Medical service quality analysis method, system, equipment and medium

Abstract

The invention provides a medical service quality analysis method, system and device and a medium, and the analysis method comprises the steps: obtaining medical service evaluation data of each medical institution, and screening variable data from the medical service evaluation data; performing integrity processing and standardization processing on the variable data to enable the processed variable data to meet integrity requirements and standardization requirements; performing principal component analysis on the processed variable data to generate an analysis result; analysis results are interpreted and analyzed through an AI large model, and corresponding optimization decision suggestions are given. The public factors are extracted through principal component analysis, and the data structure is simplified; an analysis result is interpreted and analyzed through an AI large model to provide decision suggestions, so that the requirement of a manager on statistical professional knowledge is reduced, meanwhile, the complexity and the labor cost of an analysis process are reduced, and the analysis efficiency is improved; and the analysis result is displayed in a visual form, so that the performance conditions of the medical service in different aspects can be reflected more intuitively.

Description

Technical Field

[0001] The present disclosure relates to the field of medical technology, and in particular to a method, system, device and medium for analyzing the quality of medical services. Background Art

[0002] With the rapid development of medical technology and people's growing demand for health, how to scientifically and objectively evaluate the quality of medical services and discover the advantages and disadvantages of medical services has become a key difficulty in improving the level of medical services and optimizing resource allocation. Summary of the invention

[0003] The technical problem to be solved by the present disclosure is to overcome the above-mentioned defects in the prior art and to provide a method, system, device and medium for analyzing the quality of medical services.

[0004] The present invention solves the above technical problems through the following technical solutions:

[0005] The present disclosure provides a method for analyzing medical service quality, the method comprising:

[0006] Obtaining medical service evaluation data of various medical institutions, and filtering variable data from the medical service evaluation data;

[0007] Performing integrity processing and standardization processing on the variable data so that the processed variable data meets integrity requirements and standardization requirements;

[0008] Performing principal component analysis on the processed variable data to generate analysis results;

[0009] The analysis results are interpreted and analyzed through the AI ​​big model, and corresponding optimization decision suggestions are given; wherein the AI ​​big model is built based on the big language model.

[0010] Optionally, obtaining the medical service evaluation data of each medical institution includes:

[0011] Obtaining original data of the medical institution from a hospital data center and / or a medical data system; the original data includes at least one of electronic medical records, patient satisfaction surveys, medical equipment records, and medical staff information;

[0012] The medical service evaluation data is extracted from the original data; the medical service evaluation data includes at least one of the medical technology level, medical facility conditions, medical staff quality, and medical service attitude, which are statistically analyzed by department or section.

[0013] Optionally, performing principal component analysis on the processed variable data includes:

[0014] Extracting common factors from the processed variable data according to the factor loadings to obtain a factor loading matrix;

[0015] The factor loading matrix is ​​transformed by factor rotation to show the relationship between the variable data and the potential factors, and the actual significance of each potential factor is analyzed based on the transformed factor loading matrix to obtain the score of each department in the medical institution on each factor.

[0016] Optionally, performing principal component analysis on the processed variable data further includes:

[0017] Each of the potential factors is named according to the transformed factor loading matrix.

[0018] Optionally, interpreting and analyzing the analysis results by using the AI ​​big model includes:

[0019] A dynamic prompt is constructed through engineering to interact with the AI ​​big model, and decision recommendations are made based on the output results of the analysis results by the AI ​​big model.

[0020] Optionally, the analysis method further comprises:

[0021] The analysis results are visualized, and a visualization scheme of a graphic series is used to provide a visualization basis support for the analysis; the graphic series includes: at least one of a scree plot, a factor loading plot, a variable clustering plot, a factor score plot, a radar plot, a heat map, a scatter plot, and a bar chart.

[0022] Optionally, the analysis method further comprises:

[0023] During the construction of the AI ​​big model, the pre-constructed factor analysis professional pre-training data set is input into the big language model for pre-training to obtain a first model;

[0024] Inputting the pre-constructed first question-answer pair fine-tuning dataset into the first model for fine-tuning training to obtain a second model;

[0025] The second model is used as the AI ​​big model.

