A method and system for optimizing allocation of medical resources based on big data

Abstract

The present invention discloses a method and system for optimizing the allocation of medical resources based on big data, and relates to the technical field of medical resources. Through big data collection and analysis, the system can more accurately understand patient needs and the use of medical resources, and remove and integrate a large amount of data through a preprocessing module, thereby obtaining: a slogan visibility coefficient Kjxs, a guide factor Dzyz and a waiting factor Ddyz, and the above data are correlated with each other, and a patient satisfaction index MYzs is obtained by deep calculation. The analysis and optimization strategy for the waiting factor Ddyz are helpful to reduce the waiting time of patients in the hospital; then the patient satisfaction index MYzs is compared with a preset satisfaction threshold K to determine the level satisfaction optimization strategy. At this time, the system sends the corresponding level notification to the corresponding staff according to the obtained level notification, and the staff takes corresponding decisions according to the sent level notification, which meets the needs of patients, improves patient satisfaction, and improves the optimization allocation of medical resources.

Description

Technical Field

[0001] The present invention relates to the technical field of medical resources, and in particular to a method and system for optimizing the configuration of medical resources based on big data. Background Art

[0002] In the big data-based medical field, effective allocation of medical resources is a vital part of ensuring that patients receive high-quality medical services. With the continuous development and innovation in the medical field, big data technology is gradually becoming a key tool to improve the efficiency of medical resource allocation and enhance patient satisfaction. Hospitals and medical institutions are facing huge challenges and need to reasonably allocate medical resources to meet the growing needs of patients and ensure that patients' waiting time and experience are within an acceptable range. In this improvement process, we will explore the allocation of medical resources within the hospital, especially to solve specific problems in patient medical services.

[0003] Generally speaking, medical resources refer to various elements, equipment, manpower and financial resources used to provide medical and health services, among which medical services are the core work of medical resources. However, the traditional medical resource allocation system in hospitals mainly allocates resources from various diagnosis, treatment, surgery, rehabilitation and nursing services, often ignoring the needs of patients and failing to gain their affirmation and satisfaction. For example, patients are not familiar with the internal environment of the hospital and cannot quickly go to the medical room or other location required by the doctor to take the next medical step, which can easily lead to the neglect of medical services for patients, resulting in a decrease in patient satisfaction. In addition, some factors within the hospital, such as noise and waiting time, will have a negative impact on their satisfaction, thereby indirectly reflecting the quality of medical resource allocation in the current hospital. Summary of the invention

[0004] 1. Technical issues to be resolved

[0005] In view of the deficiencies in the prior art, the present invention provides a method and system for optimizing the allocation of medical resources based on big data, which solves the problems in the background technology.

[0006] (II) Technical solution

[0007] To achieve the above objectives, the present invention is implemented through the following technical solutions: a method and system for optimizing the configuration of medical resources based on big data, including a big data acquisition module, a preprocessing module, a medical analysis module, a configuration optimization module and a communication processing module;

[0008] The big data collection module is used to record and collect patient demand data and medical resource usage data in the hospital, and update the records in real time to form a medical resource library;

[0009] The preprocessing module is used to screen, deduplicate and decode the data in the medical resource library, filter out useless data to save database space, and aggregate them into a comprehensive medical resource library;

[0010] The medical analysis module is used to conduct in-depth mining and analysis of patient demand data and medical resource usage data, and extract useful feature data from the preprocessed data, including: occlusion area Zdmj, slogan size Byz, number of inquiries Xwrs, number of windows for the same type of business Ywck and number of queues Pdrs, and establish the slogan visibility coefficient Kjxs, guidance factor Dzyz and waiting factor Ddyz respectively, and correlate the slogan visibility coefficient Kjxs, guidance factor Dzyz and waiting factor Ddyz to obtain the patient satisfaction index MYzs through in-depth calculation. The patient satisfaction index MYzs is obtained by the following formula:

[0011]

[0012] In the formula, Zy represents the noise level, f1 and f2 represent the weight values ​​of the guidance factor Dzyz and the waiting factor Ddyz respectively, and P represents the correction coefficient;

[0013] The occlusion area Zdmj is associated with the slogan size Byz to obtain the slogan visibility coefficient Kjxs; the slogan visibility coefficient Kjxs is associated with the number of inquiries Xwrs to obtain the guidance factor Dzyz; the number of windows for the same service Ywck is associated with the number of queues Pdrs to obtain the waiting factor Ddyz; the waiting factor Ddyz is associated with the guidance factor Dzyz, and the patient satisfaction index MYzs is obtained by deep calculation;

[0014] The configuration optimization module is used to compare and analyze the waiting factor Ddyz with the preset waiting threshold Q to determine the optimization strategy; compare and analyze the patient satisfaction index MYzs with the preset satisfaction threshold K to obtain the corresponding level notification and determine the level satisfaction optimization strategy;

[0015] The communication processing module is used to transmit the level notification to the same type of business processors or managers, make corresponding level management processing, and ensure effective notification and management work.

