of forms, thereby ensuring timely and accurate delivery of clinical care information.

[0043] Preferably, step S1 includes the following steps:

[0044] Step S11: Acquire historical clinical nursing form data;

[0045] Step S12: performing field requirement analysis on historical clinical nursing form data to obtain form field requirement data;

[0046] Step S13: performing data format requirement analysis on historical clinical nursing form data to obtain form format requirement data;

[0047] Step S14: performing data association demand analysis on historical clinical nursing form data to obtain form association demand data;

[0048] Step S15: performing a joint demand analysis on the form field demand data, the form format demand data, and the form association demand data to obtain historical form specification data.

[0049] As an embodiment of the present invention, refer to Figure 2 As shown, Figure 1 Detailed step flow diagram of step S1 in FIG. 1 , in this embodiment, step S1 includes the following steps:

[0050] Step S11: Acquire historical clinical nursing form data;

[0051] The embodiment of the present invention obtains historical clinical nursing form data from a clinical nursing information system or a paper clinical nursing form.

[0052] Step S12: performing field requirement analysis on historical clinical nursing form data to obtain form field requirement data;

[0053] The embodiment of the present invention performs a demand analysis on the field type, field length and validation rules of historical clinical nursing form data to understand the structure and content of the field type, field length and validation rules of historical clinical nursing form data, and merges and analyzes the analyzed field type, field length and validation rule requirement data to finally obtain the form field requirement data.

[0054] Step S13: performing data format requirement analysis on historical clinical nursing form data to obtain form format requirement data;

[0055] The embodiment of the present invention analyzes the data format requirements of historical clinical nursing form data to determine requirements on the format of date fields, the range of number fields, the length of text fields, etc., and ultimately obtains form format requirement data.

[0056] Step S14: performing data association demand analysis on historical clinical nursing form data to obtain form association demand data;

[0057] The embodiment of the present invention analyzes the association relationships in historical clinical nursing form data, such as the association relationships and dependency relationships between certain fields in the historical clinical nursing form data, and ultimately obtains form association requirement data.

[0058] Step S15: performing a joint demand analysis on the form field demand data, the form format demand data, and the form association demand data to obtain historical form specification data.

[0059] The embodiment of the present invention integrates and analyzes the analyzed form field requirement data, form format requirement data, and form association requirement data to comprehensively analyze the needs and requirements of fields, formats, association rules, etc., and through operations such as data format conversion, outlier processing, and missing value filling to ensure data consistency and accuracy, and finally obtain historical form standard data.

[0060] The present invention first obtains historical clinical nursing form data as the basis for analysis and standardization. By collecting and organizing historical clinical nursing form data, a reliable data source can be established for subsequent needs analysis and standardization processes. Historical clinical nursing form data can include clinical nursing operations, nursing records, patient information, and other content. By analyzing this data, the characteristics and problems of existing clinical nursing forms can be understood, and strategies for improvement and optimization can be formulated. Secondly, field requirements analysis is performed on the historical clinical nursing form data to determine the specific fields or data elements required in the form. By analyzing the fields and data items present in the historical form data, it is possible to determine which fields are essential for clinical nursing records and which fields may be optional or redundant. This helps identify the core elements of the form data and provides guidance for subsequent standardization and optimization. Then, data format requirements analysis is performed on the historical clinical nursing form data to determine the requirements for the form data format, data type, input restrictions, etc. By analyzing the format requirements of the historical form data, the consistency, accuracy, and readability of the form data can be ensured. For example, requirements such as the format of the date field, the range of the number field, and the length of the text field can be determined, which helps standardize the entry and use of form data. Next, a data association requirements analysis is conducted on historical clinical care form data to determine the associations and dependencies between form data. By analyzing the association requirements of historical form data, the logical relationships between data, such as the calculation, validation, and constraint rules between certain fields, can be understood. This helps ensure the correctness and consistency of form data and provide more complete and accurate data analysis and reporting. Finally, a joint requirements analysis is conducted on form field requirements data, form format requirements data, and form association requirements data to comprehensively consider the needs and requirements of various aspects and obtain historical form specification data. By integrating and synthesizing the results of various requirements analyses, specifications and standards applicable to clinical care forms can be developed, including field definitions, format specifications, association rules, etc. This helps improve the quality and usability of forms, reduce data errors and inconsistencies, and thus improve the efficiency and safety of clinical care.

[0061] Preferably, step S12 includes the following steps:

[0062] Step S121: performing field type requirement analysis on historical clinical nursing form data to obtain field type requirement data;

[0063] Step S122: performing field length requirement analysis on historical clinical nursing form data to obtain field length requirement data;

[0064] Step S123: Calculate the field completeness of the historical clinical nursing form data using the field logic completeness calculation formula to obtain the form field completeness index;

[0065] Step S124: performing validation rule requirement analysis on historical clinical nursing form data based on the form field completeness index to obtain field rule requirement data;

[0066] Step S125: Merging the field type requirement data, the field length requirement data, and the field rule requirement data to obtain form field requirement data.

[0067] As an embodiment of the present invention, refer to Figure 3 As shown, Figure 2 Detailed step flow diagram of step S12 in the embodiment, step S12 includes the following steps:

[0068] Step S121: performing field type requirement analysis on historical clinical nursing form data to obtain field type requirement data;

[0069] The embodiment of the present invention analyzes historical clinical nursing form data to understand the data type of each field in the historical clinical nursing form data. For example, a field may need to store different types of data such as integers, dates, and text. According to the content of the historical clinical nursing form data, the data type requirements of each field are determined, and finally the field type requirement data is obtained.

[0070] Step S122: performing field length requirement analysis on historical clinical nursing form data to obtain field length requirement data;

[0071] The embodiment of the present invention analyzes historical clinical nursing form data to understand the content length range of each field in the historical clinical nursing form data, and determines the length requirement of each field based on the content of the historical clinical nursing form data, such as the maximum length of the character field, the number of digits of the numeric field, etc., and finally obtains the field length requirement data.

