A vehicle rental data correction method and system based on intelligent AI

Abstract

The present application provides a method and system for correcting vehicle rental data based on intelligent AI. Among them, at least two vehicle rental records from different data sources are obtained, each record contains multiple rental events; the rental events in each record are analyzed using intelligent AI to identify potential data anomalies; based on the data anomalies, the authenticity and accuracy of each rental event are determined through a multi-factor verification algorithm; based on the authenticity and accuracy, the data anomalies in the at least two vehicle rental records from different data sources are adjusted to ensure data consistency. The technical solution provided by the present application can improve the efficiency of correcting abnormal data and improve the accuracy and consistency of vehicle rental record data.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of data processing technology, and in particular to a vehicle rental data correction method and system based on intelligent AI. Background Art

[0002] With the rapid development of the sharing economy, vehicle rental business is becoming increasingly popular. In order to better manage the huge amount of rental data, companies need to obtain detailed rental records from multiple data sources (such as different vehicle rental platforms, GPS tracking systems, etc.). These records contain specific information about each rental event, such as rental time, return time, mileage, etc. In order to ensure the integrity and consistency of this data, a technical solution that can automatically identify and correct data anomalies is needed.

[0003] Currently, most vehicle rental companies rely on manual review to check for errors or anomalies in rental records. In addition, some companies have begun to try to use basic data cleaning tools to automate some processes. However, these methods mainly focus on anomaly detection on a single data source and lack an effective processing mechanism for data consistency across data sources. At the same time, existing automated tools can often only identify predefined types of errors, and have limited recognition capabilities for complex data anomalies, especially those caused by systemic errors. Manual review is time-consuming and labor-intensive, easily affected by subjective judgment, and unable to detect and correct anomalies in the data in a timely manner. Although existing automated tools have improved efficiency, they are unable to meet the requirements of data consistency when faced with data integration across data sources. In addition, due to the lack of advanced intelligent analysis functions, these tools perform poorly when dealing with unforeseen data anomalies, resulting in data quality issues that cannot be fundamentally resolved.

[0004] In summary, existing data management and anomaly detection solutions have obvious shortcomings when facing complex, multi-source data environments, and a more efficient and intelligent solution is urgently needed. Summary of the invention

[0005] The embodiments of the present application provide a method and system for correcting vehicle rental data based on intelligent AI, so as to solve the problem of poor efficiency in correcting data anomalies in the prior art.

[0006] In a first aspect, an embodiment of the present application provides a vehicle rental data correction method based on intelligent AI, comprising:

[0007] Obtain at least two vehicle rental records from different data sources, each record containing multiple rental events;

[0008] Use intelligent AI to analyze rental events in each record and identify potential data anomalies;

[0009] Based on the data anomalies, determine the authenticity and accuracy of each rental event through a multi-factor verification algorithm;

[0010] According to the authenticity and the accuracy, the data anomalies in the at least two vehicle rental records from different data sources are adjusted to ensure data consistency.

[0011] Optionally, the utilizing of intelligent AI to analyze the rental events in each record includes:

[0012] Analyze the rental events in each record using a pre-configured AI model trained using multiple data validation strategies;

[0013] According to the analysis results of the AI ​​model, abnormal rental events are marked, and the abnormal probability score of each rental event is calculated.

[0014] Optionally, the determining the authenticity and accuracy of each rental event through a multi-factor verification algorithm based on the data anomaly includes:

[0015] Based on the data anomaly, and in combination with the geolocation information factor, timestamp factor, and vehicle status factor obtained in the rental event, the authenticity score of each rental event is calculated through a multi-factor verification algorithm;

[0016] Based on the authenticity score, the accuracy of the rental event is evaluated and a correction suggestion is generated.

[0017] Optionally, the authenticity score is determined by the following formula:

[0018]

[0019] in, represents the authenticity score; Indicates The weight coefficient of each factor; Indicates the first The degree of consistency between each factor and historical data; represents the number of factors in the rental event; represents the abnormal probability score; and is the coefficient that adjusts the degree of influence of authenticity and abnormal probability scores; Indicates The weight coefficient of external influencing factors; Indicates The degree of influence of external factors on the leasing event; Indicates the number of external influencing factors; It is the coefficient that adjusts the degree of influence of external influencing factors.

