Cross-regional auto repair resource collaborative management and sharing system based on cloud computing

Through a cross-regional automotive repair resource collaborative management system based on cloud computing, the task and technical technical feature information are analyzed and the selection of technicians is optimized, and the problems of uneven resource distribution and difficulty in information sharing in automotive repair resource management are solved, and maintenance efficiency and quality are improved.

CN118569613BActive Publication Date: 2024-11-08BEIJING CRRC HIGH-TECH CO LTD
View PDF 5 Cites 0 Cited by

Patent Information

Application Number
CN202411053608.0
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-08-02
Publication Date
2024-11-08
Estimated Expiration
2044-08-02

AI Technical Summary

Technical Problem

In the management of auto repair resource, there are uneven resource distribution among regions, difficult information to share, and low matching of technical skills and tasks, resulting in low maintenance efficiency and quality and insufficient resource utilization efficiency.

Method used

Adopt a cross-regional auto repair resource collaborative management and sharing system based on cloud computing. By deeply analyzing task feature information and technical feature information, a cross-regional cloud platform is built to realize task skill level and complex level analysis, optimize technician selection, and realize real-time resource resource Share and optimize configuration.

Benefits of technology

It improves the efficiency of auto repair resources, improves maintenance efficiency and quality, ensures the best matching between technicians and tasks, and optimizes resource allocation.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118569613B_ABST
    Figure CN118569613B_ABST
Patent Text Reader

Abstract

The present invention discloses a cross-regional auto repair resource collaborative management and sharing system based on cloud computing, which relates to the field of auto repair data processing technology. The system includes: performing task skill level analysis and task complexity level analysis to obtain local task skill level and local task complexity level; calculating and obtaining task skill level and task complexity level; retrieving technician feature information; performing technician selection optimization to obtain an optimized technician group; performing technician selection to obtain the best technician, and dispatching the best technician to the local area to process auto repair tasks. The system solves the technical problems of uneven distribution of auto repair resources between regions, difficulty in sharing auto repair information, low matching between technician skills and maintenance tasks, which in turn lead to low maintenance efficiency and quality, and insufficient resource utilization efficiency. The system realizes real-time sharing and optimal configuration of cross-regional auto repair resources, and achieves the technical effect of improving the utilization efficiency of auto repair resources and improving maintenance efficiency and quality.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the technical field related to auto repair data processing, and specifically to a cross-regional auto repair resource collaborative management and sharing system based on cloud computing. Background Art

[0002] With the rapid development of the automobile industry, the automobile maintenance industry is facing unprecedented challenges and opportunities. With the increasing maturity of technologies such as cloud computing, big data, and the Internet of Things, their applications in various industries are constantly deepening, providing strong technical support for the digital transformation of the auto repair industry. Cloud computing, with its powerful data processing capabilities, flexible resource scheduling mechanism and high scalability, has become a key technology for achieving efficient coordination of cross-regional auto repair resources. However, under the traditional auto repair management model, auto repair resources are unevenly distributed among regions, and information islands are serious. The types, difficulties and required skills of maintenance tasks faced by each region are different. Highly skilled technicians often find it difficult to quickly match the most needed maintenance tasks, while low-skilled or idle technicians may miss growth opportunities due to lack of effective guidance, resulting in high-skilled technicians finding it difficult to quickly respond to cross-regional maintenance needs, uneven maintenance efficiency and quality, and difficulty in improving customer satisfaction.

[0003] Therefore, in the current technologies related to auto repair resource management, there are technical problems such as uneven distribution of auto repair resources among regions, difficulty in sharing auto repair information, and low matching between technicians' skills and maintenance tasks, which in turn lead to low maintenance efficiency and quality, and insufficient resource utilization efficiency. Summary of the invention

[0004] This application provides a cross-regional auto repair resource collaborative management and sharing system based on cloud computing, adopts technical means such as in-depth analysis of task feature information and technician feature information, standardized processing of historical maintenance data, and construction of a cross-regional auto repair cloud platform, to solve the technical problems existing in the existing auto repair resource management, such as uneven distribution of auto repair resources between regions, difficulty in sharing auto repair information, low matching between technician skills and maintenance tasks, which in turn lead to low maintenance efficiency and quality, and insufficient resource utilization efficiency. It realizes real-time sharing and optimal allocation of cross-regional auto repair resources, and achieves the technical effect of improving the utilization efficiency of auto repair resources and improving maintenance efficiency and quality.

[0005] The present application provides a cross-regional auto repair resource collaborative management and sharing system based on cloud computing, the system comprising: a local task level acquisition module, the local task level acquisition module is used to collect task feature information of auto repair tasks to be processed in the local area, and perform auto repair task retrieval in the local auto repair database based on the task feature information to obtain the task occurrence rate, and perform task skill level analysis and task complexity level analysis to obtain the local task skill level and the local task complexity level; a task level calculation acquisition module, the task level calculation acquisition module is used to upload the task feature information to the cross-regional auto repair cloud platform, and based on cloud computing, perform integrated auxiliary task skill level analysis and task complexity level analysis based on the task occurrence rate to obtain the cloud task skill level and the cloud local task complexity level, and calculate the task skill level and the task complexity level based on the task occurrence rate. a module for retrieving characteristic information of a plurality of idle technicians based on the auto repair cloud platform, wherein each technician characteristic information includes a skill certification level and a skill practice level; a module for obtaining an optimized technician group, wherein the module for obtaining an optimized technician group is used to optimize the selection of technicians according to a plurality of skill certification levels and skill practice levels and historical auto repair data of a plurality of idle technicians, in combination with the task skill level and task complexity level, to obtain an optimized technician group; a module for obtaining a processing standardization parameter, wherein the module for obtaining a processing standardization parameter is used to perform a processing standardization analysis according to the historical auto repair data of a plurality of optimized technicians, to obtain a plurality of processing standardization parameters, to select technicians within the optimized technician group, to obtain the optimal technician, and to dispatch the optimal technician to the local area to process the auto repair task.

