Hospital cleaning task supervision method and system, program product and storage medium

Abstract

The invention provides a hospital cleaning task supervision method and system, a program product and a storage medium, and relates to the technical field of hospital cleaning supervision. Pollution degree data is calculated by collecting human traffic data and medical operation frequency data of a functional area, and the priority of cleaning tasks is determined, so that the sequence of the cleaning tasks is matched with the actual smudginess condition of the area. On the basis, key tasks and conventional tasks are distinguished, a supervision path is constructed by applying a minimum path algorithm for functional areas corresponding to the key tasks, and the areas corresponding to the key tasks can be comprehensively and timely supervised by means of the path; the conventional tasks in the same functional area and the conventional tasks corresponding to the functional areas in the coverage range of the supervision path can also be planned based on the path, so that an efficient supervision mode with highlighted key points and comprehensive consideration is realized, the supervision process of the cleaning task is optimized, and the overall cleaning effect and efficiency are improved.

Description

Technical Field

[0001] This application relates to the technical field of hospital cleaning supervision, and particularly to a hospital cleaning task supervision method, system, program product, and storage medium. Background Art

[0002] In the operation and management of modern hospitals, maintaining a good hygienic environment is of utmost importance. Hospitals contain numerous areas with different functions, such as outpatient halls, wards, operating rooms, and laboratories. These areas have a large number of people flowing in and various medical operations being carried out every day, making it easy to generate different degrees of pollution. To ensure the cleanliness and hygiene of the hospital environment, it is necessary to conduct reasonable and effective supervision of cleaning tasks to ensure that each area can complete the cleaning work in a timely and high-quality manner, improving the overall hygiene level of the hospital and the patient's medical experience.

[0003] Currently, the common hospital cleaning task supervision method mainly involves supervising the hospital according to a pre-set fixed schedule. Through the pre-planned time and task arrangements, it attempts to ensure that each area can maintain a certain level of cleanliness to meet the daily hospital operation requirements.

[0004] However, with the fixed-time cleaning tasks, it becomes difficult to meet the actual cleaning needs. Moreover, the relevant hospital cleaning task supervision methods are even less able to adapt to the changes in cleaning tasks. Areas with a rapidly rising pollution level and in urgent need of enhanced supervision are still supervised according to the conventional fixed schedule, while some areas with little actual change in pollution level and not requiring frequent supervision are still continuously monitored at the established frequency, wasting human and material resources. In short, this fixed-schedule supervision method lacks a dynamic response to the real-time hygiene changes in each functional area and cannot flexibly adjust the cleaning tasks and supervision priorities based on the actual pollution situation. Summary of the Invention

[0005] This application provides a hospital cleaning task supervision method, system, program product, and storage medium for flexibly adjusting cleaning tasks and supervision priorities based on the actual pollution situation.

[0006] In a first aspect, the present application provides a method for supervising hospital cleaning tasks, including: obtaining pollution degree data of different functional areas, where the pollution degree data is calculated based on the pedestrian flow data of the functional areas and the medical operation frequency data of the functional areas; determining the priority of the cleaning tasks corresponding to the functional areas according to the pollution degree data; generating a task time sequence chain based on the priority; determining the supervision priority according to the last supervision time of different functional areas and the corresponding pollution degree data; adjusting the supervision priority according to the personnel experience and historical problem occurrence rate corresponding to the cleaning tasks; where the greater the corresponding personnel experience, the more negatively correlated with the supervision priority, and the historical problem occurrence rate is positively correlated with the supervision priority; classifying the cleaning tasks into key tasks and regular tasks according to the adjusted supervision priority; applying the minimum path algorithm to construct a supervision path for the functional areas corresponding to the key tasks; determining the supervision tasks and order according to the supervision path, where the supervision tasks include all the cleaning tasks corresponding to the supervised areas, and the supervised areas include the functional areas corresponding to the key tasks and the regular areas covered by the supervision path.

[0007] By adopting the above technical solution, the pollution degree data is calculated by collecting the pedestrian flow data and medical operation frequency data of the functional areas. The pedestrian flow intuitively reflects the possible pollution brought by personnel activities, and the medical operation frequency reflects the hygienic impact generated by specific medical behaviors. The combination of the two can quantify the pollution degree of each area. Based on this pollution degree data, the priority of the cleaning tasks is determined, which makes the order of the cleaning tasks match the actual dirtiness of the area. On this basis, the supervision priority is determined by combining the last supervision time of different functional areas, the personnel experience corresponding to the cleaning tasks, and the historical problem occurrence rate. In this way, key tasks and regular tasks are distinguished. For the functional areas corresponding to the key tasks, the minimum path algorithm is applied to construct a supervision path. With this route, the areas corresponding to the key tasks can be comprehensively and timely supervised. At the same time, the regular tasks within the same functional area and the regular tasks corresponding to the functional areas covered by the supervision path can also rely on this path planning, realizing an efficient supervision mode with key points highlighted and overall consideration, optimizing the cleaning task supervision process, and improving the overall cleaning effect and efficiency.

[0008] In combination with some embodiments of the first aspect, in some embodiments, after the step of generating a task timing chain according to priority, the method also includes: obtaining the spatial coordinate data of the functional area corresponding to the cleaning task and the preset task duration of the cleaning task; based on the spatial coordinate data, calculating the distance between any two functional areas, and constructing an inter-area distance scoring matrix; calculating the sum of the task durations of all cleaning tasks, and dividing it by the number of cleaning personnel to obtain the per capita target duration; constructing a double-constraint objective function with the inter-area distance scoring matrix as the spatial constraint and the per capita target duration as the time constraint; performing iterative calculations based on the double-constraint objective function, wherein: selecting the number of cleaning personnel areas with the farthest distance as the initial clustering center; calculating the distance scores from other areas to each clustering center; initially assigning other areas to the clustering center with the closest distance; calculating the total duration of each cluster group; when the difference between the total duration of a cluster group and the per capita target duration is greater than the per capita target duration multiplied by a preset ratio, triggering area reallocation; repeating the iteration until the spatial distance score and the duration difference score of the cluster group converge; and outputting the optimized task timing chain.