[0072] Step S123: Calculate the field completeness of the historical clinical nursing form data using the field logic completeness calculation formula to obtain the form field completeness index;

[0073] The embodiment of the present invention combines the number of fields in historical clinical nursing form data, weight parameters, actual data completeness, time constraint range parameters for field completeness calculation, field completeness time decay function, harmonic smoothing parameter, field completeness time impact mean, field completeness time impact standard deviation, field completeness time impact function, field completeness time contribution adjustment function, field completeness time deviation function and related parameters to construct a suitable field logical completeness calculation formula for field completeness calculation to evaluate whether the field is missing, repeated, invalid or inconsistent, and finally obtain the form field completeness index.

[0074] Step S124: performing validation rule requirement analysis on historical clinical nursing form data based on the form field completeness index to obtain field rule requirement data;

[0075] In an embodiment of the present invention, the type of rule that needs to be defined is determined based on the value of the calculated form field completeness index. For example, a form field completeness index lower than a threshold value can be defined as a rule for a required field, and a form field completeness index higher than a threshold value can be defined as a rule for an optional field. According to the determined rule type, the validation rule requirements for each field in the historical clinical nursing form data are analyzed, including required rules, value range rules, format rules, etc., to ultimately obtain field rule requirement data.

[0076] Step S125: Merging the field type requirement data, the field length requirement data, and the field rule requirement data to obtain form field requirement data.

[0077] The embodiment of the present invention merges and organizes field type requirement data, field length requirement data, and field rule requirement data, and performs operations such as data format conversion, outlier processing, and missing value filling to ensure data consistency and accuracy, and finally obtains form field requirement data.

[0078] The present invention first determines the data type required for each field by performing a field type requirements analysis on historical clinical nursing form data. For example, a field may need to store different types of data, such as integers, dates, and text. By analyzing the historical clinical nursing form data, common data types for each field can be identified to facilitate subsequent data entry and use. Secondly, by performing a field length requirements analysis on the historical clinical nursing form data, the maximum length required for each field can be determined. Different fields may have different restrictions on the input of characters, numbers, or dates. By analyzing the historical clinical nursing form data, the maximum length of the field can be determined to ensure sufficient space for storing and displaying the form data. Then, the field integrity of the historical clinical nursing form data is assessed using an appropriate field logical integrity calculation formula. By performing a logical analysis on the form data, it is possible to assess whether any fields are missing, duplicated, invalid, or inconsistent. The calculated form field integrity index can provide an overall quality assessment of the historical form data, thereby guiding the subsequent validation rule requirements analysis process. Next, based on the form field integrity index, a validation rule requirements analysis is performed on the historical clinical nursing form data to identify missing, inconsistent, or invalid fields, thereby determining the validation rules applicable to each field. For example, you can define rules such as required fields, range restrictions, and format requirements to ensure the accuracy and consistency of form data. Finally, the final form field requirements data is obtained by integrating and merging the field type requirement data, field length requirement data, and field rule requirement data. By comprehensively considering requirements for field type, length, and rules, you can define specific requirements and restrictions for form fields. This helps to develop standardized form design and data entry requirements, thereby improving the quality and usability of form data.

[0079] Preferably, the field logic integrity calculation formula in step S123 is specifically:

[0080]

[0081] Where CI is the form field completeness index, n is the number of fields in the historical clinical nursing form data, and w i is the weight parameter of the i-th field in the historical clinical nursing form data, d iis the actual data completeness of the i-th field in the historical clinical nursing form data, t1 is the lower limit of the time constraint for field completeness calculation, t2 is the upper limit of the time constraint for field completeness calculation, t is the integral time variable for field completeness calculation, f(t) is the field completeness time decay function, k1 is the harmonic smoothing parameter of the field completeness time decay function, μ is the mean of the field completeness time influence, σ is the standard deviation of the field completeness time influence, g(t) is the field completeness time influence function, h(t) is the field completeness time contribution adjustment function, p(t) is the field completeness time deviation function, and ε is the correction value of the form field completeness index.

[0082] The present invention constructs a field logical completeness calculation formula for calculating field completeness on historical clinical nursing form data. This field logical completeness calculation formula uses the number of fields as the denominator and normalizes the completeness calculation for each field to obtain an overall completeness index. This facilitates fair comparison of different forms with varying numbers of fields. By adjusting the field weight parameters, different weights can be assigned to fields based on their importance, thereby affecting the degree of influence of each field on the completeness index. This allows key fields to be given higher weights, ensuring that their completeness has a greater impact on the overall index. Actual data completeness measures the degree of completeness of the actual data in a field. By calculating the proportion of missing values and detecting data anomalies, the actual data completeness of each field can be derived. This helps assess the reliability and availability of field data, thereby influencing the calculation of the completeness index. Setting lower and upper time constraints for field completeness calculations helps limit the time period for data completeness calculations, allowing for more accurate assessment of data completeness within a specific time period. Depending on the selected time range, the index can more accurately reflect data completeness within a specific time period. Older data may be relatively unreliable, while more recent data is more reflective of the current situation. The field integrity time decay function reduces the influence of older data on the completeness index, while newer data has a greater influence. This helps ensure that data integrity assessments are more realistic. The harmonic smoothing parameter balances the influence of older and more recent data in the completeness calculation. Adjusting this parameter controls the steepness of the decay function, thereby affecting the change in the completeness index. This is useful for flexibly adjusting the weighting of temporal influences. The field integrity time impact function describes the degree of time's influence on data completeness, reflecting the patterns of temporal influence. This better captures the impact of temporal changes on data completeness, helping to more accurately quantify the contribution of temporal factors to field completeness. The field integrity time impact mean and standard deviation describe the shape of the time impact function. Adjusting these two parameters adjusts the position and shape of the time impact function on the time axis, thereby affecting the completeness index. This allows for a more accurate description of the impact of time on data completeness based on actual needs. Additionally, the field integrity time contribution adjustment function and the field integrity time deviation function are used to adjust and correct the completeness index. The field complete time contribution adjustment function can adjust the contribution of time to the completeness index, while the field complete time deviation function can further correct the index based on the time deviation. The design of these functions makes the index more accurately reflect the completeness characteristics of the field. This formula fully considers the form field completeness index CI, the number of fields n in the historical clinical nursing form data, and the weight parameter w of the i-th field in the historical clinical nursing form data. i, the actual data completeness d of the i-th field in the historical clinical nursing form data i , the time constraint lower limit t1 of field complete calculation, the time constraint upper limit t2 of field complete calculation, the integral time variable t of field complete calculation, the field complete time decay function f(t), the harmonic smoothing parameter k1 of the field complete time decay function, the field complete time impact mean μ, the field complete time impact standard deviation σ, the field complete time impact function g(t), the field complete time contribution adjustment function h(t), the field complete time deviation function p(t), the form field completeness index correction value ε, according to the mutual correlation between the form field completeness index CI and the above parameters, a functional relationship is formed:

