Driving management business abnormity sensing method
Through intelligent analysis and artificial intelligence technology, combined with big data analysis, a vehicle-driven management business abnormal perception model is built, which solves the problem that traditional manual review methods are difficult to meet efficient and accurate processing needs, and realizes accurate perception and rapid response to vehicle-driven management business abnormalities. , improves the accuracy and efficiency of business processing, and assists in the assessment and training of handling personnel.
Patent Information
- Application Number
- CN202411313723.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-20
- Publication Date
- 2024-12-31
AI Technical Summary
The traditional manual review method is difficult to meet the efficient and accurate handling needs of vehicle and driving management business, and the automation system has low recognition accuracy and slow response speed in terms of abnormal perception, resulting in frequent business abnormalities.
Using intelligent analysis and big data analysis combined with artificial intelligence technology, through data collection, preprocessing, feature extraction, model training and abnormal detection, a business exception perception model is built to achieve accurate and rapid perception of vehicle and driving management business abnormalities, and through The abnormal business database and the integral algorithm are used to conduct personnel assessment and training guidance.
It improves the accuracy and efficiency of vehicle and driving management business processing, assists in the business assessment and training of auxiliary personnel, and enhances the trust of the traffic management department.
Smart Images
Figure CN119226700A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of vehicle and driver management data processing, and in particular to a method for sensing abnormalities in vehicle and driver management services. Background Art
[0002] As the number of vehicles continues to increase, the volume of vehicle and driver management business has also increased dramatically. The traditional manual review method can no longer meet the needs of efficient and accurate business processing, and is easily affected by human factors, resulting in frequent business anomalies. In the existing technology, although some systems have adopted automated processing procedures, there are still deficiencies in anomaly perception, such as low recognition accuracy and slow response speed.
[0003] As an important part of traffic management, the efficiency and accuracy of vehicle and driver management business directly affects the maintenance of traffic order and the public's trust in traffic management departments. With the continuous development of information technology, intelligence and automation have become important trends in the processing of vehicle and driver management business. Summary of the invention
[0004] The purpose of the present invention is to provide a method for perceiving vehicle and driver management business anomalies, based on intelligent analysis, combined with big data analysis and artificial intelligence technology, to achieve accurate and rapid perception of vehicle and driver management business anomalies, and improve the accuracy and efficiency of business processing.
[0005] To achieve the above object, the present invention provides the following technical solutions: A method for detecting abnormalities in vehicle and driver management services comprises the following steps: Step 1, data collection: collect data during the business handling process through the data interface of the vehicle and driver management business system, where the collected data includes: business type, handling time, handling personnel, and processing results; Step 2, data preprocessing: clean and denoise the collected data, remove duplicate, erroneous and invalid data, and then standardize the data; Step 3: feature extraction, based on business data and historical abnormality records, extract features that can characterize business abnormalities; the features that characterize business abnormalities include: abnormal processing time and abnormal processing results; Step 4: Model training: building a business anomaly perception model and using the extracted features for learning and training to improve the business anomaly perception model; Step 5, anomaly detection: input the preprocessed business data into the trained business anomaly perception model to perform anomaly detection. When an anomaly is found, the early warning mechanism is triggered and an early warning message is issued; Step 6, exception handling and model optimization: Manually review the abnormal business displayed in the warning information; if it is confirmed to be an abnormal business, handle the abnormal business; if it is confirmed to be a non-abnormal business and there is a false alarm, update and optimize the business anomaly perception model based on the false alarm.
[0006] As a further solution of the present invention: constructing an abnormal business database, the abnormal business database includes abnormal business data detected by the business anomaly perception model; The attributes of the business exception data collected in the abnormal business database include: business type, processing time, processing personnel, processing results and collection time.
[0007] As a further solution of the present invention: in step 6, in the exception handling and model optimization, if it is confirmed to be a non-abnormal business, the business exception library is updated to remove the business exception data of this item.
[0008] As a further solution of the present invention: the business exception library is cleaned up regularly, and historical data is removed to streamline the business exception library.
[0009] As a further solution of the present invention: the business abnormality data appearing in the business abnormality database uses a points algorithm to accumulate the frequency of business abnormality data within a preset time for each processing personnel, and when the frequency of business abnormality data reaches a preset threshold, a warning message is triggered.
[0010] As a further solution of the present invention: when using a points algorithm to accumulate the frequency of abnormal business data within a preset time for each processing personnel, the three situations of processing time, processing results and all abnormal business data are calculated separately, and a corresponding preset threshold is set for each situation.
[0011] As a further solution of the present invention: the business abnormality data frequency of all business abnormality data of each processing personnel is regularly sorted, and a sorted list of the business abnormality data frequency of the processing personnel is output.