[0009] By adopting the above technical solution, the spatial coordinate data of the functional area corresponding to the cleaning task and the preset task duration are obtained. The spatial coordinate data provides the basis for the subsequent calculation of the distance between regions, and the task duration is related to the rationality of the work distribution of the cleaning staff. Then, the distance between any two functional areas is calculated based on the spatial coordinate data, and the distance scoring matrix between regions is constructed, which can clearly present the distance relationship between each region in the spatial layout. Then, the sum of the task duration of all cleaning tasks is calculated and divided by the number of cleaning staff to obtain the per capita target duration, which is used as the time constraint. A double-constrained objective function is constructed with the inter-region distance scoring matrix as the spatial constraint and the per capita target duration as the time constraint. When iterative calculations are performed based on this, the area with the farthest number of cleaning staff is selected as the initial cluster center, and then the distance scores of other areas to each cluster center are gradually calculated and initially allocated, and then the area is redistributed according to the total duration of the cluster. The generated task timing chain fully considers the spatial distance between regions and the time allocation of cleaning staff, avoiding the situation where cleaning staff need to run back and forth or round trip between far-flung areas, thereby effectively improving cleaning efficiency, allowing cleaning staff to complete tasks more efficiently, and ensuring that cleaning work is carried out in an orderly and high-quality manner.

[0010] In combination with some embodiments of the first aspect, in some embodiments, area reallocation specifically includes: traversing all area exchange or transfer operations; selecting the operation that can reduce the comprehensive score the most; wherein the comprehensive score is the distance score plus the time score, the distance score is the sum of the distances between any two functional areas in the cluster multiplied by a first coefficient, and the time score is the absolute value of the difference between the total task duration of the cleaning tasks of the cluster and the average target duration per person multiplied by a second coefficient.

[0011] By adopting the above technical solution, in the process of area reallocation, all area exchange or transfer operations are traversed. Each of these operations represents a possibility of adjusting the existing area layout. Then, by setting the comprehensive score as the distance score plus the time score, the distance score is the sum of the distances between pairwise functional areas within the cluster multiplied by the first coefficient, so as to measure the rationality of the spatial layout between areas, and the time score is the absolute value of the difference between the total task duration of the cleaning tasks in the cluster and the per capita target duration multiplied by the second coefficient, to reflect the balance of the cleaning task duration allocation. Select the operation that can reduce the comprehensive score the most for execution, which means that each area reallocation is optimized in the direction of making the distance between areas more reasonable and the cleaning task duration more balanced.

[0012] Combined with some embodiments of the first aspect, in some embodiments, the iterative calculation based on the double-constraint objective function further includes: all cleaning tasks corresponding to the same functional area are regarded as one cleaning task in the iterative calculation.

[0013] By adopting the above technical solution, it is stipulated that in the iterative calculation, all cleaning tasks corresponding to the same functional area are regarded as one cleaning task. This setting fundamentally changes the logic of task allocation. When generating the task time sequence chain and performing relevant area allocation, the situation where different cleaning tasks of the same functional area are dispersed and then assigned to different cleaning personnel is avoided. Duplicate labor is avoided, waste of manpower is reduced, and the cleaning cost is lowered.

[0014] Combined with some embodiments of the first aspect, in some embodiments, after the step of determining the supervision tasks and order according to the supervision path, the method further includes: judging whether the difference in the workloads corresponding to the default areas responsible for different work inspectors is greater than a preset workload threshold according to the supervision tasks; the default area includes several connected functional areas, and the workload is positively correlated with the preset task duration of the cleaning task; when the difference in the workload is greater than the preset workload threshold, the default area with relatively less workload is determined as the expansion area, and the default area with relatively more workload is determined as the reduction area; the functional areas connecting the reduction area and the expansion area are successively incorporated into the expansion area until the difference in the workloads corresponding to the expansion area and the reduction area is not greater than the preset workload threshold.

[0015] By adopting the above technical solution, after determining the supervision tasks and order according to the supervision path, the difference in workload corresponding to the default areas responsible for different work inspectors will be further judged according to the supervision tasks. The default areas here include several connected functional areas, and the workload is positively correlated with the preset task duration of the cleaning tasks, which means that the longer the task duration, the greater the workload. When it is found that the difference in workload is greater than the preset workload threshold, it indicates that the distribution of cleaning tasks in each area is unbalanced. At this time, the default area with relatively less workload is determined as the expansion area, and the default area with relatively more workload is determined as the reduction area. Then, the functional areas connected to the reduction area and the expansion area are sequentially moved into the expansion area until the difference in workload between the two is not greater than the preset workload threshold. Through such a dynamic adjustment process, the number and duration of cleaning tasks in the areas responsible for each supervisor are rebalanced, avoiding the situation of uneven supervision caused by excessive or too light cleaning tasks in some areas due to different task time sequences.

[0016] In combination with some embodiments of the first aspect, in some embodiments, the pedestrian flow data specifically includes: the local pedestrian flow in the target functional area plus the direct pedestrian flow in the direct functional area plus the indirect pedestrian flow in the indirect functional area; the target functional area is any functional area, the direct functional area is the functional area directly connected to the target functional area, and the indirect functional area is the functional area indirectly connected to the target functional area; the local pedestrian flow is the number of registered patients in the target functional area multiplied by the corresponding pedestrian flow threshold, the direct pedestrian flow is the number of registered patients in the direct functional area multiplied by the corresponding pedestrian flow threshold of the direct functional area multiplied by the preset first-level pedestrian flow threshold, and the indirect pedestrian flow is the number of registered patients in the indirect functional area multiplied by the corresponding pedestrian flow threshold of the indirect functional area multiplied by the preset second-level pedestrian flow threshold.

[0017] By adopting the above technical solution, the pedestrian flow data specifically covers the local pedestrian flow in the target functional area, the direct pedestrian flow in the direct functional area, and the indirect pedestrian flow in the indirect functional area. For the target functional area, its local pedestrian flow is determined by multiplying the number of registered patients by the corresponding pedestrian flow threshold, which directly reflects the pedestrian flow situation generated by personnel activities in this area. The direct pedestrian flow in the direct functional area is obtained by multiplying the number of registered patients in it by the corresponding pedestrian flow threshold and then by the preset first-level pedestrian flow threshold, taking into account the influence of the inflow of personnel from the directly connected areas. The indirect pedestrian flow in the indirect functional area is calculated by multiplying the number of registered patients in it by the corresponding pedestrian flow threshold and then by the preset second-level pedestrian flow threshold, and for each additional level of connection path, the second-level pedestrian flow threshold decays accordingly, which conforms to the objective law that the influence of personnel flow gradually weakens as the connection level becomes farther away in reality, and can statistically obtain the real pedestrian flow situation of different functional areas, providing a reliable basis for accurately calculating the pollution degree data.

[0018] In some embodiments in combination with some embodiments of the first aspect, for each additional level of connection path in the indirect pedestrian flow, the second-level pedestrian flow threshold decays accordingly.

[0019] By adopting the above technical solution, a mechanism is set in the calculation of the indirect pedestrian flow that for each additional level of connection path, the second-level pedestrian flow threshold decays accordingly. Logically speaking, as the number of connection paths to the target functional area increases, its impact on the pedestrian flow in the target functional area should gradually become smaller, and this decay mechanism exactly conforms to this logical relationship. Based on such pedestrian flow data, the subsequent calculated pollution degree data and the related arrangements for the cleaning tasks formulated accordingly, such as determining the priority of the cleaning tasks and generating the task time sequence chain, etc., can all be more reasonable.

