Cloud-based endoscope repair management system

Abstract

The application relates to the technical field of medical equipment management, in particular to an endoscope maintenance management system based on clouds, which comprises a load monitoring module, a risk early warning module, a work order scheduling module, a maintenance tracking module and a data linkage module.In the application, through collection of equipment use time length, start frequency and environment data, combined with load curve fluctuation analysis, high-precision abnormality recognition is realized, equipment state sensing capability is improved, equipment identification and frequency are uploaded, an abnormal equipment set is constructed, data support is provided for high-risk equipment positioning, abnormal frequency is compared with the mean value of the same type, high-frequency abnormal equipment is screened, maintenance risk pre-positioning recognition is realized, the comprehensive skill level, geographical position and task load in scheduling are combined, resource allocation is optimized, maintenance logs, accessory use and time nodes are recorded, the traceability of the maintenance process is enhanced, accessory use frequency and replacement intervals are counted, a prediction model is established, and refined maintenance is improved.

Description

Technical Field

[0001] This invention relates to the field of medical device management technology, and in particular to a cloud-based endoscope maintenance management system. Background Technology

[0002] The field of medical equipment management technology encompasses the entire process of managing medical equipment, including its use, maintenance, repair, and resource allocation. Its core lies in using information technology to manage the lifecycle of medical equipment, implementing systematic and standardized management from procurement, warehousing, use, regular maintenance to fault repair, ensuring the stable operation and safe use of medical equipment. With the continuous development of medical technology, the types and quantities of medical equipment are constantly increasing, leading to greater complexity in equipment management. Therefore, the field of medical equipment management is constantly developing new technologies to improve the efficiency and accuracy of equipment management, reduce maintenance costs, and extend equipment lifespan.

[0003] The endoscope maintenance management system is a system that manages the entire process of maintenance and repair of endoscope equipment. It mainly covers technical aspects such as fault diagnosis, maintenance records, parts management, and equipment status tracking. By classifying endoscope equipment fault types, standardizing maintenance processes, and managing maintenance personnel and parts, it solves the problem of information silos in endoscope equipment maintenance, ensures the traceability of the equipment maintenance process, and achieves effective management of endoscope equipment through information entry, status monitoring, maintenance records, and alarm prompts, ensuring the efficiency and accuracy of maintenance work.

[0004] Existing technologies lack sophisticated real-time monitoring capabilities for operational data, making it difficult to effectively capture load variations during equipment use. This leads to delayed anomaly identification, hindering rapid response and fault prediction. The lack of structured data from equipment anomalies impacts the accuracy of subsequent maintenance strategies and makes it difficult to establish risk classification models based on anomaly frequency, resulting in untargeted allocation of maintenance resources. In personnel scheduling, reliance on manual judgment or simple shift information fails to consider personnel skill levels and geographical location, easily leading to unbalanced resource distribution and affecting maintenance response timeliness and quality. Manual data entry during maintenance is common, with data gaps and delays severely restricting traceability and evaluation of the maintenance process. The lack of a data correlation mechanism for parts replacement frequency and maintenance cycles makes it impossible to accurately assess parts lifespan, easily leading to wasted parts resources or increased equipment failure rates. In actual operation, this results in equipment interruptions, delayed maintenance responses, increased maintenance costs, and decreased management efficiency, seriously affecting the overall service level and safety assurance capabilities of endoscopic equipment. Summary of the Invention

[0005] To address the technical problems of existing technologies, embodiments of the present invention provide a cloud-based endoscope maintenance and management system. The technical solution is as follows:

[0006] On the one hand, a cloud-based endoscope maintenance management system is provided, which includes:

[0007] The load monitoring module extracts data from the endoscope equipment, including the usage time, start-up frequency, and ambient temperature and humidity of the imaging module and operating handle. It analyzes the real-time load curve, identifies abnormal segments by the fluctuation amplitude and the set stable range, and uploads the data to the cloud to generate a set of devices with abnormal load.

[0008] The risk warning module calls the device identification information in the load abnormal device set, retrieves the device abnormality records in the cloud work order, compares the abnormality frequency of each device with the average value of the same model of device, filters the device numbers with high abnormality frequency, and generates a maintenance risk trigger list.

[0009] The work order scheduling module calls the equipment number in the maintenance risk trigger list, queries the cloud maintenance personnel's shift, skill level and number of orders, identifies the geographical distance of the equipment location, compares the task load, selects the best personnel, and updates the scheduling information to the cloud work order pool to obtain the scheduling-bound work order item;

[0010] The maintenance tracking module records three types of information during the maintenance process: operation logs, parts usage, and execution time nodes, based on the work order items bound to the scheduling. It organizes the work order process nodes according to the timeline and synchronizes them with the cloud status panel to obtain a snapshot of the endoscope maintenance process record.

[0011] As a further aspect of the present invention, the load anomaly device set includes equipment operation stability indicators, anomaly trigger time periods, and equipment performance degradation characteristics; the maintenance risk trigger list includes high-frequency anomaly alarm weights, original equipment maintenance ratios, and model anomaly deviation degrees; the scheduling-bound work order items include personnel skill matching degree, geographical task coverage efficiency, and shift load balancing coefficient; and the endoscope maintenance process record snapshot includes maintenance task progress nodes, parts replacement type statistics, and operation behavior pattern characteristics.

