A one-stop maintenance service management platform based on cloud platform

Abstract

The present invention relates to the technical field of maintenance service management and intelligent scheduling, and specifically to a one-stop cloud-based maintenance service management platform, comprising a user demand analysis module, a service resource scheduling module, a maintenance process collaboration module, a data tracing and analysis module, and a service report generation module. Specifically, the user demand analysis module is used to analyze and extract equipment type parameters and generate maintenance timeliness parameters; the service resource scheduling module generates resource scheduling instructions containing the service provider ID and promised arrival time; the maintenance process collaboration module generates timeliness verification parameters containing the difference between the actual arrival time and the actual arrival time; and the data tracing and analysis module generates parts compliance parameters. By constructing a maintenance service management platform that integrates demand analysis, resource scheduling, process collaboration, and result evaluation, the present invention achieves structured processing and traceable quality supervision throughout the entire service process.

Description

Technical Field

[0001] The present invention relates to the technical field of maintenance service management and intelligent scheduling, and in particular to a one-stop maintenance service management platform based on a cloud platform. Background Art

[0002] In modern society, with the continuous improvement of the intelligence and diversification of equipment, the demand for maintenance and repair of various types of equipment is becoming more and more frequent, and maintenance service management is becoming more and more complex; traditional maintenance service processes generally rely on manual registration and telephone communication, and the needs raised by users are often described in unstructured natural language, resulting in slow service response, untimely work order distribution, and ambiguous information transmission; at the same time, the resource scheduling of maintenance services relies on manual experience and judgment, and it is impossible to efficiently and accurately match qualified service providers. The entire maintenance process lacks systematic and digital management and control methods, and it is difficult to trace service quality and define responsibilities.

[0003] Existing maintenance service management systems generally face the following technical challenges: First, they are unable to effectively analyze unstructured user needs, resulting in inaccurate identification of equipment types and fault urgency levels, which affects the scientific nature of subsequent scheduling. Second, service providers' scheduling mechanisms are imperfect, lacking the ability to intelligently match equipment types with response times, leading to low utilization of high-quality resources and untimely responses. Third, incomplete data collection on maintenance process coordination and timeliness makes the service process difficult to quantify and evaluate. Fourth, insufficient compliance supervision of parts replacement leads to a prominent phenomenon of mixing original and non-original parts, affecting maintenance quality and safety. Therefore, a one-stop cloud-based maintenance service management platform is urgently needed to address the above issues. Summary of the Invention

[0004] Based on the above objectives, the present invention provides a one-stop maintenance service management platform based on a cloud platform.

[0005] A one-stop maintenance service management platform based on a cloud platform, including a user demand analysis module, a service resource scheduling module, a maintenance process collaboration module, a data tracing and analysis module, and a service report generation module; wherein:

[0006] User demand parsing module: This module receives unstructured maintenance requirements input by users, extracts equipment type parameters through semantic parsing, and generates maintenance timeliness parameters based on fault keyword matching against a preset emergency level mapping table.

[0007] Service resource scheduling module: This module selects service providers with corresponding certification qualifications based on equipment type parameters, calculates the optimal path for service providers to reach the fault location based on repair time parameters, and generates resource scheduling instructions containing the service provider ID and promised arrival time.

[0008] Maintenance process collaboration module: This module is used to trigger a task work order based on the service provider ID in the resource scheduling instruction, collect the location data of the service provider terminal and the start time of the maintenance operation, and generate a time verification parameter containing the difference between the actual arrival time and the actual arrival time.

[0009] Data tracing and analysis module: This module compares time validation parameters with maintenance time parameters. If the difference between the actual arrival time and the maintenance time parameter threshold exceeds the maintenance time parameter threshold, a service response exception flag is generated. Furthermore, based on the device type parameters and associated parts replacement records, the proportion of non-original parts used is calculated to generate parts compliance parameters.

[0010] Service report generation module: used to integrate equipment type parameters, repair time parameters, time verification parameters and parts compliance parameters to generate a comprehensive service report that includes service provider performance ratings and parts compliance warnings.

[0011] Optionally, the user demand analysis module includes a text preprocessing unit, a semantic analysis unit, and an emergency level determination unit; wherein:

[0012] Text preprocessing unit: This unit receives unstructured maintenance requirement text from users and preprocesses it using regular expression extraction and part-of-speech segmentation algorithms. It divides the sentence structure in the text into independent semantic units, filters out stop words and common sentences not related to maintenance, and retains the language chunk information for parsing.

[0013] Semantic parsing unit: This unit is used to identify equipment type entities based on preprocessed language chunk information. By building an equipment type dictionary matching network based on semantic similarity, it identifies and extracts the equipment model and category representing the maintenance object, and generates equipment type parameters.

[0014] Emergency level determination unit: used to extract a set of keywords related to the fault status from the demand text, and assign a corresponding fault emergency value to each keyword based on the preset emergency level mapping table. The total emergency score is obtained by weighted accumulation of the emergency values ​​of all fault keywords, and the level to which it belongs is determined according to the set level threshold range, and finally the maintenance timeliness parameter is generated.

