A medical quality control index interpretation method, system, medium and program product

Abstract

A medical quality control index interpretation method, system, medium and program product, in the method, a hierarchical index dictionary is constructed; an index analysis rule library is established based on the hierarchical index dictionary; using a preset index name standardization algorithm, the index name is converted into a preset standardized format using the hierarchical index dictionary and the index analysis rule library, obtaining a plurality of standardized index names; an index semantic mapping matrix is established, and the core word, the modifier and the limiting word in the plurality of standardized index names are matched with the preset index connotation elements respectively, to obtain a hierarchical semantic mapping result; a hierarchical index interpretation template library is established; according to the hierarchical semantic mapping result, an initial template element is selected and combined in the hierarchical index interpretation template library to generate an interpretation text. The present application reduces the differences in the interpretation of index definitions between different medical institutions and regions, thereby improving the consistency of index interpretation between various medical institutions and regions.

Description

TECHNICAL FIELD

[0001] The application belongs to the field of medical information interpretation, and particularly relates to a medical quality control index interpretation method and system, a medium and a program product. BACKGROUND

[0002] Medical quality control indexes are important tools for measuring and evaluating the quality of medical services. These indexes help medical institutions and management departments monitor, evaluate and improve the quality of medical services. Proper application of indexes in hospital management can promote the standardization, professionalization, standardization and refinement of medical management and control work, analyze index definitions and accurately interpret the standard calculation of medical quality control indexes, which can promote the improvement of hospital medical quality.

[0003] In related technologies, the meanings of index names can be analyzed according to relevant normative documents of the state, on-site research of hospitals and clinical research, the index names are accurately interpreted, and the specific connotations and clear value descriptions referred to in the indexes are described in standard terms.

[0004] However, the interpretation of index definitions may differ between different medical institutions and regions, resulting in different descriptions of the specific connotations and clear value descriptions referred to in the indexes, which may reduce the consistency between different medical institutions and regions and hinder the improvement of medical quality in the medical system. SUMMARY

[0005] The application provides a medical quality control index interpretation method, system, medium and program product, which is used to reduce the differences in the interpretation of index definitions between different medical institutions and regions, and to improve the consistency of index interpretation between different medical institutions and regions.

[0006] In a first aspect, the application provides a medical quality control index interpretation method, which constructs a hierarchical index dictionary. The hierarchical index dictionary decomposes the index names of the medical quality control indexes into core words, modifier words and limit words.

[0007] Based on the hierarchical index dictionary, an index analysis rule library is established, which includes hierarchical matching rules, word combination rules and context association rules.

[0008] A preset index name standardization algorithm is used to convert index names in different expression modes into a preset standardized format using the hierarchical index dictionary and the index analysis rule library, to obtain a plurality of standardized index names.

[0009] An index semantic mapping matrix is established, and the core words, modifier words and limit words in the plurality of standardized index names are matched with preset index connotation elements based on the index semantic mapping matrix, to obtain hierarchical semantic mapping results.

[0010] A hierarchical index interpretation template library is established to set corresponding interpretation frameworks and key elements for different levels of word combinations; initial template elements with the highest similarity to the hierarchical semantic mapping results are selected and combined in the hierarchical index interpretation template library according to the hierarchical semantic mapping results to generate an interpretation text.

[0011] By adopting the above technical solutions, the construction of the hierarchical index dictionary realizes accurate decomposition of the index name, which helps to more accurately understand the core content, modification information and limitation conditions of the index. The establishment of the index analysis rule library ensures consistent processing of indexes with different expression methods, improves the accuracy and reliability of interpretation. The application of the standardized algorithm further unifies the index expression, facilitating cross-institutional and cross-regional index comparison and analysis. The creation of the index semantic mapping matrix establishes a clear correspondence between the index name and the connotation elements, which helps to more comprehensively and deeply understand the index meaning. The application of the hierarchical index interpretation template library not only improves the interpretation efficiency, but also ensures the standardization and integrity of the interpretation results. It realizes the reduction of differences in the interpretation of index definitions between different medical institutions and regions, and further improves the consistency of index interpretation between medical institutions and regions.

[0012] In combination with some embodiments of the first aspect, in some embodiments, the hierarchical index dictionary is constructed, specifically including:

[0013] An index name set of medical quality control is obtained, which includes index names published by authoritative institutions, index names used by medical institutions at all levels, index names in medical literature and index names used in clinical practice;

[0014] A word classification standard is defined, and the index names in the index name set of medical quality control are decomposed into core words, modification words and limitation words. The core words represent the measurement object of the index name, the modification words represent the words describing the core words, and the limitation words are the words of the detailed classification conditions;

[0015] The hierarchical index dictionary is constructed according to the index name set of medical quality control and the word classification standard.

[0016] By adopting the technical scheme, the comprehensiveness and representativeness of the index dictionary are ensured. By collecting index names published by authoritative agencies, index names used by medical institutions at all levels, index names in medical literature, and index names used in clinical practice, the dictionary covers comprehensive terms in the field of medical quality control and adapts to different scenarios and needs. The practice of decomposing index names into core words, modifier words, and limiting words greatly improves the accuracy of index understanding. Core words reflect the measurement object, modifier words describe the core words, and limiting words refine the classification conditions. This hierarchical structure makes the meaning of the index more clear and specific.

[0017] In combination with some embodiments of the first aspect, in some embodiments, the term classification standard is defined, and the index names in the medical quality control index name set are decomposed into core words, modifier words, and limiting words, specifically including:

[0018] Collecting common index core concepts, common modifier words, and common limiting words to obtain a term feature library;

[0019] Calculating the similarity between the index names in the medical quality control index name set and the index core concepts, common modifier words, and common limiting words one by one to obtain index core concept similarity, modifier similarity, and limiting similarity;

[0020] Defining the term classification standard according to the similarity, and the term classification standard is that when the similarity is greater than the preset similarity threshold, the corresponding word class of the index name is assigned;

[0021] Decomposing the index names in the medical quality control index name set into core words, modifier words, and limiting words according to the term feature library and the term classification standard, the core words are the words corresponding to the index core concept similarity greater than the preset similarity threshold, the modifier words are the words corresponding to the modifier similarity greater than the preset similarity threshold, and the limiting words are the words corresponding to the limiting similarity greater than the preset similarity threshold.

[0022] By adopting the above technical scheme, the common index core concepts, modifier words, and limiting words are collected to construct the term feature library, improving the professionalism and accuracy of classification and reducing classification errors. The method of calculating similarity is used for term classification, introducing quantitative analysis, making the classification process more objective and reliable, improving the accuracy and coverage of classification. The classification process is based on clear rules and calculations, and the results are consistent and repeatable, which is beneficial to the comparison and analysis of indexes of different institutions or different periods.