[0020] In a second aspect, the present application provides a hospital cleaning task supervision system, which includes: one or more processors and a memory; the memory is coupled to the one or more processors, and the memory is used to store computer program code, and the computer program code includes computer instructions. The one or more processors call the computer instructions to enable the hospital cleaning task supervision system to execute the method described in the first aspect and any possible implementation manner in the first aspect.

[0021] In a third aspect, the present application provides a computer program product containing instructions, which when running on the hospital cleaning task supervision system, enables the hospital cleaning task supervision system to execute the method described in the first aspect and any possible implementation manner in the first aspect.

[0022] In a fourth aspect, the present application provides a computer-readable storage medium, including instructions, which when running on the hospital cleaning task supervision system, enables the hospital cleaning task supervision system to execute the method described in the first aspect and any possible implementation manner in the first aspect.

[0023] One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages: 1. Calculate the pollution degree data by collecting the flow of people data and the frequency of medical operations in the functional areas. The flow of people directly reflects the pollution potential caused by personnel activities, and the frequency of medical operations reflects the health impact of specific medical behaviors. The combination of the two can quantify the pollution degree of each area. The priority of cleaning tasks is determined based on this pollution degree data, which makes the order of cleaning tasks match the actual dirtiness of the area. On this basis, the priority of supervision is determined by combining the last supervision time of different functional areas and the experience of personnel corresponding to the cleaning tasks and the historical problem incidence rate. In this way, key tasks and routine tasks are distinguished. The minimum path algorithm is applied to the functional areas corresponding to the key tasks to construct the supervision path. With the help of this route, the areas corresponding to the key tasks can be fully and timely supervised. At the same time, the routine tasks in the same functional area and the routine tasks corresponding to the functional areas within the coverage of the supervision path can also rely on this path planning, realizing an efficient supervision mode with prominent focus and comprehensive consideration, optimizing the supervision process of cleaning tasks, and improving the overall cleaning effect and efficiency.

[0024] 2. Obtain the spatial coordinate data of the functional area corresponding to the cleaning task and the preset task duration. The spatial coordinate data provides the basis for the subsequent calculation of the distance between areas, and the task duration is related to the rationality of the work distribution of the cleaning staff. Next, the distance between any two functional areas is calculated based on the spatial coordinate data, and the distance scoring matrix between areas is constructed, which can clearly present the distance relationship between the areas in the spatial layout. Then, the sum of the task durations of all cleaning tasks is calculated and divided by the number of cleaning staff to obtain the per capita target duration, which is used as the time constraint. A dual-constraint objective function is constructed with the inter-area distance scoring matrix as the spatial constraint and the per capita target duration as the time constraint. When performing iterative calculations based on this, the area with the longest distance to the number of cleaning staff is selected as the initial cluster center, and then the distance scores from other areas to each cluster center are gradually calculated and initially allocated, and then the areas are redistributed according to the total duration of the clusters. The generated task timing chain fully considers the spatial distance between regions and the time allocation of cleaning staff, avoiding the situation where cleaning staff need to run back and forth or round trip between far-flung areas, thereby effectively improving cleaning efficiency, allowing cleaning staff to complete tasks more efficiently, and ensuring that cleaning work is carried out in an orderly and high-quality manner.

[0025] 3. It is stipulated that in the iterative calculation, all cleaning tasks corresponding to the same functional area are regarded as one cleaning task. This setting fundamentally changes the logic of task allocation. When generating the task sequence chain and allocating related areas, it avoids the situation where different cleaning tasks in the same functional area are dispersed and then allocated to different cleaning personnel. It avoids duplication of work, reduces waste of manpower, and reduces cleaning costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 It is a schematic flowchart of a hospital cleaning task supervision method in an embodiment of the present application; Figure 2 It is another schematic flowchart of a hospital cleaning task supervision method in an embodiment of the present application; Figure 3 It is another schematic flowchart of a hospital cleaning task supervision method in an embodiment of the present application; Figure 4 It is a schematic diagram of an exemplary hardware structure of a hospital cleaning task supervision system in an embodiment of the present application. Detailed implementation manners

[0027] The terms used in the following embodiments of the present application are only for the purpose of describing specific embodiments, and are not intended to limit the present application. As used in the specification and appended claims of the present application, the singular forms "a", "an", "the", "above", "said", "this" are also intended to include the plural forms, unless clearly indicated to the contrary in the context. It should also be understood that the terms and / or used in the present application refer to and include any or all possible combinations of one or more of the listed items.

[0028] Hereinafter, the terms "first" and "second" are only for descriptive purposes, and cannot be understood as implying or suggesting relative importance or implicitly indicating the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of such features. In the description of the embodiments of the present application, unless otherwise specified, the meaning of "a plurality" is two or more.

[0029] Please refer to Figure 1 , Figure 1 It is a schematic flowchart of a hospital cleaning task supervision method in an embodiment of the present application; S101. Obtain the pollution degree data of different functional areas, where the pollution degree data is calculated from the pedestrian flow data and the medical operation frequency data of the functional areas; Among them, the functional area refers to each partition within the hospital, and the hospital can be partitioned according to functional segments or according to departments; the pedestrian flow data is the statistical situation of the number of people entering and leaving a certain functional area within a specific time period. The medical operation frequency data refers to the number of times of various medical behaviors, such as surgeries, examinations, treatments, etc., carried out in the corresponding functional area.

[0030] In some embodiments, the pedestrian flow data can be the number of registered patients multiplied by a certain coefficient, or can be obtained by installing intelligent counting devices at the entrances and exits of each area.

[0031] In some embodiments, the medical operation frequency data may be the number of patients received multiplied by a corresponding coefficient plus the number of patients treated multiplied by a corresponding coefficient plus the number of surgeries multiplied by a corresponding coefficient.

[0032] In some embodiments, the sum of the pedestrian flow data and the medical operation frequency data is the pollution degree data. In some other embodiments, the pedestrian flow data multiplied by a corresponding coefficient plus the medical operation frequency data multiplied by a corresponding coefficient equals the pollution degree data, which is not limited herein.

[0033] In some other embodiments, since the different functional areas of the hospital vary in area, the pollution degree data calculated only based on the pedestrian flow data and the medical operation frequency data is not accurate enough and can only be regarded as preliminary data. In actual operation, accurate area information of each functional area should be obtained, and then the pollution degree data calculated in the conventional way before is divided by the area of the corresponding functional area one by one. Thus, the final data reflecting the actual pollution degree per unit area of each area can be obtained.

