Service provider-oriented customized driver penalty handling system

Abstract

The invention relates to a service provider-oriented self-defined driver penalty handling system, in particular to the field of traffic management, a service provider logs in a rule background to enter a rule configuration page, fills and submits configuration information to enter an approval process and displays the configuration information to a driver background in a notification form, so that comprehensiveness and accuracy of rule configuration can be ensured, and the service provider can conveniently manage the penalty of a driver. A Beidou satellite navigation API interface is connected to collect driving data of a driver, service quality data of the driver is collected in a passenger evaluation and complaint feedback mode, and preprocessing and feature extraction are performed on the driving data and the service quality data of the driver. The method helps a service provider to better understand the behavior and service quality of a driver, constructs a random forest model as an illegal behavior judgment model, achieves the automatic processing of a process, improves the efficiency and accuracy, and selectively stores the illegal behavior data in a cloud and a local database.

Description

Technical Field

[0001] The present invention relates to the field of traffic management, and more specifically, to a service provider-oriented custom driver penalty system. Background Art

[0002] With the increasing number of service providers integrated by the Bailongma SASS system, there are differences in the operating conditions of each service provider. It is necessary for each service provider to independently formulate and implement penalty rules for its drivers based on the specific conditions of the city. The traffic conditions in the city have a direct impact on the behavior of drivers. In cities with serious traffic congestion, drivers will face more violations. Service providers need to strengthen penalties for violations to maintain a good riding environment and drivers' work order.

[0003] The current non-sass systems of competing companies lack the ability to manage and control from the service provider dimension, and focus on adopting a nationwide unified management approach, applying violation rules and penalties to all drivers without considering the specific conditions of each region. Due to differences in applicable cities and population configurations, violation rules and penalties are not flexible and targeted enough, and cannot adapt well to the actual conditions of various places, resulting in poor regional management results.

[0004] Therefore, there is an urgent need for a driver penalty system that can be customized for service providers. Summary of the invention

[0005] In view of the technical problems existing in the prior art, the present invention provides a system for customizing driver penalty for service providers to solve the problems raised in the above background technology.

[0006] The technical solution of the present invention to solve the above technical problem is as follows: it includes a violation rule configuration module, a behavior collection and processing module, a violation behavior judgment module, a violation handling appeal module and a dimension storage module;

[0007] Violation rule configuration module: log in to the rule backend through the service provider to enter the rule configuration page, fill in and submit the configuration information to enter the approval process and display it to the driver backend in the form of notification;

[0008] Behavior collection and processing module: connects to the Beidou satellite navigation API interface to collect the driver's driving data, collects the driver's service quality data through passenger evaluation and complaint feedback, and pre-processes and extracts features from the driver's driving data and service quality data;

[0009] Illegal behavior judgment module: divides the feature representation into training set, validation set and test set, and constructs a random forest model as an illegal behavior judgment model;

[0010] Violation handling and appeal module: divides driver violation generation and appeal into violation handling process and violation appeal process;

[0011] Dimension storage module: organizes the violation data corresponding to the rule configurations of different service providers and different cities, designs the cloud and local database table structures, and selectively stores the violation data in the cloud and local databases;

[0012] In a preferred embodiment, the violation rule configuration module logs in to the rule background through the service provider to enter the rule configuration page, and fills in the submitted violation rules, applicable cities, population configuration, penalty configuration and effective time, fills in the submitted configuration information to enter the approval process, and the system will display the effective penalty configuration to the driver's background in the form of a notification.

[0013] In a preferred embodiment, the behavior collection and processing module is connected to the Beidou satellite navigation API interface and collects the driver's driving data based on the behavioral indicators of time interval, driving distance and driving speed as trigger conditions, and collects the driver's service quality data through passenger evaluation and complaint feedback.

[0014] Furthermore, check the error values ​​in the driving data and service quality data. For the start time, end time, driving speed, driving distance and route, check whether they are beyond a reasonable range. If so, delete the data. For the driving data and service quality data, check whether there are errors and inconsistent data. If so, delete the data and prepare the driving data items to fill in the missing values.

