Parking fee reduction and remission abnormity processing method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention discloses a parking fee reduction and remission abnormity processing method and device, electronic equipment and a storage medium. The method comprises the steps of obtaining order information of a to-be-detected order; according to the order information and a pre-trained exception recognition engine, determining an exception reason of the to-be-detected order; and according to a preset processing mode corresponding to the abnormity reason, executing an abnormity processing flow, an abnormity identification engine performing multi-dimensional analysis on order information of a historical order to determine, and the historical order being a charging order which occurs before the to-be-detected order and is abnormal in parking fee reduction and remission. Therefore, according to the method, automatic identification of the abnormal reason of the to-be-detected order and timely processing of the order reduction and remission abnormity are realized based on the abnormity identification engine, and the abnormal reason identification and abnormity processing efficiency during parking fee reduction and remission abnormity can be improved.

Description

Technical Field

[0001] This invention relates to the field of computer technology, and more specifically to a method, apparatus, electronic device, and storage medium for handling abnormal parking fee reductions. Background Technology

[0002] With the widespread application of new energy electric vehicles, charging stations have become one of the most important infrastructure elements serving various modes of transportation. To increase the number of electric vehicle drivers attracted to charging stations and improve their experience, charging operators connect the gates at each station and implement parking fee reduction policies (such as limited-time free parking or free parking all day) based on the charging status when vehicles leave the station after charging. However, because the process of implementing parking fee reductions involves multiple devices (such as charging equipment, gates, and vehicles) and multiple processing steps (such as incorrect driver license plate binding), a problem in any device or step can lead to the user's parking fee reduction failing, preventing them from enjoying the discount upon leaving the station, and ultimately resulting in driver complaints to the platform.

[0003] However, in existing technologies, when parking fee reductions or exemptions are abnormal, the barrier gate system can only return basic error information. Manual investigation is required to determine the true cause of the error, which is very inefficient. Furthermore, even after identifying the cause of the abnormality, it cannot be quickly addressed, leading to persistent abnormalities and having a negative impact. Summary of the Invention

[0004] In view of this, the purpose of this invention is to provide a method for handling abnormal parking fee reductions, so as to improve the efficiency of identifying the cause of abnormalities and the efficiency of handling abnormalities when parking fee reductions are abnormal.

[0005] In a first aspect, embodiments of the present invention aim to provide a method for handling abnormal parking fee reductions, the method comprising:

[0006] Obtain the order information of the orders to be tested, which are charging orders where parking fee reductions have anomalies;

[0007] Based on the order information and the pre-trained anomaly detection engine, the cause of the anomaly in the order to be detected is determined. The anomaly detection engine determines this by performing multi-dimensional analysis on the order information of historical orders, which are charging orders that occurred before the order to be detected and had anomalies in parking fee reductions.

[0008] The exception handling process is executed according to the preset handling method corresponding to the cause of the exception.

[0009] Furthermore, the anomaly detection engine determines this through the following method:

[0010] Obtain training samples, which include multiple historical orders. Each historical order has corresponding order information and anomaly tags. The anomaly tags are determined by multi-dimensional analysis of the order information.

[0011] The preset anomaly recognition model is trained based on the training samples to determine the anomaly recognition engine.

[0012] Furthermore, the method also includes:

[0013] In response to the order to be tested successfully reducing the fee after executing the abnormal handling process, reference information is obtained, including the actual abnormal reason and / or actual handling method corresponding to the successful reduction;

[0014] The anomaly detection engine and / or the preset handling method are updated based on the reference information.

[0015] Furthermore, the order information includes order identifier, user identifier, license plate information, gate information, charging station information, charging information, fee reduction / exemption policy information, and / or complaint information.

[0016] Furthermore, the reasons for the anomalies include license plate anomalies, gate anomalies, charging anomalies, configuration anomalies, network anomalies, and / or reduction / exemption policy anomalies.

[0017] Furthermore, the step of executing the exception handling process according to the preset handling method corresponding to the exception cause includes:

[0018] In response to the reason for the anomaly being an abnormal license plate, the parking fee reduction is re-executed based on the set of license plates bound to the target user corresponding to the order to be detected;

[0019] A reminder message is sent to the target user corresponding to the order to be tested, so as to remind the target user to modify the bound license plate information.

[0020] Furthermore, the step of executing the exception handling process according to the preset handling method corresponding to the exception cause includes:

[0021] In response to the abnormality being due to a gate malfunction, maintenance information is sent to the operation and maintenance personnel at the target site, which is the charging station that completed the order to be tested.

[0022] Furthermore, the step of executing the exception handling process according to the preset handling method corresponding to the exception cause includes:

[0023] In response to the fact that the cause of the abnormality is a charging abnormality, the charging information of the order to be tested is re-pushed so as to perform parking fee reduction based on the charging information.

[0024] Secondly, embodiments of the present invention aim to provide a parking fee reduction exception handling device, the device comprising:

[0025] The acquisition unit is used to acquire the order information of the order to be detected, wherein the order to be detected is the charging order where the parking fee reduction has an anomaly;

[0026] The analysis unit is used to determine the cause of the anomaly of the order to be detected based on the order information and a pre-trained anomaly recognition engine. The anomaly recognition engine determines the cause by performing multi-dimensional analysis on the order information of historical orders, which are charging orders that occurred before the order to be detected and had anomalies in parking fee reductions.