[0034] In some specific embodiments, the pedestrian flow data specifically includes: the local pedestrian flow in the target functional area plus the direct pedestrian flow in the directly connected functional area plus the indirect pedestrian flow in the indirectly connected functional area; the target functional area is any functional area, the directly connected functional area is the functional area directly connected to the target functional area, and the indirectly connected functional area is the functional area indirectly connected to the target functional area; the local pedestrian flow is the number of registered patients in the target functional area multiplied by the corresponding pedestrian flow threshold of the target functional area, the direct pedestrian flow is the number of registered patients in the directly connected functional area multiplied by the corresponding pedestrian flow threshold of the directly connected functional area multiplied by the preset first-level pedestrian flow threshold, and the indirect pedestrian flow is the number of registered patients in the indirectly connected functional area multiplied by the corresponding pedestrian flow threshold of the indirectly connected functional area multiplied by the preset second-level pedestrian flow threshold.

[0035] Among them, the directly connected functional area refers to the functional area directly connected to the target functional area, which means that there is no other intermediate area as a transition between them, and people can directly travel between these areas.

[0036] The indirectly connected functional area refers to the functional area indirectly connected to the target functional area, that is, those areas that need to pass through one or more other areas to reach the target functional area.

[0037] It can be seen that the pedestrian flow data specifically covers the local pedestrian flow in the target functional area, the direct pedestrian flow in the direct functional area, and the indirect pedestrian flow in the indirect functional area. For the target functional area, its local pedestrian flow is determined by multiplying the number of registered patients by the corresponding pedestrian flow threshold, which directly reflects the pedestrian flow situation generated by personnel activities in this area. The direct pedestrian flow in the direct functional area is obtained by multiplying the number of registered patients by the corresponding pedestrian flow threshold and then multiplying by the preset first-level pedestrian flow threshold, taking into account the influence of the inflow of personnel from the directly connected areas. The indirect pedestrian flow in the indirect functional area is calculated by multiplying the number of registered patients by the corresponding pedestrian flow threshold and then multiplying by the preset second-level pedestrian flow threshold. Moreover, for each additional level of connection path, the second-level pedestrian flow threshold decays accordingly. This conforms to the objective law that the influence of personnel flow gradually weakens as the connection level becomes farther away in reality, and can statistically obtain the real pedestrian flow situation of different functional areas, providing a reliable basis for accurately calculating the pollution degree data.

[0038] In some specific embodiments, for each additional level of connection path in the indirect pedestrian flow, the second-level pedestrian flow threshold decays accordingly.

[0039] It can be seen that in the calculation of the indirect pedestrian flow, setting the mechanism that for each additional level of connection path, the second-level pedestrian flow threshold decays accordingly. Logically speaking, as the number of connection paths to the target functional area increases, its influence on the pedestrian flow in the target functional area should gradually become smaller, and this decay mechanism exactly conforms to this logical relationship. Based on such pedestrian flow data, the subsequent calculated pollution degree data and the related arrangements for the cleaning tasks made accordingly, such as determining the priority of the cleaning tasks and generating the task time sequence chain, etc., can all be more reasonable.

[0040] S102. Determine the priority of the cleaning tasks corresponding to the functional areas according to the pollution degree data; Specifically, according to the calculated pollution degree data of each functional area, arrange them in descending order or from the most urgently needed to be cleaned to the relatively less urgently needed to be cleaned. For example, set a pollution degree threshold. For the areas where the pollution degree data is higher than this threshold, the priority of their cleaning tasks is set as high, which means that the cleaning personnel should be arranged to clean them first; while for the areas where the pollution degree data is lower than the threshold, the priority is relatively low, and the cleaning work can be arranged later.

[0041] S103. Generate a task time sequence chain according to the priority; Among them, the task time sequence chain refers to a chain-like arrangement that connects each cleaning task in a certain time order and logical relationship.

[0042] In some embodiments, specifically, according to the priorities of the cleaning tasks for each functional area that have been determined, starting from the area with the highest priority, a specific time interval or time node is allocated to the cleaning task of each area in sequence. Thus, a complete task time sequence chain that conforms to the actual operation logic is constructed, enabling the cleaning work to be carried out methodically according to the plan.

[0043] S104. Determine the supervision priority according to the last supervision time and the corresponding pollution degree data of different functional areas; The last supervision time of different functional areas refers to the specific time record of the supervision and inspection of the cleaning work in each functional area before, which is used to reflect how long it has been since the area was last supervised.

[0044] Specifically. First, compare the last supervision times of each functional area. The area with a longer time interval has a relatively higher risk of changes in the sanitary conditions due to lack of timely supervision. Then, in combination with the current pollution degree data, for those functional areas with a relatively long last supervision time and the pollution degree data showing changes, such as an increase in the pollution degree, their supervision priority is correspondingly increased; while for the areas that have been supervised recently and the pollution degree is relatively stable, their supervision priority can be appropriately reduced. By comprehensively considering these two factors, the supervision priorities of each functional area are re-evaluated and determined, enabling the supervision work to focus on those areas that require more timely supervision.

[0045] In some embodiments, the supervision priority can be obtained by multiplying the last supervision time by the pollution degree data.

[0046] S105. Adjust the supervision priority according to the personnel experience corresponding to the cleaning task and the historical problem occurrence rate; among them, the greater the corresponding personnel experience, the more negatively correlated with the supervision priority, and the historical problem occurrence rate is positively correlated with the supervision priority; Among them, the personnel experience corresponding to the cleaning task refers to the comprehensive manifestation of the operation skills, the ability to handle various sanitary problems, and the familiarity with the cleaning characteristics of different areas accumulated by the cleaning personnel responsible for performing specific cleaning tasks, which is used to measure the proficiency level and professional quality of the cleaning personnel in their work. In some embodiments, it can be determined by the relevant working years; the historical problem occurrence rate refers to the frequency statistics of problems such as non-compliance with cleaning standards, omission of cleaning areas, and potential sanitary safety hazards caused by improper cleaning operations during the previous cleaning of each functional area.

[0047] It should be noted that the experience of the corresponding personnel is negatively correlated with the supervision priority. That is, for the areas responsible for by experienced cleaning staff, the supervision priority can be appropriately reduced, believing that they can complete the tasks well. And the incidence rate of historical problems is positively correlated with the supervision priority, meaning that due to certain circumstances, the cleaning work of relevant personnel is prone to problems and requires closer supervision, and the supervision priority should be correspondingly increased.

[0048] S106. Divide the cleaning tasks into key tasks and regular tasks according to the adjusted supervision priority; Specifically, all cleaning tasks are classified according to the determined adjusted supervision priority. For example, the cleaning tasks corresponding to the areas with a relatively high supervision priority are classified as key tasks. And the cleaning tasks corresponding to the areas with a relatively low supervision priority are classified as regular tasks, which is convenient for reasonable allocation of resources and improving the pertinence and efficiency of the overall cleaning work.