[0006] In a possible implementation, the local task level acquisition module also performs the following processing: in the local area, task feature information of the auto repair task to be processed is collected; based on the task feature information, task retrieval is performed in the local auto repair database to obtain the task occurrence rate of the auto repair task, wherein the local auto repair database is constructed by historical auto repair data records of the local area; based on the local auto repair database, a sample task feature information set is collected, and based on the task skill level and processing complexity of the sample task, a sample task skill level set and a sample task complexity level set are identified and obtained; using the sample task feature information set, the sample task skill level set and the sample task complexity level set, a local skill level analysis path and a local complexity analysis path are trained, and the task feature information is input analyzed to obtain the local task skill level and the local task complexity level.

[0007] In a possible implementation, the task level calculation module also performs the following processing: based on cloud computing, constructing a cloud skill level analysis path and a cloud complexity analysis path in the auto repair cloud platform, wherein the cloud skill level analysis path and the cloud complexity analysis path include multiple cloud skill level analysis branches and multiple cloud complexity analysis branches; uploading the task feature information to the cross-regional auto repair cloud platform, calculating the integrated auxiliary ratio according to the task occurrence rate and the average occurrence rate, and calculating the basic auxiliary quantity in combination with the number of the multiple cloud skill level analysis branches and the cloud complexity analysis branches; inputting the task feature information into the cloud skill level analysis branch and the cloud complexity analysis branch of the basic auxiliary quantity, performing integrated auxiliary analysis, obtaining an auxiliary task skill level set and an auxiliary task complexity level set, and obtaining the cloud task skill level and the cloud local task complexity level by majority screening; setting the local weight and the cloud weight according to the integrated auxiliary ratio, performing weighted calculation on the cloud task skill level, the cloud local task complexity level, the local task skill level and the local task complexity level, and obtaining the task skill level and the task complexity level.

[0008] In a possible implementation, the task level calculation module also performs the following processing: based on cloud computing, a cross-regional cloud sample task feature information set is collected through the auto repair cloud platform as input, and a cross-regional cloud sample task skill level set and a cloud sample task complexity level set are collected as output to obtain cloud skill level analysis training data and cloud complexity analysis training data; randomly select part of the training data in the cloud skill level analysis training data for multiple times, train multiple cloud skill level analysis branches respectively, and integrate to obtain a cloud skill level analysis path; randomly select part of the training data in the cloud complexity analysis training data, train multiple cloud complexity analysis branches respectively, and integrate to obtain a cloud complexity analysis path.

[0009] In a possible implementation, the technician characteristic information retrieval module also performs the following processing: based on the auto repair cloud platform, collect and retrieve multiple skill certification levels of multiple idle technicians across the region; collect auto repair data of the multiple idle technicians within a recent preset time range, and analyze to obtain multiple skill practical levels.

[0010] In a possible implementation, the optimized technician group acquisition module further performs the following processing: collecting historical auto repair data of the plurality of idle technicians, matching similar historical auto repair data based on the task feature information, and obtaining multiple similar processing rates; constructing an auto repair optimization function optimized within the plurality of idle technicians, as shown in the following formula:

[0011] ,

[0012] Among them, ARO is the auto repair adaptability, , and is the weight, and The task skill level and task complexity level of the auto repair task, and are the skill certification level and skill practice level of the idle technicians, and K is the same type processing rate; according to the auto repair optimization function, technician selection optimization is performed on the multiple idle technicians to obtain an optimized technician group.

[0013] In a possible implementation, the optimized technician group acquisition module also performs the following processing: randomly select N idle technicians from the multiple idle technicians to obtain an initial technician group, and calculate N auto repair fitnesses according to the auto repair optimization function, where N is an integer greater than 1; delete the idle technician with the smallest auto repair fitness, and reselect idle technicians to join the initial technician group, calculate the auto repair fitness, and delete the idle technician with the smallest auto repair fitness; continue to select and optimize until all idle technicians are traversed, and output the final optimized technician group.

[0014] In a possible implementation, the processing standardization parameter acquisition module also performs the following processing: extracting multiple historical service process data sets based on the historical auto repair data of the multiple optimized technicians; performing standardized analysis based on the deviations between the multiple historical service process data sets and the standard service process data to obtain multiple processing standardization parameters; performing calculations based on the multiple similar processing rates in combination with the multiple processing standardization parameters to obtain multiple standardized scores; and selecting the technician with the largest standardized score within the group of optimized technicians to obtain the best technician.

[0015] Through the cross-regional auto repair resource collaborative management and sharing system based on cloud computing proposed in this application, it is planned to conduct task skill level analysis and task complexity level analysis, obtain local task skill level and local task complexity level; calculate and obtain task skill level and task complexity level; retrieve technician feature information; optimize technician selection and obtain optimized technician group; select technicians to obtain the best technician, and dispatch the best technician to the local area to handle auto repair tasks. It solves the technical problems existing in the existing auto repair resource management, such as uneven distribution of auto repair resources between regions, difficulty in sharing auto repair information, low matching between technician skills and maintenance tasks, which in turn leads to low maintenance efficiency and quality, and insufficient resource utilization efficiency, realizes real-time sharing and optimal configuration of cross-regional auto repair resources, and achieves the technical effect of improving the utilization efficiency of auto repair resources and improving maintenance efficiency and quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solution of the embodiment of the present disclosure, the accompanying drawings of the embodiment of the present disclosure will be briefly introduced below. A flow chart is used in the present application to illustrate the operations performed by the system according to the embodiment of the present application. It should be understood that the preceding or following operations are not necessarily performed precisely in order. On the contrary, various steps can be processed in reverse order or simultaneously as needed. At the same time, other operations can also be added to these processes, or one or more operations can be removed from these processes.

