Nationwide grassroots lung function technician management platform

Abstract

The invention provides a national grassroots lung function technician management platform, and relates to the technical field of medical health information. The platform comprises a user management module for technicians to register and log in the national grassroots lung function technician management platform; the training learning module is used for providing theoretical knowledge related to lung function examination on line, supporting videos, documents and simulation exercises, and carrying out intelligent course recommendation according to the current learning state of a technician; the assessment and authentication module is used for assessing technicians and issuing certificates when the technicians pass the assessment; the continuous education module is used for regularly pushing updated courses for technicians and setting a regular reexamination and assessment interactive communication module for the technicians to issue questions and leave messages; and the data analysis module is used for displaying the number and the overall level of technicians in different areas and optimizing the resource allocation of primary lung function technicians.

Description

Technical Field

[0001] The present invention relates to the field of medical health information technology, and in particular to a national grassroots pulmonary function technician management platform. Background Art

[0002] As an important means of diagnosing chronic obstructive pulmonary disease and other respiratory diseases, pulmonary function tests have become an indispensable examination item in the medical field. Pulmonary function tests can not only help doctors accurately diagnose the condition and formulate reasonable treatment plans, but also play a key role in the prevention and management of diseases. However, despite the important medical significance of pulmonary function test technology, primary medical institutions face many challenges in the implementation of pulmonary function tests.

[0003] Traditional training for pulmonary function technicians is usually offline centralized training, organized by provincial medical institutions or hospitals, and mainly conducted through face-to-face explanations and practical operations. The training content covers the basic theory of pulmonary function tests, equipment operation skills, diagnosis and treatment methods of common pulmonary function abnormalities, etc. The training is generally taught by experts, and trainees learn through lectures, discussions, and practical operations. In addition, the allocation of technician resources usually relies on the experience of local medical institutions or management departments, and technicians are dispatched through manual decision-making.

[0004] However, the existing training methods use uniform teaching content and progress, and cannot be adjusted according to the basic level and learning progress of each technician, resulting in some trainees learning too fast or too slow in certain areas, affecting the learning effect. In addition, the existing allocation of technician resources relies on manual decisions based on the experience of local medical institutions or management departments, resulting in uneven resource allocation, affecting the overall resource utilization and service quality. Summary of the invention

[0005] In order to solve the existing training methods, unified teaching content and progress are adopted, which cannot be adjusted according to the basic level and learning progress of each technician, resulting in some trainees learning too fast or too slow in certain areas, affecting the learning effect. In addition, the existing technician resource allocation relies on manual decision-making based on the experience of local medical institutions or management departments, resulting in uneven resource allocation, affecting the overall resource utilization and service quality. The present invention provides a national grassroots pulmonary function technician management platform.

[0006] The technical solution provided by the embodiment of the present invention is as follows:

[0007] The embodiment of the present invention provides a national grassroots pulmonary function technician management platform, including:

[0008] A user management module, used for technicians to register and log in to the national grassroots pulmonary function technician management platform;

[0009] The training and learning module is used to provide online theoretical knowledge related to pulmonary function tests, support videos, documents and simulation exercises, and make intelligent course recommendations based on the technician's current learning status;

[0010] The assessment and certification module is used to assess technicians. When technicians pass the assessment, a certificate of qualification is issued;

[0011] Continuing education module, used to regularly push updated courses to technicians and set up regular reviews and assessments;

[0012] Interactive communication module, for technicians to post questions and leave messages;

[0013] The data analysis module is used to display the number and overall level of technicians in different regions and optimize the resource allocation of grassroots pulmonary function technicians.

[0014] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0015] (1) In the present invention, the training and learning module intelligently recommends suitable course content based on the basic level and learning progress of each technician, thereby avoiding the problem of students learning too fast or too slow due to the unified teaching progress. At the same time, the platform provides a variety of learning forms, such as videos, documents and simulation exercises, so that students can choose the most suitable method according to their personal learning habits, further improving their learning effect.

[0016] (2) In the present invention, through the data analysis module, the platform collects and displays the number and ability level of technicians in each region, helping managers to understand resource distribution in real time, optimize allocation, and improve resource utilization and service quality. At the same time, the continuing education module regularly updates courses and conducts reviews and assessments to continuously improve technician skills, avoid resource waste and uneven service quality caused by differences in ability, and thus achieve more scientific and efficient resource allocation. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0018] Figure 1 A flow chart of a national grassroots pulmonary function technician management platform provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0019] The technical solution of the present invention is described below in conjunction with the accompanying drawings.

[0020] In the embodiments of the present invention, words such as "exemplarily" and "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "example" in the present invention should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of the word "example" is intended to present the concept in a specific way. In addition, in the embodiments of the present invention, the meaning expressed by "and / or" can be both, or it can be either of the two.

[0021] In the embodiments of the present invention, "image" and "picture" can sometimes be used interchangeably. It should be noted that when the difference between them is not emphasized, the meanings they intend to express are the same. "of", "corresponding, relevant" and "corresponding" can sometimes be used interchangeably. It should be noted that when the difference between them is not emphasized, the meanings they intend to express are the same.