[0012] As a further aspect of the present invention, the load monitoring module includes:

[0013] The operation record extraction submodule is based on endoscope equipment data, including the usage time and start-up frequency data of the imaging module and operating handle, and collects equipment ambient temperature and humidity records. It integrates the data into a single data structure according to the equipment number, removes missing items, and generates an equipment operation status record table.

[0014] The load anomaly determination submodule uses the equipment operation status record table, including usage time data and temperature and humidity values, combined with the upper and lower limits of the stable usage time range and environmental parameter thresholds, to determine whether the fluctuation range exceeds the standard range, filter the corresponding equipment number and anomaly frequency, and generate an abnormal equipment operation list.

[0015] The maintenance task generation submodule calls the abnormal equipment operation list, classifies and summarizes the equipment numbers whose frequency values ​​are higher than the set maintenance start frequency threshold, matches the idle time period in the maintenance plan and assigns the corresponding maintenance personnel, and generates a set of abnormal load equipment.

[0016] As a further aspect of the present invention, the risk warning module includes:

[0017] The anomaly frequency extraction submodule calls the load anomaly device set, retrieves the original maintenance records of the corresponding devices in the cloud work orders, counts the number of times the maintenance record of each device appears, and establishes a maintenance frequency information set;

[0018] The same-type deviation identification submodule extracts the equipment maintenance frequency by model according to the maintenance frequency information set, calculates the average number of maintenance as a reference value, identifies the deviation of each piece of equipment from the reference value, filters the equipment numbers whose deviation exceeds the threshold, and generates a maintenance frequency abnormal list.

[0019] The maintenance work order triggering submodule calls the maintenance frequency anomaly list, queries the scheduling status of equipment in the current maintenance plan, filters out equipment that has not entered the schedule and marks it as an emergency maintenance status, and combines the equipment number, maintenance frequency and emergency status to generate a maintenance risk triggering list.

[0020] As a further aspect of the present invention, the work order scheduling module includes:

[0021] The maintenance personnel matching submodule calls the equipment number in the maintenance risk trigger list, queries the cloud maintenance personnel's schedule, skill level and number of orders, combines the equipment location and service area distance, sorts according to skill matching degree and task load difference, filters high priority personnel numbers, and generates an endoscope maintenance matching list.

[0022] The work order task binding submodule analyzes the work order binding relationship between personnel and equipment based on the personnel number and the equipment number to be dispatched in the endoscope repair matching list, updates the binding result to the cloud work order pool and marks the status as scheduled, and obtains the scheduled binding work order item.

[0023] As a further aspect of the present invention, the task scheduling matching value is expressed by the formula:

[0024]

[0025] Where R represents the task scheduling matching value, N represents the number of personnel IDs in the matching list, D represents the number of equipment IDs to be dispatched, and T represents the number of equipment IDs to be dispatched. z Y represents the optimal scheduling time value corresponding to the z-th device. z The responsive time offset represents the z-th person, and M represents the total number of valid binding candidates.

[0026] As a further aspect of the present invention, the maintenance tracking module includes:

[0027] The process log collection submodule collects maintenance logs, parts usage records, and time node data based on the scheduling-bound work order items, and integrates them in a formatted manner according to the work order number to generate a maintenance process dataset.

[0028] The node snapshot recognition submodule categorizes and organizes log content and parts usage items based on the time nodes in the maintenance process dataset, marks maintenance behaviors, sorts them in chronological order, and generates a set of work order execution timeline entries.

[0029] The status panel synchronization submodule calls the time nodes, maintenance actions and parts usage status in the work order execution time axis entry set, calculates the time field mapping correction value, checks the synchronization status between fields, writes the node information into the record table, and updates the panel display status to the current node, thus obtaining a snapshot of the endoscope maintenance process record.

[0030] As a further aspect of the present invention, the time field mapping correction value is calculated using the following formula:

[0031]

[0032] Where T represents the time field mapping correction value, t ij w represents the original time value of the j-th element in the i-th node. ij m represents the time weight factor of the j-th element in the i-th node. ij This represents the quantity of the material field used in the j-th item of the i-th node. s represents the average quantity of material fields used in all cells of the i-th node. ij represents the progress status code value of the j-th unit in the i-th node, and n represents the number of units included in the i-th node.

[0033] As a further aspect of the present invention, the system also includes a data linkage module:

[0034] The data linkage module reads the parts usage details from the maintenance process record snapshot, summarizes the usage frequency and replacement interval by parts type, binds them with the equipment number, and uploads them to the cloud prediction port to generate an endoscope parts maintenance list;

[0035] The endoscope accessory maintenance list includes accessory usage trend categories, replacement cycle predictions, and accessory lifespan distribution models.

[0036] As a further aspect of the present invention, the data linkage module includes:

[0037] The parts detail organization submodule reads the parts usage details from the maintenance process record snapshot, summarizes the replacement frequency and replacement time interval by parts type, binds the corresponding equipment number, and generates an endoscope parts replacement record table;

[0038] The maintenance list generation submodule matches the cloud prediction port configuration item with the endoscope parts replacement record table and writes it into the prediction field, identifies the parts task items of the device group, and generates an endoscope parts maintenance list.