[0016] Preferably, the big data acquisition module includes a video recording unit and a voice monitoring unit;

[0017] The video recording unit is used to install camera equipment in the hospital to obtain accurate patient demand data and medical resource utilization data. The patient demand data includes the number of people who ask for directions, the type of demand, and the designated medical staff who need help; the medical resource utilization data includes the number of medical staff, the type of medical equipment, funds and financial resources, and the size, number, and height of the signboards that serve as signs;

[0018] The voice monitoring unit is used to set up microphones in the hospital to obtain the needs orientation of patients when communicating with medical staff, the emotional changes of patients, and the noise level of the hospital's surrounding environment.

[0019] Preferably, based on the collection and acquisition of medical resource usage data, and through in-depth calculation and analysis, the slogan visibility coefficient Kjxs is obtained, and the slogan visibility coefficient Kjxs is obtained by the following formula:

[0020]

[0021] In the formula, Bys represents the number of slogans, Bgd represents the height of the slogan, Yzs represents the number of languages, w1 represents the total weight of the slogan size Byz, the number of slogans Bys and the slogan height Bgd, w2 and w3 represent the weights of the number of languages ​​Yzs and the occlusion area Zdmj respectively, among which 0.45≤w1≤0.85, 0.35≤w2≤0.40, and 0.35≤w3≤0.55.

[0022] Preferably, according to the patient demand data, the slogan visibility coefficient Kjxs is associated with the number of inquiries Xwrs to obtain the guidance factor Dzyz, which is obtained by the following formula:

[0023]

[0024] Where Yym represents the hospital area, Xzj represents the distance to seek a diagnosis, a1, a2 and a3 represent the weight values ​​of the number of inquiries Xwrs, the hospital area Yym and the distance to seek a diagnosis Xzj respectively, and R represents the correction constant, where a1+a2+a3≤1.0.

[0025] Preferably, the waiting factor Ddyz is obtained based on the collection and acquisition of medical resource usage data and patient demand data. The waiting factor Ddyz is obtained by the following formula:

[0026]

[0027] Where Ysc represents the doctor's business hours, b1, b2 and b3 represent the weight values ​​of the number of windows with the same service Ywck, the number of queues Pdrs and the doctor's business hours Ysc, respectively, and C represents the correction constant.

[0028] Preferably, the waiting factor Ddyz is compared and analyzed with a preset waiting threshold Q;

[0029] When the waiting factor Ddyz is higher than the preset waiting threshold Q, that is, Ddyz>Q, it means that the medical resource service in the current hospital is in a tense state;

[0030] When the waiting factor Ddyz is lower than the preset waiting threshold Q, i.e., Ddyz < Q, it indicates that the medical staff has successfully controlled the decline in patient medical satisfaction caused by waiting and provided good medical quality for the patient.

[0031] Preferably, the patient satisfaction index MYzs is compared and analyzed with the preset satisfaction threshold K to obtain a hierarchical satisfaction optimization strategy:

[0032] When K + 13 ≤ MYzs ≤ K + 16, a first-level notification is obtained, indicating that the current patient's experience is very good and the medical service staff is considered to be in an efficient working state;

[0033] When K + 7 ≤ MYzs ≤ K + 12, a second-level notification is obtained, indicating that the current patient is moderately satisfied with the medical service and the service efficiency needs to be further improved;

[0034] When K + 1 ≤ MYzs ≤ K + 6, a third-level notification is obtained, indicating that the current patient's experience satisfaction is in a relatively low state;

[0035] When MYzs ≤ K, a fourth-level notification is obtained, indicating that the current patient is very dissatisfied with the medical experience. At this time, the medical staff and the hospital need to conduct a thorough review and improve the service process and strengthen training.