[0015] Furthermore, feature representations of average speed, driving distance, and driving time period are extracted from the driving data, and feature representations of average score, number of complaints, and passenger feedback are extracted from the service quality data. The chi-square test is used to perform cross-tabulation statistics on each feature representation and the behavior variable to obtain a contingency table, and the chi-square statistic between the feature representation and the behavior variable is calculated. The specific calculation formula of the chi-square statistic is:

[0016]

[0017] Among them, X 2 represents the chi-square statistic, O ij represents the number of samples actually observed in the combination of the i-th feature representation category and the j-th behavior variable category in the cross table, R i represents the row sum of the i-th feature representation, C irepresents the column sum of the ith behavioral variable, m represents the total number of feature representations and behavioral variables, r represents the number of categories of feature representations, and c represents the number of categories of behavioral variables. The chi-square test uses the P value to determine the significant association between feature representations and behavioral variables and to select feature representations.

[0018] In a preferred embodiment, the violation judgment module divides the feature representation into a training set, a validation set and a test set, wherein 70% of the feature representation is used as a training set, 20% of the feature representation is used as a validation set, and 10% of the feature representation is used as a test set. A random forest model is constructed as a violation judgment model, and a random number of decision trees are used to take the violation as the root node of the decision tree and divide it into different behavior subsets. For each non-leaf node, the best feature representation in the violation is selected for splitting. The smaller the Gini index of the non-leaf node, the higher the purity of the node is, and the feature representation indicates that there is a violation and a specific judgment is made on the type of cheating behavior. The larger the Gini index of the non-leaf node, the lower the purity of the node is, and the feature representation indicates that there is no violation.

[0019] In a preferred embodiment, the violation handling appeal module is divided into a violation handling process and a violation appeal process, wherein the violation handling process is connected to the violation judgment module and records the violations committed by the driver, and displays the violation information on the service provider's backend and the driver's backend at the same time, matches the violations according to the penalty rules configured by the service provider, displays the handling results on the service provider's backend and synchronizes them to the driver's backend, wherein the violation appeal process appeals the violation and submits the appeal request through the display location of the driver's backend, calls the violation judgment model for iterative review, modifies the handling result status of the service provider and driver's backend, marks the appeal failure with a red cross, and marks the appeal success with a green check mark and cancels the penalty status.

[0020] In a preferred embodiment, the dimensional storage module organizes the violation data corresponding to different service provider rule configurations and different cities, and selectively stores the violation data in the cloud and a local database. The cloud storage has redundancy and backup mechanisms, and the local database allows complete control over the violation data, determines the violation data fields to be recorded and managed, and designs the cloud and local database table structures, wherein a column in each table corresponds to a city, wherein a row in each table corresponds to a service provider rule configuration, and a vertical storage table is established in three dimensions, wherein one table is used for violation data, and another table is used to store driver background data.

[0021] In a preferred embodiment, the method specifically includes the following steps:

[0022] S101. Log in to the rule backend through the service provider and enter the rule configuration page. Fill in and submit the configuration information to enter the approval process. The system will display the effective penalty configuration to the driver backend in the form of a notification;

[0023] S102. Connect to the Beidou satellite navigation API interface to collect the driver's driving data, collect the driver's service quality data through passenger evaluation and complaint feedback, pre-process the driver's driving data and service quality data, extract feature representation, and use the chi-square test to select feature representation;

[0024] S103. Divide the feature representation into a training set, a validation set, and a test set, and construct a random forest model as a violation judgment model;

[0025] S104. The violation handling process connects to the violation judgment module and records the driver's violations. The violation appeal process appeals the violation through the display position of the driver's backend and submits the appeal request;

[0026] S105. Organize the violation data corresponding to the rule configurations of different service providers and different cities, design the cloud and local database table structures, and selectively store the violation data in the cloud and local database;

[0027] The beneficial effects of the present invention are as follows: the service provider configures and manages the violation rules through the rule background, including the key elements in the rule configuration, which helps to ensure the comprehensiveness and accuracy of the rule configuration, enhances the transparency and standardization of the entire process, and helps drivers to understand the new penalty configuration in a timely manner, thereby avoiding violations. Preprocessing ensures the quality and reliability of data, helps service providers to better understand the driver's behavior and service quality, and provides data support for subsequent decision-making and optimization. The best features are selected for splitting according to the Gini index, which helps to improve the purity of the nodes. Through the establishment of a random forest model, a large number of feature representations can be effectively processed, and noise and complex relationships in the data can be dealt with, and the accuracy and generalization ability of the violation judgment model can be improved. The design of displaying violation information and disposal results in the service provider background and the driver background makes the information visible to both the driver and the service provider, which improves transparency and fairness. By calling the violation judgment model to match and review violations, the process is automated, efficiency and accuracy are improved, and the review results are clearly displayed by marking the complaint results. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] Figure 1 is a flow chart of the method of the present invention;

[0029] Figure 2 This is a system structure block diagram of the present invention. DETAILED DESCRIPTION

[0030] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0031] In the description of this application, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, "plurality" means two or more, unless otherwise clearly and specifically defined.