[0020] Optionally, adjusting the data anomalies in the at least two vehicle rental records from different data sources according to the authenticity and the accuracy includes:

[0021] Define a correction function;

[0022] Based on the correction function and the authenticity score and the anomaly probability score of each rental event, adjusting the data anomalies in the at least two vehicle rental records from different data sources;

[0023] Among them, the correction function for:

[0024]

[0025] in, Indicates the correction value; represents the observed rental event value; represents the reference value, i.e., the average value of normal leasing events in historical data; represents the authenticity score; represents the abnormal probability score; is a small positive number used to prevent division by zero errors; is the coefficient that adjusts the influence of the abnormal probability score; Indicates The adjustment coefficient of the external influencing factors on the correction value; Indicates The degree of influence of external factors on the leasing event; It is the coefficient that adjusts the influence of external factors on the correction value;

[0026] The abnormal probability score is determined by the following formula:

[0027]

[0028] in, Indicates The anomaly probability calculated by a data validation strategy; Indicates The reliability weight of each data verification strategy; Indicates the number of data validation strategies used.

[0029] Optionally, it also includes:

[0030] Determining the consistency of the vehicle state corresponding to the vehicle state factor;

[0031] Based on the vehicle state consistency, adjusting the authenticity score or adjusting the correction function;

[0032] The vehicle state consistency is determined by the following formula:

[0033]

[0034] in, Indicates vehicle state consistency; Indicates The actual status of the rental event; Indicates The expected status of each leasing event based on historical data analysis; and Respectively represent the maximum and minimum values ​​of the state; Indicates the number of rental events; It is the coefficient that adjusts the degree of influence of external influencing factors; Indicates The weight coefficient of external influencing factors; Indicates The influence degree of external influencing factors on the vehicle state consistency.

[0035] Optionally, adjusting the authenticity score or adjusting the correction function based on the vehicle state consistency includes:

[0036] The adjusted authenticity score is determined by the following formula:

[0037]

[0038] in, represents the adjusted authenticity score, The coefficient that represents the influence degree of adjusting vehicle state consistency, Indicates vehicle state consistency;

[0039] The adjusted correction function is determined by the following formula:

[0040]

[0041] in, represents the adjusted correction function, The coefficient that represents the influence degree of adjusting vehicle state consistency, Indicates vehicle status consistency.

[0042] In a second aspect, an embodiment of the present application provides a vehicle rental data correction system based on intelligent AI, comprising:

[0043] An acquisition module, used for acquiring at least two vehicle rental records from different data sources, each record containing multiple rental events;

[0044] The recognition module is used to analyze the rental events in each record using intelligent AI to identify potential data anomalies;

[0045] A determination module, used to determine the authenticity and accuracy of each rental event through a multi-factor verification algorithm based on the data anomaly items;

[0046] An adjustment module, configured to adjust the data anomalies in the at least two vehicle rental records from different data sources according to the authenticity and the accuracy, so as to ensure the consistency of the data;

[0047] The determination module is specifically used to calculate the authenticity score of each rental event through a multi-factor verification algorithm based on the data anomaly items and in combination with the geolocation information factors, timestamp factors, and vehicle status factors obtained in the rental event; based on the authenticity score, evaluate the accuracy of the rental event and generate correction suggestions.

[0048] In a third aspect, an embodiment of the present application provides a computing device, comprising a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement a vehicle rental data correction method based on intelligent AI as described in any one of the first aspects.

[0049] In a fourth aspect, an embodiment of the present application provides a computer storage medium storing a computer program. When the computer program is executed by a computer, it implements a vehicle rental data correction method based on intelligent AI as described in any one of the first aspects.

[0050] In an embodiment of the present application, at least two vehicle rental records from different data sources are obtained, each record containing multiple rental events; intelligent AI is used to analyze the rental events in each record to identify potential data anomalies; based on the data anomalies, the authenticity and accuracy of each rental event are determined through a multi-factor verification algorithm; based on the authenticity and accuracy, the data anomalies in the at least two vehicle rental records from different data sources are adjusted to ensure data consistency. The technical solution provided by the present application can improve the efficiency of correcting abnormal data and improve the accuracy and consistency of vehicle rental record data.