[0027] The handling unit is used to execute the abnormal handling process according to the preset handling method corresponding to the abnormal cause.

[0028] Thirdly, embodiments of the present invention aim to provide a computer program product, the computer program product including a computer program / instruction, which, when executed by a processor, implements the method described in any of the preceding claims.

[0029] Fourthly, embodiments of the present invention aim to provide an electronic device, including a memory and a processor, wherein the memory is used to store one or more computer program instructions, wherein the one or more computer program instructions are executed by the processor to implement the method as described in any of the preceding claims.

[0030] Fifthly, embodiments of the present invention aim to provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the method described in any of the preceding claims.

[0031] The technical solution of this invention determines the anomaly recognition engine by performing multi-dimensional analysis of historical order information. Based on the order information of the order to be detected and the pre-trained anomaly recognition engine, the cause of the anomaly in the order to be detected is determined. This enables automated identification of the cause of anomalies in the order to be detected, improving the efficiency of identifying anomalies related to parking fee reductions. Furthermore, since the anomaly recognition engine is determined using multi-dimensional order information, the accuracy of the identified anomaly causes is improved. In addition, by executing an anomaly handling process according to the preset handling method corresponding to the anomaly cause, order reduction anomalies can be handled promptly, improving the efficiency of handling parking fee reduction anomalies, reducing negative impacts on users, and enhancing the user charging experience. Attached Figure Description

[0032] The above and other objects, features and advantages of the present invention will become clearer from the following description of embodiments of the invention with reference to the accompanying drawings, in which:

[0033] Figure 1 This is a schematic diagram of the reduction and exemption processing system according to an embodiment of the present invention;

[0034] Figure 2 This is a flowchart of the parking fee reduction exception handling method according to an embodiment of the present invention;

[0035] Figure 3 This is a flowchart of the training method for the anomaly detection engine according to an embodiment of the present invention;

[0036] Figure 4 This is a schematic diagram of multi-dimensional analysis according to an embodiment of the present invention;

[0037] Figure 5 This is a schematic diagram illustrating the determination of anomaly tags according to an embodiment of the present invention;

[0038] Figure 6 This is a schematic diagram of the exception handling method according to an embodiment of the present invention;

[0039] Figure 7 This is a schematic diagram of the parking fee reduction exception handling device according to an embodiment of the present invention;

[0040] Figure 8 This is a schematic diagram of an electronic device according to an embodiment of the present invention. Detailed Implementation

[0041] The present application is described below based on embodiments, but it is not limited to these embodiments. In the detailed description of the present application below, certain specific details are described in detail. Those skilled in the art can fully understand the present application without these details. To avoid obscuring the substance of the present application, well-known methods, processes, flows, elements, and circuits are not described in detail.

[0042] Furthermore, those skilled in the art should understand that the accompanying drawings provided herein are for illustrative purposes only and are not necessarily drawn to scale.

[0043] Unless the context explicitly requires it, words such as "including" or "contains" throughout the application should be interpreted as including rather than exclusive or exhaustive; that is, meaning "including but not limited to".

[0044] In the description of this application, it should be understood that the terms "first," "second," etc., are used for descriptive purposes only and should not be construed as indicating or implying relative importance. Furthermore, in the description of this application, unless otherwise stated, "a plurality of" means two or more.

[0045] The solutions described in this specification and embodiments, if involving information acquisition, will collect data under legal and compliant conditions, ensuring the legality of the data source, and will take appropriate technical and management measures to ensure data security. If involving personal information processing, processing will be carried out under legal grounds (e.g., obtaining the consent of the personal information subject, or being necessary for contract performance), and will only be conducted within the prescribed or agreed scope. A user's refusal to process personal information beyond what is necessary for basic functions will not affect the user's use of basic functions.

[0046] With the widespread application of new energy electric vehicles, offering parking fee reductions for these vehicles not only meets users' charging needs but also enhances the attractiveness of charging stations, thereby maximizing their resources. However, the parking fee reduction process involves multiple devices and stages, making it susceptible to various anomalies. Currently, only manual investigation is available to determine the cause, resulting in low efficiency. Furthermore, the inability to quickly address anomalies after identification leads to persistent issues until manual intervention, generating numerous user complaints and negative public opinion. Therefore, this invention aims to provide a method for handling parking fee reduction anomalies, improving both the efficiency of cause identification and resolution.

[0047] Figure 1 This is a schematic diagram of the reduction / exemption processing system according to an embodiment of the present invention. Figure 1 As shown in the diagram, the fee reduction / exemption system in this embodiment includes a charging management system 10, a linkage system 20, and a parking management system 30. The charging management system 10 manages charging equipment and provides charging services for vehicles. The parking management system 30 manages charging stations and their gate systems to meet users' parking needs while charging. The linkage system 20 connects the charging management system 10 and the parking management system 30, establishing communication connections between the terminal devices of the users of the charging vehicles, the parking management system 30, and the charging management system 10. It also enables information synchronization and data exchange services to provide users with more efficient parking and charging services.

