Inpatient bed information intelligent management system and method

Abstract

The invention discloses an intelligent management system and method for inpatient bed information, and relates to the technical field of bed information management. The system comprises a bed information monitoring module, a scheduling decision management module, an early warning and pre-scheduling module and an interaction and notification module which run in sequence, the technical key points are as follows: the bed availability rate of each department is compared with a standard threshold value in real time, and the bed tension state grade is judged in combination with a rule engine, so that the intelligent level of hospital bed management is effectively improved; when the department beds are in shortage, a scheduling instruction is automatically started, and a proper department is screened out for bed scheduling according to the actual distance and the bed state level; by setting a flexible M% calculation formula, the reasonability of bed scheduling is ensured, the change of the loose degree of the bed in the department is fully considered, and excessive allocation of the bed is avoided; the bed use efficiency is improved, the tension condition of the bed is relieved, the medical experience of the patient is optimized, and the overall operation efficiency of the hospital is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of bed information management, and in particular to an intelligent management system and method for inpatient bed information. Background Art

[0002] Bed information management refers to the comprehensive, accurate and timely management and recording of the real-time status, availability, occupancy and other related information of beds in various departments within the hospital; it involves multiple links such as bed allocation, scheduling, and reservation, and is an important part of hospital operation management; through the bed information management system, medical staff can understand the availability and occupancy of beds in various departments in real time, and provide accurate information support for patients' hospitalization arrangements; therefore, bed information management is an indispensable part of hospital management and is of great significance to ensuring the smooth progress of medical services.

[0003] The technical solution pointed out in the document of the existing application publication number CN117196349A, entitled A Intelligent Management System for Inpatient Bed Information, includes: if the value of the weather change index exceeds the weather change threshold, the model established by the BP neural network is trained to generate a bed demand prediction model to predict the demand for beds in the hospital and obtain the prediction result; the trained cleaning evaluation model is used to evaluate whether the corresponding bed needs to be cleaned, and if cleaning is required, a cleaning instruction is issued; the corresponding bed allocation rules are matched according to the condition information of the patient to be hospitalized, and the trained bed allocation model allocates the corresponding bed to the patient from a number of idle beds, and the allocated bed location information is issued; the feedback coefficient of bed allocation is generated from the feedback data set, and when the feedback coefficient exceeds the feedback threshold, a revision instruction is issued to quickly allocate the corresponding bed to the patient, so as to achieve high efficiency and low error rate and reduce human intervention; the management direction of the above scheme is to allocate the corresponding beds to the patients, and does not consider how to solve the problem in a targeted manner if the beds are insufficient.

[0004] In combination with the above documents and existing technologies, there are many technical problems in traditional hospital bed management; for example, bed allocation often relies on manual judgment and lacks the support of real-time data and intelligent algorithms, resulting in the inability to accurately determine the bed shortage status and inefficient bed scheduling; in emergency situations, the demand for beds surges, and manual scheduling is difficult to respond quickly, which may cause patients to be unable to receive medical treatment in time; at the same time, there is a lack of scientific calculation models in the bed allocation process, and allocation is based solely on experience, which can easily lead to excessive or insufficient allocation of beds, affecting the hospital's operating efficiency; for example, when a department is short of beds, manual scheduling may take a long time to find a suitable department for bed transfer, delaying the patient's treatment; and in emergency situations, there may be an increase in the number of patients, and manual predictions of the increase in bed demand are inaccurate, which may lead to insufficient beds and affect patient treatment. Summary of the invention

[0005] 1. Technical issues to be resolved In view of the deficiencies in the prior art, the present invention provides an intelligent management system and method for inpatient bed information, which solves the problems raised in the background technology by operating the management system.