[0026] The present disclosure also provides a medical service quality analysis system, the analysis system comprising: an acquisition module, a data processing module, a principal component analysis module and an AI interpretation analysis module;

[0027] The acquisition module is used to acquire the medical service evaluation data of each medical institution and filter out variable data from the medical service evaluation data;

[0028] The data processing module is used to perform integrity processing and standardization processing on the variable data, so that the processed variable data meets the integrity requirements and standardization requirements;

[0029] The principal component analysis module is used to perform principal component analysis on the processed variable data to generate analysis results;

[0030] The AI ​​interpretation and analysis module is used to interpret and analyze the analysis results through the AI ​​big model and give corresponding optimization decision suggestions; wherein, the AI ​​big model is built based on the big language model.

[0031] The present disclosure also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and used to run on the processor, and the processor implements the aforementioned medical service quality analysis method when executing the computer program.

[0032] The present disclosure also provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the aforementioned medical service quality analysis method is implemented.

[0033] On the basis of being in accordance with the common sense in the art, the above-mentioned preferred conditions can be arbitrarily combined to obtain the preferred embodiments of the present disclosure.

[0034] The positive progressive effects of the present disclosure are: extracting a few independent common factors from a large amount of complex data through principal component analysis (factor analysis), and the obtained common factors can reflect most of the information of the original variables, thereby simplifying the data structure; interpreting and analyzing the analysis results of the principal component analysis through the AI ​​big model to provide decision-making suggestions, reducing the requirements of managers for statistical expertise, while reducing the complexity and labor costs of the analysis process and improving analysis efficiency; in addition, displaying the analysis results in visual forms such as graphics and images can more intuitively reflect the performance of medical services in different aspects, provide scientific and objective decision-making support for medical institution managers and policy makers, and facilitate decision makers to quickly grasp the essence of the problem to formulate targeted improvement measures, thereby promoting the continuous improvement and enhancement of the quality of medical services. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 A flowchart of a method for analyzing medical service quality provided in Example 1 of the present disclosure;

[0036] Figure 2 A flowchart of a specific implementation of step S11 of a method for analyzing medical service quality provided in Example 1 of the present disclosure;

[0037] Figure 3A flowchart of a specific implementation of step S13 of a method for analyzing medical service quality provided in Example 1 of the present disclosure;

[0038] Figure 4 A flowchart of a specific implementation of a method for analyzing medical service quality provided in Example 1 of the present disclosure;

[0039] Figure 5 A flowchart of another specific implementation of a method for analyzing medical service quality provided in Example 1 of the present disclosure;

[0040] Figure 6 A schematic diagram of a module of a medical service quality analysis system provided in Embodiment 1 of the present disclosure;

[0041] Figure 7 A schematic diagram of the structure of an electronic device provided in Embodiment 3 of the present disclosure. DETAILED DESCRIPTION

[0042] The present disclosure is further described below by way of examples, but the present disclosure is not limited to the scope of the examples.

[0043] Prefixes such as "first" and "second" are used in the embodiments of the present disclosure only to distinguish different description objects, and have no limiting effect on the position, order, priority, quantity or content of the described objects. The use of prefixes such as ordinal numbers to distinguish description objects in the embodiments of the present disclosure does not constitute a limitation on the described objects. For the statement of the described objects, please refer to the description in the context of the embodiments, and no unnecessary limitation should be constituted due to the use of such prefixes. In addition, in the description of the present embodiment, unless otherwise specified, the meaning of "plurality" is two or more.

[0044] Example 1

[0045] Figure 1 A flowchart of a method for analyzing medical service quality provided by an exemplary embodiment of the present disclosure, the analysis method comprising:

[0046] S11. Obtain the medical service evaluation data of each medical institution, and filter out variable data from the medical service evaluation data.

[0047] S12. Perform integrity processing and standardization processing on the variable data so that the processed variable data meets the integrity requirements and standardization requirements.

[0048] S13. Perform principal component analysis on the processed variable data to generate analysis results.

[0049] S14. Use the AI ​​big model to interpret and analyze the analysis results and give corresponding optimization decision suggestions. The AI ​​big model is built based on the big language model.