[0048] Before a vehicle enters the charging station, the system prompts the user to bind vehicle information to the charging software (including charging apps, mini-programs, etc.) on their terminal device as the basis for parking fee reduction. When the vehicle enters the charging station, the parking management system 30 controls the gate system to identify the vehicle and opens the gate after recognizing the vehicle's license plate information (such as license plate identifier, i.e., license plate number), allowing the vehicle to enter the charging station. The charging management system 10 manages the charging equipment to charge the vehicle, generates vehicle charging information, and pushes the vehicle charging information to the linkage system 20. After the vehicle finishes charging, the user initiates a parking fee reduction request through the terminal device. After receiving the parking fee reduction request, the linkage system 20 sends the vehicle's charging information to the parking management system. Subsequently, when the vehicle leaves the charging station, the parking management system again identifies the vehicle's license plate and determines the actual parking fee to be paid based on the vehicle's charging information, the time the vehicle entered and exited the charging station, and the preset reduction method (i.e., the preset parking fee reduction strategy). Therefore, through the coordinated operation of the charging management system, the linkage system, and the parking management system, this embodiment can provide charging services to users and meet their vehicle charging needs, while also reducing parking fees for users based on vehicle charging record information, thereby improving the utilization rate of charging stations and the user's charging experience.

[0049] The following describes the parking fee reduction anomaly handling method in this embodiment, using the parking fee reduction anomaly situation in the aforementioned reduction and exemption management system as an example. However, it should be understood that the parking fee reduction anomaly handling method in this embodiment can also be applied to other types of reduction and exemption management systems. Furthermore, the parking fee reduction anomaly handling method in this embodiment can be configured to be executed within the linkage system or parking management system of the aforementioned reduction and exemption management system, or it can be executed using servers or other devices outside the reduction and exemption management system. There is no limitation on the executing entity of the parking fee reduction anomaly handling method.

[0050] Figure 2 This is a flowchart of the parking fee reduction exception handling method according to an embodiment of the present invention. Figure 2 As shown, this embodiment implements the handling of abnormal parking fee reduction situations through the following method.

[0051] In step S210, the order information of the order to be detected is obtained.

[0052] In this embodiment, the orders to be detected are charging orders where parking fee reductions have encountered anomalies. After each charging completion and a reduction request is initiated, the parking management system will report the reduction result for the corresponding charging order. When the reduction result indicates that the charging order's reduction has failed, the corresponding charging order is identified as an order to be detected, and its order information is obtained. Analysis of this order information is then used to determine the cause of the abnormal parking fee reduction for the detected order.

[0053] Optionally, the order information in this embodiment includes order identifier, user identifier, license plate information, gate information, charging station information, charging information, fee reduction / exemption policy information, fee reduction / exemption result, and / or complaint information. The order identifier is a unique identifier corresponding to the charging order. The user identifier is a unique identifier of the user to whom the vehicle belongs, i.e., the unique identifier of the user bound to the charging vehicle corresponding to the charging order. The license plate information includes the license plate identifier (i.e., license plate number) of the vehicle corresponding to the current charging order, other license plate identifiers corresponding to the user to whom the current vehicle belongs, and the number of other license plate identifiers corresponding to the user to whom the current vehicle belongs, etc. The gate information includes gate system attribute information (such as brand), operational information (such as the time the vehicle enters the charging station), and other information related to the gate system. The charging station information includes charging station attribute information (such as charging station identifier), service information (such as fee reduction / exemption policy information), and other information related to the charging station. The charging information includes charging status (such as charging capacity), charging duration, charging parameters (such as charging current, power, etc.), and other information related to the charging process. The fee reduction policy information refers to the configuration information for the fee reduction policy, such as charging for 15 minutes to reduce the parking fee for 2 hours. The reduction result is either successful or unsuccessful (including uncertain results). Complaint information refers to the content of complaints posted by users after failing to receive a parking fee reduction. Therefore, by obtaining order information from different dimensions, data support can be provided to subsequently determine the cause of abnormal parking fee reductions.

[0054] It should also be understood that the order information in this embodiment can be set according to the actual use scenario in order to better identify and handle abnormal causes in abnormal parking fee reduction situations. The example given here is only an example and does not limit the specific content of the order information.

[0055] In step S220, the cause of the anomaly in the order to be detected is determined based on the order information and the pre-trained anomaly recognition engine.

[0056] In this embodiment, the anomaly detection engine determines the anomaly by performing multi-dimensional analysis of the order information of historical orders. The historical orders are charging orders that occurred before the order to be detected and where the parking fee reduction was abnormal.

[0057] Figure 3 This is a flowchart of the training method for the anomaly detection engine according to an embodiment of the present invention. Figure 3 As shown in the figure, the anomaly detection engine is trained through the following steps in this embodiment.

[0058] In step S310, training samples are obtained.

[0059] In this embodiment, the training samples include multiple historical orders, which are charging orders that occurred before the order to be detected and where parking fee reductions were abnormal. Each historical order has corresponding order information and anomaly tags, which are determined through multi-dimensional analysis of the order information.

[0060] Optionally, in this embodiment, the anomaly identification model can be trained using only charging orders that failed to receive a discount, or it can be trained by combining charging orders that failed to receive a discount and charging orders that successfully received a discount, so that the anomaly identification model can subsequently identify the anomaly cause of the charging order that failed to receive a discount.