[0006] (II) Technical solution To achieve the above objectives, the present invention is implemented through the following technical solutions: An intelligent management system for inpatient bed information, the system comprising: Bed information monitoring module, real-time acquisition of bed-related information of each department of the inpatient department; The scheduling decision management module compares the bed availability of each department with the standard threshold. Based on the comparison results, it combines the established rule engine to determine the bed shortage level of the department and uses the bed scheduling algorithm model to schedule beds between departments. The early warning and pre-scheduling module triggers the pre-scheduling mechanism in the surgical room when there is a meteorological warning for future weather, establishes a correlation model between weather and bed demand, predicts the increase in bed demand, and implements bed adjustment strategies; The interaction and notification module sends bed scheduling results in real time to display bed changes.

[0007] Furthermore, bed-related information includes bed status, basic patient data, and the bed availability rate corresponding to each department calculated through statistics; The bed status includes at least: free, occupied, and under maintenance; The basic data of the patient shall at least include: the name, age and gender of the patient in the corresponding bed; The process of calculating bed availability is as follows: According to the bed status, the number of vacant beds in the department is obtained, and the total number of beds in the department is summarized; The bed availability rate is calculated according to the following formula: Bed availability rate = (number of vacant beds in the department / total number of beds in the department) * 100%.

[0008] Furthermore, the comparison results are combined with the application process of the rule engine as follows: When the bed availability rate is greater than the second threshold, the department's bed shortage level is determined to be level one; When the second threshold ≥ bed availability rate > first threshold, the department's bed shortage level is determined to be level 2; When the first threshold is ≥ bed availability, the department’s bed shortage level is determined to be level three; Among them, the range of the standard threshold is {mo1, mo2}; mo1 and mo2 represent the first threshold and the second threshold respectively, and mo1<mo2; Furthermore, the process of applying the bed scheduling algorithm model is as follows: When the bed shortage level of any target department reaches level three, the dispatch instruction is initiated to select other departments that meet the agreed conditions and transfer M% of the beds from other departments to the target department; The constraints that must be met are: Condition 1: Other departments that are actually closest to the target department; Condition 2: Other departments are in a level 1 bed shortage situation; When M% of beds are transferred from other departments to the target department: When the bed availability rate of other departments does not exceed 50%, the M% here = the bed availability rate of other departments - 30%; when the bed availability rate of other departments exceeds 50%, the M% here = (the bed availability rate of other departments - 50%) * K + B; where K and B are constants, and 0<K<1, B=[5%, 10%].

[0009] Furthermore, when the weather conditions of the future weather do not include rain, snow or strong winds, it means that there is no meteorological warning; when the weather conditions of the future weather include rain, snow or strong winds, it means that there is a meteorological warning.

[0010] Furthermore, the process of establishing the correlation model between weather and bed demand is as follows: Collect historical data, including weather forecast data and bed occupancy data of corresponding surgical rooms; Based on historical data, data mining and machine learning techniques were used to construct a correlation model between weather and bed demand. Based on future weather forecast data, the increase in demand for surgical room beds was predicted.

[0011] Furthermore, the bed adjustment strategy implemented is: Screen out other departments that meet the agreed conditions, and set M% of beds to be transferred from other departments; When M% of the beds are not less than the predicted increase in demand, the beds corresponding to the increase in demand will be transferred from other departments; When M% of beds are less than the predicted increase in demand, M% of beds will be transferred from other departments, and other current departments will be excluded. The action of screening out other departments that meet the agreed conditions will continue. At this time, the increase in demand has deducted M% of beds transferred from other departments, until the transferred beds meet the predicted increase in demand; A function calculation model is constructed, which inputs the collected increase in demand D and the distance value d corresponding to other departments actually closest to the surgical room, and outputs the estimated number of additional beds E for advance allocation.

[0012] Furthermore, the formula used in the constructed function calculation model is as follows: ; In the formula, Express Round up, k represents a constant, and its value range is [1, 2].

[0013] Furthermore, the bed scheduling result includes the scheduling process and results of the scheduling decision management module and the early warning pre-scheduling module.