[0050] In order to have an objective, accurate and scientific evaluation of the quality of medical services, this embodiment mainly screens relevant data variables around four aspects, namely medical technology, patient satisfaction, medical efficiency and medical cost. Data sources can be widely collected from different data sources, electronic medical records, patient satisfaction surveys, medical equipment filings and other aspects. At the same time, correlation analysis is performed on the collected data to eliminate variables that are irrelevant to the research purpose or have extremely low correlation, thereby improving data quality.

[0051] Data processing is performed on the screened variable data to check the integrity of the data and ensure that there are no too many missing values ​​or outliers. Outliers can be eliminated. For variables with too many missing values, they can be eliminated or filled. At the same time, the variable data is standardized to eliminate the dimensional differences between different variable data and ensure that variable data at different latitudes can be associated with each other. In addition, factor analysis does not have strict requirements on the normality of the data, but if the data deviates seriously from the normal distribution, it may affect the results of the factor analysis. Therefore, preferably, the variable data can be tested for normality and appropriate transformations (such as logarithmic transformation, square root transformation, etc.) can be performed to improve the normality of the data.

[0052] The KMO test (Kaiser-Meyer-Olkin test) can be used to evaluate the common measure between variables (variable data) in the data set, that is, the prevalence and size of the correlation between variables. The Bartlett test can be used to test whether the correlation matrix between all variables (variable data) in the data set is the unit matrix (that is, the variables are independent of each other).

[0053] Principal component analysis (i.e. factor analysis) as a multivariate statistical analysis method has unique advantages in revealing the internal structure of data and the relationship between variables. It can effectively extract a few independent common factors from a large amount of complex data. The obtained common factors can reflect most of the information of the original variables, thereby simplifying the data structure and facilitating subsequent analysis.

[0054] The processed variables are subjected to principal component analysis, common factors are extracted according to their factor loadings, the loading matrix is ​​transformed through factor rotation, and the relationship between variables and factors is displayed. Based on the transformed factor loading matrix, each potential factor can be explained and named, and its practical significance can be analyzed.

[0055] In the evaluation of medical service quality, factor analysis can be used to obtain the key factors affecting medical service quality, such as medical technology level, service efficiency, patient satisfaction, etc., to provide a scientific basis for improving service quality.

[0056] The factor analysis results can be displayed in the form of graphics, images, etc. by combining visualization technology.

[0057] By using AI big model technology to interpret and analyze the results of factor analysis and provide decision-making recommendations, it not only reduces managers' requirements for statistical expertise, but also reduces the complexity and labor costs of the analysis process, thereby improving analysis efficiency.

[0058] The visual analysis method of medical service advantages and disadvantages based on AI big model + factor analysis collects data related to medical service quality, uses factor analysis technology to extract key factors, and combines visualization methods and AI big model to present the analysis results in an intuitive and easy-to-understand way, providing scientific and objective decision-making support for medical institution managers and policy makers, and promoting the continuous improvement and enhancement of medical service quality.

[0059] In this embodiment, principal component analysis (factor analysis) is used to extract a few independent common factors from a large amount of complex data. The obtained common factors can reflect most of the information of the original variables, thereby simplifying the data structure; the analysis results of the principal component analysis are interpreted and analyzed by the AI ​​big model to provide decision-making suggestions, which reduces the requirements of managers for statistical expertise, while reducing the complexity and labor costs of the analysis process and improving analysis efficiency; in addition, the analysis results are displayed in visual forms such as graphics and images, which can more intuitively reflect the performance of medical services in different aspects, provide scientific and objective decision-making support for medical institution managers and policy makers, and facilitate decision makers to quickly grasp the essence of the problem to formulate targeted improvement measures, thereby promoting the continuous improvement and enhancement of the quality of medical services.

[0060] In one embodiment, referring to Figure 2 , in step S11, "obtaining medical service evaluation data of each medical institution" includes:

[0061] S111. Obtaining original data of a medical institution from a hospital data center and / or a medical data system. The original data includes at least one of electronic medical records, patient satisfaction surveys, medical equipment records, and medical staff information.

[0062] S112, extracting medical service evaluation data from the original data. The medical service evaluation data includes at least one of medical technology level, medical facility conditions, medical staff quality, and medical service attitude, which are statistically analyzed by department or section.