[0015] Optionally, the semantic parsing unit includes:

[0016] Equipment entity pre-training subunit: Build a training corpus based on historical maintenance work order corpus, use a bidirectional encoder representation model to perform vector encoding training on the equipment entities in the corpus, and obtain the semantic embedding matrix of the equipment name and model phrases ,in Indicates the semantic vectors of known device names, is the total number of dictionary devices;

[0017] Dictionary matching network construction subunit: used to fuse the embedding matrix with the manually maintained device type dictionary and calculate the embedding vector of the user input fragment using cosine similarity With each in the dictionary Similarity score ,like ,in If the similarity threshold is set, the corresponding device name Considered as a matching result;

[0018] Matching result determination subunit: used to sort all device names that meet the similarity threshold by similarity score, select the first one with the highest score as the candidate device model, and combine it with the corresponding device classification label in the dictionary to jointly generate the final device type parameter ,in, Indicates the equipment category; Indicates the specific device model.

[0019] Optionally, the service resource scheduling module includes a service provider qualification screening unit, a service provider location acquisition unit, a time efficiency path calculation unit, and a resource scheduling instruction generation unit; wherein:

[0020] Service Provider Qualification Screening Unit: Based on the device type parameter, the service provider qualification database maintained by the platform is called, and the qualification tags of each service provider recorded therein are matched with the device categories in the device type parameter one by one, thereby screening out a set of service providers with the corresponding certification qualifications for the target device;

[0021] Service provider location acquisition unit: used to call the service provider location database updated in real time by the platform to obtain the current geographical location information of each screened service provider;

[0022] Time-Effective Path Calculation Unit: This unit inputs the location information of each service provider and the maintenance response time constraints corresponding to the maintenance time-efficiency parameters into the path planning algorithm. It then combines real-time traffic status data with the service provider's current task load to predict the travel time required for each service provider to reach the target fault location. The predicted results are then sorted to determine the shortest time path that meets the maintenance time-efficiency parameters and select the corresponding service provider as the target service provider.

[0023] Resource scheduling instruction generation unit: Based on the service provider ID of the target service provider and the predicted travel time corresponding to the calculated shortest path, the target service provider's promised arrival time is determined, and then a structured resource scheduling instruction containing the target service provider ID and the promised arrival time is generated.

[0024] Optionally, the time efficiency path calculation unit includes:

[0025] Geographic path construction subunit: Based on the geographic coordinates of the service provider's current location and the target fault location, it constructs a set of multiple feasible routes by calling the map service interface. Each route includes the route length, the road sections passed through, and the current traffic status information;

[0026] Driving time prediction subunit: used to estimate the driving time of each route, taking into account factors such as basic road speed limit, real-time traffic congestion factor, intersection waiting time, etc., to calculate the total expected driving time of each path ;

[0027] Sorting and screening subunit: used to predict the shortest path time corresponding to all service providers Sort by value from small to large to select a set of service providers that meet the maintenance timeliness parameters;

[0028] Optimal path confirmation subunit: used to select the corresponding The smallest service provider is selected and its shortest path is determined as the final scheduling path.

[0029] Optionally, the resource scheduling instruction generating unit includes:

[0030] Current time acquisition subunit: used to call the system server time interface to obtain the system timestamp corresponding to the current scheduling time in real time ;

[0031] Committed time calculation subunit: based on current system time The shortest path predicted travel time to the target service provider , calculate the service provider's estimated promised arrival time ;

[0032] Instruction encapsulation subunit: used to perform structured encapsulation of the target service provider's service provider identification information and the corresponding promised arrival time to generate resource scheduling instructions.

[0033] Optionally, the maintenance process collaboration module includes a work order triggering unit, a positioning data acquisition unit, an arrival determination unit, a start time recording unit, and a timeliness parameter generation unit; wherein:

[0034] Work order triggering unit: used to receive the service provider ID in the resource scheduling instruction and generate a corresponding maintenance task work order in the platform task management system. The task work order contains the service provider ID, user location, equipment type parameters and promised arrival time;

[0035] Positioning data collection unit: After the service provider receives the task work order, it calls the GPS module in the service provider's mobile terminal to collect its current location coordinate information in real time, and uploads the positioning data to the platform at fixed time intervals to record it as the service provider's travel trajectory data;

[0036] Arrival determination unit: used to compare the distance between the service provider's real-time coordinates and the user's location coordinates. If the spatial distance between the current location and the user's location is less than the set arrival determination threshold, the timestamp of the first time the condition is met will be recorded as the actual arrival time. ;

[0037] Start time recording unit: used to record the maintenance operation start timestamp when the maintenance task start button is operated in the service provider terminal , and upload it to the platform system as the official time mark for the start of maintenance operations;

[0038] Time parameter generation unit: used to generate the actual arrival time The promised arrival time recorded in the resource scheduling instruction Perform difference calculation to obtain aging verification parameters .