[0083]

[0084] This formula can realize the field completeness calculation process of historical clinical nursing form data. At the same time, by introducing the correction value ε of the form field completeness index, it can be adjusted according to actual conditions, thereby improving the accuracy and applicability of the field logical completeness calculation formula.

[0085] Preferably, step S2 includes the following steps:

[0086] Step S21: performing feature pattern mining analysis on the historical form standard data to obtain the historical form data features;

[0087] The embodiment of the present invention extracts effective feature patterns from the historical form standard data by using methods such as association rule mining and cluster analysis, and finally obtains the historical form data features.

[0088] Step S22: Using principal component analysis technology to perform dimensionality reduction processing on the historical form data features to obtain form dimensionality reduction features;

[0089] The embodiment of the present invention converts the historical form data features into a feature matrix, where each row represents a form instance and each column represents a feature. The feature matrix is then reduced in dimensionality using principal component analysis technology, high-dimensional features are mapped to a low-dimensional space, and the principal component features that best represent the original data features are selected in the low-dimensional space based on the explained variance ratio of the principal components, ultimately obtaining the form dimensionality reduction features.

[0090] Step S23: Using the feature criticality calculation formula, perform key calculation on the form dimensionality reduction features to obtain the form feature criticality;

[0091] The embodiment of the present invention constructs a suitable feature criticality calculation formula by combining adjacent form dimensionality reduction features, key reconciliation factors, additional form dimensionality reduction features and related parameters to perform key calculation on the form dimensionality reduction features, so as to calculate the criticality between the form dimensionality reduction features and finally obtain the form feature criticality.

[0092] The feature criticality calculation formula is as follows:

[0093]

[0094] In the formula, K is the key degree of form features, m is the number of form dimensionality reduction features, x j is the j-th form dimensionality reduction feature, x is the adjacent form dimensionality reduction feature, α is the key reconciliation factor, x′ is the additional form dimensionality reduction feature, and ∈ is the correction value of the form feature criticality;

[0095] The present invention constructs a feature criticality calculation formula for performing key calculation on form dimensionality reduction features. The feature criticality calculation formula is Indicates the similarity between adjacent features and describes the relationship between form dimensionality reduction features by using the Gaussian function form, where x j -x measures the difference between the form dimensionality reduction feature and the adjacent features. Smaller difference values will result in larger similarity scores. It represents the key reconciliation relationship between features, which is used to balance the similarity and difference between features. In this way, the similarity between features will be quantified in exponential form and affect the calculation of feature criticality. Calculate the sum of the similarities of all form dimensionality reduction features. By integrating the similarities of all form dimensionality reduction features, a denominator representing the overall similarity of the dimensionality reduction features is obtained. The integration operation in the denominator takes into account the relationship between all features to more comprehensively evaluate the similarity. In addition, by using correction values, the scope and interpretation of feature criticality can be further adjusted and standardized to ensure the rationality of the calculation results. This formula fully considers the form feature criticality K, the number of form dimensionality reduction features m, and the jth form dimensionality reduction feature x. j , adjacent form dimensionality reduction feature x, key reconciliation factor α, additional form dimensionality reduction feature x′, form feature criticality correction value ∈, according to the mutual correlation between form feature criticality K and the above parameters, a functional relationship is formed:

[0096]

[0097] This formula can realize the key calculation process of the form dimensionality reduction features. At the same time, by introducing the correction value ∈ of the form feature criticality, it can be adjusted according to the actual situation, thereby improving the accuracy and applicability of the feature criticality calculation formula.

[0098] Step S24: Sort the form feature criticality in descending order, select the form dimensionality reduction features corresponding to the top-ranked form feature criticality as key features, and obtain the historical form key features;

[0099] The embodiment of the present invention sorts the calculated form feature criticalities from large to small, and selects the form dimensionality reduction features corresponding to the top-ranked form feature criticalities as key features, so as to extract the most representative and discriminative features, and finally obtain the historical form key features.

[0100] Step S25: Construct a form specification generation model based on the key features of the historical form.

[0101] The embodiment of the present invention first divides the key features of historical forms into training set, validation set and test set according to a preset division ratio of 7:2:1. Then, based on the division results, a decision tree algorithm is used to perform model training, verification and testing to construct a model that can accurately generate clinical nursing forms, and finally a form specification generation model is obtained.