[0039] The beneficial effects of the technical solutions provided in the embodiments of the present invention include at least the following:

[0040] By continuously collecting data on the usage time, start-up frequency, and ambient temperature and humidity of the imaging module and operating handle, and analyzing the load curve fluctuation amplitude in real time, dynamic perception and high-precision anomaly identification of equipment operating status can be achieved, improving the sensitivity and reliability of load anomaly judgment. By uploading equipment identification and frequency to the cloud, a traceable set of equipment with load anomalies is established, providing a data foundation for subsequent accurate location of high-risk equipment. Cross-comparison of equipment anomaly frequencies with the average values ​​of equipment of the same model allows for the screening of equipment numbers with abnormally high failure frequencies, enabling proactive assessment of maintenance risks from a data perspective and enhancing the targeting of maintenance plans. During the scheduling process, the skill level of maintenance personnel, geographical distance, and the number of tasks received are comprehensively considered to ensure balanced task allocation and response efficiency, while also improving the scientific nature of resource allocation. The maintenance process records include operation logs, parts usage, and time nodes, effectively capturing maintenance behavior paths and parts replacement characteristics, making the maintenance trajectory analyzable and verifiable. By statistically analyzing parts usage details and replacement intervals, a parts maintenance data chain oriented towards equipment numbers is established, forming a parts usage prediction model based on real maintenance scenarios. This enables proactive management and refined control of maintenance strategies. Through the interconnection of equipment operation data and maintenance data, a five-in-one management mechanism integrating anomaly identification, risk prediction, resource scheduling, maintenance tracking, and maintenance prediction is constructed, significantly improving the closed-loop management capability of the maintenance process and enhancing the system's efficient operation and resource utilization. Attached Figure Description

[0041] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0042] Figure 1 This is a schematic diagram of a cloud-based endoscope repair and management system provided in an embodiment of the present invention;

[0043] Figure 2 This is a schematic diagram of the system framework of the present invention;

[0044] Figure 3 This is a flowchart of the load monitoring module in this invention;

[0045] Figure 4 This is a flowchart of the risk warning module in this invention;

[0046] Figure 5 This is a flowchart of the work order scheduling module in this invention;

[0047] Figure 6 This is a flowchart of the maintenance tracking module in this invention;

[0048] Figure 7 This is a flowchart of the data linkage module in this invention. Detailed Implementation

[0049] The technical solution of the present invention will now be described with reference to the accompanying drawings.

[0050] In embodiments of the present invention, words such as "exemplarily," "for example," etc., are used to indicate that something is an example, illustration, or description. Any embodiment or design described as "exemplary" in the present invention should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of the word "exemplary" is intended to present the concept in a concrete manner. Furthermore, in embodiments of the present invention, the meaning expressed by "and / or" can be both, or either one.

[0051] In the embodiments of this invention, the terms "image" and "picture" may sometimes be used interchangeably. It should be noted that, without emphasizing the distinction between them, their intended meanings are consistent. Similarly, the terms "of," "corresponding (relevant)," and "corresponding" may sometimes be used interchangeably. It should be noted that, without emphasizing the distinction between them, their intended meanings are consistent.

[0052] In this embodiment of the invention, sometimes a subscript such as W1 may be written in a non-subscript form such as W1. When the difference is not emphasized, the meaning they express is the same.

[0053] To make the technical problems, technical solutions and advantages of the present invention clearer, a detailed description will be given below in conjunction with the accompanying drawings and specific embodiments.

[0054] This invention provides a cloud-based endoscope repair and management system, such as... Figure 1-2 The diagram shown illustrates a cloud-based endoscope maintenance management system, which includes:

[0055] The load monitoring module extracts data from the endoscope equipment, including the usage time, start-up frequency, and ambient temperature and humidity of the imaging module and operating handle. It analyzes the real-time load curve, identifies abnormal segments by fluctuation amplitude and set stable range, extracts equipment identifiers and frequencies, and uploads them synchronously to the cloud to generate a set of abnormal load devices.

[0056] The risk warning module calls the device identification information in the load abnormal device set, retrieves the device abnormality records in the cloud work order, compares the abnormality frequency of each device with the average of the same model of device, filters the device numbers with high abnormality frequency, and generates a maintenance risk trigger list.

[0057] The work order scheduling module calls the equipment number in the maintenance risk trigger list, queries the cloud maintenance personnel's shift, skill level and number of orders, identifies the geographical distance of the equipment location, compares the task load, selects the best personnel, and updates the scheduling information to the cloud work order pool to obtain the scheduling-bound work order item;

[0058] The maintenance tracking module records three types of information during the maintenance process: operation logs, parts usage, and execution time nodes, based on the work order items bound to the schedule. It organizes the work order process nodes according to the timeline and synchronizes them with the cloud status panel to obtain a snapshot of the endoscope maintenance process record.

[0059] The data linkage module reads the parts usage details from the maintenance process record snapshot, summarizes the usage frequency and replacement interval by part type, binds them with the equipment number, and uploads them to the cloud prediction port to generate an endoscope parts maintenance list.

[0060] The load anomaly device set includes equipment operation stability indicators, anomaly trigger time periods, and equipment performance degradation characteristics. The maintenance risk trigger list includes high-frequency anomaly alarm weights, equipment original maintenance ratios, and model anomaly deviation degrees. The scheduling-bound work order items include personnel skill matching degree, geographical task coverage efficiency, and shift load balancing coefficient. The endoscope maintenance process record snapshot includes maintenance task progress nodes, parts replacement type statistics, and operation behavior pattern characteristics. The endoscope parts maintenance list includes parts usage trend categories, replacement cycle prediction values, and parts life distribution models.