[0051] These and other aspects of the present application will become more clearly understood in the description of the following embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0053] Figure 1 A flowchart of a vehicle rental data correction method based on intelligent AI provided in an embodiment of the present application;

[0054] Figure 2 A schematic diagram of the structure of a vehicle rental data correction system based on intelligent AI provided in an embodiment of the present application;

[0055] Figure 3 A schematic diagram of the structure of a computing device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0056] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application.

[0057] In some of the processes described in the specification and claims of this application and the above-mentioned figures, multiple operations that appear in a specific order are included, but it should be clearly understood that these operations may not be executed in the order in which they appear in this article or executed in parallel. The serial numbers of the operations, such as 101, 102, etc., are only used to distinguish between different operations, and the serial numbers themselves do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions of "first", "second", etc. in this article are used to distinguish different messages, devices, modules, etc., do not represent the order of precedence, and do not limit the "first" and "second" to be different types.

[0058] 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.

[0059] Figure 1 A flowchart of a vehicle rental data correction method based on intelligent AI is provided for an embodiment of the present application, such as Figure 1 As shown, the method includes:

[0060] 101. Obtain at least two vehicle rental records from different data sources, each record containing multiple rental events;

[0061] In this step, obtaining at least two vehicle rental records from different data sources means collecting data from two or more independent sources. These data sources can be databases of different vehicle rental companies, vehicle GPS tracking system records, third-party payment platform transaction records, etc. Each record contains multiple rental events, which means that each data record represents a specific rental behavior, such as a car being rented out at a certain time and returned at a later time.

[0062] In this application example, we assume that there are two data sources: one is the internal database of a car rental company (System A), and the other is the company's partner, a third-party platform that provides vehicle location tracking services (System B). These two systems each store relevant information about vehicle rentals. In order to ensure the comprehensiveness and consistency of the data, we will obtain all rental records within a specified time period from System A, and also obtain records of vehicle usage within the same time period from System B.

[0063] The specific embodiments are as follows:

[0064] System A data source example:

[0065] Lease ID: 001;

[0066] Vehicle ID: 12345;

[0067] Lease time: 2024-09-01 08:00 AM;

[0068] Return time: 2024-09-01 06:00 PM;

[0069] Rental location: Central Station Branch;

[0070] System B data source example:

[0071] Vehicle ID: 12345;

[0072] GPS recorded time: 2024-09-01 08:05 AM;

[0073] GPS location: Central Station, City;

[0074] Next recorded time: 2024-09-01 06:03 PM;

[0075] In this process, we may also encounter some professional terms, such as GPS (Global Positioning System, GPS), which is a global positioning system used to determine the precise coordinates of any location on the earth. By obtaining information from these two different data sources, we can proceed to the next step of data analysis and anomaly detection.

[0076] 102. Use intelligent AI to analyze rental events in each record and identify potential data anomalies;

[0077] Optionally, the use of intelligent AI to analyze the rental events in each record in step 102 includes: using a pre-configured AI model to analyze the rental events in each record, the AI ​​model being trained using multiple data verification strategies; marking abnormal rental events based on the analysis results of the AI ​​model, and calculating the abnormal probability score of each rental event.

[0078] In this step, using intelligent AI to analyze the rental events in each record refers to using artificial intelligence technology to analyze vehicle rental records obtained from different data sources in order to identify abnormal data that may exist. The "intelligent AI" mentioned here usually refers to trained machine learning models or deep learning networks that can predict the behavior or characteristics of new unknown data based on existing data patterns. "Data anomalies" refer to data points that do not conform to normal patterns, which may be caused by input errors, system failures, or other abnormal reasons.

[0079] Explain the concepts involved in the above steps:

[0080] Pre-configured AI model: refers to a machine learning model that has been trained. It can be a supervised learning, unsupervised learning, or semi-supervised learning model, which is used to detect anomalies in data. A variety of data validation strategies are used during model training, such as cross-validation (CV), K-fold cross-validation (KFCV), and other methods to ensure the generalization ability and accuracy of the model.

[0081] Multiple data validation strategies: refers to different technical means used to evaluate model performance, such as dividing the data set into training sets, validation sets, and test sets, so as to continuously optimize model parameters during training while preventing overfitting.

[0082] Anomaly Probability Score: refers to a set of numerical values ​​that indicate the degree of deviation of each rental event from normal behavior. The higher the score, the more likely the event is abnormal.