[0102] The present invention first analyzes and mines historical form standard data to discover characteristic patterns and important features. These features can be combinations of data fields, relationships, or other expressions. By mining characteristic patterns in historical form standard data, we can better understand the characteristics and structure of the data, preparing for subsequent analysis and processing. Secondly, by using principal component analysis (PCA) technology to reduce the dimensionality of historical form data features, high-dimensional data features can be mapped to a low-dimensional space, retaining the most important feature information. This dimensionality reduction process can reduce data dimensions, simplify the data structure, and extract the most representative features. Then, using a feature criticality calculation formula, we perform key calculations on the form dimensionality reduction features. The calculated feature criticality is used to assess the importance and contribution of each dimensionality reduction feature. The parameters in this calculation formula include the number of dimensionality reduction features, key reconciliation factors, and other relevant factors. By calculating the form feature criticality, we can determine the importance of each feature, thereby facilitating subsequent feature selection and screening. Next, by sorting the form feature criticality from highest to lowest, the form dimensionality reduction features corresponding to the top-ranked feature criticality are selected as key features. By selecting key features, we can extract the most representative and important features from historical form data for subsequent form specification generation model construction and data analysis. Finally, based on the key features of historical forms, we construct a form specification generation model. This model can be used to generate clinical care forms that conform to the characteristics of historical forms. By selecting key features and building a model, we ensure that the generated form data has similar characteristics and specifications to the historical data, thereby improving data consistency and usability. This model can be used to generate new standardized forms to meet specific needs and regulations.

[0103] Preferably, step S3 includes the following steps:

[0104] Step S31: performing patient information monitoring processing on the clinical nursing process to obtain patient information monitoring data;

[0105] The embodiment of the present invention obtains patient information monitoring data by real-time monitoring of the patient's medical records, nursing information and other data during the clinical nursing process.

[0106] Step S32: monitoring and processing the medical order information of the clinical nursing process to obtain medical order information monitoring data;

[0107] The embodiment of the present invention monitors the type, content, issuance time, execution time and other information data of the medical order in the clinical nursing process in real time, and finally obtains the medical order information monitoring data.

[0108] Step S33: performing vital sign monitoring processing on the clinical nursing process to obtain vital sign monitoring data;

[0109] The embodiment of the present invention obtains vital sign monitoring data by monitoring the patient's vital sign data such as blood pressure, heart rate, and body temperature in real time during clinical nursing.

[0110] Step S34: performing nursing record monitoring processing on the clinical nursing process to obtain nursing record monitoring data;

[0111] The embodiment of the present invention obtains nursing record monitoring data by real-time monitoring of nursing measures, nursing assessments, nursing plans and other nursing record information data during the clinical nursing process.

[0112] Step S35: merging the patient information monitoring data, the doctor's order information monitoring data, the vital signs monitoring data, and the nursing record monitoring data in a time series manner to obtain the clinical nursing data to be generated;

[0113] The embodiment of the present invention combines and organizes patient information monitoring data, medical order information monitoring data, vital sign monitoring data, and nursing record monitoring data in time series according to corresponding time points or time periods, and performs operations such as data format conversion, outlier processing, and missing value filling to ensure data consistency and accuracy, and ultimately obtain the clinical nursing data to be generated.

[0114] Step S36: Cleaning the clinical nursing data to be generated to obtain clinical nursing standard data;

[0115] The embodiment of the present invention performs abnormal peak filtering, interpolation and structured conversion on the clinical nursing data to be generated, and performs steps such as removing abnormal values in the clinical nursing data to be generated, correcting erroneous data, filling missing data and converting data formats to ensure that the data meets the standards and requirements of clinical nursing forms, and finally obtains clinical nursing standard data.

[0116] Step S37: Utilize the form specification generation model to automatically generate and process the clinical nursing specification data to obtain a clinical nursing form.

[0117] The embodiment of the present invention uses a constructed form specification generation model to automatically generate clinical nursing standard data to automatically generate a nursing form that meets the standard, and finally obtains a clinical nursing form.

[0118] First, by monitoring and processing patient information during the clinical nursing process, the present invention can ensure the accuracy of patients' personal information and promptly obtain data such as patients' medical records and nursing information. This helps medical staff fully understand the patient's condition and nursing needs, thereby providing more accurate nursing services. Monitoring and processing patient information can also help establish and update patient files, promote information sharing and collaboration among nursing teams, and thus improve the quality and safety of clinical nursing. At the same time, by monitoring and processing medical order information during the clinical nursing process, the accuracy and timeliness of medical orders can be ensured. By monitoring and processing medical order information, errors, omissions, or conflicts in medical orders can be discovered in a timely manner, and communication and adjustments can be made with doctors to avoid adverse effects on patients. In addition, monitoring and processing medical order information also helps extract medical order-related data for clinical research, quality assessment, and decision support, thereby improving the quality and effectiveness of medical services. Secondly, by monitoring and processing vital signs during the clinical nursing process, the patient's physiological condition and changes can be accurately and promptly obtained, helping nursing staff to discover and assess the patient's health status and take necessary nursing intervention measures in a timely manner. Furthermore, vital sign monitoring data can be used to assess patient care effectiveness and disease progression, providing a basis for the generation of subsequent clinical care forms, thereby improving the safety and effectiveness of clinical care. Furthermore, by monitoring and processing nursing records during the clinical care process, the integrity, accuracy, and standardization of nursing records can be ensured. Monitoring and processing nursing record data can help identify and correct errors, omissions, or non-standard recordings, ensuring the quality and consistency of nursing records. The resulting nursing record monitoring data also has important clinical significance, assisting in evaluating nursing effectiveness, tracking patient changes, and reviewing the course of the disease, providing a reference for the generation of clinical care forms and further care planning. Next, by merging different types of monitoring data over time, a complete clinical care dataset can be established for the patient, providing a comprehensive data view for medical staff, enabling a better understanding of the patient's overall condition and changing trends, and supporting personalized care and the generation of clinical care forms. Time series merging also facilitates the establishment of databases and data warehouses, providing a foundation for subsequent data analysis, mining, and research. Cleansing the generated clinical care data can improve its quality and accuracy. By removing outliers, correcting erroneous data, and filling in missing data, the data is brought into compliance with clinical care standards. This helps promote data consistency and reliability, and provides a reliable data foundation for subsequent data analysis and application. Finally, by using the constructed form specification generation model to automatically generate and process clinical care standard data, the cleaned clinical care data can be converted into compliant clinical care forms based on preset standard requirements and templates.The generated forms can include patient information forms, nursing record forms, medical order forms, etc., providing medical staff with convenient and fast data display and recording tools, reducing the workload and error rate of manual processing.