[0023] In combination with some embodiments of the first aspect, in some embodiments, after decomposing the index names in the medical quality control index name set into core words, modifier words, and limiting words according to the term feature library and the term classification standard, the method further includes:

[0024] obtain a medical synonym and near-synonym library;

[0025] identify synonyms and near-synonyms in core words, modifier words, and limiting words;

[0026] convert synonyms and near-synonyms into preset standard terms according to the medical synonym and near-synonym library;

[0027] establish a mapping table of synonyms and near-synonyms and preset standard terms.

[0028] By adopting the above technical solutions, the medical synonym and near-synonym library is obtained, the system can recognize and process the medical field-specific term variants, and the accuracy and comprehensiveness of index interpretation are improved. In the medical field, the same concept may have multiple expression methods, which ensures that indexes with different expressions can be correctly understood and classified. Converting synonyms and near-synonyms into preset standard terms unifies the expression of indexes, provides a consistent basis for subsequent analysis and comparison, and improves the reliability of index interpretation. Establishing a mapping table of synonyms and near-synonyms and preset standard terms not only retains the information of the original expression, but also establishes a clear connection between different expressions. This mapping relationship is beneficial for tracking the original expression of the index, and also provides convenience for the unified management and updating of terms. It can adapt to the dynamic changes of medical terms. With the development of medicine, new terms and expression methods are constantly emerging. By updating the library and mapping table, the system can continuously maintain the timeliness of its processing capability.

[0029] In combination with some embodiments of the first aspect, in some embodiments, after selecting and combining the initial template elements in the hierarchical index interpretation template library according to the hierarchical semantic mapping result to generate the interpretation text, the method further comprises:

[0030] establishing a scoring dimension and scoring the interpretation text using the scoring dimension to obtain a consistency score;

[0031] in a case where the consistency score is greater than a preset threshold, marking the interpretation text as a qualified text;

[0032] in a case where the consistency score is not greater than the preset threshold, sending the interpretation text to an auditing terminal;

[0033] receiving a revised interpretation text sent by the auditing terminal, and parsing the revised interpretation text to obtain a revised hierarchical index interpretation template library; and updating the hierarchical index interpretation template library according to the revised hierarchical index interpretation template library.

[0034] By adopting the technical solution, the scoring dimensions are established and the interpretation text is scored, so that high-quality interpretation texts can be identified and screened, and the reliability and consistency of the interpretation results are ensured. For interpretation texts that do not meet the standards, the system will send them to the audit terminal for manual audit, and the interpretation texts after manual audit will be more accurate. By receiving and analyzing the revised interpretation texts, the system can continuously update and optimize the hierarchical index interpretation template library, so that the system can continuously improve its interpretation ability over time and adapt to the changing medical quality control needs.

[0035] In combination with some embodiments of the first aspect, in some embodiments, the scoring dimensions are established, specifically comprising:

[0036] determining the corresponding core word accuracy according to the core word and the main measurement concept;

[0037] determining the corresponding modifier appropriateness according to the modifier and the core word;

[0038] determining the corresponding limiting word explicitness according to the limiting word and the index noun;

[0039] determining the corresponding interpretation completeness according to all key elements contained in the interpretation text and the index noun;

[0040] respectively giving the core word accuracy, the modifier appropriateness, the limiting word explicitness and the interpretation completeness a corresponding weight to obtain the scoring dimensions.

[0041] By adopting the technical solution, the core word accuracy, the modifier appropriateness, the limiting word explicitness and the interpretation completeness are respectively evaluated, realizing comprehensive and meticulous quality evaluation of the interpretation text, which can comprehensively capture each key aspect of the interpretation text and ensure the comprehensiveness and accuracy of the evaluation. The evaluation of the core word accuracy ensures that the interpretation text accurately grasps the main measurement object of the index. The evaluation of the modifier appropriateness ensures that the description of the core concept is accurate and appropriate, avoiding possible misunderstanding or ambiguity. The evaluation of the limiting word explicitness ensures that the applicable scope and conditions of the index are clearly defined. The evaluation of the interpretation completeness ensures that the interpretation text covers all key elements in the index noun, avoiding omission of information. By giving different weights to each evaluation dimension, the system can flexibly adjust the evaluation standard according to the characteristics and importance of different indexes, so that the evaluation result is more in line with the actual needs. The system can adapt to different types of medical quality control indexes, improving the universality and adaptability of the system.

[0042] In combination with some embodiments of the first aspect, in some embodiments, the interpretation text is scored using the scoring dimensions to obtain a consistency score, specifically comprising:

[0043] using a weighted average algorithm to calculate the consistency score corresponding to the interpretation text according to the scoring dimensions;

[0044] The calculation function in the weighted average algorithm is:

[0045] N = a x S + b x Y + c x Z + d x M

[0046] In the function, N is the consistency score, a is the weight corresponding to the consistency score, S is the core word accuracy, b is the weight corresponding to the modifier appropriateness, Y is the modifier appropriateness, c is the weight corresponding to the determiner explicitness, Z is the determiner explicitness, d is the weight corresponding to the interpretation completeness, M is the interpretation completeness, and the sum of a, b, c, and d is 1.

[0047] By using the above technical solution, the weighted average algorithm can comprehensively consider the four key dimensions of core word accuracy, modifier appropriateness, determiner explicitness, and interpretation completeness to obtain a consistency score that comprehensively reflects the interpretation quality. This comprehensive scoring method can more accurately reflect the overall quality of the interpreted text and avoid the one-sidedness that may be caused by single-dimensional evaluation.

[0048] In a second aspect, the embodiments of the present application provide a medical quality control indicator interpretation system, which comprises one or more processors and a memory. The memory is coupled to the one or more processors, and the memory is configured to store computer program codes, the computer program codes comprising computer instructions. The one or more processors invoke the computer instructions to enable the system to perform the method described in the first aspect and any possible implementation manner of the first aspect.

[0049] In a third aspect, the embodiments of the present application provide a computer readable storage medium comprising instructions, which, when executed on a system, cause the system to perform the method described in the first aspect and any possible implementation manner of the first aspect.

[0050] In a fourth aspect, the embodiments of the present application provide a computer program product, characterized in that when the computer program product is executed on a system, the system performs the method described in any possible implementation manner of the first aspect.