[0036] Preferably, the communication processing module includes a feedback management unit and a tracking unit;

[0037] The feedback management unit is used to transmit the obtained corresponding level results to the corresponding business handlers or managers through communication technology and make a patient satisfaction strategy in a timely manner;

[0038] The tracking unit is used to monitor various data within the hospital in real time according to the corresponding strategies adopted in the level notification to prevent failure to make a processing strategy in a timely manner due to the occurrence of emergencies.

[0039] Preferably, it includes the following steps:

[0040] Step 1: Collect patient demand data and medical resource usage data in the hospital through the big data collection module and transmit them to the medical resource library in real time;

[0041] Step 2: Use the preprocessing module to perform data cleaning and data integration on the collected data, remove redundant data to form a comprehensive medical resource library;

[0042] Step 3: Use the medical analysis module to deeply analyze the processed data, obtain the slogan visibility coefficient Kjxs, the guiding diagnosis factor Dzyz, and the waiting factor Ddyz, and then calculate and fit the patient satisfaction index MYzs;

[0043] Step 4: Compare and analyze the waiting factor Ddyz with the preset waiting threshold Q through the configuration optimization module to determine the optimization strategy; compare and analyze the patient satisfaction index MYzs with the preset satisfaction threshold K to determine the level satisfaction optimization strategy;

[0044] Step 5: The communication processing module will ensure the timely delivery of the grade results, and continuously monitor the situation within the hospital after the strategy is made, and formulate strategies in a timely manner in the face of emergencies.

[0045] (III) Beneficial effects

[0046] The present invention provides a method and system for optimizing the allocation of medical resources based on big data, which has the following beneficial effects:

[0047] (1) A medical resource optimization configuration system based on big data uses a big data collection module to collect and analyze relevant data in the hospital. The system can more accurately understand patient needs and medical resource usage, extract relevant data within the hospital in multiple dimensions, and remove and integrate a large amount of data through a preprocessing module to reduce the system's computing burden, thereby obtaining: slogan visibility coefficient Kjxs, guide factor Dzyz and waiting factor Ddyz, and the above data are correlated with each other, and the patient satisfaction index MYzs is obtained by deep calculation. The analysis and optimization strategy of the waiting factor Ddyz helps to reduce the waiting time of patients in the hospital and increase the convenience of patients' medical treatment; through the patient satisfaction index MYzs, the system can more comprehensively understand the patient's needs and experience, help meet the medical services expected by patients, and finally determine the pros and cons of the current medical configuration; then the patient satisfaction index MYzs is compared with the preset satisfaction threshold K to determine the level satisfaction optimization strategy. At this time, the system sends the corresponding level notification to the corresponding staff, and the staff takes corresponding decisions based on the sent level notification to meet the needs of patients, improve patient satisfaction, and further improve the optimization of medical resources.

[0048] (2) This is a medical resource optimization allocation system based on big data. It compares and analyzes the patient satisfaction index MYzs with the preset satisfaction threshold K to obtain different levels of notifications. For example, the first level notification indicates high service efficiency, while the fourth level notification indicates serious problems. Different levels of notifications can help hospitals decide how to allocate resources. The communication processing module ensures the timely delivery of level notifications, so that relevant business processors and managers within the hospital can quickly make corresponding management decisions, thereby improving the efficiency of coordination and response.

[0049] (3) This method of optimizing the allocation of medical resources based on big data, through steps one to five, collects and records the patient demand data and medical resource usage data in the hospital, and pre-processes and integrates them to extract effective feature data, obtains the slogan visibility coefficient Kjxs, the guide factor Dzyz and the waiting factor Ddyz by calculation, and associates the guide factor Dzyz with the waiting factor Ddyz to obtain the patient satisfaction index MYzs, and compares it with the preset satisfaction threshold K to obtain the level satisfaction optimization strategy, and sends it to relevant staff for resource optimization. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 This is a flowchart diagram of a medical resource optimization configuration system based on big data according to the present invention;

[0051] Figure 2 This is a schematic diagram of the steps of a method for optimizing allocation of medical resources based on big data according to the present invention. DETAILED DESCRIPTION

[0052] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0053] In the big data-based medical field, effective allocation of medical resources is a vital part of ensuring that patients receive high-quality medical services. With the continuous development and innovation in the medical field, big data technology is gradually becoming a key tool to improve the efficiency of medical resource allocation and enhance patient satisfaction. Hospitals and medical institutions are facing huge challenges and need to reasonably allocate medical resources to meet the growing needs of patients and ensure that patients' waiting time and experience are within an acceptable range. In this improvement process, we will explore the allocation of medical resources within the hospital, especially to solve specific problems in patient medical services.