[0061] Specifically, such as Figure 2 , 3 As shown, the load monitoring module includes:

[0062] The operation record extraction submodule is based on endoscope equipment data, including the usage time and start-up frequency data of the imaging module and operating handle, and collects equipment ambient temperature and humidity records. It integrates the data into a single data structure according to the equipment number, removes missing items, and generates an equipment operation status record table.

[0063] By collecting data on the usage time and activation frequency of the endoscope's operating handle, as well as records of the ambient temperature and humidity, a data structure is formed. This structure is then integrated according to the device number. During data integration, careful processing of the raw data is required. First, the data is validated to remove missing items. Then, the valid data is summarized. The data types used include usage time in timestamp format, device activation count, and ambient temperature and humidity data. The temperature and humidity data are expressed as real-time monitored temperature (e.g., 24℃) and humidity (e.g., 55%). Data is collected at regular intervals (e.g., hourly). To ensure accuracy, if temperature data for some devices is missing or activation frequency records are incomplete, the device's records are discarded. The remaining data is integrated by device number to form a complete device operation record, which in turn generates a device operation status record table. The generated record table should include information such as device number, operation time, activation count, ambient temperature and humidity records, for subsequent load anomaly detection and analysis.

[0064] The load anomaly determination submodule uses the equipment operation status record table, including usage time data and temperature and humidity values, combined with the upper and lower limits of the stable usage time range and environmental parameter thresholds, to determine whether the fluctuation range exceeds the standard range, filter the corresponding equipment number and anomaly frequency, and generate an abnormal equipment operation list.

[0065] By analyzing equipment usage time data and combining it with the upper and lower limits of a set stable usage time range, it can be determined whether the equipment has been in an abnormal operating state for an extended period. For example, if the set stable usage time range is 20 to 30 hours, then when the equipment usage time exceeds 30 hours or falls below 20 hours, it is considered an abnormal state. Environmental temperature and humidity data is analyzed, and temperature and humidity thresholds are set, such as a temperature threshold of 20°C to 30°C and a humidity threshold of 45% to 65%. If the equipment's operating status exceeds the set range, such as a temperature reaching 35°C or humidity reaching 80%, then the equipment's operating status is considered abnormal. All abnormal equipment is filtered out, and an abnormal equipment operation list is generated. This list lists each equipment number and its abnormal frequency, allowing the urgency level of the equipment to be determined based on the frequency of abnormalities.

[0066] The maintenance task generation submodule calls the abnormal equipment operation list, classifies and summarizes the equipment numbers whose frequency values ​​are higher than the set maintenance start frequency threshold, matches the idle time period in the maintenance plan and assigns the corresponding maintenance personnel, and generates a set of abnormal load equipment.

[0067] This list filters out devices with high anomaly frequencies. The frequency of each device is compared to a preset maintenance initiation frequency threshold, assuming this threshold is 5 times. If a device's anomaly frequency exceeds 5 times, it requires maintenance. Devices with high frequencies are then grouped by device number. Combining idle time slots and personnel arrangements in the maintenance plan, devices are matched with maintenance personnel. If a maintenance personnel has available time during a specific period, the maintenance task for that device is assigned to them. This process ultimately generates a set of devices with load anomalies, providing a list for subsequent maintenance operations.

[0068] Specifically, such as Figure 2 , 4 As shown, the risk warning module includes:

[0069] The anomaly frequency extraction submodule calls the load anomaly device set, retrieves the original maintenance records of the corresponding devices in the cloud work orders, counts the number of times the maintenance record of each device appears, and establishes a maintenance frequency information set;

[0070] When a device experiences an abnormal load, the system first retrieves the device ID and the corresponding time point from the load monitoring database. Then, based on the device ID, it queries the cloud work order database for all maintenance work orders related to that device ID. These work orders include information such as the specific fault details, maintenance time, and maintenance measures. This information is extracted and analyzed for each maintenance record. The records include the specific time of the fault, the maintenance measures taken, and the device status after maintenance. This data is used to calculate the maintenance frequency of the device. For example, device A recorded 5 maintenances in the past year, each addressing a different problem, but the device's operating status returned to normal after each maintenance. The maintenance frequency of each device is calculated using this data, and the information is stored in a maintenance frequency information set to generate an abnormal maintenance frequency list.

[0071] The same-type deviation identification submodule extracts the equipment maintenance frequency by model based on the maintenance frequency information set, calculates the average number of maintenance as a reference value, identifies the deviation of each piece of equipment from the reference value, filters the equipment numbers whose deviation exceeds the threshold, and generates a list of abnormal maintenance frequencies.

[0072] The system extracts equipment maintenance frequency by model. All equipment is categorized according to its model, for example, all equipment of model X is grouped together. Then, for each category, all maintenance frequency data for that model is extracted from the maintenance frequency information set. The data is statistically analyzed to calculate the average number of maintenance visits for each model. This average will serve as the benchmark for subsequent comparisons. For example, if the average number of maintenance visits for model X is 3 times per year, the maintenance visits of each piece of equipment are compared to the average number of maintenance visits for that model, and the deviation value is calculated. For example, if a piece of model X has 5 maintenance visits per year, the deviation value is 2 times per year. If this deviation value exceeds a set threshold, such as 1.5 times per year, then the equipment number will be filtered out and marked as having abnormal maintenance frequency, generating a list of abnormal maintenance frequencies.