[0051] The one or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:

[0052] 1. The application provides a medical quality control index interpretation method, through the construction of hierarchical index dictionary, the accurate decomposition of index name is realized, which helps to more accurately understand the core content, modification information and limitation condition of index. The establishment of index analysis rule library ensures the consistency processing of index with different expression modes, improves the accuracy and reliability of interpretation. The application of standardized algorithm further unifies the index expression, which is convenient for cross-institution, cross-regional index comparison and analysis. The creation of index semantic mapping matrix establishes a clear correspondence between index name and connotation elements, which helps to more comprehensively and deeply understand the index meaning. The application of hierarchical index interpretation template library not only improves the interpretation efficiency, but also ensures the standardization and integrity of interpretation results. It realizes the reduction of the differences in index definition interpretation between different medical institutions and regions, and further improves the consistency of index interpretation between different medical institutions and regions.

[0053] 2. The application provides a medical quality control index interpretation method, acquires a medical synonym and near-synonym library, and the system can recognize and process the specific term variants in the medical field, improving the accuracy and comprehensiveness of index interpretation. In the medical field, the same concept may have multiple expression modes, which ensures that indexes with different expression modes can be correctly understood and classified. Converting synonyms and near-synonyms into preset standard terms unifies the expression of indexes, provides a consistent basis for subsequent analysis and comparison, and improves the reliability of index interpretation. The establishment of the mapping table of synonyms and near-synonyms and preset standard terms not only retains the information of the original expression, but also establishes a clear connection between different expressions. This mapping relationship is beneficial to trace the original expression of the index, and also provides convenience for the unified management and update of terms. It can adapt to the dynamic changes of medical terms. With the development of medicine, new terms and expression modes are constantly emerging. By updating the word library and mapping table, the system can continuously maintain the timeliness of its processing ability.

[0054] 3、The application provides a medical quality control index interpretation method, which respectively evaluates core word accuracy, modifier appropriateness, qualifier explicitness and interpretation integrity, realizes comprehensive and meticulous quality evaluation of the interpreted text, can comprehensively capture each key aspect of the interpreted text, and ensures the comprehensiveness and accuracy of the evaluation. The evaluation of core word accuracy ensures that the interpreted text accurately grasps the main measurement object of the index. The evaluation of modifier appropriateness ensures that the description of the core concept is accurate and appropriate, avoiding possible misunderstanding or ambiguity. The evaluation of qualifier explicitness ensures that the applicable scope and conditions of the index are clearly defined. The evaluation of interpretation integrity ensures that the interpreted text covers all key elements in the index noun, avoiding omission of information. By giving different weights to each evaluation dimension, the system can flexibly adjust the evaluation standard according to the characteristics and importance of different indexes, so that the evaluation result is more in line with the actual demand. The system can adapt to different types of medical quality control indexes, improving the universality and adaptability of the system. BRIEF DESCRIPTION OF DRAWINGS

[0055] Figure 1 is a flowchart of a medical quality control index interpretation method in an embodiment of the application.

[0056] Figure 2 is another flowchart of a medical quality control index interpretation method in an embodiment of the application.

[0057] Figure 3 is an entity device structure schematic diagram of a medical quality control index interpretation system provided in an embodiment of the application. DETAILED DESCRIPTION

[0058] The terms used in the following embodiments of the application are only for the purpose of describing the specific embodiments and are not intended to be limiting to the application. As used in the specification and the appended claims of the application, the singular forms "a," "an" and "the" are intended to include both singular and plural forms, unless the context clearly indicates otherwise. It will be further understood that the terms "and / or" used in the application means any or all possible combinations of one or more of the listed items.

[0059] Hereinafter, the terms "first", "second" are only for the purpose of description, and cannot be understood as implying or suggesting relative importance or implicitly indicating the number of indicated technical features. Therefore, the features defined with "first", "second" can explicitly or implicitly include one or more of the features, and in the description of the embodiments of the application, unless otherwise specified, the meaning of "multiple" is two or more.

[0060] In the current medical system, medical quality control indicators play a crucial role. These indicators are not only key tools for measuring the quality of medical services, but also important bases for driving medical institutions to continuously improve and enhance service levels. However, with the continuous development and complexity of the medical system, various regional and level medical institutions often face great challenges in interpreting and applying these indicators.

[0061] Taking a certain province as an example, the province has hundreds of medical institutions of different sizes and levels, from top-tier hospitals to primary clinics, distributed in every corner of cities and rural areas. In order to improve the medical quality of the whole province, the provincial health commission has developed a series of medical quality control indicators. However, in the actual implementation process, there are significant differences in the understanding and application of these indicators among various medical institutions.

[0062] For example, for the indicator of "surgical site infection rate", a top-tier hospital interprets it as the proportion of surgical patients who develop surgical site infections, while another secondary hospital interprets it as the proportion of clean surgical patients who develop infections. This difference in interpretation leads to different standards in data statistics and reporting by the two hospitals, making it difficult for the provincial management department to accurately assess and compare the actual performance of each hospital.

[0063] For another example, in interpreting the "patient satisfaction" indicator, some hospitals only consider the feedback of inpatient patients, ignoring the evaluation of outpatient patients. In calculating the "average length of stay", some hospitals have different understandings of how to handle transferred cases, some include the transfer-in time, and some only calculate the actual hospitalization time in the hospital. These differences not only affect the comparability of data among hospitals, but also make it difficult to assess the overall medical quality of the whole province.

[0064] More complex is that with the rapid development of medical technology and the continuous emergence of new treatment methods, some new quality control indicators have also emerged. For example, in the process of promoting day surgery, there are great differences among hospitals in defining and calculating the "day surgery to inpatient transfer rate" indicator. Some hospitals include planned inpatient transfers in statistics, while others only count unplanned inpatient transfers.

[0065] These differences in interpretation not only affect the comparability of data among medical institutions, but also bring difficulties to the provincial health management department in formulating policies and allocating resources. More importantly, this inconsistency may lead some medical institutions to ignore the real improvement of medical quality in the process of pursuing indicator data improvement, and even may take some improper measures to beautify the data.

[0066] To solve the above technical problems, the present application provides a medical quality control index interpretation method for reducing the differences in the interpretation of index definitions between different medical institutions and regions, thereby improving the consistency of index interpretation between various medical institutions and regions. The following describes the medical quality control index interpretation method in the embodiments of the present application in combination with Figure 1 The medical quality control index interpretation method in the embodiments of the present application is described as follows:

[0067] Please refer to Figure 1 for a flowchart of the medical quality control index interpretation method in the embodiments of the present application.

[0068] S101, acquiring a medical quality control index name set;

[0069] The system acquires a medical quality control index name set, which includes index names published by authoritative agencies, index names used by medical institutions at various levels, index names in medical literature, and index names used in clinical practice.

[0070] In medical quality management, standardization of index names is the key to improving the accuracy of quality assessment. The system first needs to collect index names from various channels, including official indexes published by authoritative agencies, indexes used by hospitals at various levels in daily work, indexes mentioned in medical literature, and indexes commonly used in clinical practice. The purpose of this step is to establish a comprehensive index name library to lay the foundation for subsequent analysis and standardization.