[0014] An intelligent management method for inpatient bed information comprises the following steps: S1. Obtain bed-related information of each department of the inpatient department in real time; S2. Compare the bed availability rate of each department with the standard threshold. Based on the comparison results, the established rule engine is used to determine the bed shortage level of the department, and the bed scheduling algorithm model is used to schedule beds between departments. S3. Under the condition of obtaining a meteorological warning for future weather, trigger the pre-dispatching mechanism in the surgical room, establish a correlation model between weather and bed demand, predict the increase in bed demand, and implement a bed adjustment strategy; S4. Send bed scheduling results in real time to display bed changes.

[0015] (III) Beneficial effects The present invention provides an intelligent management system and method for inpatient bed information, which has the following beneficial effects: (1) This solution effectively improves the intelligent level of hospital bed management by comparing the bed availability rate of each department with the standard threshold in real time and combining it with the rule engine to determine the level of bed shortage. When the department is short of beds, the dispatch instruction is automatically started, and the appropriate department is selected for bed dispatch based on the actual distance and bed status level. By setting a flexible M% calculation formula, the rationality of bed dispatch is guaranteed, and the changes in the degree of bed availability in the department are fully considered, thus avoiding excessive allocation of beds. This not only improves the efficiency of bed utilization and alleviates the bed shortage, but also optimizes the patient medical experience and improves the overall operational efficiency of the hospital. (2) This solution implements a bed pre-dispatch mechanism under meteorological warning conditions by establishing a correlation model between weather and bed demand. It obtains weather warning information in real time and combines historical data mining and machine learning technology to predict the increase in surgical bed demand, effectively solving the problem of bed shortage in bad weather. At the same time, by setting a flexible bed adjustment strategy, it can automatically transfer the required beds from other departments or external departments to ensure that the bed demand of surgical departments such as orthopedics is met in a timely manner. In addition, the constructed function calculation model further considers the impact of the increase in demand and the distance between departments on the estimated number of additional beds, providing a scientific basis for staff deployment. The application of this technical solution not only improves the predictability and flexibility of hospital bed management, but also optimizes the allocation of bed resources, avoids excessive or insufficient allocation of beds, effectively improves the hospital's ability to respond to emergencies, ensures patients' timely medical treatment and treatment effects, and provides an intelligent and efficient solution for hospital bed management. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 It is a modular schematic diagram of an intelligent management system for inpatient bed information in the present invention; Figure 2 The figure is a schematic diagram of the overall process of an intelligent management method for inpatient bed information in the present invention. DETAILED DESCRIPTION

[0017] 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.

[0018] Embodiment 1: See also Figure 1 , this embodiment provides an intelligent management system for inpatient bed information; This inpatient bed information intelligent management system is designed to achieve flexible scheduling of beds between departments, especially when severe weather (such as rain, snow, strong wind) causes a surge in orthopedic patients, so that bed scheduling can be carried out in advance to meet patient needs; the system improves bed utilization efficiency through intelligent and automated methods to ensure that patients can receive timely treatment; The functional modules are designed as follows: The system includes a bed information monitoring module, a scheduling decision management module, an early warning pre-scheduling module, and an interaction and notification module, which are operated in sequence, among which the scheduling decision management module and the early warning pre-scheduling module are the core modules of the system; The specific functional modules are described as follows: Bed information monitoring module, real-time acquisition of bed-related information of each department of the inpatient department; Among them, bed-related information includes bed status, basic patient data, and the bed availability rate corresponding to each department calculated through statistics; specifically, bed-related information is obtained through Internet of Things technology, such as bed sensors, RFID tags, etc., to achieve automatic collection of bed information; The bed status includes at least: vacant, occupied, and under maintenance; The basic data of the patient shall at least include: the name, age and gender of the patient in the corresponding bed; The process of calculating the bed availability rate corresponding to each department is as follows: According to the bed status, the number of vacant beds in the department is obtained, and the total number of beds in the department is summarized; The bed availability rate is calculated according to the following formula: Bed availability rate = (number of vacant beds in the department / total number of beds in the department) * 100%; For example, if the number of vacant beds in a department is 50 and the total number of beds in the department is 100, then the bed availability rate of the department is 50%, which means that 50% of the beds in the department are vacant and available; The bed information monitoring module uses Internet of Things technologies, such as bed sensors and RFID tags, to obtain real-time bed-related information of each department in the inpatient department, including bed status (free, occupied, under maintenance), basic patient data (name, age, gender), and bed availability. The implementation of this module greatly improves the accuracy and real-time nature of bed information. By automatically collecting bed status, the system can quickly summarize the number of free beds and the total number of beds in the department, and then calculate the bed availability. This data provides hospital managers with intuitive bed usage information, which helps them make timely bed scheduling decisions. The use of the bed information monitoring module can improve the efficiency of hospital bed management, and to a certain extent ensure that patients can obtain bed resources in a timely manner, thereby improving the quality and satisfaction of medical services. At the same time, the real-time update of bed availability also provides strong support for hospitals to respond to emergencies.