[0039] Optionally, the data tracing and analysis module includes a time anomaly detection unit, an anomaly mark generation unit, a parts record association unit, and a compliance statistics unit; wherein:

[0040] Time anomaly detection unit: used to receive the actual arrival time difference generated by the maintenance process collaboration module , and call the maintenance time parameter threshold ;when Greater than When the time limit is exceeded,

[0041] Abnormal tag generation unit: used to write a service response abnormal tag to the corresponding task work order after the detection result meets the time limit condition, and establish an abnormal index field in the platform quality monitoring database;

[0042] Parts record association unit: used to search the platform parts replacement database based on the equipment type parameter, call the maintenance record entries that match the equipment type parameter, extract the parts number and parts source attributes in each record, and write the record into the parts statistics cache table;

[0043] Compliance statistics unit: used to traverse the accessories statistics cache table, accumulate the usage times of original accessories and non-original accessories respectively, calculate the usage ratio of non-original accessories, and convert the usage ratio into accessories compliance parameters.

[0044] Optionally, the compliance statistics unit includes:

[0045] Accessory source counting subunit: used to traverse all maintenance record entries in the accessory statistics cache table, read and classify the accessory source attribute field of each record, and if it is marked as original, it will be accumulated to the original accessory usage count If it is marked as non-original, it will be accumulated to the non-original accessories usage count ;

[0046] Usage ratio calculation subunit: used to calculate the usage ratio of non-original accessories after completing all record traversal , and its calculation formula is: ,in, The proportion of non-original accessories used;

[0047] Compliance parameter generation subunit: used to generate the compliance parameter based on the proportion of non-original accessories used. Comply with the upper limit of the compliance ratio preset by the platform Make a judgment, if , then generate accessory compliance parameters , indicating compliance; otherwise, , indicating non-compliance.

[0048] Optionally, the service report generation module includes a data aggregation unit, a performance rating calculation unit, a compliance warning generation unit, and a report construction unit; wherein:

[0049] Data aggregation unit: used to synchronously receive structured parameter information from the user demand analysis module, maintenance process collaboration module and data traceability analysis module, including equipment type parameters, maintenance time parameters, time verification parameters and accessory compliance parameters ;

[0050] Performance rating calculation unit: used to verify parameters based on timeliness , generate the service provider performance rating; when When When When and The rating level boundary value preset by the system;

[0051] Compliance alert generation unit: used to read accessory compliance parameters ,like , then add a non-compliant accessories warning label to the current work order and mark the relevant responsible parties in the report; if , it is marked as accessory compliance status;

[0052] Report construction unit: used to integrate various parameters to generate a comprehensive service report, which includes the work order number, service provider ID, equipment model, equipment category, response time level, performance rating label and accessory compliance status label.

[0053] Beneficial effects of the present invention:

[0054] The present invention uses a user demand analysis module to perform semantic extraction and urgency level determination on unstructured text, thus achieving automatic structural processing of equipment types and maintenance timeliness, and providing standardized input for service scheduling. Through the service resource scheduling module, based on equipment matching and path timeliness calculation, the optimal service providers with certification qualifications are intelligently screened and promised arrival times are generated, thereby improving the accuracy and response speed of scheduling. The maintenance process collaboration module collects positioning and startup data in real time, automatically calculates arrival deviations, and ensures that the entire maintenance process can be quantified and tracked.

[0055] The present invention evaluates service response timeliness and parts usage compliance through a data tracing and analysis module, and uniformly outputs reports containing performance ratings and compliance warnings through a service report generation module, thereby achieving standardized measurement and recording of service quality. The overall platform has a closed-loop capability from demand analysis, task dispatching, process monitoring to result evaluation, effectively solving problems such as information asymmetry, low scheduling efficiency, and difficult quality supervision in traditional maintenance services, thereby improving the level of systematic service and the transparency of industry operations and maintenance. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only for the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0057] Figure 1 A schematic diagram of a one-stop maintenance service management platform according to an embodiment of the present invention;

[0058] Figure 2 Schematic diagram of a service resource scheduling module according to an embodiment of the present invention. DETAILED DESCRIPTION

[0059] The present invention is described in detail below with reference to the accompanying drawings and specific embodiments. It is also noted that, to provide a more detailed description, the following embodiments are best and preferred embodiments, and those skilled in the art may employ alternative methods for implementing certain known technologies. Furthermore, the accompanying drawings are intended only to provide a more detailed description of the embodiments and are not intended to limit the present invention.

[0060] like Figure 1-Figure 2 As shown, a one-stop maintenance service management platform based on a cloud platform includes a user demand analysis module, a service resource scheduling module, a maintenance process collaboration module, a data tracing and analysis module, and a service report generation module; wherein:

[0061] User demand parsing module: This module receives unstructured maintenance requirements input by users, extracts equipment type parameters through semantic parsing, and generates maintenance timeliness parameters based on fault keyword matching against a preset emergency level mapping table.