[0083] In the embodiments of this application, we assume that a deep learning-based anomaly detection model has been trained, and the model uses a variety of data verification strategies for training. The following is a specific embodiment:

[0084] Data preprocessing: First, the vehicle rental records obtained from different data sources are cleaned and formatted to ensure data standardization and consistency. For example, all timestamps are converted to a unified time format.

[0085] Feature Engineering: Extract key features of each rental record, such as rental time, return time, rental location, etc. These features will be used as input to the model.

[0086] Model application: The extracted features are fed into a pre-configured AI model, which is a deep neural network that has been trained on a large number of rental records and can identify common abnormal patterns.

[0087] Anomaly Detection: The model outputs an anomaly probability score for each rental event. For example, for a record, the model may output the following results:

[0088] Lease ID: 001

[0089] Abnormal probability score: 0.85 (indicates that there is an 85% probability that this record is abnormal)

[0090] Mark anomalies: Based on the set threshold (for example, anomaly probability score greater than 0.7), mark rental events that may be abnormal. For the record in the above example, since its anomaly probability score is 0.85, which exceeds the set threshold, it will be marked as a potential abnormal rental event.

[0091] In this way, we can use intelligent AI to effectively identify anomalies in the data and provide a basis for further data cleaning and consistency verification.

[0092] 103. Based on the data anomalies, determine the authenticity and accuracy of each rental event through a multi-factor verification algorithm;

[0093] Optionally, the authenticity and accuracy of each rental event is determined based on the data anomaly items through a multi-factor verification algorithm in step 103, including: based on the data anomaly items and in combination with the acquired geolocation information factors, timestamp factors, and vehicle status factors in the rental event, the authenticity score of each rental event is calculated through a multi-factor verification algorithm; based on the authenticity score, the accuracy of the rental event is evaluated and correction suggestions are generated.

[0094] The authenticity score is determined by the following formula:

[0095]

[0096] in, represents the authenticity score; Indicates The weight coefficient of each factor; Indicates the first The degree of consistency between each factor and historical data; represents the number of factors in the rental event; represents the abnormal probability score; and is the coefficient that adjusts the degree of influence of authenticity and abnormal probability scores; Indicates The weight coefficient of external influencing factors; Indicates The degree of influence of external factors on the leasing event; Indicates the number of external influencing factors; It is the coefficient that adjusts the degree of influence of external influencing factors.

[0097] In this step, based on the data anomalies, and in combination with the geolocation information factors, timestamp factors, and vehicle status factors in the rental events obtained, the authenticity score of each rental event is calculated through a multi-factor verification algorithm. The "multi-factor verification algorithm" here refers to combining information from multiple dimensions to comprehensively evaluate the authenticity and accuracy of each rental event. In this way, the credibility of the data can be more comprehensively understood, so that more accurate data correction suggestions can be made.

[0098] Specifically, the authenticity score is determined by the following formula:

[0099]

[0100] in, represents the authenticity score; Indicates The weight coefficient of each factor; Indicates the first The degree of consistency between each factor and historical data; represents the number of factors in the rental event; represents the abnormal probability score; and is the coefficient that adjusts the degree of influence of authenticity and abnormal probability scores; Indicates The weight coefficient of external influencing factors; Indicates The degree of influence of external factors on the leasing event; Indicates the number of external influencing factors; It is the coefficient that adjusts the degree of influence of external influencing factors.

[0101] In the embodiment of this application, we assume that there is a specific rental event whose authenticity and accuracy need to be evaluated. The specific embodiment is as follows:

[0102] Data preparation: We obtained a rental record from different data sources, recording information such as rental time, return time, and rental location, and have marked the abnormal probability score through the intelligent AI model .

[0103] Factor Analysis:

[0104] Geolocation information factor: Check whether the actual vehicle return location is consistent with the recorded location.

[0105] Timestamp factor: Check whether the rental time and return time are reasonable and whether there are any logical errors in time.

[0106] Vehicle status factors: Check whether the vehicle status data during the rental period, such as mileage, fuel consumption, etc., are in line with expectations.

[0107] Empowerment Rating:

[0108] Set the weight coefficient for each factor , for example, geolocation information , timestamp factor , vehicle status factors .

[0109] Calculate the degree of consistency of each factor with historical data , for example, geolocation information , timestamp factor , vehicle status factors .