[0019] The scheduling decision management module compares the bed availability of each department with the standard threshold. Based on the comparison results, it combines the established rule engine to determine the bed shortage level of the department and uses the bed scheduling algorithm model to schedule beds between departments. Among them, the comparison process: After the system obtains the bed availability rate of each department in real time, it will compare it with the preset standard threshold; The standard threshold can be set according to the actual situation and operation strategy of the hospital. In this embodiment, the range of the standard threshold is {mo1, mo2}, where mo1 and mo2 represent the first threshold and the second threshold respectively, and mo1=15%, mo2=30%; For example, a bed availability rate below 30% can be considered a threshold for a tight situation, and a bed availability rate below 15% can be considered a threshold for a very tight situation. The specific values ​​can be adjusted based on the hospital's historical data and operational needs. Comparison results combined with the application of rule engine: If the bed availability rate is greater than the second threshold, the department's bed shortage level is determined to be level one, indicating that the department's bed status is normal; if the second threshold ≥ bed availability rate > first threshold, the department's bed shortage level is determined to be level two, indicating that the department's beds are in a moderate state and beds cannot be transferred; if the first threshold ≥ bed availability rate, the department's bed shortage level is determined to be level three, indicating that the department's beds are in a very tight state and emergency dispatch measures need to be taken immediately; The process of using the bed scheduling algorithm model is as follows: In the same medical institution, when the bed shortage level of any target department is level three, the dispatch instruction is initiated to screen out other departments that meet the agreed conditions, and transfer M% of beds from other departments to the target department (if the bed shortage level of the target department is still level three, the departments that have transferred out beds are excluded, and other departments that meet the constraint conditions are continuously screened. If it is still level three, beds can be transferred from outside); When there are two or more target departments with a bed shortage level of level three, one-to-one operations can be performed in the same way as the above-mentioned start scheduling instruction, which will not be elaborated here; The constraints that must be met are: Condition 1: Other departments that are actually closest to the target department; Condition 2: The other departments are in a level 1 bed shortage situation (if not, beds will be directly transferred from outside); When M% of beds are transferred from other departments to the target department: When the bed availability rate of other departments does not exceed 50%, then M% = bed availability rate of other departments - 30%; when the bed availability rate of other departments exceeds 50%, then M% = (bed availability rate of other departments - 50%) * K + B; where K and B are constants used to adjust the range and slope of M%, and 0<K<1, B=[5%, 10%]; It should be noted that, considering that a bed availability rate of more than 50% means that the department has relatively more vacant beds, we can set M% to a value that gradually decreases as the bed availability rate increases (but still remains positive or zero to avoid negative values) to reflect the relative degree of bed sparseness in the department; For example: when K=0.5 and B=10%, the formula becomes: M%=(corresponding bed availability of other departments - 50%)*0.5+10%; Thus, when the bed availability rate is 60%, then M% = (60% - 50%) * 0.5 + 10% = 15%; When the bed availability rate is 70%, then M% = (70% - 50%) * 0.5 + 10% = 20%; And so on; The formula can be adjusted based on the actual needs of the hospital to better reflect changes in the degree of bed availability in departments; The scheduling decision management module compares the bed availability of each department with the standard threshold in real time, and determines the level of bed shortage status in combination with the rule engine, effectively improving the intelligent level of hospital bed management. When the department is short of beds, the module can automatically start the scheduling command and select suitable departments for bed scheduling based on the actual distance and bed status level. By setting a flexible M% calculation formula, it not only ensures the rationality of bed scheduling, but also fully considers the changes in the degree of bed availability in the department, avoiding excessive allocation of beds. The application of this module not only improves the efficiency of bed utilization and alleviates the bed shortage, but also optimizes the patient medical experience and improves the overall operational efficiency of the hospital. At the same time, the adjustability of the module enables the hospital to flexibly configure parameters according to actual needs, better adapt to different operating strategies, and provide a scientific and efficient solution for hospital bed management.