[0062] Service resource scheduling module: This module selects service providers with corresponding certification qualifications based on equipment type parameters, calculates the optimal path for service providers to reach the fault location based on repair time parameters, and generates resource scheduling instructions containing the service provider ID and promised arrival time.

[0063] Maintenance process collaboration module: This module is used to trigger a task work order based on the service provider ID in the resource scheduling instruction, collect the location data of the service provider terminal and the start time of the maintenance operation, and generate a time verification parameter containing the difference between the actual arrival time and the actual arrival time.

[0064] Data tracing and analysis module: This module compares time validation parameters with maintenance time parameters. If the difference between the actual arrival time and the maintenance time parameter threshold exceeds the maintenance time parameter threshold, a service response exception flag is generated. Furthermore, based on the device type parameters and associated parts replacement records, the proportion of non-original parts used is calculated to generate parts compliance parameters.

[0065] Service report generation module: used to integrate equipment type parameters, repair time parameters, time verification parameters and parts compliance parameters to generate a comprehensive service report that includes service provider performance ratings and parts compliance warnings.

[0066] The user demand analysis module includes a text preprocessing unit, a semantic analysis unit, and an emergency level determination unit; wherein:

[0067] Text preprocessing unit: This unit receives unstructured maintenance requirement text from users and preprocesses it using regular expression extraction and part-of-speech segmentation algorithms. It divides the sentence structure in the text into independent semantic units, filters out stop words and common sentences not related to maintenance, and retains the language chunk information for parsing.

[0068] Semantic parsing unit: This unit is used to identify equipment type entities based on preprocessed language chunk information. By building an equipment type dictionary matching network based on semantic similarity, it identifies and extracts the equipment model and category representing the maintenance object, and generates equipment type parameters.

[0069] Emergency level determination unit: It is used to extract a set of keywords related to the fault status from the demand text, and assign a corresponding fault emergency value to each keyword based on the preset emergency level mapping table. The total emergency score is obtained by weighted accumulation of the emergency values ​​of all fault keywords, and the level to which it belongs is determined according to the set level threshold range. Finally, the maintenance timeliness parameter is generated. The calculation formula of the total emergency score is:

[0070] ,in, Indicates total urgency score; Indicates the The emergency value corresponding to each fault keyword; Indicates the The weight coefficient of each keyword; Indicates the number of fault keywords extracted; through the above structural design, the user demand analysis module can perform structured extraction and graded evaluation of equipment types and fault urgency in unstructured text, providing a calculable parameter basis for subsequent service scheduling.

[0071] Table 1 Example of emergency level mapping

[0072]

[0073] Based on this Table 1, we extract keywords related to the device fault status from the user input through text semantic analysis and match them one by one with the table;

[0074] According to the total emergency score , corresponding to the following table 2 set interval determination emergency level:

[0075] Table 2 Comparison of grade determination

[0076]

[0077] The aforementioned emergency level mapping table converts keywords in natural language into quantifiable urgency scores and classifies them into level intervals. This allows the system to automatically transform unstructured fault descriptions into standardized response levels and timeliness parameters, providing a direct basis for subsequent service resource scheduling. This approach eliminates the subjectivity of manual judgment and improves the consistency and timeliness of system responses.

[0078] The semantic parsing unit includes:

[0079] Equipment entity pre-training subunit: Build a training corpus based on historical maintenance work order corpus, use a bidirectional encoder representation model to perform vector encoding training on the equipment entities in the corpus, and obtain the semantic embedding matrix of the equipment name and model phrases ,in Indicates the semantic vectors of known device names, is the total number of dictionary devices;

[0080] Dictionary matching network construction subunit: used to fuse the embedding matrix with the manually maintained device type dictionary and calculate the embedding vector of the user input fragment using cosine similarity With each in the dictionary Similarity score , the formula is: ,like ,in If the similarity threshold is set, the corresponding device name Considered as a matching result;

[0081] Matching result determination subunit: used to sort all device names that meet the similarity threshold by similarity score, select the first one with the highest score as the candidate device model, and combine it with the corresponding device classification label in the dictionary to jointly generate the final device type parameter ,in, Indicates the type of equipment (e.g., industrial printer, air conditioning system); Indicates a specific device model (such as LP-320, ACX-750). Through the above structure, the semantic parsing unit can map the ambiguous or deformed device description in the user input text to structured standard device type parameters, effectively improving the parsing accuracy of unstructured semantic information.

[0082] The service resource scheduling module includes a service provider qualification screening unit, a service provider location acquisition unit, a time-sensitive path calculation unit, and a resource scheduling instruction generation unit; wherein:

[0083] Service Provider Qualification Screening Unit: Based on the device type parameter, the service provider qualification database maintained by the platform is called, and the qualification tags of each service provider recorded therein are matched with the device categories in the device type parameter one by one, thereby screening out a set of service providers with the corresponding certification qualifications for the target device;

[0084] Service provider location acquisition unit: used to call the service provider location database updated in real time by the platform to obtain the current geographical location information of each screened service provider;

[0085] Time-Effective Path Calculation Unit: This unit inputs the location information of each service provider and the maintenance response time constraints corresponding to the maintenance time-efficiency parameters into the path planning algorithm. It then combines real-time traffic status data with the service provider's current task load to predict the travel time required for each service provider to reach the target fault location. The predicted results are then sorted to determine the shortest time path that meets the maintenance time-efficiency parameters and select the corresponding service provider as the target service provider.