[0071] For example, the system may collect the following index names:

[0072] Published by authoritative agencies: incidence of surgical site infection;

[0073] Used by hospitals: postoperative wound infection rate;

[0074] Medical literature: surgical site infection index;

[0075] Clinical practice: surgical incision infection rate.

[0076] S102, defining a word classification standard to decompose the index names in the medical quality control index name set into core words, modifier words, and limiting words;

[0077] The word classification standard is defined to decompose the index names in the medical quality control index name set into core words, modifier words, and limiting words. The core word represents the measurement object of the index name, the modifier word represents the word that describes the core word, and the limiting word is the word that refines the classification condition. Specifically, the core concept of the commonly used index, the commonly used modifier word, and the commonly used limiting word are collected to obtain a word feature library.

[0078] Calculate the similarity of each term in the medical quality control indicator name set to the core concept, modifier, and qualifier. The core concept similarity, modifier similarity, and qualifier similarity are obtained.

[0079] According to the similarity definition of the word classification standard, when the similarity is greater than the preset similarity threshold, the corresponding word category is assigned to the indicator name.

[0080] According to the word feature library and word classification standard, the indicator names in the medical quality control indicator name set are decomposed into core words, modifier words, and qualifier words. The core word is the word corresponding to the core concept similarity greater than the preset similarity threshold, the modifier word is the word corresponding to the modifier similarity greater than the preset similarity threshold, and the qualifier word is the word corresponding to the qualifier similarity greater than the preset similarity threshold.

[0081] The core of this step is to establish a word classification system to accurately identify the key components in the indicator name. The system first constructs a word feature library containing common indicator core concepts (such as "infection", "satisfaction", "mortality", etc.), modifier words (such as "postoperative", "hospital", "30 days", etc.), and qualifier words (such as "clean surgery", "diabetic patients", "ICU", etc.).

[0082] Next, the system calculates the similarity of the words in the indicator name to the words in the feature library. For example, for the indicator "surgical site infection rate":

[0083] The similarity of "infection" to the core concept "infection" may be 0.9;

[0084] The similarity of "surgery" to the modifier "postoperative" may be 0.8;

[0085] The similarity of "site" to the qualifier "specific site" may be 0.7;

[0086] Assuming the system sets the similarity threshold to 0.6, "infection" will be classified as a core word, "surgery" and "site" will be classified as modifier words, and "rate" may be identified as another core word representing the type of measurement.

[0087] Of course, there may be some synonyms and near synonyms, so in order to facilitate the description of induction, obtain a medical synonym and near synonym library;

[0088] Identify synonyms and near synonyms in core words, modifier words, and qualifier words;

[0089] Convert synonyms and near synonyms to preset standard terms according to the medical synonym and near synonym library;

[0090] A mapping table of synonyms and near-synonyms to pre-defined standard terms is established.

[0091] After obtaining the mapping table, in subsequent word classification, the mapping table can be used to accurately and quickly classify synonyms and near-synonyms.

[0092] S103, constructing a hierarchical indicator dictionary according to the medical quality control indicator name set and the word classification standard;

[0093] The system uses the information obtained in the first two steps to construct a structured indicator dictionary. This dictionary not only contains the components of the indicators, but also reflects the hierarchical relationship between these components.

[0094] For example, for the indicator "surgical site infection rate", the hierarchical indicator dictionary may look like this:

[0095] Core word layer:

[0096] Infection;

[0097] Rate.

[0098] Modifier word layer:

[0099] Surgery;

[0100] Site.

[0101] This hierarchical structure allows the system to more accurately understand the meaning of the indicators and provides a basis for comparison and mapping between different indicators. For example, the system can identify that "surgical site infection rate" and "postoperative wound infection rate" are the same in core concept, only different in expression.

[0102] S104, establishing an indicator analysis rule base based on the hierarchical indicator dictionary;

[0103] In this step, the system will create a set of rules for parsing and understanding the structure and meaning of various indicator names. These rules are based on the hierarchical indicator dictionary and take into account the particularity and complexity of medical quality indicators.

[0104] The indicator analysis rule base may include the following types of rules:

[0105] Word order rules: define the typical arrangement order of core words, modifier words and limiting words in indicator names.

[0106] For example: [limiting word] + [modifier word] + [core word] + [measurement type].

[0107] Synonym rules: define the equivalence relationship between synonyms or near-synonyms.

[0108] For example: {“surgery”, “postoperative”, “surgery-related”} can be considered as equivalent modifiers.

[0109] Abbreviation Expansion Rules: Define the full form of common abbreviations.

[0110] For example: ICU - Intensive Care Unit.

[0111] Composite Indicator Resolution Rules: Handle complex indicators that contain multiple core concepts.

[0112] For example: “Surgical Site Infection Rate” = [Core Concept 1: Infection] + [Core Concept 2: Rate].

[0113] Context-Related Rules: Adjust the resolution approach based on different medical fields or departments.

[0114] For example: In the surgical field, “incision” usually refers to surgical incisions; in dermatology, it may refer to other types of skin wounds.

[0115] For example:

[0116] For the indicator “Surgical Site Infection Rate”, the system may apply the following rules:

[0117] Apply Word Order Rules: Identify “surgery” as a modifier, “site” as a modifier, “infection” as a core concept, and “rate” as a measurement type.

[0118] Apply Synonym Rules: Consider “surgical site” and “surgical incision” as equivalents.

[0119] Apply Context-Related Rules: In the surgical context, interpret “site” as “surgical incision”.

[0120] S105, using a preset indicator name standardization algorithm, using a hierarchical indicator dictionary and an indicator resolution rule library to convert indicator names with different expressions into a preset standardized format, to obtain a plurality of standardized indicator names;

[0121] In this step, the system will use a pre-set standardization algorithm, combined with a hierarchical indicator dictionary and an indicator resolution rule library, to convert variously expressed indicator names into a unified standard format. This process aims to eliminate differences in expression, so that the same or similar indicators from different sources can be consistently understood and compared.

[0122] The standardization algorithm may include the following steps:

[0123] Tokenization and Part-of-Speech Tagging: Split the indicator name into individual words and tag each word with its part of speech.

[0124] Core Concept Identification: Use the hierarchical indicator dictionary to identify the core concepts in the indicator.

[0125] Modifier and determiner classification: Classify the remaining words as modifiers or determiners based on a dictionary and rule base.

[0126] Synonym replacement: Replace non-standard expressions with standard ones using synonym rules in the rule base.

[0127] Abbreviation expansion: Replace common abbreviations with their full forms.

[0128] Word order rearrangement: Rearrange the order of words according to a predefined standard format.