[0119] Preferably, step S36 includes the following steps:

[0120] Step S361: Calculate the abnormal peak value of the clinical nursing data to be generated using the abnormal peak calculation formula to obtain the abnormal peak value of the nursing data;

[0121] The embodiment of the present invention constructs a suitable abnormal peak calculation formula by combining the time parameters for abnormal peak calculation, the abnormal value of the clinical nursing data to be generated, the abnormal change range value, the difference value, the abnormal change value, the abnormal experience value, the corresponding weight influence factor and the exponential gain factor and related parameters to perform abnormal peak calculation on the clinical nursing data to be generated, so as to identify and calculate abnormal conditions caused by measurement errors, equipment problems or special circumstances of the patient, and finally obtain the abnormal peak of the nursing data.

[0122] Step S362: performing abnormal filtering on the clinical nursing data to be generated based on abnormal peak values of the nursing data to obtain abnormal peak filtered data;

[0123] The embodiment of the present invention compares and judges the calculated abnormal peak value of the nursing data according to a preset abnormal peak threshold value to determine whether the corresponding clinical nursing data to be generated has an abnormality. When the calculated abnormal peak value of the nursing data is greater than or equal to the preset abnormal peak threshold value, it means that the clinical nursing data to be generated corresponding to the abnormal peak value of the nursing data has an abnormality, and it is filtered out. When the calculated abnormal peak value of the nursing data is less than the preset abnormal peak threshold value, it means that the clinical nursing data to be generated corresponding to the abnormal peak value of the nursing data has no abnormality, and no filtering is performed, and finally the abnormal peak filtered data is obtained.

[0124] Step S363: interpolating the abnormal peak filtered data to obtain clinical nursing interpolation data;

[0125] The embodiment of the present invention first performs missing value detection on the abnormal peak filtered data to find the missing values in the abnormal peak filtered data, and then interpolates the missing values in the abnormal peak filtered data according to the characteristics and requirements of the data by using interpolation methods such as linear interpolation, polynomial interpolation, and spline interpolation to fill the missing values, and finally obtain clinical nursing interpolation data.

[0126] Step S364: Perform structured conversion processing on the clinical nursing interpolation data to obtain clinical nursing standard data.

[0127] The embodiment of the present invention converts and adjusts the interpolated data according to the specifications and standards of clinical nursing data to ensure the standardization and consistency of the data, which includes the conversion of data units, the adjustment of data formats, etc., and performs structured processing such as data tabulation, data association and classification on the interpolated data to make it conform to specific data structures and requirements, and finally obtain clinical nursing standard data.

[0128] The present invention first processes the generated clinical nursing data using an outlier peak calculation formula to identify outlier peaks in the data. Outlier peaks typically indicate anomalies in the data, which may be caused by measurement errors, equipment problems, or special patient conditions. The calculated outlier peaks can help quickly locate and address potential data anomalies, allowing necessary intervention and resolution measures to be taken promptly. Then, based on the calculated outlier peaks in the nursing data, the generated clinical nursing data can be filtered for outliers. This means removing the data points corresponding to the calculated outlier peaks from the dataset to eliminate inaccurate or outliers caused by abnormal interference. This outlier filtering helps improve data quality and accuracy, ensuring more reliable data for subsequent analysis and decision-making. Next, interpolation is performed on the outlier-filtered data to fill in potential missing values or blank areas. Interpolation is a method that infers the values of unknown data points based on the relationships between known data points. Interpolation creates a continuous and complete data sequence within the data, ensuring the effectiveness and accuracy of subsequent analysis and structured transformation processes. Finally, the interpolated clinical care data undergoes a structured transformation, converting the data from its original format or representation to a data format that complies with clinical care standards. This structured transformation can include operations such as formatting, standardization, classification, and coding to ensure data consistency and comparability. The resulting clinical care standard data can better meet clinical needs, provide a reliable basis for healthcare professionals' decision-making, and promote applications in clinical research, quality assessment, and decision support.

[0129] Preferably, the abnormal peak calculation formula in step S361 is specifically:

[0130]

[0131] Where V is the abnormal peak value of nursing data, τ is the time variable for abnormal peak calculation, τ1 is the lower limit of the time range for abnormal peak calculation, τ2 is the upper limit of the time range for abnormal peak calculation, X a (τ) is the abnormal value of the clinical nursing data to be generated at time τ, X r (τ) is the abnormal change range value of the clinical nursing data to be generated at time τ, ρ1 is the weight influence factor of the abnormal value, a1 is the exponential gain factor of the abnormal value, Xd (τ) is the difference value of the clinical nursing data to be generated at time τ, ρ2 is the weight influence factor of the difference value, a2 is the exponential gain factor of the difference value, X t (τ) is the abnormal change value of the clinical nursing data to be generated at time τ, ρ3 is the weight influence factor of the abnormal change value, a3 is the exponential gain factor of the abnormal change value, X e (τ) is the abnormal experience value of the clinical nursing data to be generated at time τ, ρ4 is the weight influence factor of the abnormal experience value, a4 is the exponential gain factor of the abnormal experience value, and η is the correction value of the abnormal peak value of the nursing data.