[0086] Resource scheduling instruction generation unit: Based on the service provider ID of the target service provider and the predicted travel time corresponding to the calculated shortest path, the target service provider's promised arrival time is determined, and then a structured resource scheduling instruction containing the target service provider ID and promised arrival time is generated; through the above structural design, the service resource scheduling module can dynamically screen the best candidates among the service providers that meet the certification requirements, and generate complete resource scheduling instructions based on this, realizing the automation of the entire process from service provider screening to scheduling control.

[0087] The time-sensitive path calculation unit includes:

[0088] Geographic path construction subunit: Based on the geographic coordinates of the service provider's current location and the target fault location, it constructs a set of multiple feasible routes by calling the map service interface. Each route includes the route length, the road sections passed through, and the current traffic status information;

[0089] Driving time prediction subunit: used to estimate the driving time of each route, taking into account factors such as basic road speed limit, real-time traffic congestion factor, intersection waiting time, etc., to calculate the total expected driving time of each path , the formula is: ,in, For the Estimated travel time for each route; For the The number of segments contained in the path; For path Middle the distance of the road section; For the The speed limit of the road section; For the Current congestion adjustment factor of the road section (value range ; For the The average waiting time corresponding to the road segment;

[0090] Sorting and screening subunit: used to predict the shortest path time corresponding to all service providers Sort by value from small to large to select a set of service providers that meet the maintenance timeliness parameters;

[0091] Optimal path confirmation subunit: used to select the corresponding The smallest service provider is selected and its shortest path is determined as the final scheduling path. Through the above structure, the system can accurately calculate the estimated arrival time of each service provider based on multi-dimensional traffic factors, and ensure that the selected service provider has both time response capabilities and meets the needs of emergency maintenance.

[0092] The resource scheduling instruction generation unit includes:

[0093] Current time acquisition subunit: used to call the system server time interface to obtain the system timestamp corresponding to the current scheduling time in real time To ensure data consistency when generating instructions;

[0094] Committed time calculation subunit: based on current system time The shortest path predicted travel time to the target service provider , calculate the service provider's estimated promised arrival time , the formula is: ;

[0095] Instruction encapsulation subunit: used to structure the target service provider's service provider identification information and the corresponding promised arrival time to generate resource scheduling instructions , whose structure is defined as: ,in, The unique identification number of the target service provider; Promised arrival time; The device type parameter submitted by the user is used to attach task device background information. Through the above structure, it is possible to realize the automatic resource scheduling instruction generation based on accurate time prediction, ensuring that the scheduling information is clear, timely and seamlessly connected with the platform task execution mechanism.

[0096] The maintenance process collaboration module includes a work order trigger unit, a positioning data acquisition unit, an arrival determination unit, a start time recording unit, and a time parameter generation unit; wherein:

[0097] Work order triggering unit: used to receive the service provider ID in the resource scheduling instruction and generate the corresponding maintenance task work order in the platform task management system. The task work order contains the service provider ID, user location, equipment type parameters and promised arrival time, and binds the task work order to the terminal account of the target service provider to achieve synchronous task dispatch;

[0098] Positioning data collection unit: After the service provider receives the task work order, it calls the GPS module in the service provider's mobile terminal to collect its current location coordinate information in real time, and uploads the positioning data to the platform at a fixed time interval (set to every 60 seconds) to record it as the service provider's travel trajectory data;

[0099] Arrival determination unit: used to compare the distance between the service provider's real-time coordinates and the user's location coordinates. If the spatial distance between the current location and the user's location is less than the set arrival determination threshold, the timestamp of the first time the condition is met will be recorded as the actual arrival time. ;

[0100] Start time recording unit: used to record the maintenance operation start timestamp when the maintenance task start button is operated in the service provider terminal , and upload it to the platform system as the official time mark for the start of maintenance operations;

[0101] Time parameter generation unit: used to generate the actual arrival time The promised arrival time recorded in the resource scheduling instruction Perform difference calculation to obtain aging verification parameters , which is defined as follows: Through the above structure, the maintenance process collaboration module can monitor the entire process of task work order triggering, service provider progress and actual arrival, and form measurable response time indicators to provide key data support for subsequent service quality evaluation.