[0054] Generally speaking, medical resources refer to various elements, equipment, manpower and financial resources used to provide medical and health services, among which medical services are the core work of medical resources. However, the traditional medical resource allocation system in hospitals mainly allocates resources from various diagnostic, treatment, surgical, rehabilitation and nursing services, often ignoring the needs of patients and failing to gain their affirmation and satisfaction. For example, patients are not familiar with the internal environment of the hospital and cannot quickly go to the medical room or other location required by the doctor to take the next medical step, which can easily lead to the neglect of medical services for patients, resulting in a decrease in patient satisfaction. In addition, some factors within the hospital, such as noise and waiting time, will have a negative impact on their satisfaction, thereby indirectly reflecting the existence of problems in the allocation of medical resources.

[0055] Example 1

[0056] See also Figure 1 , the present invention provides a medical resource optimization configuration system based on big data, including a big data acquisition module, a preprocessing module, a medical analysis module, a configuration optimization module and a communication processing module;

[0057] The big data collection module is used to record and collect patient demand data and medical resource usage data in the hospital, and update the records in real time to form a medical resource library;

[0058] The preprocessing module is used to screen, deduplicate and decode the data in the medical resource library, filter out useless data to save database space, and aggregate them into a comprehensive medical resource library;

[0059] The medical analysis module is used to conduct in-depth mining and analysis of patient demand data and medical resource usage data, and extract useful feature data from the preprocessed data, including: occlusion area Zdmj, slogan size Byz, number of inquiries Xwrs, number of windows for the same type of business Ywck and number of queues Pdrs, and establish the slogan visibility coefficient Kjxs, guidance factor Dzyz and waiting factor Ddyz respectively, and correlate the slogan visibility coefficient Kjxs, guidance factor Dzyz and waiting factor Ddyz to obtain the patient satisfaction index MYzs through in-depth calculation. The patient satisfaction index MYzs is obtained by the following formula:

[0060]

[0061] In the formula, Zy represents the noise level, f1 and f2 represent the weight values ​​of the guidance factor Dzyz and the waiting factor Ddyz respectively, and P represents the correction coefficient;

[0062] The occlusion area Zdmj is associated with the slogan size Byz to obtain the slogan visibility coefficient Kjxs; the slogan visibility coefficient Kjxs is associated with the number of inquiries Xwrs to obtain the guidance factor Dzyz; the number of windows for the same service Ywck is associated with the number of queues Pdrs to obtain the waiting factor Ddyz; the waiting factor Ddyz is associated with the guidance factor Dzyz, and the patient satisfaction index MYzs is obtained by deep calculation;

[0063] The configuration optimization module is used to compare and analyze the waiting factor Ddyz with the preset waiting threshold Q to determine the optimization strategy; compare and analyze the patient satisfaction index MYzs with the preset satisfaction threshold K to obtain the corresponding level notification and determine the level satisfaction optimization strategy;

[0064] The communication processing module is used to transmit the level notification to the same type of business processors or managers, make corresponding level management processing, and ensure effective notification and management work.

[0065] During the operation of this system, through big data collection and analysis, the system can more accurately understand patient needs and medical resource usage, and through the preprocessing module, a large amount of data is deduplicated and integrated to obtain: slogan visibility coefficient Kjxs, guide factor Dzyz and waiting factor Ddyz, and the above data are correlated to obtain the patient satisfaction index MYzs in depth. The analysis and optimization strategy for the waiting factor Ddyz helps to reduce the waiting time of patients in the hospital; through the patient satisfaction index MYzs, the system can have a more comprehensive understanding of the patient's needs and experience; then the patient satisfaction index MYzs is compared with the preset satisfaction threshold K to determine the level satisfaction optimization strategy. At this time, the system sends the corresponding level notification to the corresponding staff, and the staff takes corresponding decisions based on the sent level notification to meet the needs of patients, improve patient satisfaction, and further improve the optimization of medical resources.

[0066] Example 2

[0067] Please refer to Figure 1 ,Specifically: the big data acquisition module includes a video recording unit and a voice monitoring unit;

[0068] The video recording unit is used to install camera equipment in the hospital to obtain accurate patient demand data and medical resource utilization data. The patient demand data includes the number of people who ask for directions, the type of demand, and the designated medical staff who need help; the medical resource utilization data includes the number of medical staff, the type of medical equipment, funds and financial resources, and the size, number, and height of the signboards that serve as signs;

[0069] The voice monitoring unit is used to set up microphones in the hospital to obtain the needs orientation of patients when communicating with medical staff, the emotional changes of patients, and the noise level of the hospital's surrounding environment.