[0063] In order to have an objective, accurate and scientific evaluation of the quality of medical services, this embodiment mainly screens relevant data variables around four aspects, namely medical technology, patient satisfaction, medical efficiency and medical cost. Data sources can be widely collected from different data sources, electronic medical records, patient satisfaction surveys, medical equipment filings and other aspects.

[0064] In one embodiment, referring to Figure 3 , in step S13, "performing principal component analysis on the processed variable data" includes:

[0065] S131. Extract common factors from the processed variable data according to the factor loadings to obtain a factor loading matrix.

[0066] S132. The factor loading matrix is ​​transformed through factor rotation to show the relationship between variable data and potential factors, and the actual significance of each potential factor is analyzed based on the transformed factor loading matrix to obtain the score of each department in the medical institution on each factor.

[0067] Among them, principal component analysis (i.e. factor analysis), as a multivariate statistical analysis method, has unique advantages in revealing the internal structure of data and the relationship between variables. It can effectively extract a few independent common factors from a large amount of complex data, and the obtained common factors can reflect most of the information of the original variables, thereby simplifying the data structure and facilitating subsequent analysis.

[0068] The processed variables are subjected to principal component analysis, common factors are extracted according to their factor loadings, the loading matrix is ​​transformed through factor rotation, and the relationship between variables and factors is displayed. Based on the transformed factor loading matrix, each potential factor can be interpreted and its practical significance analyzed.

[0069] Specifically, factor extraction: use principal component analysis to extract factors, and determine the extracted common factors and their number based on the calculated eigenvalue size and cumulative contribution rate (common factors with a contribution rate of more than 85%). Factor rotation: rotate the extracted factors by performing varimax rotation or varimax rotation on the common factors obtained using principal component analysis to more clearly explain the factor structure. The rotated factors should have clear practical significance and be able to reflect the main information of the original variables. Factor score calculation: substitute the original variable data of each department into the factor score calculation formula to calculate the scores of each department in the hospital on each factor. The scores reflect the performance of each department in the hospital in different aspects.

[0070] In one embodiment, the step S13 of “performing principal component analysis on the processed variable data” further includes:

[0071] Each potential factor is named according to the transformed factor loading matrix.

[0072] Among them, each potential factor can be named and explained according to the variable source of the factor and its composition. For example, it can be named "medical technology level factor", "medical facility condition factor", "medical service attitude factor", etc.

[0073] In one embodiment, in step S14, “interpreting and analyzing the analysis results by using the AI ​​big model” includes:

[0074] Through engineering, dynamic prompts are constructed to interact with the AI ​​big model, and decision recommendations are made based on the output of the analysis results of the AI ​​big model.

[0075] Among them, the analysis results are interpreted and analyzed through the AI ​​big model, and relevant optimization suggestions are given to provide scientific and objective decision-making support for medical institution managers and policy makers, thereby promoting the continuous improvement and enhancement of medical service quality.

[0076] In one embodiment, the analysis method further comprises:

[0077] Visualize the analysis results and provide visualization support for the analysis through a series of visualization schemes. The series of graphics includes at least one of: scree plot, factor loading plot, variable cluster plot, factor score plot, radar plot, heat map, scatter plot, and bar chart.

[0078] Among them, the factor analysis results are displayed in the form of graphics and images by combining visualization technology, and the factor analysis process is visualized through scree plots, factor loading plots, variable clustering plots, factor score plots, etc., providing visualization support for the final factor analysis results. The scores, differences, similarities and differences, and advantages and disadvantages of each department and section of the hospital in each factor are displayed through radar charts, heat maps, scatter plots, bar charts, etc., which can more intuitively reflect the performance of medical services in different aspects, making it easier for decision makers to quickly grasp the essence of the problem and formulate targeted improvement measures.

[0079] In one embodiment, referring to Figure 4 , the analysis method also includes:

[0080] S21. During the construction of the AI ​​big model, the pre-constructed factor analysis professional pre-training data set is input into the big language model for pre-training to obtain the first model.

[0081] S22. Input the pre-constructed first question-answer pair fine-tuning dataset into the first model for fine-tuning training to obtain a second model.