[0129] Generate standardized name: Combine the processed words to generate the final standardized index name.

[0130] For example, for the following different expressions of an index:

[0131] "Surgical site infection incidence"

[0132] "Postoperative wound infection rate"

[0133] "SSI occurrence proportion"

[0134] "Surgery-related infection index"

[0135] The standardization process can be as follows:

[0136] "Surgical site infection incidence"

[0137] Tokenization result: [surgery, site, infection, incidence]

[0138] Core word identification: [infection]

[0139] Modifier classification: [surgery, site]

[0140] Measurement type identification: [incidence]

[0141] Standardization result: Surgical site infection incidence

[0142] "Postoperative wound infection rate"

[0143] Tokenization result: [postoperative, wound, infection, rate]

[0144] Core word identification: [infection]

[0145] Modifier classification: [postoperative, wound]

[0146] Synonym replacement: [postoperative] -> [surgery], [wound] -> [site]

[0147] Measurement type identification: [rate] -> [incidence]

[0148] Standardized result: Surgical site infection rate

[0149] "Ssi incidence"

[0150] Segmentation result: [SSI, incidence]

[0151] Abbreviation expansion: SSI -> Surgical site infection

[0152] Core word identification: [infection]

[0153] Modifier classification: [surgical, site]

[0154] Measurement type identification: [incidence] -> [rate]

[0155] Standardized result: Surgical site infection rate

[0156] "Surgical site infection index"

[0157] Segmentation result: [surgical, related, infection, index]

[0158] Core word identification: [infection]

[0159] Modifier classification: [surgical, related]

[0160] Synonym replacement: [related] -> [site]

[0161] Measurement type identification: [index] -> [rate]

[0162] Standardized result: Surgical site infection rate

[0163] S106, establish an index semantic mapping matrix, and match the core words, modifiers and determiners in the standardized index names with the pre-defined index connotation elements based on the index semantic mapping matrix, to obtain a hierarchical semantic mapping result;

[0164] In this step, the system first establishes an index semantic mapping matrix, and then uses this matrix to match the components of the standardized index name with the pre-defined index connotation elements. The purpose of this process is to convert the index name into a deeper semantic understanding, providing a basis for subsequent interpretation.

[0165] The index semantic mapping matrix may include the following dimensions:

[0166] Measurement object: such as patients, surgeries, drugs, etc.

[0167] Quality dimension: such as safety, effectiveness, timeliness, patient-centeredness, etc.

[0168] Measurement method: such as ratio, proportion, mean, median, etc.

[0169] Time range: such as within 30 days after surgery, during hospitalization, year, etc.

[0170] Scope of application: such as all patients, patients with specific diseases, and patients undergoing specific surgical procedures.

[0171] For example, the semantic mapping process for the standardized indicator "incidence of surgical site infection" might be as follows:

[0172] Core keyword mapping:

[0173] "Infection" -> Measurement target: complications; Quality dimension: safety

[0174] Modifier mapping:

[0175] "Surgery" -> Applicable Scope: Surgical patients

[0176] "Location" -> Detailed Measurement Object: Surgical Incision

[0177] Measurement type mapping:

[0178] "Incidence" -> Measurement Method: Ratio

[0179] Based on this mapping, the system can generate the following hierarchical semantic mapping results:

[0180] Measurement target: Complications (surgical site infection)

[0181] Quality Dimension: Safety

[0182] Measurement method: ratio

[0183] Scope of application: Surgical patients

[0184] Timeframe: (Needs further clarification, usually within 30 days post-surgery)

[0185] This hierarchical semantic mapping provides richer contextual information for the indicators, enabling the system to more accurately understand their actual meaning and application scenarios. For example, the system now knows that this indicator is used to assess surgical safety, targets a surgical patient population, and measures the occurrence of a specific type of complication (incision infection).

[0186] Furthermore, this semantic mapping provides a foundation for comparing and correlating different indicators. For example, the system can easily identify all indicators related to surgical safety, or all indicators that use ratios as a measurement method.

[0187] S107. Establish a hierarchical indicator interpretation template library;

[0188] Establish a hierarchical indicator interpretation template library to set corresponding interpretation frameworks and key elements for word combinations at different levels.

[0189] In this step, the system creates a hierarchical index interpretation template library. The purpose of this template library is to provide appropriate interpretation frameworks for different types and complexities of indexes, ensuring that the interpretation results are both accurate and easy to understand. The hierarchical design allows the system to select the appropriate depth of interpretation based on the complexity of the index and the user's needs.

[0190] The hierarchical index interpretation template library may include the following levels:

[0191] Basic level: Provides simple and direct index definition and calculation methods.

[0192] Extended level: Includes detailed explanations, applicable scope, and limitations of the index.

[0193] Application level: Provides application examples and considerations of the index in actual medical quality management.

[0194] Comparison level: Contains comparisons and differences with related indexes.

[0195] Improvement level: Provides suggestions and best practices for improving the index.

[0196] For example, for the "Surgical Site Infection Rate" index, the template library may contain the following template elements:

[0197] Basic level template:

[0198] {Index Name} refers to the proportion of the number of cases of {Measurement Object} in {Time Range} within {Applicable Scope} to the total number of {Applicable Scope}.

[0199] Extended level template:

[0200] {Index Name} is mainly used to evaluate {Quality Dimension}. It reflects the occurrence of {Measurement Object} in {Applicable Scope} and is an important indicator for measuring the quality of {Related Medical Process}. The calculation method of this index is: ({Calculation Formula}). When interpreting this index, {List of Considerations} needs to be considered.

[0201] Application level template:

[0202] In practical applications, {Index Name} can be used in {List of Application Scenarios}. Medical institutions can monitor this index regularly to identify potential {Problem Types} and take appropriate {Improvement Measures Types}.

[0203] Comparison level template:

[0204] {Indicator Name} shares some similarities with {Related Indicator Name}, but the main difference lies in {Difference Description}. In some cases, it may be necessary to consider both indicators for a more comprehensive assessment.

[0205] Improvement Layer Template:

[0206] To improve {Indicator Name}, healthcare institutions can consider taking the following measures: {List of Improvement Suggestions}. When implementing these measures, attention should be paid to {Implementation Notes}.

[0207] By establishing such a hierarchical template library, the system can generate appropriate interpretation texts for indicators of different complexities and users with different needs. For example, for primary healthcare institutions, the system may mainly use the basic layer and application layer templates; while for the quality management department of a large hospital, the system may use templates of all levels to provide comprehensive interpretation.

[0208] S108, according to the hierarchical semantic mapping result, select and combine initial template elements in the hierarchical indicator interpretation template library to generate an interpretation text.