[0049] In some specific embodiments, all functional areas are sorted according to the adjusted supervision priority, arranged from high to low in turn; a specific priority boundary value is set. For example, the cleaning tasks corresponding to the areas ranked before the priority boundary value are classified as key tasks, and the rest are classified as regular tasks.

[0050] S107. Apply the minimum path algorithm to construct a supervision path for the functional areas corresponding to the key tasks; Specifically, first, the functional areas corresponding to the key tasks are regarded as nodes, and the channels between the areas are regarded as edges to construct a data model similar to a graph structure. Then, the key areas to be supervised are input into the minimum path algorithm as target nodes. This algorithm will calculate based on factors such as the actual distance and traffic convenience between the areas to find the shortest or optimal path connecting all key areas, and this path is the supervision path to be constructed.

[0051] In some specific embodiments, the center point of a functional area is regarded as a node, and the connection between nodes is regarded as an edge. Select a most outermost key area as the starting node, mark the distance from it to itself (the comprehensive weighted distance, initialized to 0) as determined, and initialize the distances from the remaining nodes to the starting node to infinity. At the same time, record that the predecessor node of each node is empty. Traverse all the edges directly connected to the starting node, and update the comprehensive distance from the adjacent nodes to the starting node according to the weight of the edge (for example, if an adjacent node is connected to the starting node through an edge, the distance weight of the edge is 5, the special passage weight is 0 or infinity, 0 in the case of passable and infinity in the case of impassable, then the comprehensive distance is 5). Select the adjacent node with the minimum comprehensive distance and mark it as determined, and record its predecessor node as the starting node. Then, based on this newly determined node, repeat the above traversal and update operations until all the nodes corresponding to the key areas are marked as determined. Starting from the last determined node, trace back in sequence according to the recorded predecessor node information, and the shortest comprehensive cost path traversing all the key areas starting from the starting node can be obtained, and this path is the preliminarily constructed supervision path.

[0052] S108. Determine the supervision tasks and order according to the supervision path, where the supervision tasks include all the cleaning tasks corresponding to the supervised areas, and the supervised areas include the functional areas corresponding to the key tasks and the regular areas covered by the supervision path.

[0053] Among them, the functional areas corresponding to the key tasks are those specific hospital areas previously classified as key tasks, and the regular areas covered by the supervision path refer to the regular areas that, although belonging to the regular cleaning task areas themselves, are along the constructed supervision path and will be incidentally involved in the process of supervising the key areas. Together, they constitute the scope of this supervision.

[0054] Specifically, along the constructed supervision path, first determine all the cleaning tasks involved in the functional areas corresponding to the key tasks on the path. These tasks usually require key attention and strict inspection due to the importance of the areas, such as whether the disinfection and cleaning of the operating room are in place, and whether there are stains on the surface of medical equipment. Then, sort out the cleaning tasks corresponding to the regular areas covered by the supervision path, list these supervision tasks in sequence, so as to ensure that when the supervisors patrol along the supervision path, they can orderly supervise and manage the cleaning tasks of all relevant areas, achieve comprehensive and efficient supervision, and ensure that the overall hygienic environment of the hospital meets the requirements.

[0055] It can be seen that by collecting the pedestrian flow data and the frequency data of medical operations in the functional area to calculate the pollution degree data, the pedestrian flow intuitively reflects the possible pollution brought by personnel activities, and the frequency of medical operations reflects the hygienic impact generated by specific medical behaviors. The combination of the two can quantify the pollution degree of each area. Based on this pollution degree data, the priority of the cleaning tasks is determined, which makes the sequence of the cleaning tasks match the actual dirt condition of the area. On this basis, combined with the last supervision time of different functional areas, the personnel experience corresponding to the cleaning tasks, and the historical problem incidence rate, the priority of supervision is determined. In this way, key tasks and regular tasks are distinguished. For the functional areas corresponding to the key tasks, the minimum path algorithm is applied to construct the supervision path. With the help of this route, the areas corresponding to the key tasks can be comprehensively and timely supervised. At the same time, the regular tasks within the same functional area and the regular tasks corresponding to the functional areas covered by the supervision path can also rely on this path planning, realizing an efficient supervision mode with key points highlighted and overall consideration, optimizing the cleaning task supervision process, and improving the overall cleaning effect and efficiency.

[0056] In the actual use process, when generating the task time sequence chain based on the priority, it often does not conform to the actual operation habits of cleaning. For example, cleaning personnel often face the situation that the cleaning locations are far apart, and they need to run back and forth between different locations, or the arrangement of the task time sequence chain may cause the cleaning personnel to need to run back and forth, resulting in a significant reduction in cleaning efficiency.

[0057] Please refer to Figure 2 , Figure 2 which is another process schematic diagram of the hospital cleaning task supervision method in the embodiment of the present application; Therefore, in some embodiments, after step S103, it specifically includes: S201. Obtain the spatial coordinate data of the functional area corresponding to the cleaning task and the preset task duration of the cleaning task; Among them, the spatial coordinate data refers to the coordinate information of the position of the center point of each functional area in the overall spatial coordinate system of the hospital. The preset task duration of the cleaning task refers to the time length estimated in advance required to complete the corresponding cleaning task of each functional area, which is used to reasonably arrange the working time and workload of the cleaning personnel and can also be determined according to historical data.

[0058] S202. Based on the spatial coordinate data, calculate the distance between any two functional areas and construct an inter-regional distance scoring matrix; Among them, the inter-region distance scoring matrix is a data structure that presents the distance situation between pairwise functional regions in matrix form. It means that all functional regions are combined pairwise, and the distances between them are calculated respectively (it should be noted that if two regions are not passable, the distance is infinite), and then filled into the matrix according to a certain arrangement rule (usually using the region number or name as the row and column index) to clearly and systematically display the spatial distance relationship between regions.

[0059] S203. Calculate the total task duration of all cleaning tasks and divide it by the number of cleaning staff to obtain the per capita target duration. Specifically, first extract the task duration values of all cleaning tasks from the previously sorted data, and then perform a summation calculation to obtain the total task duration. Next, obtain the number of cleaning staff currently participating in the cleaning work in the hospital, which can be determined accurately through the employee roster of the personnel department or the management system of the cleaning team. Finally, divide the total task duration by the number of cleaning staff to calculate the per capita target duration through operation.