[0022] In the embodiments of the present invention, sometimes a subscript such as W1 may be written as a non-subscript such as W1. When the difference is not emphasized, the meanings to be expressed are the same.

[0023] In order to make the technical problems, technical solutions and advantages to be solved by the present invention more clear, a detailed description will be given below with reference to the accompanying drawings and specific embodiments.

[0024] Reference Manual Attached Figure 1 , showing a structural diagram of a national grassroots pulmonary function technician management platform provided by an embodiment of the present invention.

[0025] The embodiment of the present invention provides a national grassroots pulmonary function technician management platform, including:

[0026] User management module 201, used for technicians to register and log in to the national grassroots pulmonary function technician management platform;

[0027] In a possible implementation, the user management module 201 is specifically configured to:

[0028] S101: The registration portal for technicians to access the platform;

[0029] Specifically, technicians access the registration page of the National Primary Lung Function Technician Management Platform through the Internet and enter the registration process.

[0030] S102: The technician fills in personal information;

[0031] Specifically, on the registration page, technicians need to fill in their basic personal information, including name, gender, contact information, education, and work experience.

[0032] S103: Technician uploads certification documents;

[0033] Specifically, technicians need to upload relevant identity authentication documents, such as ID cards, academic certificates, professional title certificates, etc., for the platform to verify their identity and qualifications.

[0034] S104: Verify technician identity;

[0035] S105: After verification, the system generates a unique user ID and confirms the login password to complete the registration;

[0036] Specifically, a hash algorithm can be used on the login password to encrypt and protect sensitive information (such as ID card number).

[0037] S106: Fill in user name and password;

[0038] S107: After successful login, enter the main interface of the National Primary Pulmonary Function Technician Management Platform;

[0039] Specifically, after successful login, the system verifies the accuracy of the user name and password. If the verification is successful, the technician enters the main interface of the platform and starts using various functions.

[0040] S108: The system displays corresponding functional modules according to the technician's role and authority.

[0041] It should be noted that the system automatically displays the corresponding function modules according to the technician's role (such as junior technician, senior technician, administrator, etc.) and permissions. Technicians with different roles will see different operation options and access permissions.

[0042] In the present invention, by uploading authentication documents (such as ID cards, education certificates, etc.) and performing identity verification, it is ensured that the registered technicians have legal qualifications and qualifications, thereby ensuring the user quality and service accuracy of the platform. At the same time, different modules are automatically displayed according to roles and permissions, effectively managing the access rights of technicians, preventing irrelevant personnel from accessing sensitive information or performing unauthorized operations, thereby enhancing the management and control capabilities of the platform.

[0043] The training and learning module 202 is used to provide online theoretical knowledge related to pulmonary function tests, support videos, documents and simulation exercises, and make intelligent course recommendations based on the technician's current learning status;

[0044] In a possible implementation, the training learning module 202 is specifically used for:

[0045] S201: Acquire technician learning behavior data;

[0046] It should be noted that the technician's learning behavior data includes video viewing records, document reading records, simulation exercise completion status, a list of courses completed by the technician, and the completion time and status of each course.

[0047] S202: Based on the technicians’ learning behavior data, the correlation strength between the courses is calculated by using the Apriori algorithm;

[0048] Among them, the Apriori algorithm is a classic data mining algorithm used to discover frequent item sets and association rules in transaction databases.

[0049] In a possible implementation, S202 specifically includes:

[0050] S2021: extracting the set of courses that each technician has learned from the technician's learning behavior data;

[0051] S2022: converting the course learning records of each technician into the form of transaction data containing multiple course combinations to adapt to the Apriori algorithm;

[0052] S2023: Calculate the frequency of occurrence of a single course in the transaction data as the support, and retain the course combinations that are higher than the first preset support:

[0053]

[0054] Among them, support(X) represents the proportion of transactions containing course set X to the total transactions, U represents the number of transactions containing course set X, and V represents the total number of transactions;

[0055] S2024: Combine the retained course combinations in pairs, recalculate the support, and retain the course combinations with support higher than the second preset support;

[0056] It should be noted that those skilled in the art can set the first preset support and the second preset support according to actual needs, and the present invention is not limited thereto.

[0057] S225: Repeat the preset number of iterations to generate frequent item sets of course combinations;

[0058] S2026: Extract association rules between courses from frequent item sets of course combinations:

[0059]

[0060] Among them, P XY represents the probability of selecting course Y when course X is selected, Support(X∪Y) represents the proportion of transactions that select both course set X and course set Y in all transactions, and Support(X) represents the proportion of transactions that select course set X in the total transactions;

[0061] S2027: Based on association rules, calculate the association strength between courses:

[0062] R A,B =P AB +P BA

[0063] Among them, R A,B represents the strength of association between course A and course B, P AB Table 1 shows the probability of taking course B if course A is chosen, P BA represents the probability of choosing course A when course B is chosen.