[0017] Figure 1 A schematic diagram of the structure of a cross-regional auto repair resource collaborative management and sharing system based on cloud computing provided in an embodiment of the present application;

[0018] Figure 2 A schematic diagram of the execution process of the task level calculation module in the cross-regional auto repair resource collaborative management and sharing system based on cloud computing provided in an embodiment of the present application.

[0019] Explanation of the reference numerals: local task level acquisition module 10, task level calculation acquisition module 20, technician characteristic information retrieval module 30, optimized technician group acquisition module 40, processing standardization parameter acquisition module 50. DETAILED DESCRIPTION

[0020] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below.

[0021] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of this application.

[0022] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments, but it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict, and the terms "first\second" involved are merely to distinguish similar objects and do not represent a specific ordering of objects. The terms "including" and "having" and any variations are intended to cover non-exclusive inclusions, for example, a process, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, products, or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those generally understood by technicians in the technical field of this application. The terms used herein are for the purpose of describing the embodiments of the present application only.

[0023] The embodiment of the present application provides a cross-regional auto repair resource collaborative management and sharing system based on cloud computing, such as Figure 1 As shown, the system comprises:

[0024] The local task level acquisition module 10 is used to collect task feature information of the auto repair task to be processed in the local area, and perform auto repair task retrieval in the local auto repair database according to the task feature information, obtain the task occurrence rate, and perform task skill level analysis and task complexity level analysis to obtain the local task skill level and local task complexity level. The local area (local emphasizes the difference from the cloud) refers to the area where the auto repair task currently appears, retrieves the occurrence rate of similar tasks of the task (the same task or similar tasks, such as the same problem of different brands of cars) in the local historical data, and performs task skill level analysis and task complexity level analysis. Specifically, the task feature information refers to the specific data content that describes the auto repair task to be processed, including but not limited to vehicle information (such as vehicle model, brand, engine model, etc.), fault description (specific faults of the vehicle, such as abnormal engine noise, shell scratches, brake failure, electrical system failure, etc.), maintenance requirements (customer's specific maintenance requirements, such as replacement of parts, repair functions, etc.). After obtaining the task feature information, this information is used as the retrieval information. Conditions are input into the local auto repair database for auto repair task retrieval, and historical maintenance records similar to the current task are quickly located, wherein the local auto repair database is a database in the current area that stores a large amount of historical maintenance records, fault cases, solutions and other information, including detailed records of various vehicle models and various fault phenomena, as well as corresponding processing methods and results; the task occurrence rate refers to the frequency with which auto repair tasks of a certain type or a certain fault phenomenon appear in the database, and the number of historical maintenance records similar to the current task is obtained by retrieval, and then divided by the total number of tasks in the local auto repair database, to calculate the occurrence rate of the current auto repair task type in the local auto repair database, wherein the total number of tasks is the number of all maintenance records stored in the local auto repair database. Then, task skill level analysis and task complexity level analysis are carried out. Task skill level analysis refers to the division of task skill levels according to the nature of the task (such as fault diagnosis, parts replacement, electrical system debugging, etc.), difficulty, and required professional knowledge and skills (such as theoretical knowledge, practical experience, tool use ability, etc.), for example, into primary tasks, intermediate tasks, advanced tasks, etc.; task complexity level analysis refers to the assessment of the complexity of the task itself to determine the difficulty of task processing and the required resources, which may include assessment of task scale (such as the number of parts involved, system complexity, etc.), technical difficulty (i.e. the technical level required to handle auto repair tasks and the complexity of solutions), time constraints (tight time constraints may increase the complexity level of tasks), variability (considering uncertain factors in the task processing process, such as fault diversity, parts availability, etc.), for example, dividing into simple tasks, ordinary tasks, difficult tasks, etc.; finally, the local task skill level and local task complexity level are obtained.

[0025] The task level calculation module 20 is used to upload the task feature information to the cross-regional auto repair cloud platform, and based on cloud computing, perform integrated auxiliary task skill level analysis and task complexity level analysis according to the task occurrence rate, obtain the cloud task skill level and cloud local task complexity level, and calculate and obtain the task skill level and task complexity level according to the task occurrence rate. Local auto repair task data takes precedence over other regions, so the task feature information is uploaded to the cross-regional cloud platform (including auto repair data of multiple regions within the local area), and the number of branches for integrated auxiliary analysis is set according to the task occurrence rate combined with integrated learning, and then the cloud task skill level and cloud local task complexity level are obtained by analysis. Specifically, the cross-regional auto repair cloud platform is an integrated information system that breaks geographical restrictions and realizes the optimal configuration and efficient use of auto repair resources. Through this platform, auto repair companies can obtain maintenance cases, technical data, accessories information and other resources from different regions, thereby improving their own maintenance capabilities and service quality. After the task feature information is uploaded, the cloud platform uses cloud computing technology to provide powerful computing and storage capabilities. In this paper, the cloud platform is used to analyze the skill level of integrated auxiliary tasks and the complexity level of tasks, that is, according to the task feature information and the knowledge base in the cloud platform, the task is divided into skill levels to evaluate the professional skill level required to complete a specific maintenance task; based on the task feature information, such as the diversity of fault phenomena, the cumbersomeness of maintenance steps, the particularity of the required tools, etc., the task is divided into complexity levels to evaluate the complexity of the maintenance task in order to reasonably allocate resources and time; then the cloud task skill level and the cloud local task complexity level are obtained; finally, based on the task occurrence rate, the results of the cloud and local analysis (cloud task skill level and cloud local task complexity level as well as local task skill level and local task complexity level) are weighted and calculated to obtain the task skill level and task complexity level.