[0060] S204. Construct a double-constraint objective function with the inter-region distance scoring matrix as the spatial constraint and the per capita target duration as the time constraint. The double-constraint objective function refers to a mathematical function model constructed by comprehensively considering two key constraint factors, namely the spatial distance between regions (reflected by the inter-region distance scoring matrix) and the time allocation of cleaning staff (referring to the per capita target duration), when optimizing the cleaning task arrangement. It is used to find the best cleaning task allocation plan that meets these two constraint conditions through mathematical calculation and optimization solution.

[0061] In some embodiments, the idea of a heuristic algorithm is used to construct the double-constraint objective function. First, analyze the characteristics of the problem and determine to solve it through the simulated annealing algorithm. Define relevant variables, such as setting yij to represent the probability that the i-th cleaning staff is assigned to the j-th functional region (the value range is between 0 and 1) to represent an uncertain allocation state; second, according to the inter-region distance scoring matrix, construct the spatial distance part in the objective function, which can be similarly expressed as ∑∑dij*yij (reflecting the spatial constraint by calculating the expected distance), and then combine the per capita target duration to construct a function part for measuring the time difference (such as reflecting the time balance by calculating the sum of the squares of the differences between the task durations of each cleaning staff and the per capita target duration), and combine these two parts as the objective function; third, set the relevant parameters of the simulated annealing algorithm (such as the initial temperature, cooling rate, etc.) and some necessary constraint conditions (such as the sum of all probability variables is 1, etc.) to form a double-constraint objective function based on the simulated annealing algorithm, and then write the corresponding algorithm program code for iterative calculation and optimization solution.

[0062] It is understandable that other methods can also be used to construct the double-constraint objective function, which is not limited herein.

[0063] S205. Perform iterative calculations based on the double-constraint objective function, where: S2051. Select the number of areas equal to the number of cleaning staff with the farthest distances as the initial clustering centers; The purpose is to have a relatively dispersed starting point for the initial division that can cover a large range, avoiding the situation of local over-concentration at the beginning.

[0064] S2052. Calculate the distance scores from other areas to each clustering center; It should be noted that the distance scores referred to here represent the relative distances from other areas to each clustering center. To obtain this distance value, common map software can be used for operation. Specifically, for the center point of each functional area that has not been selected as a clustering center (denoted as area i) and each determined clustering center (denoted as clustering center j, j = 1, 2,..., the number of cleaning staff), add the accurate location information corresponding to these two points into the map software respectively. Then, by using the built-in walking route planning function of the map software, the actual walking distance from area i to clustering center j can be obtained, and this distance value is used as the corresponding distance score.

[0065] S2053. Initially assign other areas to the nearest clustering center; S2054. Calculate the total duration of each cluster; Calculate the total duration of each cluster. After the preliminary area assignment, for each cluster (that is, a group of functional areas assigned to each cleaning staff), add up the preset task durations of the cleaning tasks corresponding to these areas to obtain the total duration of each cluster.

[0066] S2055. When the difference between the total duration of a certain cluster and the per capita target duration is greater than the per capita target duration multiplied by the preset ratio, trigger area reallocation; Specifically, obtain the total duration data of each cluster, which are obtained by adding up the preset task durations of the cleaning tasks corresponding to each functional area included in each cluster. Then, compare with the previously calculated per capita target duration and the set preset ratio, and calculate the difference between the total duration of each cluster and the per capita target duration in turn. Compare this difference with the value obtained by multiplying the per capita target duration by the preset ratio. Once it is found that a certain cluster meets the conditions, start the area reallocation mechanism to reallocate the corresponding areas in order to achieve a more reasonable task allocation effect.

[0067] In some specific embodiments, the area reallocation specifically includes: S20551. Traverse all area exchange or transfer operations; Among them, all area exchange or transfer operations refer to all possible situations in the process of area reallocation, where functional areas in different clusters are exchanged with each other or a certain area in one cluster is transferred to another cluster.

[0068] Specifically, after it is found that the difference between the total duration of a certain cluster and the per capita target duration is greater than the per capita target duration multiplied by a preset ratio, it is necessary to optimize the current area allocation. At this time, it is necessary to comprehensively sort out all possible area exchange or transfer operations. This means considering the exchange and transfer possibilities between each functional area and all other clusters. For example, for each functional area, it is necessary to imagine how the state of the entire system will change after it is transferred to another cluster. In this process, it is necessary to record the specific situation of each operation, including information such as the areas involved and the clusters involved, to provide basic data for subsequent evaluation and selection.

[0069] S20552. Select the operation that can reduce the comprehensive score the most and execute it; among them, the comprehensive score is the distance score plus the time score, the distance score is the sum of the distances between pairwise functional areas within the cluster multiplied by the first coefficient, and the time score is the absolute value of the difference between the total task duration of the cleaning tasks in the cluster and the per capita target duration multiplied by the second coefficient.

[0070] Among them, the comprehensive score is used to represent the comprehensive rationality of the current area allocation plan in terms of spatial layout and time allocation, and is a quantitative indicator for measuring the quality of area allocation. It consists of two parts: the distance score and the time score. The distance score refers to the sum of the distances between pairwise functional areas within the cluster multiplied by the first coefficient, and is used to measure the rationality of the spatial distribution of functional areas within the cluster. The first coefficient is a preset weight value used to adjust the importance of the distance score in the comprehensive score. The time score refers to the absolute value of the difference between the total task duration of the cleaning tasks in the cluster and the per capita target duration multiplied by the second coefficient, and is used to reflect the balance of the cleaning task duration allocation. The second coefficient is also a preset weight value used to adjust the importance of the time score in the comprehensive score.

[0071] It can be seen that in the process of area reallocation, all area exchange or transfer operations are traversed, and each of these operations represents a possibility of adjusting the existing area layout. Then, by setting the comprehensive score as the distance score plus the time score, the distance score is the sum of the distances between pairwise functional areas within the clustering group multiplied by the first coefficient, which is used to measure the rationality of the spatial layout between areas, and the time score is the absolute value of the difference between the total task duration of the cleaning tasks in the clustering group and the per capita target duration multiplied by the second coefficient, to reflect the balance of the cleaning task duration allocation. Select the operation that can reduce the comprehensive score the most for execution, which means that each area reallocation is optimized in the direction of making the distance between areas more reasonable and the cleaning task duration more balanced.

[0072] S2056. Repeat the iteration until both the spatial distance score and the duration difference score of the clustering group converge; It should be noted that convergence means that as the iterative calculation progresses, the spatial distance score and the duration difference score of the clustering group no longer change significantly and gradually tend to be stable. This is used to judge whether a relatively optimal cleaning task allocation scheme has been found. When the convergence state is reached, it means that the current allocation scheme has achieved a relatively good balance in both spatial layout and time allocation, and no large-scale adjustment is required. For example, after several consecutive iterations, if the fluctuation ranges of the spatial distance score and the duration difference score are within a very small interval, it can be considered that the convergence state has been reached.