[0209] According to the hierarchical semantic mapping result, select and combine initial template elements in the hierarchical indicator interpretation template library to generate an interpretation text, and the initial template elements are the template elements with the highest similarity to the hierarchical semantic mapping result.

[0210] The system will use the hierarchical semantic mapping results obtained in the previous steps to select appropriate template elements from the hierarchical indicator interpretation template library and combine them into a coherent interpretation text. This process not only considers the semantic content of the indicator, but also considers the needs and background of the user.

[0211] Taking "Surgical Site Infection Rate" as an example, suppose the user is the quality management department of a medium-sized hospital, and needs a comprehensive understanding of the indicator. The system may perform the following operations:

[0212] Select templates: based on the user's background, the system decides to use templates of the basic layer, extension layer, application layer and improvement layer.

[0213] Fill in the template: the system fills in the selected templates using the hierarchical semantic mapping results.

[0214] Combine the text: the system combines the filled-in template elements into a coherent interpretation text.

[0215] In the above embodiments, by collecting the indicator names published by authoritative agencies, the indicator names used by medical institutions at all levels, the indicator names in medical literature, and the indicator names used in clinical practice, the dictionary covers comprehensive terms in the field of medical quality control, and adapts to different scenarios and needs. Through the construction of hierarchical indicator dictionary, the accurate decomposition of indicator names is realized, which helps to more accurately understand the core content, modification information and limitation conditions of the indicators. The establishment of the indicator analysis rule library ensures the consistent processing of indicators with different expression methods, improves the accuracy and reliability of interpretation. The application of standardized algorithm further unifies the expression of indicators, facilitating cross-institutional and cross-regional comparison and analysis of indicators. The creation of the indicator semantic mapping matrix establishes a clear correspondence between the indicator name and the connotation elements, which helps to more comprehensively and deeply understand the meaning of the indicators. The application of hierarchical indicator interpretation template library not only improves the interpretation efficiency, but also ensures the standardization and integrity of the interpretation results. It reduces the differences in the interpretation of indicator definitions between different medical institutions and regions, and improves the consistency of indicator interpretation between medical institutions and regions.

[0216] The above embodiments finally obtain the interpretation text, which is automatically generated by the computer. In general cases, it is still necessary to judge whether the interpretation text meets the standard, and if it does not meet the standard, it still needs to be modified. The following describes another medical quality control indicator interpretation method in the embodiments of the present application. Figure 2 , which is another medical quality control indicator interpretation method in the embodiments of the present application.

[0217] Please refer to Figure 2 , which is another medical quality control indicator interpretation method in the embodiments of the present application.

[0218] S201, establishing a scoring dimension and scoring the interpretation text using the scoring dimension to obtain a consistency score;

[0219] The system establishes a scoring dimension and scores the interpretation text using the scoring dimension to obtain a consistency score. Specifically, the core word accuracy corresponding to the core word and the main measurement concept is determined;

[0220] The appropriateness of the modifier word corresponding to the modifier word and the core word is determined;

[0221] The definiteness of the limiting word corresponding to the limiting word and the indicator noun is determined;

[0222] The interpretation completeness corresponding to all key elements contained in the interpretation text and the indicator noun is determined;

[0223] The corresponding weights of core word accuracy, modifier word appropriateness, limiting word definiteness and interpretation completeness are respectively assigned to obtain the scoring dimension;

[0224] The consistency score corresponding to the interpretation text is calculated using a weighted average algorithm according to the scoring dimensions;

[0225] The calculation function in the weighted average algorithm is:

[0226] N = a × S + b × Y + c × Z + d × M

[0227] In the function, N is the consistency score, a is the weight corresponding to the consistency score, S is the core word accuracy, b is the weight corresponding to the modifier appropriateness, Y is the modifier appropriateness, c is the weight corresponding to the determiner explicitness, Z is the determiner explicitness, d is the weight corresponding to the interpretation completeness, M is the interpretation completeness, and the sum of a, b, c, and d is 1.

[0228] Suppose the system needs to interpret the medical quality control indicator "incidence of pressure ulcers in hospitalized patients".

[0229] The system first establishes scoring dimensions, including core word accuracy, modifier appropriateness, determiner explicitness, and interpretation completeness. For the indicator "incidence of pressure ulcers in hospitalized patients", the system may generate the following interpretation text:

[0230] "This indicator reflects the proportion of pressure ulcers in hospitalized patients, used to evaluate nursing quality and patient safety management level."

[0231] The system scores as follows:

[0232] Core word accuracy: the system identifies the core word as "incidence of pressure ulcers", which completely matches the indicator name, giving a full score of 10.

[0233] Modifier appropriateness: the system identifies the modifier as "hospitalized patients", which is consistent with the indicator description, giving 9 points.

[0234] Determiner explicitness: the system does not find specific determiners, but mentions the hospital range in the interpretation, giving 8 points.

[0235] Interpretation completeness: the system judges that the interpretation text contains the purpose of the indicator (evaluating nursing quality and patient safety management level), giving 9 points.

[0236] Then, the system calculates the consistency score using the preset weights:

[0237] Suppose the weights are a = 0.3, b = 0.2, c = 0.2, d = 0.3

[0238] N = 0.3 × 10 + 0.2 × 9 + 0.2 × 8 + 0.3 × 9 = 9.1

[0239] The system uses natural language processing techniques such as part-of-speech tagging, dependency parsing, etc. to identify core words, modifiers, and determiners. At the same time, a pre-trained medical language model (such as BioBERT) is used to evaluate the accuracy and completeness of the interpretation. This process involves machine learning and deep learning techniques that can understand the semantics of the text and perform relevance analysis.

[0240] S202, if the consistency score is greater than the preset threshold, mark the interpretation text as qualified text;

[0241] Assuming that the system's preset qualified threshold is 8.5 points. In this example, the calculated consistency score is 9.1 points, which is greater than the preset threshold of 8.5 points. Therefore, the system marks this interpretation text as qualified text.

[0242] This step involves simple conditional judgment and data labeling. The system uses database operations or file operations techniques to update the status of the interpretation text. At the same time, the system may use log recording techniques to track the scoring and judgment process of each interpretation text for subsequent analysis and improvement.

[0243] S203, if the consistency score is not greater than the preset threshold, send the interpretation text to the review terminal; although the interpretation text is marked as qualified in this example, in order to illustrate this step, assume that the system generates another interpretation text with a consistency score of 8.0, which is lower than the preset threshold of 8.5.

[0244] In this case, the system will send this interpretation text to the review terminal. The review terminal can be a special software interface for medical quality control experts. The system uses network communication technology (such as HTTP protocol or WebSocket) to transmit the interpretation text to the review terminal.