[0020] The early warning and pre-dispatch module triggers the pre-dispatch mechanism in the surgical department when there is a meteorological warning for future weather, establishes a correlation model between weather and bed demand, predicts the increase in bed demand, and implements a bed adjustment strategy (if the increase in demand is not large, pre-dispatch from other departments where beds are not in short supply; if the increase is large, beds are transferred from outside); Among them, by connecting to the meteorological station through the Internet of Things technology, the local weather conditions for a fixed period in the future can be obtained. For example, if there is no rain, snow or strong wind within a fixed period of one week, it means that there is no weather warning; If rain, snow or strong winds are expected in the future, it means there is a weather warning; The surgical room mentioned above usually refers to the orthopedic department. Due to the influence of rain and snow, the probability of pedestrian or car accidents is greatly increased. The most direct manifestation is the surge in surgical injuries such as fractures or contusions. Therefore, it is necessary to urgently dispatch beds. Usually in actual use, there is insufficient space in the inpatient ward, so the beds need to be arranged in the corridor or even the aisle. The process of modeling the association between weather and bed demand is as follows: Collect historical data, including weather forecast data and bed occupancy data of corresponding surgical rooms; Based on historical data, data mining and machine learning techniques were used to build a correlation model between weather and bed demand. Based on future weather forecast data, the increase in demand for surgical beds was predicted. The specific instructions are as follows: Historical weather forecast data collection: In the past five years, the area where the hospital is located has experienced an average of 30 days of rain and snow and 20 days of strong wind weather each winter; in rainy, snowy and windy weather, the number of orthopedic patients increased by about 30% compared to normal times; historical data collection of bed availability rates in corresponding surgical departments: during rainy, snowy and windy weather, the average occupancy rate of orthopedic beds rose to 95%, compared to 70% at normal times; the average length of stay for orthopedic patients was 7 days, but during severe weather, due to the surge in patients, the length of stay for some patients may be extended; association model establishment: based on the above historical data, the hospital used data mining and machine learning techniques to construct an association model between weather and bed demand; the model shows that whenever rainy, snowy and strong wind weather lasts for one day, the demand for orthopedic beds will increase by about 10 beds; Weather warning and bed pre-dispatch example: Weather warning reception: On January 10, XX, the meteorological department issued a warning, predicting continuous rain and snow from January 12 to January 14, accompanied by strong winds; Bed pre-dispatch decision: After receiving the weather warning, the system immediately starts the weather warning and bed pre-dispatch module; According to the correlation model prediction, the demand for orthopedic beds will increase by about 30 beds in the next three days (10 beds / day × 3 days = 30 beds); The bed adjustment strategy implemented dispatches the required beds from other departments to the orthopedic department to meet the bed demand in the next three days; At the same time, the hospital also prepared 5 temporary beds to cope with possible additional bed demand; The bed adjustment strategies implemented are: Filter out other departments that meet the agreed conditions, set M% of beds to be transferred out from other departments, and when M% of beds are not less than the predicted increase in demand, transfer the beds of the increased demand from other departments; when M% of beds are less than the predicted increase in demand, transfer M% of beds from other departments, exclude other current departments, and continue to filter out other departments that meet the agreed conditions. At this time, the increase in demand needs to deduct M% of beds transferred out from other departments until the transferred beds meet the predicted increase in demand; (If it still cannot be satisfied, it can be retrieved from outside); A function calculation model is constructed, which inputs the collected demand increase D and the distance value d corresponding to other departments that are actually closest to the surgical department (i.e. the target department), and outputs the estimated number of additional beds E for staff to make advance arrangements; The formula used in the constructed function calculation model is as follows: ; In the formula, Express Round up, k represents a constant, and its value range is [1, 2]; Logical explanation: √D is used to represent the impact of the predicted increase in demand on the additional beds, maintaining a nonlinear relationship; k is used to adjust the impact of distance on the demand for additional beds; log(d+1) uses a logarithmic function to represent the impact of distance on the additional beds, so that when d increases, E will also increase to a certain extent, but the rate of increase will gradually slow down; Example: Assume constant k=1, refer to Table 1 below; Table 1: Calculation of additional beds for different predicted increases in demand and actual distance values;