[0102] The data traceability analysis module includes a time anomaly detection unit, an anomaly tag generation unit, a parts record association unit, and a compliance statistics unit; among them:

[0103] Time anomaly detection unit: used to receive the actual arrival time difference generated by the maintenance process collaboration module , and call the maintenance time parameter threshold ;when Greater than When the time limit is exceeded,

[0104] Maintenance time parameter threshold It is an important criterion for judging whether the service provider's response time meets expectations. Its calculation needs to be combined with the fault emergency level label. Task dispatch delay compensation coefficient , the specific expression is as follows: ,in, The threshold value of the maintenance time parameter indicates the upper limit of the time allowed for the system to determine whether the service provider arrives on time, in minutes; Represents the emergency level label according to the fault The corresponding standard maintenance response time, in minutes, is determined by the system's preset level mapping table; The dispatch delay compensation coefficient is expressed in minutes. It represents the average system delay caused by task instructions in the network and platform scheduling processes. It is usually obtained by system operation evaluation. For example, it is set to a fixed value of 5 minutes.

[0105] Table 3 Level mapping example

[0106]

[0107] Abnormal tag generation unit: This is used to write a service response abnormal tag to the corresponding task work order after the detection result meets the time limit condition, and to establish an abnormal index field in the platform quality monitoring database for subsequent quality statistics and accountability queries;

[0108] Parts record association unit: used to search the platform parts replacement database based on the equipment type parameter, call the maintenance record entries that match the equipment type parameter, extract the parts number and parts source attributes in each record, and write the record into the parts statistics cache table;

[0109] Compliance statistics unit: used to traverse the accessories statistics cache table, accumulate the number of times original accessories and non-original accessories are used, calculate the usage ratio of non-original accessories, and convert the usage ratio into accessories compliance parameters; at the same time, the accessories compliance parameters are written into the accessories compliance field of the same task work order for the service report generation module to read; through the above structure, the data traceability analysis module can generate exception tags in a timely manner in the scenario of service response timeout, and simultaneously complete compliance statistics for the source of accessories, providing data basis for subsequent comprehensive service reports and ensuring traceability integrity.

[0110] Compliance statistics units include:

[0111] Accessory source counting subunit: used to traverse all maintenance record entries in the accessory statistics cache table, read and classify the accessory source attribute field of each record, and if it is marked as original, it will be accumulated to the original accessory usage count If it is marked as non-original, it will be accumulated to the non-original accessories usage count ;

[0112] Usage ratio calculation subunit: used to calculate the usage ratio of non-original accessories after completing all record traversal , and its calculation formula is: ,in, is the usage ratio of non-original accessories, and the value range is ;

[0113] Compliance parameter generation subunit: used to generate the compliance parameter based on the proportion of non-original accessories used. Comply with the upper limit of the compliance ratio preset by the platform Make a judgment, if , then generate accessory compliance parameters , indicating compliance; otherwise, , indicating non-compliance; this parameter will serve as an important input field for the service report generation module; the above unit quantifies and classifies the accessory usage records by source type, calculates the proportion of non-original usage with a clear proportion formula, and then determines whether the accessory usage is compliant based on the set proportion threshold, so that the accessory compliance parameters have an objective and quantifiable basis, ensuring that the compliance judgment results in the service report are accurate and credible, which will help strengthen accessory quality supervision and service transparency.

[0114] The service report generation module includes a data aggregation unit, a performance rating calculation unit, a compliance warning generation unit, and a report construction unit; among which:

[0115] Data aggregation unit: used to synchronously receive structured parameter information from the user demand analysis module, maintenance process collaboration module and data traceability analysis module, including equipment type parameters, maintenance time parameters, time verification parameters and accessory compliance parameters And bind the data to the corresponding maintenance task work order number to ensure data association and consistency;

[0116] Performance rating calculation unit: used to verify parameters based on timeliness , generate the service provider performance rating; when When When When and The rating level boundary value preset by the system;

[0117] Compliance alert generation unit: used to read accessory compliance parameters ,like , then add a non-compliant accessories warning label to the current work order and mark the relevant responsible parties in the report; if , it is marked as accessory compliance status;

[0118] Report construction unit: used to integrate various parameters to generate a comprehensive service report. The comprehensive service report includes the work order number, service provider ID, equipment model, equipment category, response time level, performance rating label and parts compliance status label, and is output in a visual structured manner; the above unit processes the key structured parameters through centralized aggregation and scoring mechanism. The service report generation module can automatically output maintenance evaluation results that combine performance performance and parts quality compliance, improve the integrity, objectivity and traceability of the report, and provide platform users and managers with a clear and transparent basis for service quality evaluation.

[0119] The present invention encompasses any alternatives, modifications, equivalents, and solutions that fall within the spirit and scope of the present invention. To provide a thorough understanding of the present invention, specific details are described in detail below in connection with the preferred embodiments of the present invention, but those skilled in the art will be able to fully understand the present invention without these detailed descriptions. Furthermore, to avoid unnecessary confusion regarding the essence of the present invention, well-known methods, processes, procedures, components, and circuits have not been described in detail.