[0061] Optionally, to further improve the accuracy of identifying the causes of charging anomalies, this embodiment combines charging orders that failed to receive a reduction and charging orders that successfully received a reduction to train the anomaly identification model. The training samples include multiple historical orders that failed to receive a reduction and multiple original charging orders that successfully received a reduction. The historical orders are the original charging orders that failed to receive a reduction, and the original charging orders are the charging orders that occurred before the order to be detected.

[0062] Furthermore, in this embodiment, when acquiring training samples, multiple original charging orders that occurred before the order to be detected are first acquired; then, each original charging order is classified to determine multiple historical orders that failed to reduce the fee and original charging orders that successfully reduced the fee; then, through multi-dimensional analysis of multiple historical orders, complete abnormal cause types are classified; finally, based on the abnormal cause type, the order information of the historical orders that failed to reduce the fee, and the order information of the original charging orders that successfully reduced the fee, the abnormal label of each historical order is determined.

[0063] Optionally, to improve the reliability of training samples, the original charging orders in this embodiment are preprocessed charging orders. Preprocessing operations may include data cleaning, data filtering and / or data aggregation, which makes the obtained original charging orders more reliable and better able to meet the training needs of the anomaly detection engine. This is conducive to improving the training efficiency of the subsequent anomaly detection engine and ensuring the accuracy of the output results of the trained anomaly detection engine.

[0064] The following section details the processing steps at each stage of obtaining training samples.

[0065] Figure 4 This is a schematic diagram illustrating the multi-dimensional analysis of an embodiment of the present invention. For example... Figure 4As shown in the illustration, this embodiment first acquires order information from multiple original charging orders that occurred before the order to be detected, as supporting data. This order information includes order identifier, user identifier, license plate information, gate information, charging station information, charging information, fee reduction results, and complaint information. Then, based on the fee reduction status (feasibility or success) in the fee reduction results, each original charging order is categorized. Historical orders with failed fee reductions and other original orders with successful fee reductions are filtered out from all original orders, and these are then grouped together.

[0066] After identifying the historical orders for which the fee reduction failed, such as Figure 4 As shown in the figure, this embodiment first determines multiple dimensions related to charging orders through data analysis, including error codes, users, charging stations, gate systems, and charging orders. Then, it aggregates each historical order using error codes, users, charging stations, gate systems, and charging orders as aggregation factors to obtain order information for each dimension. Next, it analyzes the order information for each dimension to determine any abnormal situations that occur under that dimension. For example, abnormal situations under the error code dimension include system errors, network errors, and configuration errors; abnormal situations under the user dimension include no license plate or multiple license plates; and abnormal situations under the charging order dimension include charging failure due to disconnected charging guns, order cancellation, and other reasons. Finally, since there may be overlaps between the abnormal situations corresponding to different dimensions, the abnormal situations can be aggregated according to the actual abnormal causes. For example, if both the system abnormality under the abnormal code dimension and the barrier gate abnormality under the barrier gate system dimension are caused by barrier gate abnormality, the system abnormality and barrier gate abnormality can be aggregated into the situation corresponding to the abnormal cause of barrier gate abnormality. After such aggregation, the final abnormal cause type of parking fee reduction can be obtained, including license plate abnormality, barrier gate abnormality, strategy abnormality, charging abnormality, configuration abnormality and other abnormalities.

[0067] It should be noted that the exception codes in this embodiment are exception identification codes corresponding to some basic error information fed back by the gate system when parking fee reduction is abnormal. However, they cannot cover all abnormal situations and causes. Therefore, this embodiment will combine the exception codes and the order information of the charging order to analyze and determine a more comprehensive type of abnormal cause corresponding to the parking fee reduction.

[0068] Furthermore, after determining all the types of anomalies corresponding to each historical order, this embodiment uses, as follows: Figure 5 The method shown identifies the exception tags corresponding to each historical order. For example... Figure 5As shown, for historical orders with undetermined abnormal tags, this embodiment first uses data analysis methods to determine the abnormality rate of each historical order across various dimensions, including the user dimension, the barrier gate system dimension, and the charging station dimension, based on all historical orders and successfully reduced original charging orders from multiple original charging orders. Specifically, the user dimension abnormality rate represents the probability that a user's license plate abnormality causes a reduction abnormality, and can be represented by the ratio of the number of original charging orders with failed reductions corresponding to the same user to the total number of original charging orders. The barrier gate system dimension abnormality rate represents the probability that a reduction abnormality is caused by a barrier gate system abnormality, and can be represented by the ratio of the number of original charging orders with failed reductions corresponding to the same brand of barrier gate system to the total number of original charging orders. The charging station dimension abnormality rate represents the probability that a reduction abnormality is caused by a charging station abnormality, and can be represented by the ratio of the number of original charging orders with failed reductions corresponding to the same charging station to the total number of original charging orders.

[0069] After determining the anomaly rate of a historical order in different dimensions based on the order information corresponding to the historical order, this embodiment will determine the anomaly label based on the preset judgment strategy and the anomaly rate of the historical order in different dimensions.

[0070] Optionally, the preset judgment strategy in this embodiment can be determined based on a preset threshold corresponding to the anomaly rate of at least one dimension. The preset threshold can be an allowable anomaly rate value, and the same or different preset thresholds can be used for the anomaly rates of different dimensions. It should also be understood that the specific settings of the preset threshold and the preset judgment strategy in this embodiment can be determined according to the actual usage scenario; the examples given here are merely illustrative.