[0032] In the description of the present application, the term "for example" is used to mean "used as an example, illustration or description". Any embodiment described as "for example" in the present application is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is given to enable any technician in the field to implement and use the present invention. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other examples, well-known structures and processes will not be elaborated in detail to avoid unnecessary details to obscure the description of the present invention. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed in the present application.

[0033] Example 1

[0034] This embodiment provides Figure 1 A driver penalty system customized for service providers is shown, which specifically includes the following steps:

[0035] S101. Log in to the rule backend through the service provider and enter the rule configuration page. Fill in and submit the configuration information to enter the approval process. The system will display the effective penalty configuration to the driver backend in the form of a notification;

[0036] S102. Connect to the Beidou satellite navigation API interface to collect the driver's driving data, collect the driver's service quality data through passenger evaluation and complaint feedback, pre-process the driver's driving data and service quality data, extract feature representation, and use the chi-square test to select feature representation;

[0037] S103. Divide the feature representation into a training set, a validation set, and a test set, and construct a random forest model as a violation judgment model;

[0038] S104. The violation handling process connects to the violation judgment module and records the driver's violations. The violation appeal process appeals the violation through the display position of the driver's backend and submits the appeal request;

[0039] S105. Organize the violation data corresponding to the rule configurations of different service providers and different cities, design the cloud and local database table structures, and selectively store the violation data in the cloud and local database.

[0040] Example 2

[0041] This embodiment provides Figure 2 A driver penalty system for service providers to customize the driver penalty system specifically includes: a violation rule configuration module, a behavior collection and processing module, a violation behavior judgment module, a violation handling appeal module and a dimension storage module;

[0042] Violation rule configuration module: log in to the rule backend through the service provider to enter the rule configuration page, fill in and submit the configuration information to enter the approval process and display it to the driver backend in the form of notification;

[0043] Behavior collection and processing module: connects to the Beidou satellite navigation API interface to collect the driver's driving data, collects the driver's service quality data through passenger evaluation and complaint feedback, and pre-processes and extracts features from the driver's driving data and service quality data;

[0044] Illegal behavior judgment module: divides the feature representation into training set, validation set and test set, and constructs a random forest model as an illegal behavior judgment model;

[0045] Violation handling and appeal module: divides driver violation generation and appeal into violation handling process and violation appeal process;

[0046] Dimension storage module: organizes the violation data corresponding to the rule configurations of different service providers and different cities, designs the cloud and local database table structures, and selectively stores the violation data in the cloud and local databases;

[0047] S101. Log in to the rule backend through the service provider and enter the rule configuration page. Fill in and submit the configuration information to enter the approval process. The system will display the effective penalty configuration to the driver backend in the form of a notification;

[0048] Furthermore, log in to the rule background through the service provider to enter the rule configuration page, and fill in the submission violation rules, applicable cities, population configuration, penalty configuration and effective time. The applicable city is effective in a specific city or region, and choose to fill in the applicable city information, including a list of provinces and cities. The population configuration applies to a specific group of people, including age, gender, and occupation, and choose to fill in the corresponding group of people related to user attributes and identity authentication. The penalty configuration includes the type of penalty, penalty duration, and fine amount. The effective time is set to be scheduled or periodic, including the effective date and time range. Fill in and submit the configuration information to enter the approval process. When the approval is passed, the penalty configuration will take effect according to the effective time. When the approval is not passed, return to the rule configuration and re-fill in and submit for approval. The system will display the effective penalty configuration to the driver's background in the form of a notification.