[0064] In the present invention, frequent item sets and association rules are extracted through the Apriori algorithm, and the course relevance in the technician's learning behavior is analyzed, so that learning habits and preferences can be accurately identified. According to learning habits and preferences, the recommendation strategy is dynamically adjusted to adapt the technician's learning progress and new course content, and enhance the learning effect and experience. At the same time, related courses are recommended according to the strength of association to ensure that the recommendation results are logically related to the technician's current learning content, providing technicians with a learning path that is more in line with actual needs.

[0065] S203: Based on the technicians' learning behavior data, the similarity between the technicians is calculated by a collaborative filtering algorithm;

[0066] Among them, the collaborative filtering algorithm (CF) is a core algorithm of the recommendation system. It analyzes the user's behavior or interests, finds patterns based on similarities, and recommends items that may interest users.

[0067] In a possible implementation, the similarity calculation formula is:

[0068]

[0069] Among them, sim(i,j) represents the similarity score between the i-th technician and the j-th technician, I i,j represents the set of courses selected by the i-th technician and the j-th technician, r i,a represents the learning performance rating of the i-th technician on course a, r j,a represents the learning performance score of the jth technician on course a, represents the historical average score of the i-th technician, represents the historical average score of the j-th technician.

[0070] In the present invention, the calculation of similarity is based on the technician's actual learning behavior and scoring history, which can accurately find technicians with similar learning habits. Through the learning records of similar technicians, courses that the target technician may be interested in are recommended to improve the accuracy of the recommendation. At the same time, collaborative filtering based on technician similarity not only recommends highly relevant courses that the target technician has not been exposed to, but also may recommend new courses that similar technicians like but the target technician has not been exposed to, enriching the recommendation results and avoiding the monotony of recommended content.

[0071] S204: combining the correlation strength between the courses and the similarity between the technicians, predicting the target technician's recommendation value for each course;

[0072] In a possible implementation manner, S204 specifically includes:

[0073] Combining the correlation strength between courses and the similarity between technicians, the following formula is used to predict the target technician's recommendation value for each course:

[0074]

[0075] Among them, P i,a represents the recommended value for the i-th technician to study course a, represents the historical average score of the i-th technician, λ represents the weight factor, S represents the technician's nearest neighbor set, sim(i,j) represents the similarity score between the i-th technician and the j-th technician, r j,a represents the learning performance score of the jth technician on course a, represents the historical average score of the jth technician, N a represents the set of associated courses of course a, R a,b represents the strength of the association between course b and course a, r i,b represents the learning performance score of the i-th technician on course b, Represents the average rating of course b.

[0076] Optionally, λ=0.5.

[0077] In the present invention, by integrating the dual information sources of technician similarity and course association strength, the interests of technicians and the learning logic of courses are fully considered, the limitations of a single information source are made up, and the recommendation results are ensured to be comprehensive and reliable. At the same time, technician similarity and course association strength are based on real-time updated learning behavior data, and the recommendation value can be dynamically adjusted as the technician's learning behavior changes, so that the technician's learning path recommendation always matches his latest learning behavior.

[0078] S205: Sort the recommended values ​​of each course from high to low in descending order;

[0079] S206: Pushing courses in the sorting results whose course recommendation values ​​are greater than the preset course recommendation values ​​to corresponding target technicians.

[0080] It should be noted that those skilled in the art can set the size of the course recommendation value according to actual needs, and the present invention is not limited thereto.

[0081] The assessment and certification module 203 is used to assess the technicians and issue a certificate of qualification when the technicians pass the assessment;

[0082] In a possible implementation, the assessment and authentication module 203 is specifically used for:

[0083] S301: The technician completes the course content of the learning module;

[0084] S302: The technician submits an assessment application;

[0085] Specifically, after completing the designated training, the technician can submit an assessment application, and the system will generate an assessment task based on the assessment content.

[0086] S303: The platform conducts assessment;

[0087] Specifically, the platform evaluates the technician's ability level based on multiple dimensions such as the technician's test scores, actual operation performance, and simulation practice scores. If the technician passes all the assessment items, the system will record his or her assessment results.

[0088] S304: Certificate of qualification will be issued after passing the assessment;

[0089] Specifically, after the technician passes the assessment, the platform automatically generates and issues an electronic certificate of qualification, proving that the technician is qualified to conduct lung function tests, and saves the certificate in the technician's personal file for them to review at any time.

[0090] S305: Regular review and assessment.

[0091] Specifically, the platform sets up a regular review and assessment mechanism, and technicians need to take regular review exams as required to ensure that their professional knowledge and skills are constantly updated and improved.

[0092] In the present invention, by setting up an assessment and certification module, it is possible to effectively ensure that the professional ability of technicians reaches a standardized level, and provide them with authoritative proof of their professional qualifications through the issuance of qualification certificates. The platform comprehensively measures the actual ability of technicians based on multi-dimensional evaluations of test scores, operational performance, and simulation exercises, avoiding the limitations of a single evaluation. At the same time, through regular review and assessment mechanisms, the professional knowledge and skills of technicians can be dynamically updated to ensure that they always meet the latest requirements of industry development.