[0245] In order to ensure the security of data transmission, the system may use encryption technology (such as SSL / TLS) to protect sensitive medical information. At the same time, the system will use identity authentication and authorization mechanisms to ensure that only experts can access these interpretation texts that need to be reviewed.

[0246] In addition, the system may use task queue management technology (such as RabbitMQ or Apache Kafka) to handle a large number of interpretation texts that need to be reviewed, ensuring that the workload is evenly distributed to different review experts. The system may also monitor the length of the review queue in real time and automatically expand the review resources when necessary.

[0247] In addition, the information in the review queue can also be assigned different levels, with higher levels indicating higher priority for review, so that important tasks can be quickly addressed.

[0248] S204. Receive the revision interpretation text sent by the audit terminal, parse the revision interpretation text, and obtain the revision hierarchical indicator interpretation template library;

[0249] Continuing with the example from the previous step, suppose the review expert modified the interpretation text as follows:

[0250] "This indicator measures the proportion of new pressure ulcers among hospitalized patients within a specific time period. It is an important indicator for assessing the quality of care, patient safety management, and the effectiveness of preventive measures. A lower incidence rate generally indicates that the hospital is performing well in preventing and identifying pressure ulcers early."

[0251] The system receives this revised interpreted text and parses it using natural language processing techniques. Specifically, the system may:

[0252] Keywords and phrases such as "specific time period", "new occurrence", and "effectiveness of preventive measures" are identified using word frequency analysis and phrase extraction techniques.

[0253] Using syntactic analysis techniques to understand text structure, we can identify different parts of the indicator, such as its definition, purpose, and interpretation.

[0254] Named entity recognition technology is used to identify medical terms and concepts such as "pressure ulcer" and "quality of care".

[0255] Text similarity algorithms are used to compare the text before and after revision to identify the key points of expert modification.

[0256] Based on these analyses, the system updates the hierarchical indicator interpretation template library. For example, the system might create or update the following templates:

[0257] Define template: "{Indicator Name} measures the proportion of {Events} in {Measurement Object} within {Time Range}".

[0258] Usage template: "It is an important indicator for evaluating {Evaluation Item 1}, {Evaluation Item 2}, and {Evaluation Item 3}."

[0259] Explanation template: "Indicator names that are {higher / lower} usually indicate {meaning}."

[0260] These templates are stored in a database, which may use a relational database (such as MySQL) or a document-oriented database (such as MongoDB). The system may also use version control technology to track the history of template changes.

[0261] S205. Update the hierarchical indicator interpretation template library according to the revised hierarchical indicator interpretation template library.

[0262] In this step, the system compares and integrates the newly generated revised template with the existing template library. This continuous optimization process ensures that the system can continuously learn and improve, generating more accurate and comprehensive medical quality control indicator interpretation.

[0263] In the above embodiments, the score dimension is established and the interpretation text is scored, which can identify and screen high-quality interpretation texts, ensuring the reliability and consistency of the interpretation results. For interpretation texts that do not meet the standards, the system will send them to the review terminal for manual review, and the interpretation texts after manual review will be more accurate. By receiving and analyzing the revised interpretation texts, the system can continuously update and optimize the hierarchical indicator interpretation template library, so that the system can continuously improve its interpretation ability over time and adapt to the changing needs of medical quality control.

[0264] Next, the system in the embodiments of the present application will be described from the perspective of hardware processing. Please refer to Figure 3 , which is an entity device structure diagram of a medical quality control indicator interpretation system provided by the embodiments of the present application.

[0265] It should be noted that Figure 3 The structure of the system shown is only an example and should not impose any limitations on the functions and use range of the embodiments of the present application.

[0266] As Figure 3 shown, the system includes a central processing unit (CPU) 301, which can perform various appropriate actions and processes according to programs stored in a read-only memory (ROM) 302 or loaded from a storage portion 308 into a random access memory (RAM) 303, such as performing the methods in the above embodiments. In the RAM 303, various programs and data required for system operation are also stored. The CPU 301, the ROM 302, and the RAM 303 are connected to each other through a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.

[0267] The following components are connected to the I / O interface 305: an input section 306 including a camera, a microphone, and the like; an output section 307 including a liquid crystal display (LCD), a speaker, and the like; a storage section 308 including a hard disk and the like; and a communication section 309 including a network interface card such as a LAN (Local Area Network) card, a modem, and the like. The communication section 309 performs a communication process via a network such as the Internet. A drive 310 is also connected to the I / O interface 305 as necessary. A removable medium 311 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, and the like is attached to the drive 310 as necessary, so that a computer program read out therefrom is installed in the storage section 308 as necessary.

[0268] In particular, the processes described above with reference to the flowcharts can be implemented as a computer software program according to embodiments of the present application. For example, embodiments of the present application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing a computer program for executing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network by the communication section 309, and / or installed from the removable medium 311. When the computer program is executed by the central processing unit (CPU) 301, various functions defined in the present application are executed.

[0269] It should be noted that the computer-readable medium in the embodiments of the present application can be a computer-readable signal medium or a computer-readable storage medium or any combination of the two. The computer-readable storage medium may, for example, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or apparatus, or any combination of the above. More specific examples of the computer-readable storage medium can include, but are not limited to, an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disk read-only memory (Compact Disc Read-Only Memory, CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, the computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, device or apparatus. In the present application, the computer-readable signal medium can include a data signal carrying computer-readable computer programs in a baseband or as a part of a carrier wave. Such a propagated data signal can take various forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above.

[0270] The flowcharts and block diagrams in the drawings illustrate the possible implementation architectures, functions and operations of the systems, methods and computer program products according to various embodiments of the present application. In the flowcharts or block diagrams, each block can represent a module, a program segment or a part of code containing one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions noted in the blocks can occur in different orders than that shown in the drawings. For example, two blocks indicated in succession can actually be executed substantially in parallel, and sometimes in reverse order, depending on the functions involved. It should also be noted that each block in the block diagram or flowchart, and the combination of blocks in the block diagram or flowchart, can be implemented by a dedicated hardware-based system that performs the specified functions or operations, or can be implemented by a combination of dedicated hardware and computer instructions.

[0271] As another aspect, the present application also provides a computer readable storage medium, which can be included in the system described in the above embodiments, or can exist independently without being assembled into the system. The above storage medium carries one or more computer programs, which, when executed by a processor of a system, enable the system to implement the method provided in the above embodiments.

[0272] The above embodiments are only used to illustrate the technical solutions of the present application, but not limit the present application; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that they can still make modifications to the technical solutions recorded in the foregoing embodiments, or make equivalent replacements to some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

[0273] In the above embodiments, according to the context, the term "when" can be interpreted as meaning "if" or "after" or "in response to determining" or "in response to detecting". Similarly, according to the context, the phrase "upon determining" or "if detecting (the stated condition or event)" can be interpreted as meaning "if determining" or "in response to determining" or "upon detecting (the stated condition or event)" or "in response to detecting (the stated condition or event)".