[0132] The present invention constructs an abnormal peak calculation formula for calculating abnormal peaks of clinical nursing data to be generated. The abnormal peak calculation formula comprehensively considers the importance of multiple factors such as abnormal values, difference values, abnormal change values and abnormal experience values within a given time range. It also allows the relative weight and influence of each factor to be adjusted by using the weight influence factor and exponential gain factor of each part to meet the needs of practical applications. The goal of the abnormal peak calculation formula is to identify abnormal peaks in clinical nursing data for abnormal filtering and data interpolation processing, so that abnormal data can be filtered out and missing data can be filled by interpolation methods to obtain more standardized and reliable clinical nursing standard data. The calculation formula fully considers factors such as abnormal values, difference values, abnormal change values and abnormal experience values, and performs a comprehensive evaluation by weighting and summing them, making the calculation of abnormal peaks more accurate and flexible. The formula fully considers the abnormal peak value V of the nursing data, the time variable τ for abnormal peak calculation, the lower limit τ1 of the time range for abnormal peak calculation, the upper limit τ2 of the time range for abnormal peak calculation, the abnormal value X of the clinical nursing data to be generated at time τ a (τ), the abnormal change range value X of the clinical nursing data to be generated at time τ r (τ), the weight influence factor ρ1 of the outlier, the exponential gain factor a1 of the outlier, and the difference value X of the clinical nursing data to be generated at time τ d (τ), the weighted influence factor of the difference value ρ2, the exponential gain factor of the difference value a2, and the abnormal change value X of the clinical nursing data to be generated at time τ t (τ), the weighted influence factor ρ3 of the abnormal change value, the exponential gain factor a3 of the abnormal change value, and the abnormal experience value X of the clinical nursing data to be generated at time τ e (τ), the weighted influence factor ρ4 of the abnormal experience value, the exponential gain factor a4 of the abnormal experience value, the correction value η of the abnormal peak value of the nursing data, where the time variable τ calculated by the abnormal peak value, the abnormal value X of the clinical nursing data to be generated at time τ a (τ), the abnormal change range value X of the clinical nursing data to be generated at time τr (τ), the outlier weight influence factor ρ1 and the outlier exponential gain factor a1 constitute an outlier influence function relationship The time variable τ calculated by the abnormal peak value is used to generate the difference value X of the clinical nursing data at time τ d (τ), the abnormal change range value X of the clinical nursing data to be generated at time τ r (τ), the weighted influence factor ρ2 of the difference value and the exponential gain factor a2 of the difference value constitute a difference value influence function relationship The time variable τ calculated by the abnormal peak value is used to generate the abnormal change value X of the clinical nursing data at time τ. t (τ), the abnormal change range value X of the clinical nursing data to be generated at time τ r (τ), the weight influence factor ρ3 of the abnormal change value and the exponential gain factor a3 of the abnormal change value constitute an abnormal change value influence function relationship Furthermore, the abnormal peak value is calculated by the time variable τ, the lower limit of the time range τ1, and the upper limit of the time range τ2, and the abnormal experience value X of the clinical nursing data at time τ is generated. e (τ), the weighted influence factor ρ4 of the abnormal experience value, the exponential gain factor a4 of the abnormal experience value, and the abnormal change range value X of the clinical nursing data to be generated at time τ r (τ) constitutes a functional relationship of abnormal experience value influence According to the correlation between the abnormal peak value V of the nursing data and the above parameters, a functional relationship is formed:

[0133]

[0134] The formula can realize the abnormal peak calculation process of the generated clinical nursing data. At the same time, by introducing the correction value η of the abnormal peak of the nursing data, it can be adjusted according to the actual situation, thereby improving the accuracy and applicability of the abnormal peak calculation formula.

[0135] Preferably, step S4 includes the following steps:

[0136] Step S41: Perform real-time monitoring and processing on the clinical nursing data to be generated to obtain clinical nursing change data;

[0137] The embodiment of the present invention uses sensors, monitoring equipment and other technical means to monitor the generated clinical nursing data in real time to monitor the changes and abnormalities of the patient's physiological parameters, physical signs and other related data, and finally obtain clinical nursing change data.

[0138] Step S42: performing filling and updating processing on the clinical nursing change data to obtain clinical nursing update data;

[0139] The embodiment of the present invention fills in the changes in the clinical nursing change data obtained by monitoring. For example, when the sensor or monitoring equipment detects that data is lost or missing in the clinical nursing data to be generated, the missing values are estimated by using interpolation methods, mean filling, regression models and other technologies to fill in the gaps or missing values in the data, and the filled data is updated to the clinical nursing change data to ensure the integrity and consistency of the data, and finally obtain clinical nursing update data.

[0140] Step S43: Calculate the matching relationship between the clinical nursing update data and the clinical nursing form to obtain the form update matching relationship;

[0141] The embodiment of the present invention calculates the matching relationship between clinical nursing update data and clinical nursing forms by using matching algorithms such as text matching, pattern matching, and field matching. The matching relationship shows the correspondence between clinical nursing update data and clinical nursing forms to ensure that the changed data can be correctly mapped to the corresponding form fields or items of the clinical nursing form, and finally obtains the form update matching relationship.

[0142] Step S44: updating and modifying the clinical nursing update data and the clinical nursing form according to the form update matching relationship to obtain a clinical nursing update form.

[0143] The embodiment of the present invention updates the corresponding changed field values in the clinical nursing update data to the corresponding clinical nursing form according to the calculated form update matching relationship, so as to ensure that the form is consistent with the latest clinical nursing data, and finally obtains the clinical nursing update form.