[0070] In this embodiment, the video recording unit and the voice monitoring unit will collect and record various relevant data in the hospital through different collection methods, so as to fully understand the hospital situation.

[0071] Example 3

[0072] Please refer to Figure 1 Specifically: Based on the collection and acquisition of medical resource usage data, and through in-depth calculation and analysis, the slogan visibility coefficient Kjxs is obtained. The slogan visibility coefficient Kjxs is obtained by the following formula:

[0073]

[0074] In the formula, Bys represents the number of slogans, Bgd represents the height of the slogan, Yzs represents the number of languages, w1 represents the total weight of the slogan size Byz, the number of slogans Bys and the slogan height Bgd, w2 and w3 represent the weights of the number of languages ​​Yzs and the occlusion area Zdmj respectively, among which 0.45≤w1≤0.85, 0.35≤w2≤0.40, and 0.35≤w3≤0.55.

[0075] The above-mentioned number of slogans Bys, slogan size Byz, slogan height Bgd, number of languages ​​Yzs and occlusion area Zdmj are all obtained through image recognition technology;

[0076] Among them: The number of slogans Bys includes various signs or reminder stickers that serve as reminders, signs, and warnings in the hospital; and the image recognition algorithm is used to analyze the scene images inside the hospital to determine the text or signs in the image and calculate the number of slogans

[0077] Slogan size Byz refers to the area of ​​the signboard or notice sticker, and by analyzing the number of pixels and position of the slogan in the image, the size and height of the slogan can be measured;

[0078] Number of languages ​​Yzs refers to the number of languages ​​of text, symbols and letters on signs or notices;

[0079] The shielding area Zdmj refers to the area of ​​the covering material on the surface of the signboard or reminder sticker, where the covering material includes surface dust, various wastes and other overlapping signs;

[0080] According to the patient demand data, the slogan visibility coefficient Kjxs is associated with the number of inquiries Xwrs to obtain the guidance factor Dzyz, which is obtained by the following formula:

[0081]

[0082] In the formula, Yym represents the hospital area, Xzj represents the distance for seeking medical advice, a1, a2, and a3 respectively represent the weight values of the number of people questioned Xwrs, the hospital area Yym, and the distance for seeking medical advice Xzj, and R represents the correction constant, where a1 + a2 + a3 ≤ 1.0.

[0083] The distance for seeking medical advice Xzj refers to the distance that a patient travels to the next specific department or location in the hospital for medical examinations or diagnoses as required by the doctor, and is obtained by monitoring through video recording.

[0084] The number of people questioned Xwrs refers to the number of people a patient consults during the process of seeking medical advice, and is obtained by analyzing and identifying the patient's voice through video recording and a microphone.

[0085] Both the doctor's business hours Ysc and the hospital area Yym are obtained by integrating the work schedules of medical staff in each department recorded in the hospital management system and the areas of various internal regions of the hospital through big data technology.

[0086] Based on the collection of medical resource usage data and patient demand data, the waiting factor Ddyz is obtained. The waiting factor Ddyz is obtained through the following formula:

[0087]

[0088] In the formula, Ysc represents the doctor's business hours, b1, b2, and b3 respectively represent the weight values of the number of windows for the same type of business Ywck, the number of people in the queue Pdrs, and the doctor's business hours Ysc, and C represents the correction constant.

[0089] The number of windows for the same type of business Ywck includes windows for obtaining different medicinal materials, payment windows, and consulting windows in different departments, etc. The number of people in the queue Pdrs represents the number of people waiting in front of a patient when handling different types of business, and both the number of windows for the same type of business Ywck and the number of people in the queue Pdrs are obtained through video recording.

[0090] The waiting factor Ddyz is compared and analyzed with the preset waiting threshold Q.

[0091] When the waiting factor Ddyz is higher than the preset waiting threshold Q, that is, Ddyz > Q, it indicates that the medical resource service within the current hospital is in a tense state. At this time, corresponding emergency window business handling work needs to be increased according to specific circumstances.