[0021] From this formula and table, we can see that: 1. When the predicted increase in demand D increases, the number of additional beds E also increases; 2. When the actual distance value d increases, the estimated number of additional beds E also increases to a certain extent, but the rate of increase gradually slows down (due to the nature of the logarithmic function); The results are all positive integers, which meet the actual requirements; In practice, the value of k can be adjusted according to the situation to better meet the needs of a specific hospital or scenario; In summary, due to the advance pre-dispatch of beds, the hospital successfully coped with the surge in orthopedic patients during the rainy and snowy weather, and no patients were delayed in treatment due to insufficient beds; through real-time monitoring and flexible adjustments, the hospital also successfully responded to possible additional bed demands and ensured the quality and efficiency of medical services; the weather warning and bed pre-dispatch example demonstrated the effect of the warning pre-dispatch module in actual application. By collecting historical data, establishing correlation models, predicting bed demands, and implementing pre-dispatch operations, the hospital can prepare in advance and effectively respond to the surge in patients in severe weather.

[0022] Through the above technical solutions, a correlation model between weather and bed demand was established, and a bed pre-dispatch mechanism under meteorological warning conditions was realized. Weather warning information was obtained in real time through the Internet of Things technology, and the increase in surgical bed demand was predicted by combining historical data mining and machine learning technology, effectively solving the problem of bed shortage in severe weather. At the same time, by setting a flexible bed adjustment strategy, the required beds can be automatically transferred from other departments or external departments to ensure that the bed demand of surgical departments such as orthopedics is met in a timely manner; in addition, the constructed function calculation model further considers the impact of the increase in demand and the distance between departments on the estimated number of additional beds, providing a scientific basis for staff to allocate; The application of this technical solution not only improves the predictability and flexibility of hospital bed management, but also optimizes the allocation of bed resources, avoids excessive or insufficient allocation of beds, effectively improves the hospital's ability to respond to emergencies, ensures patients' timely medical treatment and treatment effects, and provides an intelligent and efficient solution for hospital bed management.