[0093] The continuing education module 204 is used to regularly push updated courses to technicians and set up regular reviews and assessments;

[0094] In a possible implementation, the continuing education module 204 is specifically used to:

[0095] S401: The platform updates course content based on the latest industry standards and technological advances;

[0096] Specifically, the platform regularly updates course content based on the latest medical technology and industry standards, including new knowledge, new technologies, and changes in relevant laws and regulations. Course updates include video tutorials, documentation, case studies, etc., to ensure that technicians' knowledge is always up to date.

[0097] S402: Regularly push updated courses to technicians;

[0098] Specifically, the platform regularly pushes updated course content to technicians through the system's automatic push function, ensuring that every technician can obtain the latest training resources at the first time.

[0099] S403: Regular review and assessment;

[0100] Specifically, during the review period, technicians need to complete the corresponding online assessment, which includes the test of new course learning outcomes, skills assessment and theoretical examination. Technicians who pass the examination will continue to have valid qualification certificates, while technicians who fail the review will need to take a make-up exam or re-learn relevant courses until they pass the review.

[0101] In the present invention, the continuous education module ensures that the technicians' knowledge and skills keep pace with the times by dynamically updating course content, regularly pushing learning resources, and setting up review and assessment mechanisms. The platform regularly updates course content based on the latest industry standards and technological advances, enabling technicians to master new knowledge, new technologies, and relevant regulations in a timely manner and maintain their leading professional capabilities. Regularly pushing courses and review assessments further enhance the learning effect of technicians, prompting them to consolidate their knowledge and improve their practical skills.

[0102] Interactive communication module 205, used for technicians to post questions and leave messages for communication;

[0103] In a possible implementation, the interactive communication module 205 is specifically used for:

[0104] S501: technicians leave messages for communication;

[0105] Specifically, technicians can leave messages on the platform to comment, discuss or provide solutions to published questions or questions raised by other technicians. The message function supports multiple forms such as text, pictures, and videos, making it convenient for technicians to communicate detailed information.

[0106] S502: Experts or colleagues respond to questions;

[0107] Specifically, for questions posted by technicians, the platform will automatically assign them to experts or senior technicians in related fields for answers based on the content of the questions. Experts or colleagues can respond to questions through the platform and provide detailed solutions or guidance. All responses can be viewed by other technicians for reference and learning.

[0108] In the present invention, the interactive communication module provides a real-time, open learning and collaboration platform for technicians by providing the functions of message exchange and question answering. Technicians can describe the problems in detail in various forms such as text, pictures, and videos to promote the clear transmission of information. The platform automatically assigns questions to experts or senior technicians in related fields to ensure the professionalism and pertinence of the answers. All answers are open and transparent, and other technicians can also view and learn, forming an environment for knowledge sharing and collaborative improvement. This approach not only improves the efficiency of problem solving, but also promotes communication and experience sharing among technicians, and helps to create a community of technicians who help each other professionally and grow together.

[0109] The data analysis module 206 is used to display the number and overall level of technicians in different regions and optimize the resource allocation of grassroots pulmonary function technicians.

[0110] In a possible implementation, the data analysis module 206 is specifically configured to:

[0111] S601: Collect resource distribution data of technicians in different regions, where the resource distribution data includes the number of technicians, the skill level of technicians, and the degree of demand for technicians in the region;

[0112] S602: Analyze the dynamic changes of technician resource flow in different regions according to the resource distribution data, and extract technician resource flow data;

[0113] It should be noted that technician resource flow data refers to data that reflects the flow status and changes of technicians between different regions, positions or time periods. It can be used to analyze the distribution, deployment, flow trend of technician resources and the impact of external factors on resource flow.

[0114] In a possible implementation manner, S602 specifically includes:

[0115] S6021: Technician resource flow value for analyzing resource distribution data:

[0116] g c(l+1) =R(g c ,g b ,t)

[0117] Among them, g c(l+1)represents the technician resource flow value of the next time step, g c Indicates the technician resource flow value at the current time step, g b represents the external background factors that affect the flow of technician resources, t represents the time step, and R() represents the resource flow function;

[0118] S6022: According to the technician resource flow value calculation result, determine the technician's flow status and flow output, and use the technician's flow status and flow output as technician resource flow data:

[0119]

[0120] in, represents the technician resource flow state at time t, represents the technician resource flow output at time t, ζ(t) represents the external change factor at time t, t represents the current time point, R[] represents the state evolution function, and S[] represents the flow output function.

[0121] In the present invention, by analyzing the technician resource flow value and extracting the flow status and output data, the dynamic changes of technician resources in different regions can be accurately described, thereby optimizing resource allocation and management. At the same time, resource allocation is adjusted according to the latest flow data to ensure the timeliness and adaptability of resource allocation and meet the actual needs of each region.

[0122] S603: Based on the technician resource flow data, the teacher structure of each region is predicted through Markov chain. The teacher structure includes the distribution of technician resources and the future flow trend of technicians.