[0092] When the waiting factor Ddyz is lower than the preset waiting threshold Q, that is, Ddyz < Q, it indicates that the medical staff have successfully controlled the decline in medical satisfaction caused by patients waiting, and provided good medical quality for patients.

[0093] In this embodiment, through deep learning of the data in the preprocessing module, in-depth insights into the needs and experiences of patients during the medical treatment process are provided, and the slogan visibility coefficient Kjxs, the guidance factor Dzyz and the waiting factor Ddyz are obtained in turn, so as to determine the patient's satisfaction from multiple angles. At the same time, the waiting factor Ddyz is compared and analyzed with the preset waiting threshold Q. If the waiting factor Ddyz is higher than the preset waiting threshold Q, the corresponding urgent window processing business work is increased according to the specific situation to improve patient satisfaction and medical service quality.

[0094] Example 4

[0095] Please refer to Figure 1 Specifically: Compare and analyze the patient satisfaction index MYzs with the preset satisfaction threshold K to obtain the level satisfaction optimization strategy:

[0096] When K+13≤MYzs≤K+16, a first-level notification is obtained, indicating that the current patient experience is very good, and the medical service staff is considered to be in an efficient working state, and there is no need to reallocate medical resources.

[0097] When K+7≤MYzs≤K+12, the second-level notification is obtained, indicating that the patient is currently in a moderately satisfied state with the medical service and needs to further improve the service efficiency, such as medical staff communicating more with patients or improving communication skills, and using more gentle communication language;

[0098] When K+1≤MYzs≤K+6, the third level notification is obtained, indicating that the current patient experience satisfaction is at a low level. At this time, the hospital needs to identify the problem in a timely manner and improve the service process, such as adding corresponding emergency business windows and adjusting the schedule.

[0099] When MYzs≤K, the fourth level notification is received, indicating that the patient is very dissatisfied with the medical experience. At this time, medical staff and hospitals need to conduct a thorough review and improve service processes, strengthen training, and conduct more summaries and reports.

[0100] The communication processing module includes a feedback management unit and a tracking unit;

[0101] The feedback management unit is used to transmit the obtained corresponding grade results to the corresponding business processing personnel or managers through communication technology, and make patient satisfaction strategies in a timely manner;

[0102] The tracking unit is used to monitor various data within the hospital in real time after taking corresponding strategies according to the level notification, so as to prevent the failure to make timely treatment strategies due to emergencies.

[0103] In this embodiment, the patient satisfaction index MYzs is obtained by correlating the guide factor Dzyz and the waiting factor Ddyz, and the patient satisfaction index MYzs is compared and analyzed with the preset satisfaction threshold K to obtain different levels of notifications, such as the first level notification indicates high service efficiency, and the fourth level notification indicates serious problems; based on these notifications, the hospital can optimize the service process according to different situations or severity to ensure efficient and high-quality medical services; the tracking unit is used to monitor the internal data of the hospital in real time to prevent the failure to take timely response measures due to emergencies, which helps to discover problems in advance and reduce the occurrence of unsatisfactory situations, thereby improving the efficiency of medical resource allocation.

[0104] Example 5

[0105] Please refer to Figure 2 Specifically: A method for optimizing the allocation of medical resources based on big data, comprising the following steps:

[0106] Step 1: Collect patient demand data and medical resource usage data in the hospital through the big data collection module, and transmit it to the medical resource library in real time;

[0107] Step 2: Use the pre-processing module to clean and integrate the collected data, remove redundant data and form a comprehensive medical resource library;

[0108] Step 3: Perform in-depth analysis on the processed data through the medical analysis module, obtain the slogan visibility coefficient Kjxs, the guidance factor Dzyz and the waiting factor Ddyz, and then calculate and fit the patient satisfaction index MYzs;

[0109] Step 4: Compare and analyze the waiting factor Ddyz with the preset waiting threshold Q through the configuration optimization module to determine the optimization strategy; compare and analyze the patient satisfaction index MYzs with the preset satisfaction threshold K to determine the level satisfaction optimization strategy;

[0110] Step 5: The communication processing module will ensure the timely delivery of the grade results, and continuously monitor the situation within the hospital after the strategy is made, and formulate strategies in a timely manner in the face of emergencies.

[0111] In this embodiment, through steps one to five, the patient demand data and medical resource usage data in the hospital are collected and recorded, and preprocessed and integrated to extract effective feature data. The slogan visibility coefficient Kjxs, the guide factor Dzyz and the waiting factor Ddyz are obtained by calculation, and the guide factor Dzyz and the waiting factor Ddyz are associated to obtain the patient satisfaction index MYzs. It is compared with the preset satisfaction threshold K to obtain the level satisfaction optimization strategy, which is sent to relevant staff for resource optimization.