[0023] The interaction and notification module sends bed scheduling results in real time to display bed changes; Among them, the bed scheduling result represents the scheduling process and results of the scheduling decision management module and the early warning pre-scheduling module; In addition, when users (including medical staff) perform bed query, reservation or scheduling operations in the system, the system will immediately process these requests and generate bed scheduling results based on the actual situation; these results not only include the latest status of the bed, such as whether it is available, has been reserved or has been assigned to which patient, but also record in detail the specific time, reason and relevant personnel information of the bed scheduling; To ensure that these critical messages are delivered in real time, the existing notification system is also used; The system will automatically select the most appropriate notification method (such as SMS, APP push, email, etc.) according to the user's role and authority, and send the bed scheduling results to relevant personnel in a timely manner; for example, medical staff may receive APP push notifications so that they can quickly respond to bed changes and make subsequent medical arrangements; patients and their families may receive notifications via SMS or email to ensure that they are always aware of the latest bed conditions; In this way, the interaction and notification module effectively solves the problem of poor bed information transmission, improves the work efficiency of medical staff and the satisfaction of patients; at the same time, the intuitive and easy-to-use user interface and mobile access support also make bed management more convenient and efficient.

[0024] Embodiment 2: See also Figure 2 Based on Example 1, this embodiment also provides an intelligent management method for inpatient bed information, including the following specific steps: S1. Obtain bed-related information of each department of the inpatient department in real time; The bed-related information includes bed status (vacant, occupied, or under repair), basic patient data (patient name, age, and gender), and the bed availability rate corresponding to each department calculated through statistics; S2. Compare the bed availability rate of each department with the standard threshold. Based on the comparison results, the established rule engine is used to determine the bed shortage level of the department, and the bed scheduling algorithm model is used to schedule beds between departments. Among them, the range of the standard threshold is {mo1, mo2}; mo1 and mo2 represent the first threshold and the second threshold respectively, and mo1<mo2; when the bed availability rate>the second threshold, it is determined that the bed shortage level of the department is level one; When the second threshold ≥ bed availability rate > first threshold, the department's bed shortage level is determined to be level 2; When the first threshold is ≥ bed availability, the department’s bed shortage level is determined to be level three; S3. Under the condition of obtaining a meteorological warning for future weather, trigger the pre-dispatching mechanism in the surgical room, establish a correlation model between weather and bed demand, predict the increase in bed demand, and implement a bed adjustment strategy; The bed adjustment strategy is as follows: Screen out other departments that meet the agreed conditions, and set M% of beds to be transferred from other departments; When M% of the beds are not less than the predicted increase in demand, the beds corresponding to the increase in demand will be transferred from other departments; When M% of beds are less than the predicted increase in demand, M% of beds will be transferred from other departments, and other current departments will be excluded. The action of screening out other departments that meet the agreed conditions will continue. At this time, the increase in demand has deducted M% of beds transferred from other departments, until the transferred beds meet the predicted increase in demand; A function calculation model is constructed, which inputs the collected demand increase D and the distance value d corresponding to other departments closest to the surgical department, and outputs the estimated number of additional beds E for pre-allocation; S4. Send bed scheduling results in real time to display bed changes.

[0025] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented using software, the above embodiments may be implemented in whole or in part in the form of a computer program product. A person of ordinary skill in the art may appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein may be implemented in electronic hardware, or in a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution.

[0026] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, and may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0027] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. An intelligent management system for inpatient bed information, characterized in that: The system includes: Bed information monitoring module, real-time acquisition of bed-related information of each department of the inpatient department; The scheduling decision management module compares the bed availability of each department with the standard threshold. Based on the comparison results, it combines the established rule engine to determine the bed shortage level of the department and uses the bed scheduling algorithm model to schedule beds between departments. The early warning and pre-scheduling module triggers the pre-scheduling mechanism in the surgical room when there is a meteorological warning for future weather, establishes a correlation model between weather and bed demand, predicts the increase in bed demand, and implements bed adjustment strategies; The interaction and notification module sends bed scheduling results in real time to display bed changes.

2. The intelligent management system for inpatient bed information according to claim 1 is characterized by: Bed-related information includes bed status, basic patient data, and the bed availability rate corresponding to each department calculated through statistical calculations; The bed status includes at least: free, occupied, and under maintenance; The basic data of the patient shall at least include: the name, age and gender of the patient in the corresponding bed; The process of calculating bed availability is as follows: According to the bed status, the number of vacant beds in the department is obtained, and the total number of beds in the department is summarized; The bed availability rate is calculated according to the following formula: Bed availability rate = (number of vacant beds in the department / total number of beds in the department) * 100%.