[0144] The present invention first uses sensors, monitoring devices, and other technical means to collect and monitor patients' physiological parameters, vital signs, and other relevant data in real time within the clinical care data to be generated. This allows timely acquisition and analysis of the patient's latest data to detect potential changes and anomalies, and generates clinical care change data. This helps nursing staff identify changes in the patient's condition early, enabling timely intervention and form update decisions. The clinical care change data obtained through real-time monitoring is then subjected to a fill-in and update process, which fills gaps or missing values in the data and updates existing data records. The purpose of this fill-in and update process is to ensure data integrity and continuity. When monitoring devices or sensors experience data loss or uneven sampling frequencies, the fill-in method can be used to supplement the data, making the dataset more complete and useful for subsequent analysis and decision-making. Next, a matching relationship calculation is performed on the filled-in and updated clinical care data and the corresponding clinical care form to determine the corresponding relationship between the clinical care data and the form data, ensuring that the changed data is correctly mapped to the corresponding form fields or items. This matching relationship calculation ensures the accuracy and consistency of the clinical care data and provides the data association information required for form updates. Finally, based on the calculated form update matching relationships, the updated clinical care data and the corresponding clinical care forms are updated and modified. This means that the changed data is correctly mapped and updated to the corresponding form fields or items to generate a clinical care update form. The updated form data can be used by medical staff for reference and tracking of real-time patient changes and care progress, supporting clinical decision-making and optimizing care quality.

[0145] Preferably, the present invention further provides a system for generating a clinical nursing form, for executing the method for generating a clinical nursing form as described above, wherein the system for generating a clinical nursing form comprises:

[0146] The form requirement analysis module is used to obtain historical clinical nursing form data, perform rule requirement analysis on the historical clinical nursing form data, and thus obtain historical form standard data;

[0147] The form generation model building module is used to perform association rule mining and analysis on historical form specification data to obtain key features of historical forms; and to build a form specification generation model based on the key features of historical forms;

[0148] The form generation module is used to obtain the clinical nursing data to be generated, clean the clinical nursing data to be generated, and obtain clinical nursing standard data; the form standard generation model is used to automatically generate and process the clinical nursing standard data, thereby obtaining a clinical nursing form;

[0149] The form monitoring and updating module is used to monitor and process the clinical nursing data to be generated in real time to obtain clinical nursing update data; and to update and match the clinical nursing form using the clinical nursing update data to obtain the clinical nursing update form;

[0150] The personalized management module is used to personalize the clinical nursing update form to obtain a personalized clinical form; and to execute corresponding clinical nursing form management decisions based on the personalized clinical form.

[0151] In summary, the present invention provides a system for generating clinical nursing forms. The system comprises a form requirement analysis module, a form generation model construction module, a form generation module, a form monitoring and updating module, and a personalized management module. The system can implement any of the methods for generating clinical nursing forms described in the present invention. The internal structures of the system cooperate with each other and adopt a variety of data processing methods to achieve efficient and personalized generation and customization of clinical nursing forms, thereby improving the efficiency and accuracy of form generation. In addition, by automatically generating clinical nursing forms, the workload of manual filling is reduced, and the efficiency of nursing work is improved. This can greatly reduce repetitive work and manpower input, and can quickly and effectively provide a more accurate and efficient clinical nursing form generation process, thereby simplifying the operating procedures of the system for generating clinical nursing forms.

[0152] The present invention is therefore intended to be illustrative and non-restrictive in all respects, with the scope of the invention being defined by the appended claims rather than the foregoing description, and all changes that come within the meaning and range of equivalents of the application documents are intended to be embraced therein.

[0153] The foregoing description is intended only to provide specific embodiments of the present invention, which will enable those skilled in the art to understand and implement the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention is not intended to be limited to the embodiments shown herein, but is to be construed in the widest possible manner consistent with the principles and novel features disclosed herein.

Claims

1. A method for generating a clinical nursing form, characterized in that: The following steps are involved: Step S1: Obtain historical clinical nursing form data, perform rule requirement analysis on the historical clinical nursing form data, and obtain historical form standard data; Step S2: Perform association rule mining analysis on the historical form specification data to obtain key features of the historical form; and construct a form specification generation model based on the key features of the historical form; Step S3: Acquire the clinical nursing data to be generated, clean the clinical nursing data to be generated, and obtain clinical nursing standard data; use the form standard generation model to automatically generate the clinical nursing standard data to obtain a clinical nursing form; Step S4: performing real-time monitoring processing on the clinical nursing data to be generated to obtain clinical nursing update data; performing update matching processing on the clinical nursing form using the clinical nursing update data to obtain a clinical nursing update form; Step S5: Perform personalized customization on the clinical nursing update form to obtain a personalized clinical form; and execute corresponding clinical nursing form management decisions based on the personalized clinical form.

2. The method for generating a clinical nursing form according to claim 1, wherein: Step S1 includes the following steps: Step S11: Obtain historical clinical nursing form data; Step S12: performing field requirement analysis on historical clinical nursing form data to obtain form field requirement data; Step S13: performing data format requirement analysis on historical clinical nursing form data to obtain form format requirement data; Step S14: performing data association demand analysis on historical clinical nursing form data to obtain form association demand data; Step S15: performing a joint demand analysis on the form field demand data, the form format demand data, and the form association demand data to obtain historical form specification data.

3. The method for generating a clinical nursing form according to claim 2, wherein: Step S12 includes the following steps: Step S121: performing field type requirement analysis on historical clinical nursing form data to obtain field type requirement data; Step S122: performing field length requirement analysis on historical clinical nursing form data to obtain field length requirement data; Step S123: Calculate the field completeness of the historical clinical nursing form data using the field logic completeness calculation formula to obtain the form field completeness index; Step S124: performing validation rule requirement analysis on historical clinical nursing form data based on the form field completeness index to obtain field rule requirement data; Step S125: Merging the field type requirement data, the field length requirement data, and the field rule requirement data to obtain form field requirement data.