[0082] S23. Use the second model as the AI ​​big model.

[0083] After the AI ​​big model is built, an access interface is provided to the outside world. During factor analysis, the dynamic prompt is constructed through engineering to interact with the big model and make decision recommendations based on the results. The constructed AI big model is consistent with the actual situation, which improves the accuracy of decision recommendations.

[0084] In one embodiment, referring to Figure 5 After step S22, the analysis method further includes:

[0085] S24. Mount the knowledge base on the second model, correct the inaccurate information, and store the corrected information in the knowledge base in the form of question-answer pairs.

[0086] S25. When the number of new information after correction reaches a preset threshold, a second question-answer pair fine-tuning dataset is constructed from the corrected information, and the second question-answer pair fine-tuning dataset is input into the second model for fine-tuning training to obtain a fine-tuned second model.

[0087] At this time, the fine-tuned second model is used as the AI ​​big model.

[0088] Multiple rounds of fine-tuning can be performed continuously to continuously improve the accuracy of the AI ​​large model, so that the AI ​​large model can be continuously updated and keep in line with the actual situation.

[0089] The following is an example of an analytical approach to implementing quality of care.

[0090] Step (1) Variable acquisition:

[0091] Determine the variable indicators for data acquisition, extract medical service evaluation data from the hospital's data centers and medical data systems, including indicator data in multiple dimensions such as medical technology level, medical facility conditions, medical staff quality, and medical service attitude among different departments, and store the data separately.

[0092] Step (2) Data processing:

[0093] Process the stored variable data. Data integrity processing, i.e., missing values ​​and outlier processing. For variables with too many missing values, you can consider removing or filling them. Data standardization processing: Use the Z-score standardization method to standardize different variables so that their mean is 0 and their variance is 1, eliminating the dimensional differences between different variables. Data normality test: To ensure the accuracy and credibility of the factor analysis results, you can perform a normality test on the data, and consider appropriate transformations (such as logarithmic transformation, square root transformation, etc.) to improve the normality of the data.

[0094] Step (3) Factor analysis feasibility verification:

[0095] The KMO test and Bartlett test results of the variables after the original data processing are used to judge whether the current data is suitable for factor analysis. Usually, the judgment standard of the KMO value is 0.6. When the KMO value is greater than 0.6, it means that the current data can be analyzed by factor analysis. Otherwise, it is not suitable for analysis. Through the Bartlett test, when the corresponding P value is less than 0.05, factor analysis can be used, otherwise it is not suitable for analysis.

[0096] Step (4) Factor extraction:

[0097] The principal component analysis method is used to extract factors, and the extracted common factors and their number are determined based on the calculated eigenvalue size and cumulative contribution rate (common factors with a contribution rate of more than 85%).

[0098] Step (5) Factor rotation:

[0099] By performing varimax rotation or varimax rotation on the common factors obtained by principal component analysis, the extracted factors are rotated to explain the factor structure more clearly. The rotated factors should have clear practical significance and reflect the main information of the original variables.

[0100] Step (6) Factor naming explanation:

[0101] According to the rotated factor loading matrix, the extracted factors are named and explained. They can be named and explained according to the variable sources and composition of the factors, for example, they can be named "medical technology level factor", "medical facility condition factor", "medical service attitude factor", etc.

[0102] Step (7) Factor score calculation:

[0103] Substitute the original variable data of each department into the factor score calculation formula to calculate the score of each department in the hospital on each factor. The score reflects the performance of each department in the hospital in different aspects.

[0104] Step (8) Visualization and decision-making suggestions:

[0105] The factor analysis process is visualized through scree plots, factor loading plots, variable clustering plots, factor score plots, etc., providing visual support for the final factor analysis results. Radar charts, heat maps, scatter plots, bar charts, etc. are used to display the scores, differences, similarities, differences, and advantages and disadvantages of each department of the hospital in each factor. The AI ​​big model is used to interpret and analyze the analysis results, and relevant optimization suggestions are given to provide scientific and objective decision-making support for medical institution managers and policy makers, and promote the continuous improvement and enhancement of medical service quality.