[0071] Furthermore, considering that different causes of anomalies may have varying degrees of impact on the entire user group, this embodiment uses different preset threshold values ​​for the anomaly rates of different dimensions. Additionally, when the preset judgment strategy includes anomaly judgments across multiple dimensions—that is, when the preset judgment strategy includes preset thresholds corresponding to the anomaly rates of multiple dimensions—this embodiment determines the anomaly label according to the relationship between the anomaly rate of each dimension and its corresponding preset threshold, as well as the priority order of each dimension.

[0072] For example, since the number of users affected by a charging station anomaly is greater than the number of users affected by a license plate anomaly, if the anomaly rate of the charging station dimension corresponding to the charging order is greater than the anomaly rate threshold of the charging station dimension, and the anomaly rate of the user dimension is greater than the anomaly rate threshold of the user dimension, this embodiment will determine that the cause of the anomaly of the charging order is closer to a charging station anomaly, and at this time the anomaly label of the charging order will be determined as a charging station anomaly.

[0073] For example, suppose the order information in historical order A indicates that historical order A was a charging order completed by user x at charging station #1. Among user x's a original charging orders, b are historical orders that failed to receive fee reductions (including historical order A). Among the m original charging orders completed at charging station #1, n are historical orders that failed to receive fee reductions (including historical order A). Therefore, based on the above information, we can determine that the anomaly rate of historical order A at the user level is (a / b), and the anomaly rate at the charging station level is (m / n).

[0074] Subsequently, when determining the anomaly label for historical order A, it is assumed that the preset judgment strategy is "when the anomaly rate in the charging station dimension is >50%, the anomaly rate in the user dimension is <10%, and the number of license plates bound to the user is <2, the anomaly label of the order is defined as charging station anomaly." Historical order A has an anomaly rate (m / n) of 75% in the charging station dimension and 2% in the user dimension, and user x has only one license plate bound to them. In this case, by comparing the anomaly rate of 75% in the charging station dimension and the anomaly rate of 2% in the user dimension with the corresponding thresholds of 50% and 10%, respectively, and comparing the number of license plates bound to user x (1) with the license plate threshold 2, it can be determined that historical order A meets the preset judgment strategy, thus determining the anomaly label of historical order A as charging station anomaly. Therefore, in this embodiment, the anomaly label can be determined by the anomaly rate of different dimensions corresponding to historical orders.

[0075] In step S320, a preset anomaly recognition model is trained based on training samples to determine the anomaly recognition engine.

[0076] In this embodiment, optionally, the anomaly recognition model can employ a language model, a neural network model, a Boolean model, a vector space model, a probabilistic model, or other types of models. After determining the order information and anomaly labels of each historical order in the training samples, the pre-defined anomaly recognition model is trained using a supervised learning method with the historical orders bearing the anomaly labels, thereby determining an anomaly recognition engine for identifying the cause of anomalies in the order to be detected.

[0077] Furthermore, in determining the cause of an anomaly in an order to be detected, this embodiment inputs the order information of the order to be detected into a pre-trained anomaly recognition engine for analysis to determine the cause of the anomaly in the order to be detected. The output of the anomaly recognition engine is the cause of the anomaly in the order to be detected.

[0078] Specifically, after inputting the order information of the order to be detected into a pre-trained anomaly detection engine, in one optional implementation, the anomaly detection engine is configured with feature parameters of the order information corresponding to different anomaly causes. By inputting the order information of the order to be detected into the anomaly detection engine, the engine extracts and processes the features of the order information, thereby outputting the anomaly cause of the order to be detected. In another optional implementation, the anomaly detection engine is configured with anomaly rates on different dimensions determined based on the order information of all original orders that occurred before the order to be detected, as well as a preset judgment strategy. After inputting the order information of the order to be detected into the anomaly detection engine, the engine first extracts the order information of the order to be detected in different dimensions, then determines the anomaly rate on the corresponding dimension based on the order information in different dimensions, and finally determines the anomaly label of the order to be detected based on the anomaly rate on each dimension and the preset judgment strategy, and outputs the anomaly cause corresponding to the anomaly label.

[0079] In step S230, the exception handling process is executed according to the preset handling method corresponding to the cause of the exception.

[0080] In this embodiment, after determining the cause of the abnormality of the order to be tested, in order to restore the user's parking fee reduction rights, the abnormality handling process will be executed according to the preset handling method corresponding to the cause of the abnormality.

[0081] Optionally, such as Figure 6 As shown in the figure, different handling methods are usually adopted for different types of abnormal causes to deal with parking fee reduction abnormalities. This can effectively handle parking fee reduction situations under different abnormal causes, thereby improving the efficiency of abnormal handling when different parking fee reduction abnormalities occur.

[0082] Furthermore, when the cause of the abnormality is an abnormal license plate, this embodiment can resolve the parking fee reduction problem caused by the abnormal license plate by modifying the license plate information (such as the license plate identifier, i.e., the license plate number) identified by the gate system when executing the parking fee reduction process, reminding the driver to reverse and re-trigger the parking fee reduction process, or other effective handling methods.