[0123] Among them, Markov Chain is a mathematical model that describes random processes and is used to study random phenomena with the characteristic of "no memory". It describes the dynamic changes of the system through a set of states and the transition probabilities between states, and is widely used to predict the future state distribution of the system.

[0124] In the present invention, the state transition analysis of the Markov chain provides a prediction of the future trend of technician flow, helps the platform to grasp the changing law of resource distribution, provides accurate data support for the platform or management department, formulates a scientific resource allocation plan, and avoids excessive concentration or dispersion of resources. At the same time, based on the prediction of the future faculty structure, the allocation plan of technicians is adjusted to ensure that the resource needs of each region are met in a timely manner, alleviate the imbalance of technician resources between regions, and improve the coverage and quality of medical services.

[0125] In a possible implementation manner, S603 specifically includes:

[0126] S6031: According to the flow status and flow output of technicians, multiple possible states of technician resources are determined, and multiple possible states are represented as state sequences using Markov chains to form a state space:

[0127] E=[E1 E2…E n ]

[0128] Among them, E represents the state space of technician resources, E1 represents the number of technician resources entering the internal area from the external area, E2 represents the number of technician resources flowing out of the internal area, and E n represents the number of technician resources remaining in the inner area, and n represents the total number of state spaces;

[0129] S6032: Based on the state space, construct the transition probability matrix:

[0130]

[0131] Among them, P represents the transition probability matrix, p ij Indicates that from state E i To state E j The transition probability, i∈[1,n], j∈[1,n];

[0132] S6033: Determine the initial status matrix of technician resources in each area:

[0133] E0=[E 01 ,E 02 ,…,E 0n ]

[0134] Among them, E0 represents the initial state matrix predicted by the Markov chain, E 0i Represents the initial state E i The number of technician resources under , n represents the total number of state spaces;

[0135] S6034: Based on the transition probability matrix and the initial state matrix of technician resources in each region, determine the prediction results of the teacher structure in the first phase:

[0136] E1=[E 01 E 02 …E 0n ]×P

[0137] Among them, E1 represents the technician resource distribution state in the first stage obtained through Markov chain prediction;

[0138] S6035: Based on the prediction results of the teacher structure in the first stage, the prediction results of the teacher structure in multiple stages are gradually determined through the recursive formula:

[0139]

[0140] Among them, E t represents the technician resource distribution state at stage t predicted by Markov chain, (p ij ) n represents the transition probability matrix, m represents the total number of prediction stages;

[0141] In the present invention, the state transition analysis of the Markov chain provides a prediction of the future trend of technician flow, helps the platform to grasp the changing law of resource distribution, provides accurate data support for the platform or management department, formulates a scientific resource allocation plan, and avoids excessive concentration or dispersion of resources. At the same time, the initial state matrix is ​​combined with the transition probability matrix to predict the short-term and long-term distribution of technician resources, ensuring that the resource allocation in different regions matches the actual demand, which helps to balance the resource allocation between regions, alleviate the imbalance of technician resources between regions, and improve the coverage and quality of medical services.

[0142] Furthermore, the state space and transition probability matrix of technician resource flow quantify the dynamic changes of resource distribution, avoid subjectivity in decision-making, and improve the transparency and feasibility of resource allocation.

[0143] S6036: Integrate the prediction results of teacher structure at each stage and predict the teacher structure in each region.

[0144] S604: construct a multi-objective optimization model for teacher allocation, and determine the objective function and constraint conditions of the multi-objective optimization model for teacher allocation according to the prediction results of the teacher structure in each region;

[0145] In a possible implementation, the objective function specifically includes a first objective function and a second objective function; the first objective function and the second objective function are specifically determined as follows:

[0146] Optimize the allocation of technician resources, balance the resources of each workstation, and determine the first objective function:

[0147]

[0148] Among them, f1 represents the first objective function, M represents the total number of workstations, N represents the total number of technicians, and Z ij represents the resource value provided by the i-th technician to the j-th workstation, X ij Indicates whether the i-th technician is assigned to the j-th workstation, Represents the average value of resource allocation received by all workstations;

[0149] Ensure reasonable resource allocation between technicians and workstations and determine the second objective function:

[0150]

[0151] Among them, f2 represents the second objective function, P ij represents the matching difference value of the i-th technician to the j-th workstation;

[0152] The constraint conditions specifically include a first constraint condition and a second constraint condition; the first constraint condition and the second constraint condition are specifically determined as follows:

[0153] Each workstation has only one technician responsible for the relevant tasks, and the first constraint is determined:

[0154]

[0155] Among them, X ij Indicates whether the i-th technician is assigned to the j-th workstation, and M represents the total number of workstations;

[0156] The total number of workstations that technician i is responsible for is recorded as s i , determine the second constraint:

[0157]

[0158] Among them, s i represents the total number of task points to which the i-th technician can be assigned, and N represents the total number of technicians.