[0106] In general, the method for analyzing the quality of medical services in this embodiment has the following advantages:

[0107] (1) Reduce data dimensions: Factor analysis can significantly reduce the number of variables, extract the key factors that affect the quality of medical services, and make the evaluation process more concise and efficient.

[0108] (2) Provide objective data support: The conclusions drawn through statistical methods avoid the influence of subjective factors on the evaluation results and improve the objectivity and accuracy of the evaluation.

[0109] (3) Clarify the direction of improvement: Factor analysis can identify the weaknesses and strengths in medical services, provide comprehensive, in-depth and specific directions for improvement for medical institutions, and help improve the overall service level.

[0110] (4) Visual analysis: Combined with data visualization technology, the results of factor analysis are presented in the form of charts, graphs, etc., so that decision makers and patients can more intuitively understand the current status and room for improvement of medical service quality.

[0111] (5) AI large model analysis: By interpreting and analyzing the results of the analysis and providing decision-making recommendations, the complexity of the analysis process is reduced.

[0112] Example 2

[0113] Corresponding to the aforementioned embodiment of the method for analyzing the quality of medical services, the present disclosure also provides an embodiment of a system for analyzing the quality of medical services.

[0114] Figure 6 A module diagram of a medical service quality analysis system provided for an exemplary embodiment of the present disclosure, the system comprising: an acquisition module 1, a data processing module 2, a principal component analysis module 3 and an AI interpretation and analysis module 4.

[0115] The acquisition module 1 is used to acquire the medical service evaluation data of each medical institution and filter out variable data from the medical service evaluation data.

[0116] The data processing module 2 is used to perform integrity processing and standardization processing on the variable data so that the processed variable data meets the integrity requirements and standardization requirements.

[0117] The principal component analysis module 3 is used to perform principal component analysis on the processed variable data to generate analysis results.

[0118] The AI ​​interpretation and analysis module 4 is used to interpret and analyze the analysis results through the AI ​​big model and give corresponding optimization decision suggestions. Among them, the AI ​​big model is built based on the big language model.

[0119] In this embodiment, principal component analysis (factor analysis) is used to extract a few independent common factors from a large amount of complex data. The obtained common factors can reflect most of the information of the original variables, thereby simplifying the data structure; the analysis results of the principal component analysis are interpreted and analyzed by the AI ​​big model to provide decision-making suggestions, which reduces the requirements of managers for statistical expertise, while reducing the complexity and labor costs of the analysis process and improving analysis efficiency; in addition, the analysis results are displayed in visual forms such as graphics and images, which can more intuitively reflect the performance of medical services in different aspects, provide scientific and objective decision-making support for medical institution managers and policy makers, and facilitate decision makers to quickly grasp the essence of the problem to formulate targeted improvement measures, thereby promoting the continuous improvement and enhancement of the quality of medical services.

[0120] In one embodiment, the acquisition module 1 is also used to acquire the original data of the medical institution from the hospital data center and / or the medical data system. The original data includes at least one of electronic medical records, patient satisfaction surveys, medical equipment records and medical staff information.

[0121] The acquisition module 1 is also used to extract medical service evaluation data from the original data. The medical service evaluation data includes at least one of the medical technology level, medical facility conditions, medical staff quality, and medical service attitude, which are statistically analyzed by department or section.

[0122] In one embodiment, the principal component analysis module 3 is further used to extract common factors from the processed variable data according to the factor loadings to obtain a factor loading matrix.

[0123] The principal component analysis module 3 is also used to transform the factor loading matrix through factor rotation to show the relationship between variable data and potential factors, and analyze the actual significance of each potential factor based on the transformed factor loading matrix to obtain the score of each department in the medical institution on each factor.

[0124] In one embodiment, the principal component analysis module 3 is further used to name each potential factor according to the converted factor loading matrix.

[0125] In one embodiment, the AI ​​interpretation and analysis module 4 is also used to construct a dynamic prompt through engineering tInteract with the AI ​​big model and make decision recommendations based on the output of the analysis results of the AI ​​big model.

[0126] In one embodiment, the analysis system further includes: a visualization module 5 .

[0127] The visualization module 5 is used to visualize the analysis results and provide visualization support for the analysis through a visualization scheme of a graphic series. The graphic series includes: at least one of a scree plot, a factor loading plot, a variable clustering plot, a factor score plot, a radar plot, a heat map, a scatter plot, and a bar chart.