[0073] S2057. Output the optimized task time sequence chain.

[0074] It can be seen that obtaining the spatial coordinate data of the functional areas corresponding to the cleaning tasks and the preset task duration, the spatial coordinate data provides the basis for calculating the distance between areas later, and the task duration is related to the rationality of the work allocation of the cleaning personnel. Then, based on the spatial coordinate data, calculate the distance between any two functional areas, and construct a distance score matrix between areas, which can clearly present the distance relationship between each area in the spatial layout. Then, calculate the total task duration of all cleaning tasks and divide it by the number of cleaning personnel to obtain the per capita target duration, which is used as the time constraint. Using the distance score matrix between areas as the spatial constraint and the per capita target duration as the time constraint to construct a double-constraint objective function. When performing iterative calculations based on this, select the areas with the number of cleaning personnel with the farthest distance as the initial clustering centers, and then gradually calculate the distance scores of other areas to each clustering center and perform initial allocation. After that, perform area reallocation according to the total duration situation of the clustering group. The generated task time sequence chain fully considers the regional spatial distance and the time allocation of the cleaning personnel, avoiding the situation where the cleaning personnel need to run back and forth between areas that are far apart, thereby effectively improving the cleaning efficiency, enabling the cleaning personnel to complete tasks more efficiently, and ensuring the orderly and high-quality development of the cleaning work.

[0075] In the actual use process, in special cases, there is a situation where different cleaning tasks in the same functional area are assigned to different cleaners. This will not only result in the phenomenon of repeated cleaning but also increase the total cleaning cost.

[0076] Therefore, in some embodiments, all the cleaning tasks corresponding to the same functional area are regarded as one cleaning task in the iterative calculation.

[0077] Regarding it as one cleaning task means that in the iterative calculation process, all the cleaning tasks in the same functional area are treated as a whole and are not split up and processed separately.

[0078] The scenario is to optimize the cleaning task allocation plan and avoid the problems of repeated cleaning and increased cleaning costs. Specifically, in the actual cleaning work, if such a regulation is not made, due to various reasons, such as unreasonable personnel arrangement and lack of overall planning in task allocation, different cleaning tasks in the same functional area may be assigned to different cleaners. In the iterative calculation, after all the cleaning tasks corresponding to the same functional area are regarded as one cleaning task, when generating the task time sequence chain and performing area allocation, the system will consider all the cleaning tasks in this functional area as a whole and assign them to one cleaner or a group of cleaners working together. In this way, it fundamentally avoids the situation where different cleaning tasks in the same functional area are separately assigned to different cleaners, thus effectively avoiding repeated labor, reducing waste of manpower, and lowering the cleaning cost.

[0079] It can be seen that the regulation of regarding all the cleaning tasks corresponding to the same functional area as one cleaning task in the iterative calculation changes the task allocation logic at the root. When generating the task time sequence chain and performing relevant area allocation, it avoids the situation where different cleaning tasks in the same functional area are split up and then assigned to different cleaners. It avoids repeated labor, reduces waste of manpower, and lowers the cleaning cost.

[0080] In the actual use process, each supervisor is usually responsible for supervising a specific area. However, since the task time sequence chains generated each time are not the same, this leads to the problem of uneven numbers and durations of cleaning tasks in the areas supervised by each supervisor.

[0081] Please refer to Figure 3 , Figure 3 which is another process schematic diagram of the hospital cleaning task supervision method in the embodiments of the present application; After step S108, it further includes: S109. Determine whether the difference in the workload corresponding to the default areas responsible for different work inspectors is greater than a preset workload threshold according to the tasks of supervision; the default areas include several connected functional areas, and the workload is positively correlated with the preset task duration of the cleaning tasks. Specifically, in actual cleaning work, due to the different task time series chains generated each time, there will be differences in the number and duration of cleaning tasks in each default area. To ensure the fairness and effectiveness of supervision, it is necessary to evaluate the workloads of different default areas. In this step, first, clarify the tasks supervised by each work inspector, and then count the total preset task duration of the cleaning tasks in each default area to determine the workload of each default area. Then, calculate the difference in workloads between different default areas and compare this difference with the preset workload threshold. If the difference is greater than the preset workload threshold, it means that there is an uneven workload distribution and subsequent adjustments are required.

[0082] S110. When the difference in workload is greater than the preset workload threshold, determine the default area with relatively less workload as the expansion area and the default area with relatively more workload as the reduction area. Specifically, when the difference in workloads between different default areas obtained in step S109 exceeds the preset workload threshold, it indicates that the current distribution of cleaning tasks in each area is unreasonable and needs to be adjusted. In this step, by comparing the workloads of each default area, mark the default area with relatively less workload as the expansion area and the default area with relatively more workload as the reduction area. This is to prepare for transferring some cleaning tasks in the reduction area to the expansion area later to achieve a balance in the workloads of each area.

[0083] S111. Sequentially incorporate the functional areas connected to the reduction area into the expansion area until the difference in workloads between the expansion area and the reduction area is not greater than the preset workload threshold.

[0084] Specifically, when the difference in workloads between different default areas obtained in step S109 exceeds the preset workload threshold, it indicates that the current distribution of cleaning tasks in each area is unreasonable and needs to be adjusted. In this step, by comparing the workloads of each default area, mark the default area with relatively less workload as the expansion area and the default area with relatively more workload as the reduction area. This is to prepare for transferring some cleaning tasks in the reduction area to the expansion area later to achieve a balance in the workloads of each area.

[0085] It can be seen that after determining the supervision tasks and order according to the supervision path, the difference in workload corresponding to the default areas responsible for different work inspectors will be further judged according to the supervision tasks. The default areas here include several connected functional areas, and the workload is positively correlated with the preset task duration of the cleaning tasks, which means that the longer the task duration, the greater the workload. When it is found that the difference in workload is greater than the preset workload threshold, it indicates that the distribution of cleaning tasks in each area is unbalanced. At this time, the default area with relatively less workload is determined as the expansion area, and the default area with relatively more workload is determined as the reduction area. Then, the functional areas connected to the reduction area and the expansion area are successively moved into the expansion area until the difference in workload between the two is not greater than the preset workload threshold. Through such a dynamic adjustment process, the quantity and duration of cleaning tasks in the areas responsible for each supervisor are rebalanced, avoiding the situation of over-heavy or over-light cleaning tasks in some areas caused by different task time sequences, resulting in unbalanced supervision.

[0086] The following introduces the exemplary hospital cleaning task supervision system 400 provided by the embodiments of the present application. Figure 4 It is a schematic diagram of the exemplary hardware structure of the hospital cleaning task supervision system 400 provided by the embodiments of the present application.