[0159] In the present invention, by constructing a multi-objective optimization model with balance and matching as the core, and combining strict constraints, the platform can achieve efficient, fair and reasonable allocation of technician resources. This approach not only improves resource utilization efficiency and reduces operating costs, but also ensures the matching degree between technicians and workstations, and improves the overall service quality and management capabilities of the platform.

[0160] S605: Under the constraints, with the goal of minimizing the objective function, the multi-objective optimization model of teacher allocation is solved by the firefly swarm algorithm, and the optimal teacher allocation plan is output;

[0161] Among them, the firefly swarm algorithm is an efficient and flexible global optimization algorithm, which is suitable for solving complex multi-objective optimization problems. By simulating the attraction behavior of fireflies, the algorithm has both global exploration and local development capabilities, and can balance the diversity of solutions and the convergence speed, becoming a powerful tool in resource allocation and optimization problems.

[0162] In a possible implementation manner, S605 specifically includes:

[0163] S6051: According to the objective function, construct the fitness function of the firefly swarm algorithm:

[0164] F=ω1f1+ω2f2

[0165] Where F represents the fitness function, f1 represents the balance target of resource allocation, ω1 represents the weight represented by the balance target of resource allocation, f2 represents the matching target of resource allocation, and ω2 represents the weight represented by the matching target of resource allocation;

[0166] S6052: Initialize the firefly population. The firefly population contains multiple individuals. Each individual represents a feasible technician configuration scheme. The technician configuration scheme is encoded as a matrix X:

[0167]

[0168] Where X represents the technician configuration matrix, M represents the total number of workstations, N represents the total number of technicians, and X ij Indicates whether the i-th technician is assigned to the j-th workstation;

[0169] S6053: Calculate the fitness value of each firefly individual;

[0170] S6054: For the current firefly individual, select the firefly individual with a fitness value lower than itself as the attraction target, and update the position of the current firefly in combination with the correction strategy under the constraints:

[0171]

[0172] Among them, v ij represents the priority of the i-th technician being assigned to the j-th workstation;

[0173] S6055: Under the constraints, set a random number for each firefly individual. If the random number is less than the threshold, perform a mutation operation on the firefly individual:

[0174]

[0175] Among them, η represents the mutation threshold;

[0176] In the present invention, through the attraction and mutation mechanism between fireflies, a better solution is dynamically explored based on the initial solution, thereby improving the exploration ability of the algorithm and ensuring that even if the quality of the initial solution is poor, a better solution can still be gradually found through iteration.

[0177] S6056: Recalculate the fitness value of each firefly and determine the firefly individual with the best fitness value in the current population;

[0178] In the present invention, the algorithm checks the constraint conditions in each iteration to ensure that the output configuration scheme is feasible in actual operation and to avoid allocation results that do not meet the conditions.

[0179] S6057: Repeat the iteration until the maximum number of iterations is met, and output the technician configuration plan corresponding to the firefly individual with the lowest fitness value as the optimal technician configuration plan.

[0180] S606: Optimize the allocation of resources for grassroots pulmonary function technicians based on the optimal faculty allocation plan.

[0181] In this invention, the firefly swarm algorithm is used to solve the multi-objective optimization model of teacher allocation, which can efficiently and scientifically find the global optimal solution under the constraints, while meeting the requirements of balance and matching of resource allocation. Its powerful dynamic optimization ability, global search performance and constraint adaptability make this method particularly suitable for complex resource allocation problems, providing an efficient and intelligent solution for the platform.

[0182] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0183] (1) In the present invention, the training and learning module intelligently recommends suitable course content based on the basic level and learning progress of each technician, thereby avoiding the problem of students learning too fast or too slow due to the unified teaching progress. At the same time, the platform provides a variety of learning forms, such as videos, documents and simulation exercises, so that students can choose the most suitable method according to their personal learning habits, further improving their learning effect.

[0184] (2) In the present invention, through the data analysis module, the platform collects and displays the number and ability level of technicians in each region, helping managers to understand resource distribution in real time, optimize allocation, and improve resource utilization and service quality. At the same time, the continuing education module regularly updates courses and conducts reviews and assessments to continuously improve technician skills, avoid resource waste and uneven service quality caused by differences in ability, and thus achieve more scientific and efficient resource allocation.

[0185] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

[0186] There are a few points to note:

[0187] (1) The drawings of the embodiments of the present invention only relate to the structures related to the embodiments of the present invention, and other structures may refer to the general design.

[0188] (2) For the sake of clarity, in the drawings used to describe the embodiments of the present invention, the thickness of the layers or regions is exaggerated or reduced, that is, these drawings are not drawn according to the actual scale. It is understood that when an element such as a layer, film, region or substrate is referred to as being "on" or "under" another element, the element may be "directly" "on" or "under" the other element or there may be intermediate elements.

[0189] (3) In the absence of conflict, the embodiments of the present invention and the features therein may be combined with each other to obtain new embodiments.