[0128] In one embodiment, the analysis system further includes: an AI big model building module 6.

[0129] The AI ​​big model construction module 6 is used to input the pre-constructed factor analysis professional pre-training data set into the big language model for pre-training during the construction process of the AI ​​big model to obtain the first model.

[0130] The AI ​​big model construction module 6 is also used to input the pre-constructed first question-answer pair fine-tuning data set into the first model for fine-tuning training to obtain the second model.

[0131] The AI ​​big model building module 6 is also used to use the second model as the AI ​​big model.

[0132] In one embodiment, the AI ​​large model construction module 6 is also used to mount the knowledge base on the second model, correct the inaccurate information, and store the corrected information in the knowledge base in the form of question and answer pairs.

[0133] The AI ​​big model construction module 6 is also used to construct a second question-answer pair fine-tuning data set from the corrected information when the number of new information after correction reaches a preset threshold, and input the second question-answer pair fine-tuning data set into the second model for fine-tuning training to obtain a fine-tuned second model.

[0134] At this time, the AI ​​big model construction module 6 is also used to use the fine-tuned second model as the AI ​​big model.

[0135] As for the system embodiment, since it basically corresponds to the method embodiment, the relevant parts can refer to the partial description of the method embodiment. The system embodiment described above is only illustrative, wherein the units described as separate components may or may not be physically separated, and the components as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the disclosed solution.

[0136] Example 3

[0137] Figure 7 This is a structural diagram of an electronic device shown in an example embodiment of the present disclosure, the electronic device includes a memory, a processor, and a computer program stored in the memory and used to run on the processor, and when the processor executes the computer program, the method for analyzing the quality of medical services described in any of the above embodiments is implemented. Figure 7 The electronic device 90 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0138] like Figure 7 As shown, the electronic device 90 may be in the form of a general-purpose computing device, for example, it may be a server device. The components of the electronic device 90 may include, but are not limited to: at least one processor 91, at least one memory 92, and a bus 93 connecting different system components (including the memory 92 and the processor 91).

[0139] The bus 93 includes a data bus, an address bus, and a control bus.

[0140] The memory 92 may include a volatile memory, such as a random access memory (RAM) 921 and / or a cache memory 922 , and may further include a read-only memory (ROM) 923 .

[0141] The memory 92 may also include a program tool 925 (or utility) having a set (at least one) of program modules 924, such program modules 924 including but not limited to: an operating system, one or more application programs, other program modules and program data, each of which or some combination may include an implementation of a network environment.

[0142] The processor 91 executes various functional applications and data processing by running the computer program stored in the memory 92, such as the analysis method of medical service quality provided by any of the above embodiments.

[0143] The electronic device 90 may also communicate with one or more external devices 94 (e.g., keyboards, pointing devices, etc.). Such communication may be performed via an input / output (I / O) interface 95. Furthermore, the electronic device 90 may also communicate with one or more networks (e.g., local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) via a network adapter 96. As shown, the network adapter 96 communicates with other modules of the electronic device 90 via a bus 93. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the electronic device 90, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID (disk array) systems, tape drives, and data backup storage systems, etc.

[0144] It should be noted that although several units / modules or sub-units / modules of the electronic device are mentioned in the above detailed description, this division is merely exemplary and not mandatory. In fact, according to the embodiments of the present disclosure, the features and functions of two or more units / modules described above can be embodied in one unit / module. Conversely, the features and functions of one unit / module described above can be further divided into multiple units / modules to be embodied.

[0145] Example 4

[0146] The embodiments of the present disclosure also provide a computer-readable storage medium having a computer program stored thereon, and when the program is executed by a processor, the method for analyzing the quality of medical services provided by any of the above embodiments is implemented.

[0147] The readable storage medium may include but is not limited to: a portable disk, a hard disk, a random access memory, a read-only memory, an erasable programmable read-only memory, an optical storage device, a magnetic storage device or any suitable combination of the above.

[0148] Example 5

[0149] The present disclosure also provides a computer program product, including a computer program, which, when executed by a processor, implements any of the above-mentioned methods for analyzing the quality of medical services.