[0120] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A one-stop maintenance service management platform based on a cloud platform, characterized by: It includes user demand analysis module, service resource scheduling module, maintenance process collaboration module, data tracing and analysis module, and service report generation module; among which: User demand parsing module: This module receives unstructured maintenance requirements input by users, extracts equipment type parameters through semantic parsing, and generates maintenance timeliness parameters based on fault keyword matching against a preset emergency level mapping table. The user demand analysis module includes a text preprocessing unit, a semantic analysis unit, and an emergency level determination unit; wherein: Text preprocessing unit: This unit receives unstructured maintenance requirement text from users and preprocesses it using regular expression extraction and part-of-speech segmentation algorithms. It divides the sentence structure in the text into independent semantic units, filters out stop words and common sentences not related to maintenance, and retains the language chunk information for parsing. Semantic parsing unit: This unit is used to identify equipment type entities based on preprocessed language chunk information. By building an equipment type dictionary matching network based on semantic similarity, it identifies and extracts the equipment model and category representing the maintenance object, and generates equipment type parameters. Emergency level determination unit: This unit is used to extract a set of keywords related to the fault status from the demand text and assign a corresponding fault emergency value to each keyword based on a preset emergency level mapping table. The total emergency score is obtained by weighted accumulation of the emergency values ​​of all fault keywords. The emergency level is then determined based on the set level threshold range, ultimately generating a maintenance timeliness parameter. The semantic parsing unit includes: Equipment entity pre-training subunit: Build a training corpus based on historical maintenance work order corpus, use a bidirectional encoder representation model to perform vector encoding training on the equipment entities in the corpus, and obtain the semantic embedding matrix of the equipment name and model phrases ,in Indicates the semantic vectors of known device names, is the total number of dictionary devices; Dictionary matching network construction subunit: used to fuse the embedding matrix with the manually maintained device type dictionary and calculate the embedding vector of the user input fragment using cosine similarity With each in the dictionary Similarity score ,like ,in If the similarity threshold is set, the corresponding device name Considered as a matching result; Matching result determination subunit: used to sort all device names that meet the similarity threshold by similarity score, select the first one with the highest score as the candidate device model, and combine it with the corresponding device classification label in the dictionary to jointly generate the final device type parameter ,in, Indicates the equipment category; Indicates the specific device model; Service resource scheduling module: This module selects service providers with corresponding certification qualifications based on equipment type parameters, calculates the optimal path for service providers to reach the fault location based on repair time parameters, and generates resource scheduling instructions containing the service provider ID and promised arrival time. Maintenance process collaboration module: This module is used to trigger a task work order based on the service provider ID in the resource scheduling instruction, collect the location data of the service provider terminal and the start time of the maintenance operation, and generate a time verification parameter containing the difference between the actual arrival time and the actual arrival time. Data tracing and analysis module: This module compares time validation parameters with maintenance time parameters. If the difference between the actual arrival time and the maintenance time parameter threshold exceeds the maintenance time parameter threshold, a service response exception flag is generated. Furthermore, based on the device type parameters and associated parts replacement records, the proportion of non-original parts used is calculated to generate parts compliance parameters. Service report generation module: used to integrate equipment type parameters, repair time parameters, time verification parameters and parts compliance parameters to generate a comprehensive service report that includes service provider performance ratings and parts compliance warnings.

2. The one-stop maintenance service management platform based on a cloud platform according to claim 1, characterized in that: The service resource scheduling module includes a service provider qualification screening unit, a service provider location acquisition unit, a time efficiency path calculation unit, and a resource scheduling instruction generation unit; wherein: Service Provider Qualification Screening Unit: Based on the device type parameter, the service provider qualification database maintained by the platform is called, and the qualification tags of each service provider recorded therein are matched with the device categories in the device type parameter one by one, thereby screening out a set of service providers with the corresponding certification qualifications for the target device; Service provider location acquisition unit: used to call the service provider location database updated in real time by the platform to obtain the current geographical location information of each screened service provider; Time-Effective Path Calculation Unit: This unit inputs the location information of each service provider and the maintenance response time constraints corresponding to the maintenance time-efficiency parameters into the path planning algorithm. It then combines real-time traffic status data with the service provider's current task load to predict the travel time required for each service provider to reach the target fault location. The predicted results are then sorted to determine the shortest time path that meets the maintenance time-efficiency parameters and select the corresponding service provider as the target service provider. Resource scheduling instruction generation unit: Based on the service provider ID of the target service provider and the predicted travel time corresponding to the calculated shortest path, the target service provider's promised arrival time is determined, and then a structured resource scheduling instruction containing the target service provider ID and the promised arrival time is generated.

3. The one-stop maintenance service management platform based on a cloud platform according to claim 2, characterized in that: The time-sensitive path calculation unit includes: Geographic path construction subunit: Based on the geographic coordinates of the service provider's current location and the target fault location, it constructs a set of multiple feasible routes by calling the map service interface. Each route includes the route length, the road sections passed through, and the current traffic status information; Driving time prediction subunit: used to estimate the driving time of each route, taking into account factors such as basic road speed limit, real-time traffic congestion factor, intersection waiting time, etc., to calculate the total expected driving time of each path ; Sorting and screening subunit: used to predict the shortest path time corresponding to all service providers Sort by value from small to large to select a set of service providers that meet the maintenance timeliness parameters; Optimal path confirmation subunit: used to select the corresponding The smallest service provider is selected and its shortest path is determined as the final scheduling path.