[0083] Optionally, when the license plate information identified by the gate system during the execution of the parking fee reduction process is modified, in this embodiment, in response to the abnormality cause being an abnormal license plate, the parking fee reduction is re-executed based on the set of license plates bound to the target user corresponding to the order to be detected. That is, the license plate information identified by the gate system is modified according to the set of license plates bound to the target user, and the parking fee reduction process is re-executed based on the modified license plate information, so that the user can successfully reduce the parking fee when meeting the parking fee reduction policy and enjoy the preferential service of parking fees generated by charging.

[0084] Specifically, when re-executing parking fee reduction based on the set of license plates bound to the target user corresponding to the order to be detected, in one optional implementation, this embodiment can directly use the license plate information corresponding to the license plate in the set as the modified license plate information to re-execute the parking fee reduction. This can overcome the problem of abnormal parking fee reduction caused by the user binding incorrect license plate information, thereby helping the user to quickly pass through the parking fee reduction process and successfully achieve parking fee reduction, thus improving the user's charging experience.

[0085] In another optional implementation, since the license plate information recognition process is prone to misidentifying license plate information as similar license plate information (for example, the character "C" in the license plate information is easily identified as "G"), this embodiment can also establish a modification strategy based on the correspondence between easily misidentified characters (such as C-G), and then modify the easily misidentified characters in the barrier gate system according to the modification strategy, and re-execute the parking fee reduction process based on the modified license plate information. Therefore, this embodiment provides different methods to modify license plate information, enabling the parking fee reduction process to be re-executed based on the modified license plate information, thereby overcoming the problem of abnormal parking fee reduction caused by abnormal license plates, helping users quickly pass the parking fee reduction process and successfully achieve parking fee reduction, thus improving the user's charging experience.

[0086] Furthermore, to facilitate users in successfully completing the parking fee reduction in one go, this embodiment will send a reminder message to the target user corresponding to the order to be tested after the license plate information is modified and the reduction is successful. This will remind the target user to modify the bound license plate information, preventing the user from triggering the parking fee reduction process again with the incorrectly bound license plate information. This will improve the execution efficiency of the parking fee reduction process and further enhance the user's charging experience.

[0087] Optionally, when the cause of the anomaly is a gate malfunction, since existing gate systems typically use image acquisition devices (such as cameras) to identify vehicle information to assist in the parking fee reduction process, gate malfunctions are mostly attributed to image acquisition device failures. In this case, after locating the cause of the anomaly as a gate malfunction, on-site personnel need to eliminate the fault. Therefore, in this embodiment, in response to the cause of the anomaly being a gate malfunction, maintenance information is sent to the maintenance personnel of the target charging station, which is the charging station that has completed the order to be tested. Thus, by sending maintenance information to the maintenance personnel of the corresponding target station when an anomaly occurs in the gate system, maintenance personnel can quickly troubleshoot the gate system, promptly understand the existing anomalies, and quickly resolve the anomalies, which helps improve the efficiency of handling gate anomalies, thereby timely and effectively resolving the user's parking fee reduction anomaly problem, helping users to successfully complete the parking fee reduction, and improving the user experience.

[0088] Optionally, when the cause of the error is charging failure, it is usually due to a delay in triggering the parking fee reduction, causing the reduction to fail. Therefore, in this embodiment, in response to the cause of the error being charging failure, the charging information of the order to be tested is re-pushed to perform the parking fee reduction based on the charging information. Thus, by re-pushing the charging information of the order to be tested after the parking fee reduction fails, the user can re-execute the parking fee reduction process based on the resent charging information, thereby compensating for the failure to complete the parking fee reduction due to the delay in charging information transmission, helping the user to successfully complete the parking fee reduction, and thus improving the user experience.

[0089] Optionally, for parking fee reductions caused by reasons other than those mentioned above, this embodiment also has corresponding preset handling methods. For example, when the reason for the abnormality is a policy abnormality (e.g., there are no charging orders that meet the reduction policy), this embodiment will modify the reduction policy. For example, the charging limit duration, parking fee reduction amount, and / or reduction duration in the reduction policy can be modified according to the distribution of charging duration and parking duration in the original charging order to ensure that a reasonable number of charging users can meet the requirements of the reduction policy and improve the user charging experience. Furthermore, for some abnormal problems that cannot be overcome by the self-repair of on-site equipment, such as network abnormalities, the corresponding handling method can be set to send a prompt message to relevant staff to prompt them to promptly investigate and resolve the problem, thereby providing users with better charging and parking fee reduction services.

[0090] Furthermore, after executing the abnormal handling process according to the preset handling method corresponding to the abnormal cause, in order to further improve the performance of the charging parking fee reduction service, this embodiment will also record the abnormal cause (i.e., the actual abnormal cause) and handling method (i.e., the actual handling method) corresponding to the successful reduction after the abnormal handling process is completed and the execution result is successful parking fee reduction, so as to optimize the abnormal cause identification and handling method based on the recorded abnormal cause and handling method.