[0150] Among them, the program code for executing the computer program product of the present disclosure can be written in any combination of one or more programming languages, and the program code can be executed completely on the user device, partially on the user device, as an independent software package, partially on the user device and partially on a remote device, or completely on the remote device.

[0151] Although the specific embodiments of the present disclosure are described above, those skilled in the art should understand that this is only an example, and the protection scope of the present disclosure is defined by the appended claims. Those skilled in the art may make various changes or modifications to these embodiments without departing from the principles and essence of the present disclosure, but these changes and modifications all fall within the protection scope of the present disclosure.

Claims

1. A method for analyzing the quality of medical services, characterized in that: The analysis method comprises: Obtaining medical service evaluation data of various medical institutions, and filtering variable data from the medical service evaluation data; Performing integrity processing and standardization processing on the variable data so that the processed variable data meets integrity requirements and standardization requirements; Performing principal component analysis on the processed variable data to generate analysis results; The analysis results are interpreted and analyzed through the AI ​​big model, and corresponding optimization decision suggestions are given; wherein the AI ​​big model is built based on the big language model.

2. The method for analyzing the quality of medical services according to claim 1, characterized in that: The obtaining of medical service evaluation data of each medical institution includes: Obtaining original data of the medical institution from a hospital data center and / or a medical data system; the original data includes at least one of electronic medical records, patient satisfaction surveys, medical equipment records, and medical staff information; The medical service evaluation data is extracted from the original data; the medical service evaluation data includes at least one of the medical technology level, medical facility conditions, medical staff quality, and medical service attitude, which are statistically analyzed by department or section.

3. The method for analyzing the quality of medical services according to claim 1, characterized in that: The performing principal component analysis on the processed variable data comprises: Extracting common factors from the processed variable data according to the factor loadings to obtain a factor loading matrix; The factor loading matrix is ​​transformed by factor rotation to show the relationship between the variable data and the potential factors, and the actual significance of each potential factor is analyzed based on the transformed factor loading matrix to obtain the score of each department in the medical institution on each factor.

4. The method for analyzing the quality of medical services according to claim 3, characterized in that: The performing principal component analysis on the processed variable data further includes: Each of the potential factors is named according to the transformed factor loading matrix.

5. The method for analyzing the quality of medical services according to claim 1, characterized in that: The analysis results are interpreted and analyzed by the AI ​​big model, including: A dynamic prompt is constructed through engineering to interact with the AI ​​big model, and decision recommendations are made based on the output results of the analysis results by the AI ​​big model.

6. The method for analyzing the quality of medical services according to claim 1, characterized in that: The analysis method further comprises: The analysis results are visualized, and a visualization scheme of a graphic series is used to provide a visualization basis support for the analysis; the graphic series includes: at least one of a scree plot, a factor loading plot, a variable clustering plot, a factor score plot, a radar plot, a heat map, a scatter plot, and a bar chart.

7. The method for analyzing the quality of medical services according to claim 1, characterized in that: The analysis method further comprises: During the construction of the AI ​​big model, the pre-constructed factor analysis professional pre-training data set is input into the big language model for pre-training to obtain a first model; Inputting the pre-constructed first question-answer pair fine-tuning dataset into the first model for fine-tuning training to obtain a second model; The second model is used as the AI ​​big model.

8. A medical service quality analysis system, characterized in that: The analysis system includes: an acquisition module, a data processing module, a principal component analysis module and an AI interpretation and analysis module; The acquisition module is used to acquire the medical service evaluation data of each medical institution and filter out variable data from the medical service evaluation data; The data processing module is used to perform integrity processing and standardization processing on the variable data, so that the processed variable data meets the integrity requirements and standardization requirements; The principal component analysis module is used to perform principal component analysis on the processed variable data to generate analysis results; The AI ​​interpretation and analysis module is used to interpret and analyze the analysis results through the AI ​​big model and give corresponding optimization decision suggestions; wherein, the AI ​​big model is built based on the big language model.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and used to run on the processor, characterized in that: When the processor executes the computer program, the method for analyzing the quality of medical services according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for analyzing the quality of medical services according to any one of claims 1 to 7 is implemented.

Images