[0026] The mechanic characteristic information retrieval module 30 is used to retrieve the mechanic characteristic information of multiple idle mechanics based on the auto repair cloud platform, wherein each mechanic characteristic information includes a skill certification level and a skill practical level. When the mechanic characteristic information of multiple idle mechanics is retrieved based on the auto repair cloud platform, it refers to screening and matching according to preset query conditions (such as skill certification level, skill practical level, type of work, work experience, etc.), quickly finding mechanics who meet the requirements, and viewing their detailed characteristic information. The characteristic information of each technician usually includes a skill certification level and a skill practical level. These two levels are important criteria for evaluating the professional skills and actual operational capabilities of technicians. Specifically, the skill certification level refers to the skill level certificate obtained by the technician by participating in official or industry-recognized examinations, assessments or training, which is used to prove the technician's skill level and qualifications in a certain field or position. The skill certification level It may include multiple levels, such as junior workers, intermediate workers, senior workers, technicians, senior technicians, etc. Different levels of certification require different theoretical knowledge and practical skill levels. Only by passing relevant assessments can the corresponding certification level be obtained; the practical skill level refers to the skill level and proficiency demonstrated by technicians in actual operations. It is usually evaluated through on-site operations, simulated operations, etc. to measure the technicians' ability to apply skills in actual work. The practical skill level may include multiple aspects, such as operating speed, operating accuracy, troubleshooting ability, problem-solving ability, etc. Technicians demonstrate their skill level and proficiency in actual operations to obtain the corresponding practical level evaluation.

[0027] The module 40 for obtaining an optimized group of technicians is used to optimize the selection of technicians and obtain an optimized group of technicians based on multiple skill certification levels and skill practice levels and historical auto repair data of multiple idle technicians, combined with the task skill level and task complexity level. Historical auto repair data refers to the historical auto repair records of each idle technician, including information on efficiency, quality, troubleshooting ability, customer satisfaction, etc. in completing auto repair tasks, in order to evaluate the actual work performance of the technicians, match the skill certification level, skill practice level, and historical auto repair data of the idle technicians with the skill level and complexity level of the task, and look for technicians who can meet the task requirements in terms of skill level and actual operational ability. Specifically, on the basis of matching technicians with tasks, further comprehensive evaluations are conducted on qualified technicians, including evaluations of the technicians' experience, skill proficiency, work attitude, and teamwork ability. In terms of aspects, optimization algorithms (such as multi-objective optimization, genetic algorithms, etc.) are introduced to assist the selection process, that is, according to the set goals (such as maximizing task completion efficiency, minimizing costs, etc.) and constraints (such as the availability and skill level of technicians), while considering other factors that may affect task completion, such as the technician's geographical location (for quick response) and workload (to avoid excessive fatigue), the optimal technician is automatically calculated, and finally the optimized technician group is determined. The optimized technicians in this group can meet the task requirements in terms of skill level, actual operation ability, work experience, etc., and can complete the task in an efficient and collaborative manner.

[0028] A processing standardization parameter acquisition module 50 is used to perform processing standardization analysis based on the historical auto repair data of multiple optimized technicians, obtain multiple processing standardization parameters, select technicians within the group of optimized technicians, obtain the best technician, and dispatch the best technician to the local area to process the auto repair task. The historical auto repair data of multiple optimized technicians are collected from the auto repair cloud platform. These historical auto repair data contain information on multiple dimensions such as the efficiency, quality, troubleshooting ability, and customer satisfaction of the technicians in completing tasks. The collected data are cleaned to remove duplicate, erroneous or inconsistent data to ensure the accuracy and completeness of the data. Then, appropriate data standardization methods (such as Z-Score standardization, maximum and minimum value standardization, normalization, etc.) are used to process the cleaned data to eliminate the dimensional differences between the data, so that the performance of different technicians on the same indicator is comparable. Through standardization processing, multiple processing standardization parameters can be obtained. These parameters reflect the performance level of the technicians in different dimensions; selecting technicians within the group of optimized technicians specifically refers to selecting technicians based on the specific requirements and optimization of the task. Optimization goals (such as maximizing task completion efficiency, minimizing costs, etc.), comprehensively considering multiple factors such as the technician's skill level, work efficiency, customer satisfaction, etc., establish a suitable technician selection model, input the standardized data into the selection model, and conduct a comprehensive evaluation of each technician in the optimized technician group. The evaluation results will reflect the overall ability and advantages of each technician in completing the task. According to the comprehensive evaluation results, the best technician is determined. The best technician should be the technician who performs best or closest to the task requirements in multiple dimensions. Then, considering the technician's geographical location, workload, time schedule and other factors, the determined best technician will be dispatched to the local area, and specific auto repair tasks will be assigned to ensure that the tasks can be completed on time and with quality. After receiving the task, the best technician will handle the auto repair task as required.

[0029] The cross-regional auto repair resource collaborative management and sharing system based on cloud computing according to the embodiment of the present invention is used to solve the technical problems existing in the existing auto repair resource management, such as uneven distribution of auto repair resources between regions, difficulty in sharing auto repair information, low matching between technician skills and maintenance tasks, which in turn leads to low maintenance efficiency and quality, and insufficient resource utilization efficiency, and realizes real-time sharing and optimal configuration of cross-regional auto repair resources, achieving the technical effect of improving the utilization efficiency of auto repair resources and improving maintenance efficiency and quality. The cross-regional auto repair resource collaborative management and sharing system based on cloud computing includes: a local task level acquisition module 10, a task level calculation acquisition module 20, a technician feature information retrieval module 30, an optimized technician group acquisition module 40, and a processing standardized parameter acquisition module 50.

[0030] The specific configuration of the local task level acquisition module 10 will be described in detail below. The local task level acquisition module 10 may further include: collecting task feature information of the auto repair task to be processed in the local area. Collecting specific information of the auto repair task that needs to be processed, including but not limited to the task type and specific content of the task, such as vehicle model, fault type, degree of damage, parts to be replaced, etc.