[0091] Correspondingly, the anomaly handling method in this embodiment further includes: in response to the order to be detected successfully reducing the parking fee after executing the anomaly handling process, obtaining reference information, including the actual anomaly cause and / or actual handling method corresponding to the successful reduction; and updating the anomaly identification engine and / or preset handling method according to the reference information. Therefore, by recording the actual anomaly cause and actual handling method corresponding to the order to be detected successfully reducing the parking fee after executing the anomaly handling process, and updating the anomaly identification engine and the preset handling method corresponding to the anomaly cause based on the actual anomaly cause and actual handling method, the anomaly cause and corresponding handling method can cover more anomaly situations of parking fee reduction failure, thereby further improving the accuracy of anomaly cause identification and the efficiency of handling parking fee reduction anomalies. Simultaneously, after a certain number of updates, the anomaly causes and corresponding handling methods that can be identified in this embodiment will gradually converge to a limited number of types while continuously enriching the existing ones, thereby making the anomaly identification engine more accurate in identifying anomaly causes and the anomaly handling method more efficient, providing users with a better charging and parking experience.

[0092] The technical solution of this embodiment determines the anomaly identification engine by performing multi-dimensional analysis of historical order information. Based on the order information of the order to be detected and the pre-trained anomaly identification engine, the cause of the anomaly in the order to be detected is determined. This overcomes the drawback of relying solely on manual investigation of anomalies, achieving automated identification of the cause of anomalies in the order to be detected and improving the efficiency of identifying anomalies related to parking fee reductions. Furthermore, since the anomaly identification engine is determined using multi-dimensional order information, the accuracy of anomaly identification is improved. In addition, by executing an anomaly handling process according to the preset handling method corresponding to the anomaly cause, order reduction anomalies can be handled promptly, improving the efficiency of handling parking fee reduction anomalies, reducing the probability of parking fee reduction anomalies and the negative impact on users, improving the user charging experience, and reducing complaints and public opinion arising from the inability to receive parking fee reductions.

[0093] Figure 7 This is a schematic diagram of the parking fee reduction exception handling device according to an embodiment of the present invention. Figure 7 As shown, the parking fee reduction anomaly handling device in this embodiment includes an acquisition unit 1, an analysis unit 2, and a processing unit 3. The acquisition unit 1 acquires the order information of the order to be detected, which is a charging order where the parking fee reduction anomaly occurred. The analysis unit 2 determines the cause of the anomaly in the order to be detected based on the order information and a pre-trained anomaly recognition engine. The anomaly recognition engine determines this by performing multi-dimensional analysis of historical order information, where historical orders are charging orders where the parking fee reduction anomaly occurred before the order to be detected. The processing unit 3 executes the anomaly handling process according to the preset processing method corresponding to the anomaly cause.

[0094] Optionally, the order information in this embodiment includes order identifier, user identifier, license plate information, gate information, charging station information, charging information, fee reduction / exemption policy information, and / or complaint information. The reasons for the anomalies include license plate anomalies, gate anomalies, charging anomalies, configuration anomalies, network anomalies, and / or fee reduction / exemption policy anomalies.

[0095] Optionally, the analysis unit 2 in this embodiment is further used to train and determine the anomaly recognition engine. Specifically, it is used to acquire training samples, which include multiple historical orders, and to train a preset anomaly recognition model based on the training samples to determine the anomaly recognition engine. Each historical order has corresponding order information and anomaly tags, and the anomaly tags are determined through multi-dimensional analysis of the order information.

[0096] Furthermore, in this embodiment, the analysis unit 2 is also used to, in response to the order to be detected successfully reducing the fee after executing the exception handling process, obtain reference information and update the exception identification engine and / or the preset handling method based on the reference information. The reference information includes the actual exception cause and / or the actual handling method corresponding to the successful fee reduction.

[0097] Optionally, in this embodiment, when the processing unit 3 executes the abnormal handling process according to the preset processing method corresponding to the abnormal cause, it is also used to respond to the abnormal cause being a license plate abnormality by re-executing the parking fee reduction based on the set of license plates bound to the target user corresponding to the order to be tested, and sending a reminder message to the target user corresponding to the order to be tested to remind the target user to modify the bound license plate information; responding to the abnormal cause being a gate abnormality by sending maintenance information to the maintenance personnel of the target station, the target station being the charging station that completed the order to be tested; and responding to the abnormal cause being a charging abnormality by re-pushing the charging information of the order to be tested to execute the parking fee reduction based on the charging information.

[0098] The technical solution of this embodiment uses an analysis unit to perform multi-dimensional analysis of historical order information to determine an anomaly identification engine. Based on the order information of the order to be detected and the pre-trained anomaly identification engine, the cause of the anomaly in the order to be detected is determined. This enables automated identification of the cause of anomalies in the order to be detected, improving the efficiency of identifying anomalies when parking fee reductions are abnormal. Furthermore, since the anomaly identification engine is determined using multi-dimensional order information, the accuracy of anomaly cause identification is improved. In addition, the handling unit executes an anomaly handling process according to the preset handling method corresponding to the anomaly cause, enabling timely handling of charging orders with abnormal fee reductions, improving the efficiency of handling abnormal parking fee reductions, reducing negative impacts on users, and enhancing the user charging experience.