[0110] Setting the anomaly probability score .

[0111] Consider external factors , such as weather conditions , traffic conditions , assuming that weather conditions affect the event , the impact of traffic conditions on the incident .

[0112] Calculate the authenticity score:

[0113] Setting the adjustment factor .

[0114] Substituting the above values ​​into the formula:

[0115]

[0116] Evaluation and correction suggestions: Based on the calculated authenticity score , the accuracy of the rental event is assessed to be low. Based on this assessment result, corresponding correction suggestions are generated, such as further verification of geolocation information, recalibration of timestamps, etc., to ensure the consistency and accuracy of the data.

[0117] Through the above steps, the authenticity and accuracy of each rental event can be effectively evaluated, and specific corrective measures can be proposed accordingly to improve the overall quality of the data.

[0118] 104. According to the authenticity and the accuracy, adjust the data anomalies in the at least two vehicle rental records from different data sources to ensure data consistency.

[0119] Optionally, the step 104 of adjusting the data anomalies in the at least two vehicle rental records from different data sources according to the authenticity and the accuracy includes: defining a correction function; adjusting the data anomalies in the at least two vehicle rental records from different data sources based on the correction function and the authenticity score and the anomaly probability score of each rental event;

[0120] Among them, the correction function for:

[0121]

[0122] in, Indicates the correction value; represents the observed rental event value; represents the reference value, i.e., the average value of normal leasing events in historical data; represents the authenticity score; represents the abnormal probability score; is a small positive number used to prevent division by zero errors; is the coefficient that adjusts the influence of the abnormal probability score; Indicates The adjustment coefficient of the external influencing factors on the correction value; Indicates The degree of influence of external factors on the leasing event; It is the coefficient that adjusts the influence of external factors on the correction value; Indicates the number of external influencing factors;

[0123] The abnormal probability score is determined by the following formula:

[0124]

[0125] in, Indicates The anomaly probability calculated by a data validation strategy; Indicates The reliability weight of each data verification strategy; Indicates the number of data validation strategies used.

[0126] In this step, a correction function needs to be defined, and based on the correction function and the authenticity score and anomaly probability score of each rental event, the data anomalies in at least two vehicle rental records from different data sources are adjusted to ensure data consistency. This process aims to quantify and correct anomalies in the data through mathematical models, thereby improving data quality.

[0127] Correction function : This is a mathematical expression used to adjust for data anomalies, which determines how to correct the data based on truthfulness and accuracy.

[0128] Observed rent event value : This refers to the actual rental record value obtained from different data sources.

[0129] Reference value : The average value of normal rental events in historical data, used as a comparison benchmark.

[0130] Authenticity score : Reflects a comprehensive evaluation of the authenticity and accuracy of the leasing event.

[0131] Abnormal Probability Score : Reflects the possibility of abnormality in leasing events.

[0132] Small positive number : Used to prevent division by zero errors and ensure stability during formula calculations.

[0133] Adjustment coefficient : Used to adjust the impact of the abnormal probability score on the correction value.

[0134] Adjustment coefficient of external influencing factors : Reflects the influence of different external factors on the correction value.

[0135] The degree of influence of external factors : Indicates the impact of external factors on leasing events.

[0136] Coefficient for adjusting the degree of influence of external influencing factors : Used to adjust the influence of external factors on the correction value.

[0137] In the embodiment of this application, it is assumed that we have rental records from two data sources, and we need to adjust the data anomalies according to authenticity and accuracy. The specific embodiment is as follows:

[0138] Data preparation:

[0139] Get a rental record from two data sources, including rental time, return time, mileage, and other information.

[0140] Define the correction function :

[0141]

[0142] in, is the actual observed rental event value, for example, the actual mileage is 200 kilometers; As a reference value, it is assumed that the average normal mileage in historical data is 150 kilometers; is the authenticity score, assumed to be 0.364; The value is 0.001; The value is 0.5; is the abnormal probability score, assumed to be 0.8; The value is 0.2; is the number of external influencing factors, assumed to be 2; is the adjustment coefficient of external influencing factors, which are assumed to be 0.5 and 0.5 respectively; is the influence degree of external influencing factors, which are assumed to be 0.1 and 0.2 respectively;

[0143] Calculate correction value :

[0144]

[0145] Adjust data anomalies:

[0146] Based on the calculated correction value , the abnormal data in the original record can be adjusted. For example, if the actual mileage is 200 kilometers, it can be adjusted to 150 kilometers + 129.223 kilometers according to the correction value Of course, in practical applications, the actual significance of the correction value needs to be adjusted according to specific circumstances.