[0031] The local task level acquisition module 10 further includes, according to the task feature information, performing task retrieval in the local auto repair database to obtain the task occurrence rate of the auto repair task, wherein the local auto repair database is constructed by the historical auto repair data records of the local area. According to the task feature information as a retrieval condition, historical records matching or similar to it are retrieved in the local auto repair database, and these records are statistically analyzed to obtain the task occurrence rate, that is, the frequency of occurrence of this type of task in the historical data, wherein the local auto repair database is constructed by the historical auto repair data records of the local area, including detailed information of various auto repair tasks previously processed.

[0032] The local task level acquisition module 10 also includes, according to the local auto repair database, collecting a sample task feature information set, and identifying and obtaining a sample task skill level set and a sample task complexity level set according to the task skill level and processing complexity of the sample task. The sample task feature information set refers to a set of representative tasks selected from the local auto repair database, and the feature information of these tasks is collected, covering auto repair tasks of different types and different difficulty levels. According to the task skill level of the sample task, each sample task is identified to obtain a sample task skill level set. Similarly, according to the processing complexity of the sample task, each sample task is identified to obtain a sample task complexity level set.

[0033] The local task level acquisition module 10 also includes: using the sample task feature information set, the sample task skill level set and the sample task complexity level set to train the local skill level analysis path and the local complexity analysis path, and performing input analysis on the task feature information to obtain the local task skill level and the local task complexity level. The sample task feature information set, the sample task skill level set and the sample task complexity level set are used to train the local skill level analysis path and the local complexity analysis path, and then the new task feature information is input analyzed to obtain the local task skill level and the local task complexity level. Specifically, each sample in the sample task feature information set is converted into a feature vector, and these feature vectors are used as inputs of the training model. The sample task skill level and the complexity level will be used as the target output of the training model. Specifically, an analysis model is constructed based on machine learning (such as decision trees, neural networks, gradient boosting machines, etc.), and the analysis model is trained using sample data (feature vectors and target outputs). During the training process, the model learns the mapping relationship from feature vectors to skill level and complexity level labels. After the training is completed, the local skill level analysis path and the local complexity analysis path are obtained to predict the skill level and complexity level of the new auto repair task. Input analysis of task feature information refers to obtaining the task feature information of a new auto repair task and converting it into a feature vector, and then inputting the feature vector of the new task into the local skill level analysis path and the local complexity analysis path respectively. The analysis path will output the prediction results, namely the local task skill level and the local task complexity level.

[0034] The specific configuration of the task level calculation module 20 will be described in detail below. Figure 2 As shown, the task level calculation acquisition module 20 further includes: based on cloud computing, constructing a cloud skill level analysis path and a cloud complexity analysis path in the auto repair cloud platform, wherein the cloud skill level analysis path and the cloud complexity analysis path include multiple cloud skill level analysis branches and multiple cloud complexity analysis branches. In the auto repair cloud platform, according to the different characteristics of the auto repair tasks, a cloud skill level analysis path is constructed, including multiple cloud skill level analysis branches, each branch performs a special skill level analysis for a specific vehicle model, fault type or skill field; similarly, a cloud complexity analysis path is constructed, including multiple cloud complexity analysis branches, which are used to evaluate the complexity of different auto repair tasks, and these branches may consider multiple aspects of the task, such as the number of steps required, the diversity of required parts, technical difficulty, etc.

[0035] The task level calculation module 20 also includes uploading the task feature information to the cross-regional auto repair cloud platform, calculating the integrated assistance ratio according to the task occurrence rate and the average occurrence rate, and calculating the basic assistance quantity in combination with the number of the multiple cloud skill level analysis branches and the cloud complexity analysis branches. The new auto repair task feature information is uploaded to the cross-regional auto repair cloud platform, and the integrated assistance ratio is calculated according to the occurrence rate of the task on the cloud platform (i.e., the frequency of the task being requested for analysis) and the average occurrence rate (the average frequency of all tasks being requested for analysis), which reflects the necessity of the cloud platform to perform integrated auxiliary analysis on the task. For example, if the task occurrence rate is 4% and the average occurrence rate of each type of task is 5%, the integrated assistance ratio is (5-1) / 5=20%, and 20% of the branches are selected for auxiliary analysis. The more the task occurrence rate, the more auto repair data of the same type of task in the local area, the more accurate the analysis, and the smaller the proportion of cloud platform auxiliary analysis required. Finally, the basic assistance quantity is calculated in combination with the number of multiple cloud skill level analysis branches and cloud complexity analysis branches.

[0036] The task level calculation and acquisition module 20 also includes inputting the task feature information into the cloud skill level analysis branch and cloud complexity analysis branch of the basic auxiliary quantity, performing integrated auxiliary analysis, obtaining an auxiliary task skill level set and an auxiliary task complexity level set, and obtaining the cloud task skill level and cloud local task complexity level by majority screening. The task feature information is input into the cloud skill level analysis branch and cloud complexity analysis branch of the basic auxiliary quantity. Each branch analyzes the task feature information according to its own algorithm and model, and outputs its own auxiliary task skill level and auxiliary task complexity level. The cloud task skill level and cloud local task complexity level are screened out from multiple auxiliary results through the majority screening method. Among them, majority screening is a commonly used method for aggregating multiple decision or prediction results. In the cloud skill level analysis path and cloud complexity analysis path in the auto repair cloud platform, majority screening is used to determine the final cloud task skill level and cloud local task complexity level from the output results of multiple cloud analysis branches. Specifically, these prediction results are statistically voted to find the skill level and complexity level that receive the most votes. This level is the result of majority screening, that is, it is considered to be the final cloud task skill level and cloud local task complexity level. If multiple levels receive the same number of highest votes (that is, a tie), a level is randomly selected.