[0073] The maintenance work order triggering submodule calls the maintenance frequency anomaly list, queries the scheduling status of equipment in the current maintenance plan, filters out equipment that has not entered the schedule and marks it as an emergency maintenance status, and combines the equipment number, maintenance frequency and emergency status to generate a maintenance risk triggering list;

[0074] The system queries the scheduling status of equipment in the current maintenance plan, reads all equipment numbers from the abnormal maintenance frequency list, and for each equipment in the list, queries the current maintenance plan database to view the equipment's scheduling status, including the maintenance plan time, responsible person, and expected maintenance measures. For equipment that has not yet been included in the schedule, it is marked as an emergency maintenance status. For example, if equipment number B is in the abnormal list and the query results show that the equipment has not been scheduled in any maintenance plan, then equipment B is marked as an emergency status and recorded. The system combines the equipment number, maintenance frequency, and emergency status to generate a maintenance risk trigger list. This list will be used for subsequent maintenance scheduling and priority determination to ensure that high-risk equipment is handled first.

[0075] Specifically, such as Figure 2 , 5 As shown, the work order scheduling module includes:

[0076] The maintenance personnel matching submodule calls the equipment number in the maintenance risk trigger list, queries the cloud maintenance personnel's schedule, skill level and number of orders, combines the equipment location and service area distance, sorts according to skill matching degree and task load difference, filters high priority personnel numbers, and generates an endoscope maintenance matching list.

[0077] First, a cloud query is performed to locate the device using its device ID and retrieve related cloud-based maintenance personnel data, including scheduling information, skill level, and number of orders received. The device's location is then compared to the distance to the maintenance personnel's service area to calculate the distance difference between each maintenance personnel and the device. For each maintenance personnel, a comprehensive evaluation is conducted based on their skill matching degree and current workload difference. Skill matching degree refers to the degree of consistency between the maintenance personnel's skill level and the skill requirements of the device, while workload difference refers to the gap between the maintenance personnel's current number of orders and their ideal number of orders. After calculation, each repairman is scored based on the comprehensive data. The higher the score, the more suitable the repairman is to perform the repair task for that equipment. Repairmen are sorted from high to low according to their comprehensive scores, and high-priority repairmen are selected. Assuming the equipment number is E001 and the equipment is located in region A, repairman P1 is found to have a high skill level in region A, has a small number of orders, and is 5 kilometers away from the equipment. P2 has an intermediate skill level, has a large number of orders, and is 10 kilometers away from the equipment. P1 is given a higher priority and P2 a lower priority, and finally an endoscope repair matching list is generated.

[0078] The work order task binding submodule calculates the task scheduling matching value based on the personnel number and the equipment number to be dispatched in the endoscope repair matching list, analyzes the work order binding relationship between personnel and equipment, updates the binding result to the cloud work order pool and marks the status as scheduled, and obtains the scheduling bound work order item.

[0079] The task scheduling matching value is calculated by associating the personnel ID with the equipment ID to be dispatched in the endoscope repair matching list. This value is determined by considering the personnel ID, equipment ID, and the work order binding relationship between them. It analyzes whether the personnel possess the skills and experience required to complete the current equipment repair, whether they have received similar tasks before, and whether the equipment's fault type matches the repair personnel's skills. Based on the personnel's skill matching degree and task load, task allocation is further optimized to ensure its rationality and balance. For example, if the work order binding relationship between repair personnel P1 and equipment E001 is strong because P1's skills highly match the equipment's fault type, and P1 currently has a low number of orders, while the repair task for equipment E001 requires relatively complex technical support, calculations determine that P1 is the best choice for this task. The work order task is then bound to P1, the binding result is updated in the cloud work order pool, and the work order task is marked as scheduled.

[0080] The task scheduling matching value is calculated using the following formula:

[0081]

[0082] Where R represents the task scheduling matching value, N represents the number of personnel IDs in the matching list, D represents the number of equipment IDs to be dispatched, and T represents the number of equipment IDs to be dispatched. z Y represents the optimal scheduling time value corresponding to the z-th device. z Represents the responsive time offset of the z-th person, and M represents the total number of valid binding candidates;

[0083] N: The number of personnel IDs in the matching list, which is obtained by counting the current list of maintenance personnel to be dispatched in the work order system. According to the actual operation data, there are currently 12 maintenance personnel to be dispatched, so N = 12.

[0084] D: The number of equipment numbers to be dispatched, which is obtained by counting the number of equipment currently awaiting repair. According to the equipment management system data, there are currently 10 pieces of equipment awaiting repair, therefore, D = 10;

[0085] T z The optimal scheduling time value corresponding to the z-th device is calculated by analyzing the original maintenance data and combining the device type, fault level and maintenance complexity. Taking the first device as an example, the optimal scheduling time is 4 hours.

[0086] Y z The response time offset for the z-th person is calculated based on the person's work schedule, geographical location, and current task load. For example, the response time offset for the first person is 1 hour.

[0087] M: Total number of valid binding candidates. The number of valid binding candidates is determined by matching feasible combinations of personnel and equipment. Based on the current data, there are 5 valid personnel and equipment binding candidates. Therefore, M = 5.