[0147] Through the above steps, anomalies in the data can be adjusted based on authenticity and accuracy to ensure the consistency and accuracy of the data, thereby improving the overall data quality.

[0148] Optionally, the method further comprises:

[0149] Determining the consistency of the vehicle state corresponding to the vehicle state factor;

[0150] Based on the vehicle state consistency, adjusting the authenticity score or adjusting the correction function;

[0151] The vehicle state consistency is determined by the following formula:

[0152]

[0153] in, Indicates vehicle state consistency; Indicates The actual status of the rental event; Indicates The expected status of each leasing event based on historical data analysis; and Respectively represent the maximum and minimum values ​​of the state; Indicates the number of rental events; It is the coefficient that adjusts the influence of external factors; Indicates The weight coefficient of external influencing factors; Indicates The degree of influence of external factors on vehicle state consistency; Represents the number of external influencing factors.

[0154] Wherein, adjusting the authenticity score or adjusting the correction function based on the vehicle state consistency includes:

[0155] The adjusted authenticity score is determined by the following formula:

[0156]

[0157] in, represents the adjusted authenticity score, The coefficient that represents the influence degree of adjusting vehicle state consistency, Indicates vehicle state consistency;

[0158] The adjusted correction function is determined by the following formula:

[0159]

[0160] in, represents the adjusted correction function, The coefficient that represents the influence degree of adjusting vehicle state consistency, Indicates vehicle status consistency.

[0161] In this step, the vehicle state consistency corresponding to the vehicle state factor is determined:

[0162] in, Indicates vehicle status consistency, reflecting whether the actual status of the vehicle during the rental period is consistent with the expectations of historical data; Indicates The actual status of the rental event; Indicates The expected status of each leasing event based on historical data analysis; and Respectively represent the maximum and minimum values ​​of the state; Indicates the number of rental events; It is the coefficient that adjusts the influence of external factors; Indicates The weight coefficient of external influencing factors; Indicates The influence degree of external influencing factors on the vehicle state consistency.

[0163] Based on the vehicle state consistency, the authenticity score is adjusted or the correction function is adjusted:

[0164] Adjusted authenticity score Indicates that adjustments are made to the original authenticity score to account for vehicle status consistency.

[0165] Adjusted correction function It indicates that the adjustment of vehicle status consistency is added on the basis of the original correction function.

[0166] A coefficient that indicates the degree of influence on adjusting the consistency of vehicle status.

[0167] A coefficient that represents the degree of influence of adjusting vehicle state consistency on the correction function.

[0168] In the embodiment of the present application, the vehicle state consistency is determined :

[0169] Suppose we have a set of rental event data and need to determine the consistency of vehicle status :

[0170] Assume that there is a leasing events;

[0171] The actual status of each event They are ;

[0172] Expected status based on historical data analysis They are [0.8, 0.7, 0.9, 0.7, 0.6] respectively;

[0173] State Maximum , state minimum ;

[0174] External factors , assuming that the weather conditions and traffic conditions are respectively, the weight coefficient and The impact levels are and ;

[0175] Adjustment coefficient ;

[0176] Calculating vehicle state consistency :

[0177]

[0178] Adjusting the authenticity score :

[0179] Assume the authenticity score is known , abnormal probability score , external factors , weight coefficient and , the degree of impact and , adjustment coefficient , adjustment coefficient .

[0180] Calculate the adjusted authenticity score :

[0181]

[0182] Adjustment correction function :

[0183] Assume that the observed rental event value is known , reference value , adjustment coefficient , adjustment coefficient .

[0184] Calculate the adjusted correction function :

[0185]

[0186] Through the above steps, the authenticity score and correction function can be adjusted based on the consistency of the vehicle state, thereby further improving the consistency and accuracy of the data.