[0190] The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. The protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A national grassroots pulmonary function technician management platform, characterized by: include: A user management module, used for technicians to register and log in to the national grassroots pulmonary function technician management platform; The training and learning module is used to provide online theoretical knowledge related to pulmonary function tests, support videos, documents and simulation exercises, and make intelligent course recommendations based on the technician's current learning status; The assessment and certification module is used to assess technicians. When technicians pass the assessment, a certificate of qualification is issued; Continuing education module, used to regularly push updated courses to technicians and set up regular reviews and assessments; Interactive communication module, for technicians to post questions and leave messages; The data analysis module is used to display the number and overall level of technicians in different regions and optimize the resource allocation of grassroots pulmonary function technicians.

2. The national grassroots pulmonary function technician management platform according to claim 1 is characterized in that: The training and learning module is specifically used for: S201: Acquire technician learning behavior data; S202: Based on the technician learning behavior data, calculate the correlation strength between each course through the Apriori algorithm; S203: Based on the technician learning behavior data, calculate the similarity between technicians through a collaborative filtering algorithm; S204: combining the correlation strength between the courses and the similarity between the technicians, predicting the target technician's recommendation value for each course; S205: Sort the recommended values ​​of each course from high to low in descending order; S206: Pushing courses in the sorting results whose course recommendation values ​​are greater than the preset course recommendation values ​​to corresponding target technicians.

3. The national grassroots pulmonary function technician management platform according to claim 2 is characterized in that: The S202 specifically includes: S2021: extracting the set of courses that each technician has learned from the technician's learning behavior data; S2022: converting the course learning records of each technician into the form of transaction data containing multiple course combinations to adapt to the Apriori algorithm; S2023: Calculate the frequency of occurrence of a single course in the transaction data as support, and retain course combinations with support higher than a first preset support: Among them, support(X) represents the proportion of transactions containing course set X to the total transactions, U represents the number of transactions containing course set X, and V represents the total number of transactions; S2024: Combine the retained course combinations in pairs, recalculate the support, and retain the course combinations with support higher than the second preset support; S225: Repeat the preset number of iterations to generate frequent item sets of course combinations; S2026: Extract association rules between courses from frequent item sets of course combinations: Among them, P XY represents the probability of selecting course Y when course X is selected, Support(X∪Y) represents the proportion of transactions that select both course set X and course set Y in all transactions, and Support(X) represents the proportion of transactions that select course set X in the total transactions; S2027: Based on the association rules, calculate the association strength between the courses: R A,B =P AB +P BA Among them, R A,B represents the strength of association between course A and course B, P AB Table 1 shows the probability of taking course B if course A is chosen, P BA represents the probability of choosing course A when course B is chosen.

4. The national grassroots pulmonary function technician management platform according to claim 2 is characterized in that: The calculation formula of the similarity is: Among them, sim(i,j) represents the similarity score between the i-th technician and the j-th technician, I i,j represents the set of courses selected by the i-th technician and the j-th technician, r i,a represents the learning performance rating of the i-th technician on course a, r j,a represents the learning performance score of the jth technician on course a, represents the historical average score of the i-th technician, represents the historical average score of the j-th technician.

5. The national grassroots pulmonary function technician management platform according to claim 2 is characterized in that: The S204 is specifically as follows: Combining the correlation strength between courses and the similarity between technicians, the following formula is used to predict the target technician's recommendation value for each course: Among them, P i,a represents the recommended value for the i-th technician to study course a, represents the historical average score of the i-th technician, λ represents the weight factor, S represents the technician's nearest neighbor set, sim(i,j) represents the similarity score between the i-th technician and the j-th technician, r j,a represents the learning performance score of the jth technician on course a, represents the historical average score of the jth technician, N a represents the set of associated courses of course a, R a,b represents the strength of the association between course b and course a, r i,b represents the learning performance score of the i-th technician on course b, Represents the average rating of course b.

6. The national grassroots pulmonary function technician management platform according to claim 1 is characterized in that: The data analysis module is specifically used for: S601: Collect resource distribution data of technicians in different regions, where the resource distribution data includes the number of technicians, the skill level of technicians, and the degree of demand for technicians in the region; S602: Analyze the dynamic changes of technician resource flows in different regions according to the resource distribution data, and extract technician resource flow data; S603: Based on the technician resource flow data, predict the teacher structure of each region through a Markov chain, wherein the teacher structure includes the distribution of technician resources and the future flow trend of technicians; S604: construct a multi-objective optimization model for teacher allocation, and determine the objective function and constraint conditions of the multi-objective optimization model for teacher allocation according to the prediction results of the teacher structure of each region; S605: Under the constraints of the constraints, with the goal of minimizing the objective function, the multi-objective optimization model of teacher allocation is solved by the firefly swarm algorithm, and the optimal teacher allocation plan is output; S606: Optimize the allocation of resources for primary pulmonary function technicians based on the optimal teacher allocation plan.