[0112] Example: A certain hospital has introduced a method and system for optimizing the allocation of medical resources based on big data. The following is an example for the certain hospital:

[0113] Data collection:

[0114] Slogan size Byz: 10; number of slogans Bys: 50; slogan height Bgd: 3m; number of languages ​​Yzs: 2; blocked area Zdmj: 30; number of inquiries Xwrs: 4; hospital area Yym: 1500; distance to seek medical treatment Xzj: 3; doctor's business hours Ysc: 8h; number of windows for the same service Ywck: 2; number of people in line Pdrs: 12;

[0115] With the above data, the following calculations can be performed:

[0116] Patient satisfaction index

[0117] If K is 30, then 30+13≤MYzs≤30+16, and the first-level notification is obtained, indicating that the current patient experience is very good, and the medical service staff is considered to be in an efficient working state, and there is no need to re-allocate medical resources.

[0118] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A medical resource optimization configuration system based on big data, Features: It includes big data acquisition module, preprocessing module, medical analysis module, configuration optimization module and communication processing module; The big data collection module is used to record and collect patient demand data and medical resource usage data in the hospital, and update the records in real time to form a medical resource library; The preprocessing module is used to screen, deduplicate and decode the data in the medical resource library, filter out useless data to save database space, and aggregate them into a comprehensive medical resource library; The medical analysis module is used to conduct in-depth mining and analysis of patient demand data and medical resource usage data, and extract useful feature data from the preprocessed data, including: occlusion area Zdmj, slogan size Byz, number of inquiries Xwrs, number of windows for the same type of business Ywck and number of queues Pdrs, and establish the slogan visibility coefficient Kjxs, guidance factor Dzyz and waiting factor Ddyz respectively, and correlate the slogan visibility coefficient Kjxs, guidance factor Dzyz and waiting factor Ddyz to obtain the patient satisfaction index MYzs through in-depth calculation. The patient satisfaction index MYzs is obtained by the following formula: In the formula, Zy represents the noise level, f 1 and f 2 They are respectively represented as the weight values ​​of the guidance factor Dzyz and the waiting factor Ddyz, where P represents the correction coefficient; The occlusion area Zdmj is associated with the slogan size Byz to obtain the slogan visibility coefficient Kjxs; the slogan visibility coefficient Kjxs is associated with the number of inquiries Xwrs to obtain the guidance factor Dzyz; the number of windows for the same service Ywck is associated with the number of queues Pdrs to obtain the waiting factor Ddyz; the waiting factor Ddyz is associated with the guidance factor Dzyz, and the patient satisfaction index MYzs is obtained by deep calculation; The configuration optimization module is used to compare and analyze the waiting factor Ddyz with the preset waiting threshold Q to determine the optimization strategy; compare and analyze the patient satisfaction index MYzs with the preset satisfaction threshold K to obtain the corresponding level notification and determine the level satisfaction optimization strategy; The communication processing module is used to transmit the level notification to the same type of business processors or managers, make corresponding level management processing, and ensure effective notification and management work.

2. According to the medical resource optimization configuration system based on big data of claim 1, Features: The big data acquisition module includes a video recording unit and a voice monitoring unit; The video recording unit is used to install camera equipment in the hospital to obtain accurate patient demand data and medical resource utilization data. The patient demand data includes the number of people who ask for directions, the type of demand, and the designated medical staff who need help; the medical resource utilization data includes the number of medical staff, the type of medical equipment, funds and financial resources, and the size, number, and height of the signboards that serve as signs; The voice monitoring unit is used to set up microphones in the hospital to obtain the needs orientation of patients when communicating with medical staff, the emotional changes of patients, and the noise level of the hospital's surrounding environment.

3. According to the medical resource optimization configuration system based on big data of claim 2, Features: Based on the acquisition of medical resource usage data and through in-depth calculation and analysis, the slogan visibility coefficient Kjxs is obtained. The slogan visibility coefficient Kjxs is obtained through the following formula: In the formula, Bys represents the number of slogans, Bgd represents the height of the slogans, Yzs represents the number of languages, and w 1 It is expressed as the total weight of the slogan size Byz, the number of slogans Bys and the slogan height Bgd, w 2 and w 3 They are respectively represented as the weight values ​​of the number of languages ​​Yzs and the occlusion area Zdmj, where 0.45≤w 1 ≤0.85,0.35≤w 2 ≤0.40,0.35≤w 3 ≤0.