[0187] Figure 2 A structural diagram of a vehicle rental data correction system based on intelligent AI is provided for an embodiment of the present application, such as Figure 2 As shown, the system includes:

[0188] An acquisition module 21, used to acquire at least two vehicle rental records from different data sources, each record containing multiple rental events;

[0189] The identification module 22 is used to analyze the rental events in each record using intelligent AI to identify potential data anomalies;

[0190] A determination module 23, configured to determine the authenticity and accuracy of each rental event through a multi-factor verification algorithm based on the data anomaly;

[0191] An adjustment module 24, configured to adjust the data anomalies in the at least two vehicle rental records from different data sources according to the authenticity and the accuracy, so as to ensure the consistency of the data;

[0192] The determination module 23 is specifically used to calculate the authenticity score of each rental event through a multi-factor verification algorithm based on the data anomaly items and in combination with the geolocation information factors, timestamp factors, and vehicle status factors obtained in the rental event; based on the authenticity score, evaluate the accuracy of the rental event and generate correction suggestions.

[0193] Figure 2 The vehicle rental data correction system based on intelligent AI can perform Figure 1 The implementation principle and technical effect of the intelligent AI-based vehicle rental data correction method described in the illustrated embodiment will not be repeated. The specific manner in which each module and unit performs operations in the intelligent AI-based vehicle rental data correction system in the above embodiment has been described in detail in the embodiment of the method, and will not be elaborated here.

[0194] In one possible design, Figure 2 The vehicle rental data correction system based on intelligent AI of the illustrated embodiment can be implemented as a computing device, such as Figure 3 As shown, the computing device may include a storage component 31 and a processing component 32;

[0195] The storage component 31 stores one or more computer instructions, wherein the one or more computer instructions are called and executed by the processing component 32 .

[0196] The processing component 32 is used to: obtain at least two vehicle rental records from different data sources, each record containing multiple rental events; use intelligent AI to analyze the rental events in each record to identify potential data anomalies; based on the data anomalies, determine the authenticity and accuracy of each rental event through a multi-factor verification algorithm; based on the authenticity and accuracy, adjust the data anomalies in the at least two vehicle rental records from different data sources to ensure data consistency.

[0197] The processing component 32 may include one or more processors to execute computer instructions to complete all or part of the steps in the above method. Of course, the processing component may also be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components to perform the above method.

[0198] The storage component 31 is configured to store various types of data to support operations at the terminal. The storage component can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0199] Of course, the computing device may also include other components, such as input / output interfaces, display components, communication components, etc.

[0200] The input / output interface provides an interface between the processing component and the peripheral interface module, which may be an output device, an input device, etc.

[0201] The communication component is configured to facilitate, among other things, wired or wireless communications between the computing device and other devices.

[0202] Among them, the computing device can be a physical device or an elastic computing host provided by a cloud computing platform, etc. In this case, the computing device can refer to a cloud server, and the above-mentioned processing components, storage components, etc. can be basic server resources rented or purchased from the cloud computing platform.

[0203] The present application also provides a computer storage medium storing a computer program, wherein the computer program can achieve the above-mentioned Figure 1 The vehicle rental data correction method based on intelligent AI of the illustrated embodiment.

[0204] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0205] The system embodiment described above is merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art may understand and implement it without creative work.

[0206] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0207] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A vehicle rental data correction method based on intelligent AI, characterized in that: include: Obtain at least two vehicle rental records from different data sources, each record containing multiple rental events; Use intelligent AI to analyze rental events in each record and identify potential data anomalies; Based on the data anomalies, determine the authenticity and accuracy of each rental event through a multi-factor verification algorithm; According to the authenticity and the accuracy, adjusting the data anomalies in the at least two vehicle rental records from different data sources to ensure data consistency; Based on the data anomaly, the authenticity and accuracy of each rental event is determined through a multi-factor verification algorithm, including: Based on the data anomaly, and in combination with the geolocation information factor, timestamp factor, and vehicle status factor obtained in the rental event, the authenticity score of each rental event is calculated through a multi-factor verification algorithm; According to the authenticity score, evaluating the accuracy of the rental event and generating correction suggestions; The authenticity score is determined by the following formula: ； in, represents the authenticity score; Indicates The weight coefficient of each factor; Indicates the first The degree of consistency between each factor and historical data; represents the number of factors in the rental event; represents the abnormal probability score; and is the coefficient that adjusts the degree of influence of authenticity and abnormal probability scores; Indicates The weight coefficient of external influencing factors; Indicates The degree of influence of external factors on the leasing event; Indicates the number of external influencing factors; It is the coefficient that adjusts the degree of influence of external influencing factors.