[0049] S102. Connect to the Beidou satellite navigation API interface to collect the driver's driving data, collect the driver's service quality data through passenger evaluation and complaint feedback, pre-process the driver's driving data and service quality data, extract feature representation, and use the chi-square test to select feature representation;

[0050] Furthermore, the Beidou satellite navigation API interface is connected and the driver's driving data is collected based on the behavioral indicators of time interval, driving distance and driving speed as trigger conditions, including start time, end time, driving speed, driving distance and route, and the driver's service quality data is collected through passenger evaluation and complaint feedback.

[0051] Furthermore, check the error values ​​in the driving data and service quality data. For the start time, end time, driving speed, driving distance and route, check whether they are beyond a reasonable range. If so, delete the data. For the driving data and service quality data, check whether there are errors and inconsistent data. If so, delete the data and prepare the driving data items to fill in the missing values.

[0052] Furthermore, feature representations of average speed, driving distance, and driving time period are extracted from the driving data, and feature representations of average score, number of complaints, and passenger feedback are extracted from the service quality data. The chi-square test is used to perform cross-tabulation statistics on each feature representation and the behavior variable to obtain a contingency table, and the chi-square statistic between the feature representation and the behavior variable is calculated. The specific calculation formula of the chi-square statistic is:

[0053]

[0054] Among them, X 2 represents the chi-square statistic, O ijrepresents the number of samples actually observed in the combination of the i-th feature representation category and the j-th behavior variable category in the cross table, R i represents the row sum of the i-th feature representation, C i represents the column sum of the ith behavioral variable, m represents the total number of feature representations and behavioral variables, r represents the number of categories of feature representations, and c represents the number of categories of behavioral variables. The chi-square test uses the P value to determine the significant association between feature representations and behavioral variables and select feature representations. The P value uses the chi-square distribution table to list the chi-square statistics under different degrees of freedom, and represents the probability of observing the current statistic or a more extreme statistic when the null hypothesis is true.

[0055] S103. Divide the feature representation into a training set, a validation set, and a test set, and construct a random forest model as a violation judgment model;

[0056] Furthermore, the feature representation is divided into a training set, a validation set, and a test set, where 70% of the feature representation is used as a training set, 20% of the feature representation is used as a validation set, and 10% of the feature representation is used as a test set. A random forest model is constructed as a violation judgment model, and a random number of decision trees are used to take the violation as the root node of the decision tree and divide it into different behavior subsets. For each non-leaf node, the best feature representation in the violation is selected for splitting. The smaller the Gini index of the non-leaf node, the higher the purity of the node is, and the feature representation indicates that there is a violation and a specific judgment is made on the type of cheating behavior. The larger the Gini index of the non-leaf node, the lower the purity of the node is, and the feature representation indicates that there is no violation.

[0057] S104. The violation handling process connects to the violation judgment module and records the driver's violations. The violation appeal process appeals the violation through the display position of the driver's backend and submits the appeal request;

[0058] Furthermore, it is divided into a violation handling process and a violation appeal process, wherein the violation handling process is connected to the violation judgment module and records the driver's violations, while displaying the violation information in the service provider's backend and the driver's backend, matching the violations according to the penalty rules configured by the service provider, and executing and issuing the handling measures when the match is successful, and executing and recording the violations when the match fails. The handling results are displayed in the service provider's backend and synchronized to the driver's backend, wherein the violation appeal process appeals against the violation and submits the appeal request through the display position of the driver's backend, and calls the violation judgment model for iterative review. When the appeal fails, the process ends and the handling result is maintained. When the appeal is successful, it rolls back to the initial handling result and connects to the penalty rule for cancellation, modifies the handling result status of the service provider and driver's backend, marks the appeal failure with a red cross, and marks the appeal success with a green check mark and the penalty status is revoked.

[0059] S105. Organize the violation data corresponding to the rule configurations of different service providers and different cities, design the cloud and local database table structures, and selectively store the violation data in the cloud and local database;

[0060] Furthermore, the violation data corresponding to different service provider rule configurations and different cities are sorted out, and the violation data are selectively stored in the cloud and local database. The cloud storage has redundancy and backup mechanisms, and the local database allows complete control of the violation data, including storage structure, backup strategy and data migration, determine the violation data fields to be recorded and managed, and design the cloud and local database table structures, wherein a column in each table corresponds to a city, wherein a row in each table corresponds to a service provider rule configuration, and a vertical storage table is established in three dimensions, wherein one table is used for violation data, and another table is used to store driver background data.