[0088] Detailed calculation process:

[0089] Calculate N·D: N·D = 12·10 = 120;

[0090] calculate

[0091] Assuming 5 groups of bound candidates T z and Y z They are respectively:

[0092] Group 1: T1 = 4 hours, Y1 = 1 hour;

[0093] Group 2: T2 = 5 hours, Y2 = 2 hours;

[0094] Group 3: T3 = 6 hours, Y3 = 1.5 hours;

[0095] Group 4: T4 = 3.5 hours, Y4 = 1 hour;

[0096] Group 5: T5 = 4.5 hours, Y5 = 1.2 hours;

[0097] Calculate the difference for each group:

[0098] Group 1: 4-1=3 hours;

[0099] Group 2: 5 - 2 = 3 hours;

[0100] Group 3: 6 - 1.5 = 4.5 hours;

[0101] Group 4: 3.5 - 1 = 2.5 hours;

[0102] Group 5: 4.5 - 1.2 = 3.3 hours;

[0103] Summation:

[0104] calculate

[0105] Calculate the numerator:

[0106] Calculate the denominator: 1 + |ND| = 1 + |12 - 10| = 1 + 2 = 3;

[0107] Calculate the final result R:

[0108] The results indicate that the current matching degree between personnel and equipment is relatively high, with a task scheduling matching value of 38.654. ​​This means that, given the current number of personnel and equipment and the corresponding scheduling time differences, the system's scheduling efficiency is quite ideal. This value can be used to further optimize the allocation strategy of personnel and equipment and improve overall maintenance efficiency.

[0109] Specifically, such as Figure 2 , 6 As shown, the maintenance tracking module includes:

[0110] The process log collection submodule collects maintenance logs, parts usage records, and time node data based on work order items bound to the schedule, and integrates them in a formatted manner according to the work order number to generate a maintenance process dataset.

[0111] The system retrieves the original maintenance log entries associated with the work order number from the maintenance management database, filters records whose time field falls between the start time of the dispatched work order and the current time, and sorts the log entries in ascending order by time field. It then sequentially reads the parts call records under the work order number from the parts management database, including the parts number, call time, inventory status, and corresponding equipment number. The log entries and parts records are then compared and concatenated along the time dimension, aligned using the "event occurrence time" field. When multiple records overlap at a certain time point, the priority field is used for sorting, prioritizing records marked "on-site operation" for insertion into the final dataset. If no "on-site operation" mark is found, the first record is selected and inserted according to the lexicographical order of the parts number. The process involves inputting data into the node event records in the scheduler, extracting the node data generated during the scheduling process for the work order item, including operation flags such as "Start," "Pause," "Continue," and "Complete," and their timestamps. This data is then converted into a standard format, with the fields standardized as "Node Type" and "Node Time." The aforementioned maintenance log content, parts records, and node data are linked together using "Work Order Number" as the primary key. The data format fields are then uniformly processed, including converting the operator's number in the log entry into a name, matching the equipment number in the parts call record with the corresponding equipment name, and converting the node type from a numeric label to a text description. After completion, the three types of data are merged into a unified format record set, generating a maintenance process dataset, assigning a unique identifier, and storing it in the process dataset.

[0112] The node snapshot recognition submodule categorizes and organizes log content and parts usage items based on time nodes in the maintenance process dataset, marks maintenance behaviors, sorts them in chronological order, and generates a set of work order execution timeline entries.

[0113] The log content and accessory usage items are categorized and organized. When reading each log record in the dataset, the "event occurrence time" field is extracted and compared with all time nodes. Records with a time difference of less than or equal to 1 minute are considered to match that node, and the log entry is attached to the corresponding node. If a log record appears near multiple node times, each time difference is calculated, and the node with the smallest difference is selected for attachment. The same operation is performed on accessory usage records, comparing their "call time" field with all node times, and attaching them to the closest node in the same way. If the differences are the same, the node with the highest priority in the node type order "Start > Continue > Pause > Complete" is selected for assignment. After organization, the logs and accessory items attached to each node are... Internal sorting is performed, arranged in ascending order based on the "Event Time" field. If the time field is duplicated, the logs are sorted by operation type "Disassembly > Replacement > Installation". Parts are sorted in ascending order by equipment number. Then, an execution behavior label is generated for each node. The defined operation code is called and matched with the keyword field in the log content. When the log description contains keywords such as "replacement", "installation", or "testing", it is marked as the corresponding maintenance behavior. The same processing is performed when keywords such as "use" or "remove" appear in the part record. The work order execution timeline entry set is generated by combining the behavior label and time sequence. The record includes fields such as "node time", "behavior description", "parts change information", and "operator information". It is archived into the entry set library by work order number.

[0114] The status panel synchronization submodule calls the time nodes, maintenance actions and parts usage status in the work order execution time axis item set, calculates the time field mapping correction value, checks the synchronization status between fields, writes the node information into the record table, and updates the panel display status to the current node, thus obtaining a snapshot of the endoscope maintenance process record.

[0115] The time field mapping correction value is calculated using the following formula:

[0116]

[0117] Where T represents the time field mapping correction value, t ij w represents the original time value of the j-th element in the i-th node. ij m represents the time weight factor of the j-th element in the i-th node. ij This represents the quantity of the material field used in the j-th item of the i-th node. s represents the average quantity of material fields used in all cells of the i-th node. ij This represents the progress status code value of the j-th unit in the i-th node, where n represents the number of units included in the i-th node.