[0012] As a further solution of the present invention: the business abnormality data of each different business type is accumulated for each processing personnel respectively, and a business type preset threshold is set for the business abnormality data of each different business type respectively. When the business abnormality data of the business type corresponding to the processing personnel reaches the business type preset threshold, a warning message is triggered.
[0013] As a further solution of the present invention: for each different type of business abnormality data, an integral algorithm is used to accumulate the frequency of business abnormality data within a preset time, and when the frequency of business abnormality data reaches a preset threshold, a warning message is triggered.
[0014] As a further solution of the present invention: regularly sorting the frequency of business abnormality data of each different business type, and outputting a sorted list of the frequency of business abnormality data for each different business type.
[0015] Compared with the prior art, the invention has the following beneficial effects: the abnormal perception method of vehicle and driver management business, combined with big data analysis and artificial intelligence technology, can realize accurate and rapid perception of abnormal vehicle and driver management business, and improve the accuracy and efficiency of business processing. The constructed abnormal business database can assist in the business assessment of the processing personnel, and can assist in the assessment of timeliness and accuracy. The sorting list can be used as an auxiliary assessment indicator and to inform the processing personnel to conduct corresponding business training.
[0016] Abnormal statistical processing for business types can provide guidance for subsequent training of the group as a whole.
[0017] Other features and advantages of the present invention will be disclosed in detail in the following specific embodiments and drawings. BRIEF DESCRIPTION OF THE DRAWINGS
[0018] Figure 1 It is a flow chart of a method for sensing abnormalities in vehicle and driver management services in an embodiment of the present application. DETAILED DESCRIPTION
[0019] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0020] like Figure 1 As shown, a method for sensing abnormalities in vehicle and driver management services includes the following steps: Step 1, data collection: collect data during the business handling process through the data interface of the vehicle and driver management business system, where the collected data includes: business type, handling time, handling personnel, and processing results; Step 2, data preprocessing: clean and denoise the collected data, remove duplicate, erroneous and invalid data, and then standardize the data to ensure that data from different sources can be uniformly identified and ensure the accuracy and availability of the data; Step 3, feature extraction, based on business data and historical abnormality records, extract features that can characterize business abnormalities; the features that characterize business abnormalities include: abnormal processing time, abnormal processing results; among them, abnormal processing time actually means that the processing time deviates from the normal range, and abnormal processing results actually mean that the processing result does not meet expectations. The recorded abnormal data is not limited to abnormal processing time and abnormal processing results, and abnormal features can be set according to specific circumstances;
[0021] Step 4: Model training: building a business anomaly perception model and using the extracted features for learning and training to improve the business anomaly perception model; Step 5, anomaly detection: input the preprocessed business data into the trained business anomaly perception model to perform anomaly detection. When an anomaly is found, the early warning mechanism is triggered and an early warning message is issued; Step 6, exception handling and model optimization: Manually review the abnormal business displayed in the warning information; if it is confirmed to be an abnormal business, handle the abnormal business; if it is confirmed to be a non-abnormal business and there is a false alarm, update and optimize the business anomaly perception model based on the false alarm.
[0022] As a preferred implementation, an abnormal business database is constructed, and the abnormal business database includes abnormal business data detected by the business anomaly perception model; The attributes of the business abnormality data collected in the abnormal business database include: business type, processing time, processing personnel, processing results and collection time. Business types include: driver management business, vehicle management business and business types determined based on specific business.
[0023] As a specific implementation, in step 6, in exception handling and model optimization, if it is confirmed to be a non-abnormal business, the business exception library is updated to remove the business exception data included in it.
[0024] As a specific implementation method, the business exception library is cleaned up regularly, and historical data is removed to streamline the business exception library.
[0025] As a specific implementation method, the business exception data appearing in the business exception library uses a points algorithm to accumulate the frequency of business exception data within a preset time for each processing personnel, and when the frequency of business exception data reaches a preset threshold, a warning message is triggered.
[0026] Counting the frequency of abnormal business data for each processing staff can assist in the staff’s business assessment and improvement of their business level.
[0027] As a specific implementation method, when the frequency of abnormal business data within a preset time is accumulated by using a point algorithm for each processing staff, the processing time, processing results and all abnormal business data are calculated separately, and a corresponding preset threshold is set for each case. This can assist the business assessment and business level improvement of processing staff.
[0028] As a specific implementation method, the frequency of all abnormal business data of each processing staff is regularly sorted, and a frequency sorting list of abnormal business data for processing staff is output. By introducing competition, processing staff are encouraged to improve their business level.
[0029] As a specific implementation method, business abnormality data of each different business type is accumulated for each processing personnel, and a business type preset threshold is set for the business abnormality data of each different business type. When the accumulated business abnormality data of the business type corresponding to the processing personnel reaches the business type preset threshold, a warning message is triggered.