[0037] The task level calculation module 20 also includes setting local weights and cloud weights according to the integrated auxiliary ratio, performing weighted calculations on the cloud task skill level, cloud local task complexity level, local task skill level, and local task complexity level to obtain the task skill level and task complexity level. According to the integrated auxiliary ratio, the local weight and cloud weight are set. For example, the integrated auxiliary ratio is the cloud weight, and 1-cloud weight is the local weight, which reflects the relative importance of local analysis and cloud analysis in the final level determination. The cloud task skill level, cloud local task complexity level, local task skill level, and local task complexity level are weightedly calculated. Specifically, each level is multiplied by the corresponding weight, and then all weighted levels are added together to obtain the final task skill level and task complexity level.

[0038] The specific configuration of the task level calculation module 20 will be described in detail below. The task level calculation module 20 further includes: based on cloud computing, collecting a cross-regional cloud sample task feature information set as input through the auto repair cloud platform, collecting a cross-regional cloud sample task skill level set and a cloud sample task complexity level set as output, and obtaining cloud skill level analysis training data and cloud complexity analysis training data. Based on cloud computing, cross-regional cloud data is collected through the auto repair cloud platform, wherein the cross-regional cloud sample task feature information set is a set as input data, which contains auto repair task feature information from different regions, which may include but is not limited to the vehicle model, fault type, fault description, maintenance history, etc. of the historical auto repair tasks recorded by the cloud platform; the cross-regional cloud sample task skill level set and the cloud sample task complexity level set are sets as output data, which respectively record the skill level and complexity level corresponding to the feature information of the corresponding task; using the collected data, respectively construct cloud skill level analysis training data and cloud complexity analysis training data, which are used to train the analysis model and learn how to map the task feature information to the corresponding skill level and complexity level.

[0039] The task level calculation acquisition module 20 also includes randomly selecting part of the training data in the cloud skill level analysis training data multiple times, training multiple cloud skill level analysis branches respectively, and integrating to obtain a cloud skill level analysis path. In the cloud skill level analysis training data, multiple cloud skill level analysis branches are trained separately by randomly selecting part of the training data multiple times (for example, using cross-validation or bootstrap sampling techniques, etc.), wherein each branch is constructed based on a machine learning model (such as a decision tree, random forest, neural network, etc.), trained using different subsets of training data, and learning the mapping relationship between task feature information and skill level from the data; the trained multiple cloud skill level analysis branches are integrated to form a complete analysis path, for example, using weighted average, and finally integrated to obtain a cloud skill level analysis path.

[0040] The task level calculation module 20 also includes randomly selecting part of the training data in the cloud complexity analysis training data, training multiple cloud complexity analysis branches respectively, and integrating to obtain a cloud complexity analysis path. Similar to the cloud skill level analysis branch, the operation of randomly selecting part of the training data is also performed multiple times in the cloud complexity analysis training data, and multiple cloud complexity analysis branches are trained respectively to learn how to map task feature information to complexity levels; the trained multiple cloud complexity analysis branches are integrated to form a cloud complexity analysis path.

[0041] The specific configuration of the mechanic characteristic information retrieval module 30 will be described in detail below. The mechanic characteristic information retrieval module 30 further includes: based on the auto repair cloud platform, collecting and retrieving multiple skill certification levels of multiple idle mechanics across regions. Based on the cross-regional coverage of the auto repair cloud platform, the skill certification level information of multiple idle mechanics from different regions is collected through a data interface, database query or integration with other systems.

[0042] The mechanic characteristic information retrieval module 30 also includes collecting the auto repair data of the plurality of idle mechanics within a recent preset time range, and analyzing to obtain a plurality of skill practice levels. The preset time range is a specific time period used to limit the scope of data collection. It can be set according to actual needs, such as the last month, three months or six months. Auto repair data is collected through multiple channels such as technicians' work records, system logs, customer feedback, etc. The auto repair data records detailed information such as auto repair tasks completed by multiple technicians within the preset time range, tools used, maintenance processes, fault resolution, etc., and multiple skill practice levels are obtained through analysis. Specifically, features related to skill practice levels are extracted from the auto repair data, such as task completion time, fault resolution rate, maintenance quality score, type and quantity of tools used, special skill usage, etc. An analysis model of the relationship between technician features and their skill practice levels is established based on support vector machines or neural networks. The auto repair data is divided into a training set and a test set, and then the training set is used to train the model, and the model parameters are tuned through methods such as cross-validation, and the test set is used for evaluation. The skill practice level prediction model is trained and applied to new auto repair data to predict the skill practice level of idle technicians.

[0043] The specific configuration of the optimized technician group acquisition module 40 will be described in detail below. The optimized technician group acquisition module 40 further includes: collecting the historical auto repair data of the plurality of idle technicians, matching the same historical auto repair data based on the task feature information, and obtaining a plurality of same processing rates. The historical auto repair data of the plurality of idle technicians are collected from the auto repair cloud platform, and the key task feature information is extracted from each historical auto repair task record to distinguish different task types, difficulty and complexity, etc. Based on the extracted task feature information, the new auto repair task is matched with the historical auto repair data of the idle technician, and the similarity between the feature information is calculated, that is, various similarity measurement methods are used, such as cosine similarity, Euclidean distance, etc., to find the historical task records that are similar or identical to the new task in feature information. For each idle technician, the proportion of historical tasks that are successfully processed in the history with similar features to the new task is counted, that is, the same processing rate, which reflects the success rate and experience level of the technician in processing similar tasks. Specifically, the number of similar historical tasks successfully processed by the technician is divided by the total number of similar historical tasks, and the result obtained is the same processing rate.

[0044] The auto repair optimization function constructed to optimize within the plurality of idle technicians is as follows:

[0045] ,

[0046] Among them, ARO is the auto repair adaptability, , and is the weight, and The task skill level and task complexity level of the auto repair task, and is the skill certification level and skill practice level of the idle technician, and K is the similar processing rate. Specifically, the auto repair optimization function is used to reduce the deviation between the task skill level and the skill certification level, increase the margin by which the skill practice level is greater than the task complexity level, and increase the similar processing rate.