[0118] Time value t ijAssume the original time value t of the j-th element in the i-th node. ij It is obtained based on monitoring past event records, for example: the time value of node 1 is t. 11 = 2.5 hours, t 12 = 3.0 hours;

[0119] Time weighting factor w ij :w ij To adjust the weight of time values, it is set according to the priority of the nodes. For example, if the task of unit 1 of node 1 is more urgent, then w 11 =1.5, while unit 2 is less urgent, so w 12 =0.5, the weighting factor is set based on the urgency of the task and the priority of execution;

[0120] Material usage quantity m ij :m ij This represents the quantity of material used in the j-th item of the i-th node. For example, if unit 1 of node 1 uses 5 units of material, then m... 11 =5, Unit 2 uses 3 units, m 12 =3, the data is obtained directly through the material inventory management system;

[0121] Average material usage It is the average quantity of materials used in all units within a node, calculated as (m 11 +m 12 ) / 2 = (5+3) / 2 = 4;

[0122] Progress status code value s ij :s ij Indicates the progress status, for example: if unit 1 is 50% complete, then s 11 =0.5, Unit 2 is 75% complete, then s 12 =0.75, the value is automatically updated based on the progress tracking system;

[0123] Number of elements n: In this example, n = 2 means that the node contains two elements;

[0124] Calculate the numerator of the time mapping correction value T:

[0125]

[0126] The denominator for calculating the time mapping correction value T:

[0127] Final time mapping correction value T:

[0128] The calculated value of T is 2.05, indicating that after considering material usage deviation, time weight, and schedule status, the time mapping correction value for the i-th node is 2.05, representing the time efficiency adjustment coefficient for that node. This result is used to adjust the cloud status panel display, ensuring real-time synchronization and accurate reflection of the time, schedule, and material fields, thereby optimizing resource allocation and process monitoring.

[0129] Specifically, such as Figure 2 , 7 As shown, the data linkage module includes:

[0130] The Parts Details Organization submodule reads the parts usage details from the maintenance process record snapshot, summarizes the replacement frequency and replacement time interval by part type, binds the corresponding equipment number, and generates an endoscope parts replacement record table;

[0131] By calling the interface with the maintenance process record database, the system retrieves the parts usage records corresponding to the work orders, including key data such as part number, usage time, and replacement frequency. To ensure data accuracy, SQL queries are used for data filtering, with the work order number and maintenance date included as filtering conditions to ensure that the retrieved data is consistent with the actual maintenance records. The extracted data is categorized according to part type, and the specific data for each type of part is loaded into an in-memory data table for processing. Through a built-in algorithm, the replacement frequency and replacement time interval for each type of part are calculated. This calculation process involves parsing timestamps and calculating time differences. By iterating through all part records, the average replacement time interval for each type of part is calculated. The calculation results are then formatted into a report format and summarized according to part type and its corresponding equipment number. The final report not only includes detailed usage records of parts but also integrates statistical results of replacement frequency and time interval, forming an endoscope parts replacement record table, which is stored in the database for subsequent querying and analysis.

[0132] The maintenance list generation submodule matches the cloud prediction port configuration items with the endoscope parts replacement record table and writes them into the prediction field, identifies the parts task items of the equipment group, and generates an endoscope parts maintenance list.

[0133] The system retrieves the endoscope parts replacement record table from the database and reads the data from the table. This process includes extracting the replacement frequency and time interval of each part from the SQL database. It then connects to the cloud prediction port via a built-in API and sends the acquired parts replacement data to the cloud. The cloud prediction port uses a preset machine learning model to predict future maintenance needs based on the received data. The prediction process includes time series analysis and regression models to ensure the accuracy of the prediction results. After the prediction is completed, the cloud returns the prediction results to the maintenance list. The received data includes not only the predicted maintenance needs but also the predicted time points and the types of parts to be replaced. Based on the equipment number to which the part belongs, the system identifies the parts replacement tasks for different equipment groups. During the identification process, the parts tasks are grouped according to the equipment number. The grouping algorithm is optimized based on the equipment usage frequency and original maintenance records to ensure the rationality of the task grouping. Based on the grouping results and the cloud prediction information, an endoscope parts maintenance list is generated. The list details the parts that need to be maintained or replaced for each equipment group within a certain period in the future. After the list is generated, it is automatically formatted and saved for use by the maintenance department.