[0030] Specific to different business types, it is convenient for processing personnel to understand the advantages and disadvantages based on management personnel.
[0031] As a specific implementation method, for each different type of business abnormality data, an integral algorithm is used to accumulate the frequency of business abnormality data within a preset time, and when the frequency of business abnormality data reaches a preset threshold, a warning message is triggered.
[0032] As a specific implementation method, the frequency of business abnormality data of business abnormality data of each different business type is regularly sorted, and a sorted list of the frequency of business abnormality data of each different business type is output.
[0033] Based on overall statistics, it is convenient to guide and arrange subsequent business training.
[0034] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the equivalent elements of the claims be included in the invention. Any reference numeral in a claim should not be considered as limiting the claim to which it relates.
[0035] In addition, it should be understood that although the present specification is described according to implementation modes, not every implementation mode contains only one independent technical solution. This description of the specification is only for the sake of clarity. Those skilled in the art should regard the specification as a whole. The technical solutions in each embodiment may also be appropriately combined to form other implementation modes that can be understood by those skilled in the art.
Claims
1. A method for sensing abnormalities in vehicle and driver management services, characterized in that: The following steps are involved: Step 1, data collection: collect data during the business handling process through the data interface of the vehicle and driver management business system, where the collected data includes: business type, handling time, handling personnel, and processing results; Step 2, data preprocessing: clean and denoise the collected data, remove duplicate, erroneous and invalid data, and then standardize the data; Step 3: feature extraction, based on business data and historical abnormality records, extract features that can characterize business abnormalities; the features that characterize business abnormalities include: abnormal processing time and abnormal processing results; Step 4: Model training: building a business anomaly perception model and using the extracted features for learning and training to improve the business anomaly perception model; Step 5, anomaly detection: input the preprocessed business data into the trained business anomaly perception model to perform anomaly detection. When an anomaly is found, the early warning mechanism is triggered and an early warning message is issued; Step 6, exception handling and model optimization: Manually review the abnormal business displayed in the warning information; if it is confirmed to be an abnormal business, handle the abnormal business; if it is confirmed to be a non-abnormal business and there is a false alarm, update and optimize the business anomaly perception model based on the false alarm.
2. A method for detecting abnormalities in vehicle and driver management services according to claim 1, characterized in that: Building an abnormal business database, wherein the abnormal business database includes business abnormality data detected by the business abnormality perception model; The attributes of the business abnormality data recorded in the abnormal business database include: business type, processing time, processing personnel, processing results and recording time.
3. A method for detecting abnormalities in vehicle and driver management services according to claim 2, characterized in that: In step 6, in the exception handling and model optimization, if it is confirmed to be a non-abnormal business, the business exception library is updated to remove the business exception data included in the item.
4. A method for detecting abnormalities in vehicle and driver management services according to claim 2, characterized in that: The business exception database is cleaned up regularly, and historical data is removed to streamline the business exception database.
5. A method for detecting abnormalities in vehicle and driver management services according to claim 2, characterized in that: The business anomaly data appearing in the business anomaly database is accumulated by a points algorithm for each of the processing personnel within a preset time, and when the frequency of the business anomaly data reaches a preset threshold, a warning message is triggered.
6. A method for detecting abnormalities in vehicle and driver management services according to claim 5, characterized in that: When a points algorithm is used to accumulate the frequency of abnormal business data within a preset time for each processing personnel, the three situations of processing time, processing results and all abnormal business data are calculated separately, and a corresponding preset threshold is set for each situation.
7. A method for detecting abnormalities in vehicle and driver management services according to claim 6, characterized in that: The business abnormality data frequencies of all business abnormality data of each of the processing personnel are regularly sorted, and a frequency sorting list of the business abnormality data for the processing personnel is output.
8. A method for detecting abnormalities in vehicle and driver management services according to claim 2, characterized in that: The business abnormality data of each different business type is accumulated for each of the processing personnel, and a business type preset threshold is set for the business abnormality data of each different business type. When the accumulated business abnormality data of the business type corresponding to the processing personnel reaches the business type preset threshold, a warning message is triggered.
9. A method for detecting abnormalities in vehicle and driver management services according to claim 2, characterized in that: For each different type of business abnormality data, an integral algorithm is used to accumulate the frequency of business abnormality data within a preset time. When the frequency of business abnormality data reaches a preset threshold, a warning message is triggered.
10. A method for sensing abnormalities in vehicle and driver management services according to claim 9, characterized in that: Regularly sort the frequency of business abnormality data of each different business type, and output a sorted list of the frequency of business abnormality data for each different business type.