[0274] In the above embodiments, all or some of the embodiments can be implemented by software, hardware, firmware or any combination thereof. When implemented by software, all or some of the embodiments can be implemented in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or some of the processes or functions described in the embodiments of the present application are generated. The computer can be a general purpose computer, a special purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer readable storage medium, or transmitted from one computer readable storage medium to another computer readable storage medium, for example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center through wired (such as coaxial cable, optical fiber, digital subscriber line) or wireless (such as infrared, wireless, microwave, etc.) mode. The computer readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. integrated with one or more available media. The available media can be magnetic media (such as floppy disk, hard disk, magnetic tape), optical media (such as DVD), or semiconductor media (such as solid state disk) and the like.

[0275] Those skilled in the art can understand that all or part of the processes in the above-mentioned method embodiments can be implemented by a computer program instructing relevant hardware to complete, the program can be stored in a computer readable storage medium, and the program can include the processes of the above-mentioned method embodiments when executed. The aforementioned storage medium includes ROM or random storage memory RAM, magnetic disc or optical disc and various storage code medium.

Claims

1. A medical quality control indicator interpretation method, characterized by, The method comprises the following steps: constructing a hierarchical index word dictionary, which decomposes index nouns of medical quality control indexes into core words, modifying words and limiting words; establishing an index analysis rule library based on the hierarchical index word dictionary, which comprises hierarchical matching rules, word combination rules and context association rules; using a preset index name standardization algorithm to convert index names in different expression modes into a preset standardized format using the hierarchical index word dictionary and the index analysis rule library, to obtain a plurality of standardized index names; establishing an index semantic mapping matrix, and matching the core words, modifying words and limiting words in the plurality of standardized index names with preset index connotation elements based on the index semantic mapping matrix, to obtain hierarchical semantic mapping results; establishing a hierarchical index interpretation template library to set corresponding interpretation frameworks and key elements for word combinations at different levels; selecting and combining initial template elements from the hierarchical index interpretation template library according to the hierarchical semantic mapping results to generate interpretation texts, wherein the initial template elements are the template elements with the highest similarity to the hierarchical semantic mapping results.

2. The method of claim 1, wherein, The method of constructing a hierarchical index word dictionary specifically comprises: obtaining a set of medical quality control index names, which includes index names published by authoritative agencies, index names used by medical institutions at different levels, index names in medical literature and index names used in clinical practice; defining a word classification standard to decompose the index names in the set of medical quality control index names into core words, modifying words and limiting words, wherein the core words represent the measurement objects of the index names, the modifying words represent words that describe the core words, and the limiting words are words that refine classification conditions; constructing a hierarchical index word dictionary according to the set of medical quality control index names and the word classification standard.

3. The method of claim 2, wherein, The method of defining a word classification standard to decompose the index names in the set of medical quality control index names into core words, modifying words and limiting words specifically comprises: collecting common index core concepts, common modifying words and common limiting words to obtain a word feature library; calculating the similarity between the index names in the set of medical quality control index names and the index core concepts, the common modifying words and the common limiting words to obtain index core concept similarity, modifying similarity and limiting similarity; defining the word classification standard according to the similarity, wherein the word classification standard assigns index names to word categories corresponding to similarity greater than a preset similarity threshold; decomposing the index names in the set of medical quality control index names into core words, modifying words and limiting words according to the word feature library and the word classification standard, wherein the core words are words corresponding to index core concept similarity greater than the preset similarity threshold, the modifying words are words corresponding to modifying similarity greater than the preset similarity threshold, and the limiting words are words corresponding to limiting similarity greater than the preset similarity threshold.

4. The method of claim 3, wherein, After the medical quality control indicator name set is decomposed into core words, modifier words and limit words according to the word feature library and the word classification standard, the method further comprises: obtaining a medical synonym and near-synonym library; identifying synonyms and near-synonyms in the core words, the modifier words and the limit words; converting the synonyms and the near-synonyms into preset standard terms according to the medical synonym and near-synonym library; establishing a mapping table of the synonyms and the near-synonyms and the preset standard terms.

5. The method of claim 1, wherein, After the initial template element is selected and combined in the hierarchical indicator interpretation template library according to the hierarchical semantic mapping result to generate an interpretation text, the method further comprises: establishing a scoring dimension and scoring the interpretation text using the scoring dimension to obtain a consistency score; in a case where the consistency score is greater than a preset threshold, marking the interpretation text as a qualified text; in a case where the consistency score is not greater than the preset threshold, sending the interpretation text to an auditing terminal; receiving a revised interpretation text sent by the auditing terminal and parsing the revised interpretation text to obtain a revised hierarchical indicator interpretation template library; updating the hierarchical indicator interpretation template library according to the revised hierarchical indicator interpretation template library.

6. The method of claim 5, wherein, The establishment of the scoring dimension specifically comprises: determining a corresponding core word accuracy according to the core word and the main measurement concept; determining a corresponding modifier word appropriateness according to the modifier word and the core word; determining a corresponding limit word explicitness according to the limit word and the indicator noun; determining a corresponding interpretation integrity according to all key elements contained in the interpretation text and the indicator noun; respectively giving the core word accuracy, the modifier word appropriateness, the limit word explicitness and the interpretation integrity to calculate corresponding weights to obtain a scoring dimension.

7. The method according to claim 5 or 6, characterized in that, The scoring of the interpretation text using the scoring dimension to obtain a consistency score specifically comprises: using a weighted average algorithm to calculate the consistency score corresponding to the interpretation text according to the scoring dimension; the calculation function in the weighted average algorithm is: N = a × S + b × Y + c × Z + d × M In the function, N is the consistency score, a is the weight corresponding to the consistency score, S is the core word accuracy, b is the weight corresponding to the modifier word appropriateness, Y is the modifier word appropriateness, c is the weight corresponding to the limit word explicitness, Z is the limit word explicitness, d is the weight corresponding to the interpretation integrity, M is the interpretation integrity, and the sum of a, b, c and d is 1.

8. A medical quality control indicator interpretation system characterized by, The system comprises: one or more processors and a memory; the memory is coupled with the one or more processors, the memory is used to store computer program code, the computer program code comprises computer instructions, and the one or more processors invoke the computer instructions to enable the system to perform the method of any one of claims 1-7.

9. A computer-readable storage medium comprising instructions, characterized in that, When the instructions are executed on the system, the system is caused to perform the method of any one of claims 1-7.

10. A computer program product, characterised in that, When the computer program product is run on the system, the system is caused to perform the method of any one of claims 1-7.

Images