[0134] The above are merely specific embodiments of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A cloud-based endoscope repair management system, characterized by, The system comprises: The load monitoring module extracts the use time length, start frequency, and environment temperature and humidity data of the imaging module and the operating handle based on the endoscope device data, analyzes a real-time load curve, judges an abnormal section through a fluctuation amplitude and a set stable interval, and synchronously uploads to the cloud to generate a load abnormal device set; The risk early warning module calls device identification information in the load abnormal device set, retrieves device abnormal records in a cloud work order, compares the abnormal frequency of each device with the average value of devices of the same type, screens device numbers with abnormally high frequency, and generates a maintenance risk trigger list; The risk early warning module comprises: An abnormal frequency extraction submodule calls the load abnormal device set, retrieves original maintenance records of corresponding devices in the cloud work order, counts the number of maintenance records of each device, and establishes a maintenance frequency information set; A same-type deviation identification submodule extracts device maintenance frequencies according to the maintenance frequency information set, calculates an average maintenance number as a reference value, identifies the deviation of each device from the reference value, screens device numbers with a deviation exceeding a threshold, and generates a maintenance frequency abnormality list; A maintenance work order trigger submodule calls the maintenance frequency abnormality list, queries the scheduling state of devices in a current maintenance plan, screens devices not entering the scheduling, marks a maintenance emergency state, combines device numbers, maintenance frequencies, and emergency states, generates a maintenance risk trigger list, and generates a maintenance risk trigger list; A work order scheduling module calls device numbers in the maintenance risk trigger list, queries the scheduling, skill level, and order quantity of cloud maintenance personnel, identifies the geographical distance of the device location, compares the task load, screens the optimal personnel, updates the scheduling information to the cloud work order pool, and obtains a scheduling binding work order item; The work order scheduling module comprises: A maintenance person selection matching submodule calls device numbers in the maintenance risk trigger list, queries the scheduling, skill level, and order quantity of cloud maintenance personnel, combines the device location and the distance of the service area, sorts according to the skill matching degree and the task load difference, screens high-priority personnel numbers, and generates an endoscope maintenance matching list; A work order task binding submodule calculates a task scheduling matching value according to the personnel numbers and the to-be-issued device numbers in the endoscope maintenance matching list, analyzes the work order binding relationship between the personnel and the device, updates the binding result to the cloud work order pool and marks the state as scheduled, and obtains a scheduling binding work order item; The task scheduling matching value adopts the formula: Wherein, R represents the task scheduling matching value, N represents the number of personnel in the matching list, D represents the number of to-be-issued device numbers, T z represents the optimal scheduling time value corresponding to the zth device, Y z represents the response time offset of the zth personnel, and M represents the total number of effective binding candidates. A maintenance tracking module records three types of information uploaded during maintenance, namely operation logs, accessory use, and execution time nodes, arranges work order process nodes according to a time axis and synchronizes a cloud state panel, and obtains an endoscope maintenance process record snapshot based on the scheduling binding work order item; The maintenance tracking module comprises: A process log collection submodule collects maintenance logs, accessory use records, and time node data based on the scheduling binding work order item, formats and integrates according to the work order number, and generates a maintenance process data set; A node snapshot identification submodule classifies and arranges log content and accessory use items according to the time nodes in the maintenance process data set, marks maintenance behaviors and sorts according to time sequence, and generates a work order execution time axis item set. The state panel synchronization submodule calls the time node, maintenance action and accessory use state in the work order execution timeline entry set, calculates the time field mapping correction value, checks the inter-field synchronization state, and then writes the node information into the record table and updates the panel display state to the current node to obtain an endoscope maintenance process record snapshot; The time field mapping correction value uses the formula: wherein T represents a time field mapping correction value, t ij represents an original time value of the jth unit in the ith node, w ij represents a time weight factor of the jth unit in the ith node, m ij represents a usage number of the material field in the jth unit in the ith node, represents an average value of the usage number of the material field in all units in the ith node, s ij represents a progress state encoding value of the jth unit in the ith node, n represents a number of units included in the ith node; The data linkage module reads the accessory use details in the maintenance process record snapshot, aggregates the use frequency and replacement interval according to the accessory type, and binds the device number to upload to the cloud prediction port to generate an endoscope accessory maintenance list; The endoscope accessory maintenance list includes accessory use trend categories, replacement cycle prediction values and accessory life distribution models; The data linkage module includes: The accessory details sorting submodule reads the accessory use details in the maintenance process record snapshot, aggregates the replacement frequency and replacement time interval according to the accessory type, binds the device number, and generates an endoscope accessory replacement record table; The maintenance list generation submodule matches the cloud prediction port configuration item according to the endoscope accessory replacement record table and writes into the prediction field, identifies the accessory task item of the device group, and generates an endoscope accessory maintenance list.

2. The cloud-based endoscope repair management system of claim 1, wherein: The load abnormality device set includes device operation stability indicators, abnormality triggering time periods and device performance degradation characteristics, the maintenance risk triggering list includes high-frequency abnormality alarm weights, device original maintenance ratios and model abnormality deviation degrees, the dispatch binding work order item includes personnel skill matching degrees, geographical task coverage efficiency and scheduling load balancing coefficients, and the endoscope maintenance process record snapshot includes maintenance task progress nodes, accessory replacement type statistics and operation behavior mode characteristics. 3.The cloud-based endoscope repair management system of claim 1, wherein: The load monitoring module includes: The operation record extraction submodule generates a device operation state record table based on endoscope device data, including imaging module and operation handle use time length and start frequency data, and collects device environment temperature and humidity records, integrates them into a single data structure according to the device number, and generates a device operation state record table after removing missing items; The load abnormality determination submodule determines whether the fluctuation section exceeds the standard range according to the device operation state record table, including use time length data and temperature and humidity values, in combination with the upper and lower limits of the use time length stable interval and the environment parameter threshold, selects the corresponding device number and abnormality frequency, and generates an abnormal device operation list; The maintenance task generation submodule classifies and aggregates device numbers with frequency values higher than the set maintenance start frequency threshold according to the abnormal device operation list, matches idle time periods in the maintenance plan and assigns corresponding maintenance personnel, and generates a load abnormality device set.

Images