[0047] The optimized technician group acquisition module 40 also includes, according to the auto repair optimization function, performing technician selection optimization among the plurality of idle technicians to obtain an optimized technician group. Performing technician selection optimization among the plurality of idle technicians specifically refers to using the auto repair optimization function to select technicians who handle more similar tasks, have strong practical skills, and have similar skill certification levels (i.e., do not blindly call the person with the highest skill certification level), thereby improving the quality of auto repair processing and avoiding waste of auto repair human resources.

[0048] Next, the specific configuration of the module 40 for obtaining the optimized technician group will be described in detail. The module 40 for obtaining the optimized technician group further includes: randomly selecting N idle technicians from the plurality of idle technicians to obtain an initial technician group, and calculating and obtaining N auto repair fitnesses according to the auto repair optimization function, where N is an integer greater than 1. Randomly select N idle technicians from all idle technicians to form an initial technician group, where N is a pre-set integer greater than 1, representing the number of technicians in the initial group, and use the auto repair optimization function to calculate the fitness of each technician in the initial technician group for the current auto repair task according to factors such as each technician's skill level, historical performance, and task matching, and obtain N auto repair fitnesses. The higher the fitness, the more suitable the technician is for performing the current task.

[0049] The optimized technician group acquisition module 40 also includes deleting the idle technician with the smallest auto repair fitness, reselecting an idle technician to join the initial technician group, calculating the auto repair fitness, and deleting the idle technician with the smallest auto repair fitness. Deleting the idle technician with the smallest auto repair fitness in the current technician group, that is, selecting the technician with the worst performance and removing it from the group, reselecting a technician from the remaining idle technicians to join the initial technician group to supplement the deleted technician, calculating the auto repair fitness of each technician in the new technician group again, and then deleting the idle technician with the smallest fitness.

[0050] The optimized technician group obtaining module 40 further includes: continuing the selection optimization until all idle technicians are traversed, and outputting the final optimized technician group. Repeating the above steps of deleting the technician with the minimum fitness and reselecting technicians until all idle technicians are traversed (that is, each idle technician is selected and evaluated once), and then outputting the current technician group as the final optimized technician group, which includes the technicians who are most suitable for performing the auto repair task under the current conditions.

[0051] The specific configuration of the processing standardized parameter acquisition module 50 will be described in detail below. The processing standardized parameter acquisition module 50 further includes: extracting multiple historical service process data sets based on the historical auto repair data of the multiple optimized technicians. From the historical auto repair data of the multiple optimized technicians, their respective historical service process data sets are extracted, and these historical service process data sets record the detailed service processes of the technicians when performing similar tasks in the past, including the tools used, operation steps, time consumption, quality control points, etc.

[0052] The processing standardization parameter acquisition module 50 also includes performing standardization analysis based on the deviations between the multiple historical service process data sets and the standard service process data to obtain multiple processing standardization parameters. The historical service process data set of each technician is compared with the standard service process data, wherein the standard service process data is pre-defined service process data that meets the industry practice standards and is used to measure the compliance and efficiency of the technician in actual operation, and the deviation between the historical service process data set and the standard service process data is calculated, such as the omission of steps, the reversal of the order, the excessive or short time consumption, etc., and then the deviation is subjected to standardization analysis, and the deviation is quantified into multiple processing standardization parameters, which reflects the degree of closeness or deviation of the technician from the standard process when executing the service process.

[0053] The processing standardization parameter acquisition module 50 also includes, according to the multiple similar processing rates, combined with the multiple processing standardization parameters, to calculate and obtain multiple standardized scores. Based on the obtained multiple similar processing rates (reflecting the success rate and experience level of the technician in processing similar tasks), a comprehensive score calculation is performed in combination with multiple processing standardization parameters. Specifically, considering the importance of the similar processing rate (directly related to the success rate of the task) and the weight of the processing standardization parameter (reflecting the standardization and professionalism of the technician), the similar processing rate and the processing standardization parameter are combined into a comprehensive score by weighted average to evaluate the overall performance of each optimized technician.

[0054] The processing standardized parameter acquisition module 50 also includes selecting a technician with the largest standardized score in the optimized technician group to obtain the best technician. In the optimized technician group, the technicians are sorted according to the comprehensive scores, and then the technician with the largest comprehensive score is selected as the best technician. The best technician is considered to be the most suitable technician for performing the current auto repair task, and has a higher success rate in processing similar tasks and can better follow the standard service process.

[0055] Although the present application makes various references to certain modules in the system according to the embodiments of the present application, any number of different modules may be used and run on the user terminal and / or server, and the various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.

[0056] The above specific implementations do not constitute a limitation on the protection scope of this application. It should be understood by those skilled in the art that various modifications, combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of this application should be included in the protection scope of this application.