7. The national grassroots pulmonary function technician management platform according to claim 6 is characterized in that: The S602 specifically includes: S6021: Analyze the technician resource flow value of the resource distribution data: g c(l+1) =R(g c ,g b ,t) Among them, g c(l+1) represents the technician resource flow value of the next time step, g c Indicates the technician resource flow value at the current time step, g b represents the external background factors that affect the flow of technician resources, t represents the time step, and R() represents the resource flow function; S6022: Determine the flow status and flow output of the technician according to the technician resource flow value calculation result, and use the flow status and flow output of the technician as the technician resource flow data: in, represents the technician resource flow state at time t, represents the technician resource flow output at time t, ζ(t) represents the external change factor at time t, t represents the current time point, R[] represents the state evolution function, and S[] represents the flow output function.

8. The national grassroots pulmonary function technician management platform according to claim 6 is characterized in that: The S603 specifically includes: S6031: According to the flow status and flow output of technicians, multiple possible states of technician resources are determined, and multiple possible states are represented as state sequences using Markov chains to form a state space: E=[E1 E2…E n ] Among them, E represents the state space of technician resources, E1 represents the number of technician resources entering the internal area from the external area, E2 represents the number of technician resources flowing out of the internal area, and E n represents the number of technician resources remaining in the inner area, and n represents the total number of state spaces; S6032: Based on the state space, construct a transition probability matrix: Among them, P represents the transition probability matrix, p ij Indicates that from state E i To state E j The transition probability, i∈[1,n], j∈[1,n]; S6033: Determine the initial status matrix of technician resources in each area: E0=[E 01 ,E 02 ,…,E 0n ] Among them, E0 represents the initial state matrix predicted by the Markov chain, E 0i Represents the initial state E i The number of technician resources under , n represents the total number of state spaces; S6034: Based on the transition probability matrix and the initial state matrix of technician resources in each region, determine the teacher structure prediction result of the first stage: E1=[E 01 HAVE BEEN 02 …HAVE BEEN 0n ]×P Among them, E1 represents the technician resource distribution state in the first stage obtained through Markov chain prediction; S6035: Based on the prediction results of the teacher structure in the first stage, the prediction results of the teacher structure in multiple stages are gradually determined through the recursive formula: Among them, E t represents the technician resource distribution state at stage t predicted by Markov chain, (p ij ) n represents the transition probability matrix, m represents the total number of prediction stages; S6036: Integrate the teacher structure prediction results at each stage and predict the teacher structure in each region.

9. The national grassroots pulmonary function technician management platform according to claim 6, characterized in that: The objective function specifically includes a first objective function and a second objective function; the first objective function and the second objective function are specifically determined as follows: Optimize the allocation of technician resources, balance the resources of each workstation, and determine the first objective function: Among them, f1 represents the first objective function, M represents the total number of workstations, N represents the total number of technicians, and Z ij represents the resource value provided by the i-th technician to the j-th workstation, X ij Indicates whether the i-th technician is assigned to the j-th workstation, Represents the average value of resource allocation received by all workstations; Ensure that the resources of technicians and workstations are reasonably allocated and determine the second objective function: Among them, f2 represents the second objective function, P ij represents the matching difference value of the i-th technician to the j-th workstation; The constraint conditions specifically include a first constraint condition and a second constraint condition; the first constraint condition and the second constraint condition are specifically determined as follows: Each workstation has only one technician responsible for the relevant tasks, and the first constraint is determined as follows: Among them, X ij Indicates whether the i-th technician is assigned to the j-th workstation, and M represents the total number of workstations; The total number of workstations that technician i is responsible for is recorded as s i , determine the second constraint: Among them, s i represents the total number of task points to which the i-th technician can be assigned, and N represents the total number of technicians.

10. The national grassroots pulmonary function technician management platform according to claim 6, characterized in that: The S605 specifically includes: S6051: According to the objective function, construct a fitness function of the firefly swarm algorithm: F=ω1f1+ω2f2 Where F represents the fitness function, f1 represents the balance target of resource allocation, ω1 represents the weight represented by the balance target of resource allocation, f2 represents the matching target of resource allocation, and ω2 represents the weight represented by the matching target of resource allocation; S6052: Initialize the firefly population, which includes multiple individuals. Each individual represents a feasible technician configuration scheme. The technician configuration scheme is encoded as a matrix X: Where X represents the technician configuration matrix, M represents the total number of workstations, N represents the total number of technicians, and X ij Indicates whether the i-th technician is assigned to the j-th workstation; S6053: Calculate the fitness value of each firefly individual; S6054: For the current firefly individual, select the firefly individual with a fitness value lower than itself as the attraction target, and update the position of the current firefly in combination with the correction strategy under the constraints: Among them, v ij represents the priority of the i-th technician being assigned to the j-th workstation; S6055: Under the constraints of the constraints, a random number is set for each firefly individual, and when the random number is less than a threshold, a mutation operation is performed on the firefly individual: Among them, η represents the mutation threshold; S6056: Recalculate the fitness value of each firefly and determine the firefly individual with the best fitness value in the current population; S6057: Repeat the iteration until the maximum number of iterations is met, and output the technician configuration plan corresponding to the firefly individual with the lowest fitness value as the optimal technician configuration plan.

Images