2. The method according to claim 1, characterized in that The use of intelligent AI to analyze the rental events in each record includes: Analyze the rental events in each record using a pre-configured AI model trained using multiple data validation strategies; According to the analysis results of the AI ​​model, abnormal rental events are marked, and the abnormal probability score of each rental event is calculated.

3. The method according to claim 1, characterized in that: The adjusting, based on the authenticity and the accuracy, data anomalies in the at least two vehicle rental records from different data sources includes: Define a correction function; Based on the correction function and the authenticity score and the anomaly probability score of each rental event, adjusting the data anomalies in the at least two vehicle rental records from different data sources; Among them, the correction function for: ； in, Indicates the correction value; represents the observed rental event value; represents the reference value, i.e., the average value of normal leasing events in historical data; represents the authenticity score; represents the abnormal probability score; is a small positive number used to prevent division by zero errors; is the coefficient that adjusts the influence of the abnormal probability score; Indicates The adjustment coefficient of the external influencing factors on the correction value; Indicates The degree of influence of external factors on the leasing event; It is the coefficient that adjusts the influence of external factors on the correction value; Indicates the number of external influencing factors; The abnormal probability score is determined by the following formula: ； in, Indicates The anomaly probability calculated by a data validation strategy; Indicates The reliability weight of each data verification strategy; Indicates the number of data validation strategies used.

4. The method according to claim 3, characterized in that Also includes: Determining the consistency of the vehicle state corresponding to the vehicle state factor; Based on the vehicle state consistency, adjusting the authenticity score or adjusting the correction function; The vehicle state consistency is determined by the following formula: ； in, Indicates vehicle state consistency; Indicates The actual status of the rental event; Indicates The expected status of each leasing event based on historical data analysis; and Respectively represent the maximum and minimum values ​​of the state; Indicates the number of rental events; It is the coefficient that adjusts the influence of external factors; Indicates The weight coefficient of external influencing factors; Indicates The degree of influence of external factors on vehicle state consistency; Represents the number of external influencing factors.

5. The method according to claim 4, characterized in that The adjusting the authenticity score or adjusting the correction function based on the vehicle state consistency includes: The adjusted authenticity score is determined by the following formula: ； in, represents the adjusted authenticity score, The coefficient that represents the influence degree of adjusting vehicle state consistency, Indicates vehicle state consistency; The adjusted correction function is determined by the following formula: ； in, represents the adjusted correction function, The coefficient that represents the influence degree of adjusting vehicle state consistency, Indicates vehicle status consistency.

6. A vehicle rental data correction system based on intelligent AI, characterized in that: include: An acquisition module, used for acquiring at least two vehicle rental records from different data sources, each record containing multiple rental events; The recognition module is used to analyze the rental events in each record using intelligent AI to identify potential data anomalies; A determination module, used to determine the authenticity and accuracy of each rental event through a multi-factor verification algorithm based on the data anomaly items; An adjustment module, configured to adjust the data anomalies in the at least two vehicle rental records from different data sources according to the authenticity and the accuracy, so as to ensure the consistency of the data; The determination module is specifically used to calculate the authenticity score of each rental event through a multi-factor verification algorithm based on the data anomaly items and in combination with the acquired geolocation information factor, timestamp factor, and vehicle status factor in the rental event; evaluate the accuracy of the rental event according to the authenticity score, and generate correction suggestions; The authenticity score is determined by the following formula: ； in, represents the authenticity score; Indicates The weight coefficient of each factor; Indicates the first The degree of consistency between each factor and historical data; represents the number of factors in the rental event; represents the abnormal probability score; and is the coefficient that adjusts the degree of influence of authenticity and abnormal probability scores; Indicates The weight coefficient of external influencing factors; Indicates The degree of influence of external factors on the leasing event; Indicates the number of external influencing factors; It is the coefficient that adjusts the degree of influence of external influencing factors.

7. A computing device, characterized in that It includes a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement a vehicle rental data correction method based on intelligent AI as described in any one of claims 1 to 5.

8. A computer storage medium, characterized in that A computer program is stored, and when the computer program is executed by a computer, a vehicle rental data correction method based on intelligent AI as described in any one of claims 1 to 5 is implemented.

Images