55.

4. The big data-based medical resource optimization allocation system according to claim 3, characterized in that: According to the patient demand data, and associating the slogan visibility coefficient Kjxs with the number of inquiries Xwrs, the guiding diagnosis factor Dzyz is obtained. The guiding diagnosis factor Dzyz is obtained through the following formula: In the formula, Yym represents the hospital area, Xzj represents the distance to seek medical advice, and a 1 、a 2 and a 3 They are respectively represented by the weight values ​​of the number of inquiries Xwrs, the hospital area Yym and the distance to seek a diagnosis Xzj, and R is represented by the correction constant. 1 +a 2 +a 3 ≤1.

0.

5. The big data-based medical resource optimization allocation system according to claim 4, characterized in that: Based on the acquisition of medical resource usage data and patient demand data, the waiting factor Ddyz is obtained. The waiting factor Ddyz is obtained through the following formula: In the formula, Ysc represents the doctor's business hours, b 1 , b 2 and b 3 They are respectively represented as the weight values ​​of the number of windows with the same business Ywck, the number of people in queues Pdrs and the doctor's business hours Ysc, and C is represented as the correction constant.

6. The big data-based medical resource optimization allocation system according to claim 5, characterized in that: Comparatively analyzing the waiting factor Ddyz with the preset waiting threshold Q; When the waiting factor Ddyz is higher than the preset waiting threshold Q, that is, Ddyz > Q, it indicates that the medical resource service inside the current hospital is in a tense state; When the waiting factor Ddyz is lower than the preset waiting threshold Q, that is, Ddyz < Q, it indicates that the medical staff has successfully controlled the decline in medical satisfaction caused by patients' waiting and provided good medical quality for patients.

7. The big data-based medical resource optimization allocation system according to claim 1, characterized in that: Comparatively analyzing the patient satisfaction index MYzs with the preset satisfaction threshold K to obtain a hierarchical satisfaction optimization strategy: When K + 13 ≤ MYzs ≤ K + 16, a first-level notification is obtained, indicating that the current patient's experience is very good and the medical service staff is considered to be in an efficient working state; When K + 7 ≤ MYzs ≤ K + 12, a second-level notification is obtained, indicating that the current patient is moderately satisfied with the medical service and the service efficiency needs to be further improved; When K + 1 ≤ MYzs ≤ K + 6, a third-level notification is obtained, indicating that the current patient's experience satisfaction is in a low state; When MYzs ≤ K, a fourth-level notification is obtained, indicating that the current patient is very dissatisfied with the medical experience. At this time, the medical staff and the hospital need to conduct a thorough review and improve the service process and strengthen training.

8. The big data-based medical resource optimization allocation system according to claim 7, characterized in that: The communication processing module includes a feedback management unit and a tracking unit; The feedback management unit is used to transmit the obtained corresponding level results to the corresponding business processing personnel or managers through communication technology and make a patient satisfaction strategy in a timely manner; The tracking unit is used to monitor various data inside the hospital in real time after adopting the corresponding strategy according to the level notification to prevent the failure to make a processing strategy in time due to the occurrence of emergencies.

9. A big data-based medical resource optimization allocation method, applied to the big data-based medical resource optimization allocation system described in claim 1, characterized in that: It includes the following steps: Step 1: Collect patient demand data and medical resource usage data in the hospital through the big data collection module and transmit them to the medical resource library in real time; Step 2: Use the pre-processing module to clean and integrate the collected data, remove redundant data and form a comprehensive medical resource library; Step 3: Perform in-depth analysis on the processed data through the medical analysis module, obtain the slogan visibility coefficient Kjxs, the guidance factor Dzyz and the waiting factor Ddyz, and then calculate and fit the patient satisfaction index MYzs; Step 4: Compare and analyze the waiting factor Ddyz with the preset waiting threshold Q through the configuration optimization module to determine the optimization strategy; compare and analyze the patient satisfaction index MYzs with the preset satisfaction threshold K to determine the level satisfaction optimization strategy; Step 5: The communication processing module will ensure the timely delivery of the grade results, and continuously monitor the situation within the hospital after the strategy is made, and formulate strategies in a timely manner in the face of emergencies.

Images