3. The intelligent management system for inpatient bed information according to claim 1 is characterized by: The comparison results combined with the application process of the rule engine are as follows: When the bed availability rate is greater than the second threshold, the department’s bed shortage level is determined to be level one; When the second threshold ≥ bed availability rate > first threshold, the department's bed shortage level is determined to be level 2; When the first threshold is ≥ bed availability, the department’s bed shortage level is determined to be level three; Among them, the range of the standard threshold is {mo1, mo2}; mo1 and mo2 represent the first threshold and the second threshold respectively, and mo1<mo2.

4. The intelligent management system for inpatient bed information according to claim 3 is characterized by: The process of using the bed scheduling algorithm model is as follows: When the bed shortage level of any target department reaches level three, the dispatch instruction is initiated to select other departments that meet the agreed conditions and transfer M% of the beds from other departments to the target department; The constraints that must be met are: Condition 1: Other departments that are actually closest to the target department; Condition 2: Other departments are in a level 1 bed shortage situation; When M% of beds are transferred from other departments to the target department: When the bed availability rate of other departments does not exceed 50%, M%=the bed availability rate of other departments-30%; when the bed availability rate of other departments exceeds 50%, M%=(the bed availability rate of other departments-50%)*K+B; where K and B are constants, and 0<K<1, B=[5%, 10%].

5. The intelligent management system for inpatient bed information according to claim 1 is characterized by: When the weather conditions for future weather do not include rain, snow or strong winds, it means that there is no weather warning; when the weather conditions for future weather include rain, snow or strong winds, it means that there is a weather warning.

6. The intelligent management system for inpatient bed information according to claim 1 is characterized by: The process of modeling the association between weather and bed demand is as follows: Collect historical data, including weather forecast data and bed occupancy data of corresponding surgical rooms; Based on historical data, data mining and machine learning techniques were used to construct a correlation model between weather and bed demand. Based on future weather forecast data, the increase in demand for surgical room beds was predicted.

7. The intelligent management system for inpatient bed information according to claim 4 is characterized by: The bed adjustment strategies implemented are: Screen out other departments that meet the agreed conditions, and set M% of beds to be transferred from other departments; When M% of the beds are not less than the predicted increase in demand, the beds corresponding to the increase in demand will be transferred from other departments; When M% of beds are less than the predicted increase in demand, M% of beds will be transferred from other departments, and other current departments will be excluded. The action of screening out other departments that meet the agreed conditions will continue. At this time, the increase in demand has deducted M% of beds transferred from other departments, until the transferred beds meet the predicted increase in demand; A function calculation model is constructed, which inputs the collected increase in demand D and the distance value d corresponding to other departments actually closest to the surgical room, and outputs the estimated number of additional beds E for advance allocation.

8. The intelligent management system for inpatient bed information according to claim 7 is characterized by: The formula used in the constructed function calculation model is as follows: ; In the formula, Express Round up, k represents a constant, and its value range is [1, 2].

9. The intelligent management system for inpatient bed information according to claim 1 is characterized by: The bed scheduling results include the scheduling process and results of the scheduling decision management module and the early warning pre-scheduling module.

10. An intelligent management method for inpatient bed information, using any system described in claim 1 to claim 9, characterized in that: The steps include: S1. Obtain bed-related information of each department of the inpatient department in real time; S2. Compare the bed availability rate of each department with the standard threshold. Based on the comparison results, the established rule engine is used to determine the bed shortage level of the department, and the bed scheduling algorithm model is used to schedule beds between departments. S3. Under the condition of obtaining a meteorological warning for future weather, trigger the pre-dispatching mechanism in the surgical room, establish a correlation model between weather and bed demand, predict the increase in bed demand, and implement a bed adjustment strategy; S4. Send bed scheduling results in real time to display bed changes.

Images