4. The one-stop maintenance service management platform based on a cloud platform according to claim 3, characterized in that: The resource scheduling instruction generating unit includes: Current time acquisition subunit: used to call the system server time interface to obtain the system timestamp corresponding to the current scheduling time in real time ; Committed time calculation subunit: based on current system time The shortest path predicted travel time to the target service provider , calculate the service provider's estimated promised arrival time ; Instruction encapsulation subunit: used to perform structured encapsulation of the target service provider's service provider identification information and the corresponding promised arrival time to generate resource scheduling instructions.

5. The one-stop maintenance service management platform based on a cloud platform according to claim 1, characterized in that: The maintenance process collaboration module includes a work order triggering unit, a positioning data acquisition unit, an arrival determination unit, a start time recording unit, and a time parameter generation unit; wherein: Work order triggering unit: used to receive the service provider ID in the resource scheduling instruction and generate a corresponding maintenance task work order in the platform task management system. The task work order contains the service provider ID, user location, equipment type parameters and promised arrival time; Positioning data collection unit: After the service provider receives the task work order, it calls the GPS module in the service provider's mobile terminal to collect its current location coordinate information in real time, and uploads the positioning data to the platform at fixed time intervals to record it as the service provider's travel trajectory data; Arrival determination unit: used to compare the distance between the service provider's real-time coordinates and the user's location coordinates. If the spatial distance between the current location and the user's location is less than the set arrival determination threshold, the timestamp of the first time the condition is met will be recorded as the actual arrival time. ; Start time recording unit: used to record the maintenance operation start timestamp when the maintenance task start button is operated in the service provider terminal , and upload it to the platform system as the official time mark for the start of maintenance operations; Time parameter generation unit: used to generate the actual arrival time The promised arrival time recorded in the resource scheduling instruction Perform difference calculation to obtain aging verification parameters .

6. The one-stop maintenance service management platform based on a cloud platform according to claim 1, characterized in that: The data tracing and analysis module includes a time anomaly detection unit, an anomaly mark generation unit, a parts record association unit, and a compliance statistics unit; wherein: Time anomaly detection unit: used to receive the actual arrival time difference generated by the maintenance process collaboration module , and call the maintenance time parameter threshold ;when Greater than When the time limit is exceeded, Abnormal tag generation unit: used to write a service response abnormal tag to the corresponding task work order after the detection result meets the time limit condition, and establish an abnormal index field in the platform quality monitoring database; Parts record association unit: used to search the platform parts replacement database based on the equipment type parameter, call the maintenance record entries that match the equipment type parameter, extract the parts number and parts source attributes in each record, and write the record into the parts statistics cache table; Compliance statistics unit: used to traverse the accessories statistics cache table, accumulate the usage times of original accessories and non-original accessories respectively, calculate the usage ratio of non-original accessories, and convert the usage ratio into accessories compliance parameters.

7. The one-stop maintenance service management platform based on a cloud platform according to claim 6, characterized in that: The compliance statistics unit includes: Accessory source counting subunit: used to traverse all maintenance record entries in the accessory statistics cache table, read and classify the accessory source attribute field of each record, and if it is marked as original, it will be accumulated to the original accessory usage count If it is marked as non-original, it will be accumulated to the non-original accessories usage count ; Usage ratio calculation subunit: used to calculate the usage ratio of non-original accessories after completing all record traversal , and its calculation formula is: ,in, The proportion of non-original accessories used; Compliance parameter generation subunit: used to generate the compliance parameter based on the proportion of non-original accessories used. Comply with the upper limit of the compliance ratio preset by the platform Make a judgment, if , then generate accessory compliance parameters , indicating compliance; otherwise, , indicating non-compliance.

8. The one-stop maintenance service management platform based on a cloud platform according to claim 5, characterized in that: The service report generation module includes a data aggregation unit, a performance rating calculation unit, a compliance warning generation unit, and a report construction unit; wherein: Data aggregation unit: used to synchronously receive structured parameter information from the user demand analysis module, maintenance process collaboration module and data traceability analysis module, including equipment type parameters, maintenance time parameters, time verification parameters and accessory compliance parameters ; Performance rating calculation unit: used to verify parameters based on timeliness , generate the service provider performance rating; when When When When and The rating level boundary value preset by the system; Compliance alert generation unit: used to read accessory compliance parameters ,like , then add a non-compliant accessories warning label to the current work order and mark the relevant responsible parties in the report; if , it is marked as accessory compliance status; Report construction unit: used to integrate various parameters to generate a comprehensive service report, which includes the work order number, service provider ID, equipment model, equipment category, response time level, performance rating label and accessory compliance status label.

Images