Claims

1. A cross-regional auto repair resource collaborative management and sharing system based on cloud computing, characterized by: The system comprises: A local task level acquisition module, the local task level acquisition module is used to collect task feature information of the auto repair task to be processed in the local area, perform auto repair task retrieval in the local auto repair database according to the task feature information, obtain the task occurrence rate, and perform task skill level analysis and task complexity level analysis to obtain the local task skill level and the local task complexity level, wherein the task occurrence rate refers to the frequency of auto repair tasks of a certain type or a certain fault phenomenon appearing in the database; A task level calculation module, which is used to upload the task feature information to the cross-regional auto repair cloud platform, and based on cloud computing, perform integrated auxiliary task skill level analysis and task complexity level analysis according to the task occurrence rate, obtain the cloud task skill level and cloud local task complexity level, and calculate and obtain the task skill level and task complexity level according to the task occurrence rate; A mechanic characteristic information retrieval module, the mechanic characteristic information retrieval module is used to retrieve mechanic characteristic information of multiple idle mechanics based on the auto repair cloud platform, wherein each mechanic characteristic information includes a skill certification level and a skill practical level; An optimized technician group acquisition module, the optimized technician group acquisition module is used to optimize the selection of technicians according to multiple skill certification levels and skill practice levels and historical auto repair data of multiple idle technicians, combined with the task skill level and task complexity level, to obtain an optimized technician group; A processing standardization parameter acquisition module, the processing standardization parameter acquisition module is used to perform processing standardization analysis based on historical auto repair data of multiple optimized technicians, obtain multiple processing standardization parameters, select technicians within the optimized technician group, obtain the best technician, and dispatch the best technician to the local area to process the auto repair task; The task level calculation module performs the following steps: Based on cloud computing, a cloud skill level analysis path and a cloud complexity analysis path are constructed in the auto repair cloud platform, wherein the cloud skill level analysis path and the cloud complexity analysis path include multiple cloud skill level analysis branches and multiple cloud complexity analysis branches; Upload the task feature information to the cross-regional auto repair cloud platform, calculate the integrated assistance ratio according to the task occurrence rate and the average occurrence rate, and calculate the basic assistance quantity by combining the number of the multiple cloud skill level analysis branches and the cloud complexity analysis branches; Input the task feature information into the cloud skill level analysis branch and cloud complexity analysis branch of the basic auxiliary quantity, perform integrated auxiliary analysis, obtain an auxiliary task skill level set and an auxiliary task complexity level set, and obtain a cloud task skill level and a cloud local task complexity level by majority screening; According to the integrated auxiliary ratio, a local weight and a cloud weight are set, and weighted calculation is performed on the cloud task skill level, the cloud local task complexity level, the local task skill level and the local task complexity level to obtain a task skill level and a task complexity level; The steps of optimizing the skilled worker group acquisition module include: Collecting historical auto repair data of the plurality of idle technicians, matching similar historical auto repair data based on the task feature information, and obtaining a plurality of similar processing rates, wherein the similar processing rate reflects the success rate and experience level of the technicians in processing similar tasks, and the number of similar historical tasks successfully processed by the technicians is divided by the total number of similar historical tasks, and the result obtained is the similar processing rate; The auto repair optimization function constructed to optimize within the plurality of idle technicians is as follows: ; Among them, ARO is the auto repair adaptability, , and is the weight, and The task skill level and task complexity level of the auto repair task, and is the skill certification level and skill practice level of the idle technicians, and K is the same type of processing rate; According to the auto repair optimization function, perform technician selection optimization on the plurality of idle technicians to obtain an optimized technician group; The processing standardization parameter acquisition module performs the following steps: Extracting a plurality of historical service process data sets based on the historical auto repair data of the plurality of optimized technicians; Performing standardized analysis based on the deviations between the plurality of historical service process data sets and the standard service process data to obtain a plurality of processing standardized parameters; Calculating according to the multiple similar treatment rates in combination with the multiple treatment standardization parameters to obtain multiple standardized scores; A technician with the largest standardized score is selected from the optimized technician group to obtain the best technician.

2. The cross-regional auto repair resource collaborative management and sharing system based on cloud computing according to claim 1 is characterized in that: The local task level acquisition module performs the following steps: In the local area, task characteristic information of the auto repair task to be processed is collected; According to the task feature information, performing task retrieval in a local auto repair database to obtain the task occurrence rate of the auto repair task, wherein the local auto repair database is constructed by historical auto repair data records of the local area; According to the local auto repair database, a sample task feature information set is collected, and according to the task skill level and processing complexity of the sample task, a sample task skill level set and a sample task complexity level set are identified and obtained; The sample task feature information set, sample task skill level set and sample task complexity level set are used to train a local skill level analysis path and a local complexity analysis path, and the task feature information is input and analyzed to obtain a local task skill level and a local task complexity level.

3. The cross-regional auto repair resource collaborative management and sharing system based on cloud computing according to claim 1 is characterized in that: The task level calculation module performs the following steps: Based on cloud computing, the auto repair cloud platform collects cross-regional cloud sample task feature information sets as input, collects cross-regional cloud sample task skill level sets and cloud sample task complexity level sets as output, and obtains cloud skill level analysis training data and cloud complexity analysis training data; Randomly selecting part of the training data multiple times in the cloud skill level analysis training data, respectively training multiple cloud skill level analysis branches, and integrating to obtain a cloud skill level analysis path; Part of the training data is randomly selected from the cloud complexity analysis training data, and multiple cloud complexity analysis branches are trained respectively, and a cloud complexity analysis path is obtained through integration.

4. The cross-regional auto repair resource collaborative management and sharing system based on cloud computing according to claim 1 is characterized in that: The steps performed by the technician feature information retrieval module include: Based on the auto repair cloud platform, multiple skill certification levels of multiple idle technicians across regions are collected and retrieved; The auto repair data of the plurality of idle technicians within a recent preset time range are collected, and a plurality of skill practice levels are obtained through analysis.

5. The cross-regional auto repair resource collaborative management and sharing system based on cloud computing according to claim 1 is characterized in that: The steps of optimizing the skilled worker group acquisition module include: Randomly selecting N idle technicians from the plurality of idle technicians to obtain an initial technician group, and calculating and obtaining N auto repair fitnesses according to the auto repair optimization function, where N is an integer greater than 1; Delete the idle technician with the lowest auto repair fitness, and reselect idle technicians to join the initial technician group, calculate the auto repair fitness, and delete the idle technician with the lowest auto repair fitness; Continue to select and optimize until all idle workers have been traversed, and output the final optimized worker group.

Citation Information

Patent Citations

  • Training and management of technicians in the service or repair of machines, devices, or systems

    US11113987B1

  • System and method for skill managememt of knowledge workers in a software industry

    US20050222899A1

  • System for electronically managing and assessing competency of skilled workers

    US20170103358A1

  • Planning optimisation for human-machine interactive tasks considering machine emission goal and human competence growth

    US20230121776A1

  • Automotive industry high performance capability assessment

    US8781882B1