[0061] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and for parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0062] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0063] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0064] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0065] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0066] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0067] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A driver penalty system customized for service providers, characterized in that: Specifically include: It includes violation rule configuration module, behavior collection and processing module, violation behavior judgment module, violation handling appeal module and dimension storage module; Violation rule configuration module: log in to the rule backend through the service provider to enter the rule configuration page, fill in and submit the configuration information to enter the approval process and display it to the driver backend in the form of notification; Behavior collection and processing module: connects to the Beidou satellite navigation API interface to collect the driver's driving data, collects the driver's service quality data through passenger evaluation and complaint feedback, and pre-processes and extracts features from the driver's driving data and service quality data; Illegal behavior judgment module: divides the feature representation into training set, validation set and test set, and constructs a random forest model as an illegal behavior judgment model; Violation handling and appeal module: divides driver violation generation and appeal into violation handling process and violation appeal process; Dimension storage module: organizes the violation data corresponding to the rule configurations of different service providers and different cities, designs the cloud and local database table structures, and selectively stores the violation data in the cloud and local database.

2. A driver penalty system for service providers according to claim 1, characterized in that: The violation rule configuration module logs in to the rule background through the service provider to enter the rule configuration page, fills in and submits the configuration information to enter the approval process, and the system will display the effective penalty configuration to the driver background in the form of a notification.

3. The driver penalty system for service providers according to claim 1, characterized in that: The behavior collection and processing module is connected to the Beidou satellite navigation API interface to collect the driver's driving data, collects the driver's service quality data through passenger evaluation and complaint feedback, checks the error values ​​in the driving data and service quality data, checks whether the start time, end time, driving speed, driving distance and route are beyond a reasonable range, deletes the data if they are beyond a reasonable range, checks whether there are errors and inconsistent data in the driving data and service quality data, extracts the feature representation of the average speed, driving distance and driving time period from the driving data, extracts the feature representation of the average score, number of complaints and passenger feedback from the service quality data, uses the chi-square test to perform cross-tabulation statistics on each feature representation and the behavior variable to obtain a de-contingency table, and calculates the chi-square statistic between the feature representation and the behavior variable.

4. A driver penalty system for service providers according to claim 3, characterized in that: The specific calculation formula of the chi-square statistic is: Among them, X 2 represents the chi-square statistic, O ij represents the number of samples actually observed in the combination of the i-th feature representation category and the j-th behavior variable category in the cross table, R i represents the row sum of the i-th feature representation, C i represents the column sum of the ith behavioral variable, m represents the total number of feature representations and behavioral variables, r represents the number of categories of feature representations, and c represents the number of categories of behavioral variables.

5. The driver penalty system for service providers according to claim 1, characterized in that: The violation judgment module constructs a random forest model as a violation judgment model, uses a random number of decision trees to take the violation as the root node of the decision tree and divides it into different behavior subsets, and for each non-leaf node, selects the best feature representation in the violation for splitting.

6. A driver penalty system for service providers according to claim 5, characterized in that: The specific steps of the violation judgment model are: when the Gini index of the non-leaf node is smaller, the purity of the node is judged to be higher, and this feature indicates that there is a violation and a specific judgment is made on the type of cheating behavior; when the Gini index of the non-leaf node is larger, the purity of the node is judged to be lower, and this feature indicates that there is no violation.

7. The driver penalty system for service providers according to claim 1, characterized in that: The violation handling and appeal module is divided into a violation handling process and a violation appeal process, wherein the violation handling process is connected to the violation judgment module and records the violations committed by the driver, matches the violations according to the penalty rules configured by the service provider, displays the handling results on the service provider's backend and synchronizes them to the driver's backend, wherein the violation appeal process appeals against the violation and submits an appeal request through the display location of the driver's backend, calls the violation judgment model for iterative review, and modifies the handling result status of the service provider and driver's backend.

8. The driver penalty system for service providers according to claim 1, characterized in that: The dimensional storage module organizes the violation data corresponding to different service provider rule configurations and different cities, selectively stores the violation data in the cloud and local database, designs the cloud and local database table structures, wherein a column in each table corresponds to a city, wherein a row in each table corresponds to a service provider rule configuration, and establishes a vertical storage table in three dimensions, wherein one table is used for violation data, and another table is used to store driver background data.

Images