[0087] In some embodiments, the hospital cleaning task supervision system 400 is a computer device or the hospital cleaning task supervision system 400 includes a computer device. The computer device includes a processor, a memory, and a network interface connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data. The network interface of the computer device is used to communicate with other external terminals or servers through a network connection. In some embodiments, the network interface can be a wired network interface, and in some embodiments, the network interface can also be a wireless network interface. The computer program, when executed by the processor, implements the method in the embodiments of the present application.

[0088] Those skilled in the art can understand that Figure 4 the structure shown in

[0089] As described above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the various embodiments of the present application.

[0090] As used in the above embodiments, depending on the context, the term "when..." can be interpreted to mean "if...", or "after...", or "in response to determining...", or "in response to detecting...". Similarly, depending on the context, the phrase "when determining..." or "if detecting (the stated condition or event)" can be interpreted to mean "if determining...", or "in response to determining...", or "when detecting (the stated condition or event)", or "in response to detecting (the stated condition or event)".

[0091] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions described in the embodiments of the present application are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another, for example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center by wire (such as coaxial cable, optical fiber, digital subscriber line) or wirelessly (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that includes one or more integrated available media. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a magnetic tape), an optical medium (for example, a DVD), or a semiconductor medium (for example, a solid-state drive), etc.

[0092] Those of ordinary skill in the art can understand all or part of the processes in the methods of the above embodiments. The processes can be completed by relevant hardware instructed by a computer program. The program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the above method embodiments. The foregoing storage media include: various media that can store program codes such as ROM or random access memory RAM, magnetic disks, or optical discs.

Claims

1. A hospital cleaning task supervision method, characterized in that, Including: Obtaining pollution degree data of different functional areas, where the pollution degree data is calculated based on the pedestrian flow data of the functional area and the medical operation frequency data of the functional area; Determining the priority of the cleaning tasks corresponding to the functional areas according to the pollution degree data; Generating a task time sequence chain according to the priority; Determining the supervision priority according to the last supervision time of different functional areas and the corresponding pollution degree data; Adjusting the supervision priority according to the personnel experience corresponding to the cleaning tasks and the historical problem occurrence rate; where the greater the corresponding personnel experience, the more negatively correlated with the supervision priority, and the historical problem occurrence rate is positively correlated with the supervision priority; Dividing the cleaning tasks into key tasks and regular tasks according to the adjusted supervision priority; Applying the minimum path algorithm to construct a supervision path for the functional areas corresponding to the key tasks; Determining the supervision tasks and order according to the supervision path, where the supervision tasks include all the cleaning tasks corresponding to the supervised areas, and the supervised areas include the functional areas corresponding to the key tasks and the regular areas covered by the supervision path.

2. The method according to claim 1, wherein After the step of generating the task time sequence chain according to the priority, the method further includes: Obtaining the spatial coordinate data of the functional areas corresponding to the cleaning tasks and the preset task duration of the cleaning tasks; Based on the spatial coordinate data, calculating the distance between any two functional areas and constructing an inter-regional distance scoring matrix; Calculating the total task duration of all cleaning tasks and dividing it by the number of cleaning personnel to obtain the per capita target duration; Constructing a double-constrained objective function with the inter-regional distance scoring matrix as the spatial constraint and the per capita target duration as the time constraint; Performing iterative calculations based on the double-constrained objective function, where: Selecting the number of areas equal to the number of the farthest cleaning personnel as the initial clustering centers; Calculating the distance scores of other areas to each clustering center; Initializing the assignment of other areas to the nearest clustering center; Calculating the total duration of each clustering group; When the difference between the total duration of a certain clustering group and the per capita target duration is greater than the per capita target duration multiplied by a preset ratio, triggering area reallocation; Repeating the iteration until both the spatial distance score and the duration difference score of the clustering groups converge; Outputting the optimized task time sequence chain.

3. The method according to claim 2, characterized in that, The area reallocation specifically includes: Traversing all area exchange or transfer operations; Selecting and executing the operation that can reduce the comprehensive score the most; where the comprehensive score is the distance score plus the time score, the distance score is the sum of the distances between pairwise functional areas within the clustering group multiplied by a first coefficient, and the time score is the absolute value of the difference between the total task duration of the cleaning tasks in the clustering group and the per capita target duration multiplied by a second coefficient.

4. The method according to claim 2, wherein The iterative calculation based on the double-constrained objective function further includes: Regarding all the cleaning tasks corresponding to the same functional area as one cleaning task during the iterative calculation.

5. The method according to claim 2, wherein After the step of determining the supervision tasks and order according to the supervision path, the method further includes: Judge whether the difference in the workload corresponding to the default areas responsible for different work inspectors according to the supervision tasks is greater than a preset workload threshold; the default areas include several connected functional areas, and the workload is positively correlated with the preset task duration of the cleaning tasks. When the difference in workload is greater than the preset workload threshold, determine the default area with relatively less workload as the expansion area, and the default area with relatively more workload as the reduction area. Sequentially incorporate the functional areas connecting the reduction area and the expansion area into the expansion area until the difference in workload between the expansion area and the reduction area is not greater than the preset workload threshold.

6. The method according to claim 1, characterized in that, The pedestrian flow data specifically includes: The local pedestrian flow in the target functional area plus the direct pedestrian flow in the direct functional area plus the indirect pedestrian flow in the indirect functional area; the target functional area is any functional area, the direct functional area is the functional area directly connected to the target functional area, and the indirect functional area is the functional area indirectly connected to the target functional area; the local pedestrian flow is the number of registered patients in the target functional area multiplied by the corresponding pedestrian flow threshold of the target functional area, the direct pedestrian flow is the number of registered patients in the direct functional area multiplied by the corresponding pedestrian flow threshold of the direct functional area multiplied by a preset first-level pedestrian flow threshold, and the indirect pedestrian flow is the number of registered patients in the indirect functional area multiplied by the corresponding pedestrian flow threshold of the indirect functional area multiplied by a preset second-level pedestrian flow threshold.

7. The method according to claim 6, characterized in that, For each additional connection path in the indirect pedestrian flow, the second-level pedestrian flow threshold decays accordingly.

8. A hospital cleaning task supervision system, characterized in that, The hospital cleaning task supervision system includes: one or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code includes computer instructions, and the one or more processors call the computer instructions to cause the hospital cleaning task supervision system to execute the method according to any one of claims 1-7.

9. A computer program product comprising instructions, characterized in that, When the computer program product runs on the hospital cleaning task supervision system, it causes the hospital cleaning task supervision system to execute the method according to any one of claims 1-7.

10. A computer-readable storage medium, comprising instructions, characterized in that, When the instruction runs on the hospital cleaning task supervision system, it causes the hospital cleaning task supervision system to execute the method according to any one of claims 1-7.

Images