4. The method for generating a clinical nursing form according to claim 3, wherein: The field logic integrity calculation formula in step S123 is specifically: Where CI is the form field completeness index, n is the number of fields in the historical clinical nursing form data, and w i is the weight parameter of the i-th field in the historical clinical nursing form data, d i is the actual data completeness of the i-th field in the historical clinical nursing form data, t1 is the lower limit of the time constraint for field completeness calculation, t2 is the upper limit of the time constraint for field completeness calculation, t is the integral time variable for field completeness calculation, f(t) is the field completeness time decay function, k1 is the harmonic smoothing parameter of the field completeness time decay function, μ is the mean of the field completeness time influence, σ is the standard deviation of the field completeness time influence, g(t) is the field completeness time influence function, h(t) is the field completeness time contribution adjustment function, p(t) is the field completeness time deviation function, and ε is the correction value of the form field completeness index.

5. The method for generating a clinical nursing form according to claim 1, wherein: Step S2 includes the following steps: Step S21: performing feature pattern mining analysis on the historical form standard data to obtain the historical form data features; Step S22: Using principal component analysis technology to perform dimensionality reduction processing on the historical form data features to obtain form dimensionality reduction features; Step S23: Using the feature criticality calculation formula, perform key calculation on the form dimensionality reduction features to obtain the form feature criticality; The feature criticality calculation formula is as follows: In the formula, K is the key degree of form features, m is the number of form dimensionality reduction features, x j is the j-th form dimensionality reduction feature, x is the adjacent form dimensionality reduction feature, α is the key reconciliation factor, x ′ is the additional form dimensionality reduction feature, ∈ is the correction value of the form feature criticality; Step S24: Sort the form feature criticality in descending order, select the form dimensionality reduction features corresponding to the top-ranked form feature criticality as key features, and obtain the historical form key features; Step S25: Construct a form specification generation model based on the key features of the historical form.

6. The method for generating a clinical nursing form according to claim 1, wherein: Step S3 includes the following steps: Step S31: performing patient information monitoring processing on the clinical nursing process to obtain patient information monitoring data; Step S32: monitoring and processing the medical order information of the clinical nursing process to obtain medical order information monitoring data; Step S33: performing vital sign monitoring processing on the clinical nursing process to obtain vital sign monitoring data; Step S34: performing nursing record monitoring processing on the clinical nursing process to obtain nursing record monitoring data; Step S35: merging the patient information monitoring data, the doctor's order information monitoring data, the vital signs monitoring data, and the nursing record monitoring data in a time series manner to obtain the clinical nursing data to be generated; Step S36: Cleaning the clinical nursing data to be generated to obtain clinical nursing standard data; Step S37: Utilize the form specification generation model to automatically generate and process the clinical nursing specification data to obtain a clinical nursing form.

7. The method for generating a clinical nursing form according to claim 6, wherein: Step S36 includes the following steps: Step S361: Calculate the abnormal peak value of the clinical nursing data to be generated using the abnormal peak calculation formula to obtain the abnormal peak value of the nursing data; Step S362: filtering out abnormalities from the clinical nursing data to be generated based on abnormal peaks of the nursing data to obtain abnormal peak-filtered data; Step S363: interpolating the abnormal peak filtered data to obtain clinical nursing interpolation data; Step S364: Perform structured conversion processing on the clinical nursing interpolation data to obtain clinical nursing standard data.

8. The method for generating a clinical nursing form according to claim 7, wherein: The abnormal peak calculation formula in step S361 is specifically: Where V is the abnormal peak value of nursing data, τ is the time variable for abnormal peak calculation, τ1 is the lower limit of the time range for abnormal peak calculation, τ2 is the upper limit of the time range for abnormal peak calculation, X a (τ) is the abnormal value of the clinical nursing data to be generated at time τ, X r (τ) is the abnormal change range value of the clinical nursing data to be generated at time τ, ρ1 is the weight influence factor of the abnormal value, a1 is the exponential gain factor of the abnormal value, X d (τ) is the difference value of the clinical nursing data to be generated at time τ, ρ2 is the weight influence factor of the difference value, a2 is the exponential gain factor of the difference value, X t (τ) is the abnormal change value of the clinical nursing data to be generated at time τ, ρ3 is the weight influence factor of the abnormal change value, a3 is the exponential gain factor of the abnormal change value, X e (τ) is the abnormal experience value of the clinical nursing data to be generated at time τ, ρ4 is the weight influence factor of the abnormal experience value, a4 is the exponential gain factor of the abnormal experience value, and η is the correction value of the abnormal peak value of the nursing data.

9. The method for generating a clinical nursing form according to claim 1, wherein: Step S4 includes the following steps: Step S41: Perform real-time monitoring and processing on the clinical nursing data to be generated to obtain clinical nursing change data; Step S42: performing filling and updating processing on the clinical nursing change data to obtain clinical nursing update data; Step S43: Calculate the matching relationship between the clinical nursing update data and the clinical nursing form to obtain the form update matching relationship; Step S44: updating and modifying the clinical nursing update data and the clinical nursing form according to the form update matching relationship to obtain a clinical nursing update form.

10. A system for generating clinical nursing forms, characterized in that: A system for generating a clinical nursing form according to claim 1, wherein the system comprises: The form requirement analysis module is used to obtain historical clinical nursing form data, perform rule requirement analysis on the historical clinical nursing form data, and thus obtain historical form standard data; The form generation model building module is used to perform association rule mining and analysis on historical form specification data to obtain key features of historical forms; and to build a form specification generation model based on the key features of historical forms; The form generation module is used to obtain the clinical nursing data to be generated, clean the clinical nursing data to be generated, and obtain clinical nursing standard data; the form standard generation model is used to automatically generate and process the clinical nursing standard data, thereby obtaining a clinical nursing form; The form monitoring and updating module is used to monitor and process the clinical nursing data to be generated in real time to obtain clinical nursing update data; and to update and match the clinical nursing form using the clinical nursing update data to obtain the clinical nursing update form; The personalized management module is used to personalize the clinical nursing update form to obtain a personalized clinical form; and to execute corresponding clinical nursing form management decisions based on the personalized clinical form.

Images