[0099] Figure 8 This is a schematic diagram of an electronic device according to an embodiment of the present invention. (For example...) Figure 8 As shown, Figure 8 The illustrated electronic device is a general-purpose data processing device, comprising a general-purpose computer hardware architecture, including at least a processor 81 and a memory 82. The processor 81 and memory 82 are connected via a bus 83. The memory 82 is adapted to store instructions or programs executable by the processor 81. The processor 81 can be a standalone microprocessor or a collection of one or more microprocessors. Thus, the processor 81 executes the instructions stored in the memory 82, thereby performing the method flow of the embodiments of the present invention as described above to process data and control other devices. The bus 83 connects the aforementioned components together, and also connects these components to a display controller 84, a display device, and an input / output (I / O) device 85. The input / output (I / O) device 85 can be a mouse, keyboard, modem, network interface, touch input device, motion-sensing input device, printer, and other devices known in the art. Typically, the input / output device 85 is connected to the system via an input / output (I / O) controller 86.

[0100] Those skilled in the art will understand that embodiments of this application can be provided as methods, apparatus (devices), or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-readable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0101] This application is described with reference to flowchart illustrations of methods, apparatus (devices), and computer program products according to embodiments of this application. It should be understood that each step in the flowchart can be implemented by computer program instructions.

[0102] These computer program instructions may be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including an instruction means, the implementation process of which is described in the instruction means. Figure 1 The function specified in one or more processes.

[0103] These computer program instructions may also be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing device to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing device, produce instructions for implementing processes. Figure 1 A device for a function specified in one or more processes.

[0104] Another embodiment of the present invention relates to a non-volatile storage medium for storing a computer-readable program for use by a computer to execute some or all of the above-described method embodiments.

[0105] That is, those skilled in the art will understand that all or part of the steps in the methods of the above embodiments can be implemented by a program specifying the relevant hardware. This program is stored in a storage medium and includes several instructions to cause a device (which may be a microcontroller, chip, etc.) or processor to execute all or part of the steps of the methods described in the embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, a portable hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0106] The above description is merely a preferred embodiment of this application and is not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A method for handling abnormal parking fee reductions, characterized in that, The method includes: Obtain the order information of the orders to be tested, which are charging orders where parking fee reductions have anomalies; Based on the order information and the pre-trained anomaly detection engine, the cause of the anomaly in the order to be detected is determined. The anomaly detection engine determines this by performing multi-dimensional analysis on the order information of historical orders, which are charging orders that occurred before the order to be detected and had anomalies in parking fee reductions. The exception handling process is executed according to the preset handling method corresponding to the cause of the exception.

2. The method according to claim 1, characterized in that, The anomaly detection engine determines this through the following method: Obtain training samples, which include multiple historical orders. Each historical order has corresponding order information and anomaly tags. The anomaly tags are determined by multi-dimensional analysis of the order information. The preset anomaly recognition model is trained based on the training samples to determine the anomaly recognition engine.

3. The method according to claim 1, characterized in that, The method further includes: In response to the order to be tested successfully reducing the fee after executing the abnormal handling process, reference information is obtained, including the actual abnormal reason and / or actual handling method corresponding to the successful reduction; The anomaly detection engine and / or the preset handling method are updated based on the reference information.

4. The method according to claim 1, characterized in that, The order information includes order identifier, user identifier, license plate information, gate information, charging station information, charging information, fee reduction / exemption policy information, and / or complaint information.

5. The method according to claim 1, characterized in that, The reasons for the anomalies include license plate anomalies, gate anomalies, charging anomalies, configuration anomalies, network anomalies, and / or reduction / exemption policy anomalies.

6. The method according to claim 1, characterized in that, The step of executing the exception handling process according to the preset handling method corresponding to the exception cause includes: In response to the reason for the anomaly being an abnormal license plate, the parking fee reduction is re-executed based on the set of license plates bound to the target user corresponding to the order to be detected; A reminder message is sent to the target user corresponding to the order to be tested, so as to remind the target user to modify the bound license plate information.

7. The method according to claim 1, characterized in that, The step of executing the exception handling process according to the preset handling method corresponding to the exception cause includes: In response to the abnormality being due to a gate malfunction, maintenance information is sent to the operation and maintenance personnel at the target site, which is the charging station that completed the order to be tested.

8. The method according to claim 1, characterized in that, The step of executing the exception handling process according to the preset handling method corresponding to the exception cause includes: In response to the fact that the cause of the abnormality is a charging abnormality, the charging information of the order to be tested is re-pushed so as to perform parking fee reduction based on the charging information.

9. A device for handling abnormal parking fee reductions, characterized in that, The device includes: The acquisition unit is used to acquire the order information of the order to be detected, wherein the order to be detected is the charging order where the parking fee reduction has an anomaly; The analysis unit is used to determine the cause of the anomaly of the order to be detected based on the order information and a pre-trained anomaly recognition engine. The anomaly recognition engine determines the cause by performing multi-dimensional analysis on the order information of historical orders, which are charging orders that occurred before the order to be detected and had anomalies in parking fee reductions. The handling unit is used to execute the abnormal handling process according to the preset handling method corresponding to the abnormal cause.

10. A computer program product, characterized in that, The computer program product includes a computer program / instruction that, when executed by a processor, implements the method of any one of claims 1-8.

11. An electronic device comprising a memory and a processor, characterized in that, The memory is used to store one or more computer program instructions, wherein the one or more computer program instructions are executed by the processor to implement the method of any one of claims 1-8.

12. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the method of any one of claims 1-8.

Images