CN118916824A - Vehicle lease data correction method and system based on intelligent AI - Google Patents
Vehicle lease data correction method and system based on intelligent AI Download PDFInfo
- Publication number
- CN118916824A CN118916824A CN202411406343.8A CN202411406343A CN118916824A CN 118916824 A CN118916824 A CN 118916824A CN 202411406343 A CN202411406343 A CN 202411406343A CN 118916824 A CN118916824 A CN 118916824A
- Authority
- CN
- China
- Prior art keywords
- data
- rental
- representing
- authenticity
- adjusting
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000012937 correction Methods 0.000 title claims abstract description 81
- 238000000034 method Methods 0.000 title claims abstract description 41
- 230000002159 abnormal effect Effects 0.000 claims abstract description 43
- 238000012795 verification Methods 0.000 claims abstract description 21
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 20
- 238000012545 processing Methods 0.000 claims description 17
- 238000013524 data verification Methods 0.000 claims description 14
- 230000005856 abnormality Effects 0.000 claims description 13
- 238000004590 computer program Methods 0.000 claims description 5
- 238000004458 analytical method Methods 0.000 claims description 4
- 230000006870 function Effects 0.000 description 24
- 238000001514 detection method Methods 0.000 description 5
- 238000012549 training Methods 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 238000002790 cross-validation Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000011156 evaluation Methods 0.000 description 3
- 230000002547 anomalous effect Effects 0.000 description 2
- 238000013459 approach Methods 0.000 description 2
- 230000006399 behavior Effects 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000002360 preparation method Methods 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000013523 data management Methods 0.000 description 1
- 238000013502 data validation Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000000556 factor analysis Methods 0.000 description 1
- 239000000446 fuel Substances 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000009897 systematic effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000010200 validation analysis Methods 0.000 description 1
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application provides a vehicle lease data correction method and system based on intelligent AI. At least two vehicle lease records from different data sources are obtained, and each record contains a plurality of lease events; analyzing lease events in each record by using an intelligent AI, and identifying potential data abnormal items; based on the data abnormal items, determining the authenticity and accuracy of each lease event through a multi-factor verification algorithm; and adjusting data abnormal items in the at least two vehicle lease records from different data sources according to the authenticity and the accuracy so as to ensure the consistency of the data. The technical scheme provided by the application can improve the efficiency of correcting the abnormal data and improve the accuracy and consistency of the vehicle lease record data.
Description
Technical Field
The embodiment of the application relates to the technical field of data processing, in particular to a vehicle leasing data correction method and system based on intelligent AI.
Background
With the rapid development of sharing economy, vehicle rental businesses are becoming increasingly popular. To better manage vast rental data, businesses need to obtain detailed rental records from multiple data sources (e.g., different vehicle rental platforms, GPS tracking systems, etc.). These records contain specific information for each rental event, such as rental time, return time, mileage, etc. In order to ensure the integrity and consistency of these data, a technical solution is needed that can automatically identify and correct anomalies in the data.
Currently, most vehicle rental companies rely on manual auditing to check rental records for errors or anomalies. In addition, some companies have begun to attempt to automate part of the process using basic data cleansing tools. However, these approaches focus primarily on anomaly detection on a single data source, lacking an efficient handling mechanism for cross-data source data consistency. At the same time, existing automation tools often can only identify predefined types of errors, which have limited identification capabilities for complex data anomalies, especially those caused by systematic errors. The manual auditing mode is time-consuming and labor-consuming, is easily affected by subjective judgment, and cannot discover and correct abnormal conditions in data in time. While existing automation tools increase efficiency, they are struggling in the face of data integration across data sources, and it is difficult to meet data consistency requirements. Furthermore, these tools perform poorly in handling unforeseen data anomalies due to the lack of advanced intelligent analysis functionality, resulting in data quality problems that are not fundamentally addressed.
In view of the foregoing, there is a clear need for a more efficient and intelligent solution to the drawbacks of existing data management and anomaly detection schemes in the face of complex, multi-source data environments.
Disclosure of Invention
The embodiment of the application provides a vehicle leasing data correction method and system based on intelligent AI (advanced technology attachment), which are used for solving the problem of poor data correction abnormal efficiency in the prior art.
In a first aspect, an embodiment of the present application provides a vehicle rental data correction method based on an intelligent AI, including:
Acquiring at least two vehicle rental records from different data sources, each record containing a plurality of rental events;
analyzing lease events in each record by using an intelligent AI, and identifying potential data abnormal items;
Based on the data abnormal items, determining the authenticity and accuracy of each lease event through a multi-factor verification algorithm;
And adjusting data abnormal items in the at least two vehicle lease records from different data sources according to the authenticity and the accuracy so as to ensure the consistency of the data.
Optionally, the analyzing the rental events in each record with the intelligent AI includes:
analyzing lease events in each record by adopting a preconfigured AI model, wherein the AI model is trained by using a plurality of data verification strategies;
and marking out the leasing event with abnormality according to the AI model analysis result, and calculating the abnormality probability score of each leasing event.
Optionally, the determining the authenticity and accuracy of each rental event by a multi-factor verification algorithm based on the data anomaly item includes:
Based on the data abnormal items, and combining the obtained geographic positioning information factors, the obtained timestamp factors and the obtained vehicle state factors in the leasing events, calculating the authenticity score of each leasing event through a multi-factor verification algorithm;
and evaluating the accuracy of the leasing event according to the authenticity score, and generating a correction suggestion.
Optionally, the authenticity score is determined by the following formula:
wherein, Representing an authenticity score; Represent the first The weight coefficient of each factor; representing the first of the rental events The degree of agreement of the individual factors with the historical data; Representing a number of factors in the rental event; Representing an anomaly probability score; And Is a coefficient for adjusting the degree of influence of the score of the probability of abnormality and the authenticity; Represent the first A weight coefficient of each external influence factor; Represent the first The degree of influence of the individual external influencing factors on the rental event; representing the number of external influencing factors; is a coefficient for adjusting the degree of influence of an external influence factor.
Optionally, said adjusting data anomalies in said at least two vehicle rental records from different data sources according to said authenticity and said accuracy comprises:
defining a correction function;
Adjusting data anomaly items in the at least two vehicle rental records from different data sources based on the correction function and the authenticity score and anomaly probability score for each rental event;
wherein the correction function The method comprises the following steps:
wherein, Representing the correction value; representing observed rental event values; Representing a reference value, i.e., an average of normal rental events in the historical data; Representing an authenticity score; Representing an anomaly probability score; Is a small positive number for preventing zero removal errors; Is a coefficient for adjusting the degree of influence of the anomaly probability score; Represent the first An adjustment coefficient of the correction value by the external influence factors; Represent the first The degree of influence of the individual external influencing factors on the rental event; Is a coefficient for adjusting the degree of influence of the external influence factor on the correction value;
Wherein the anomaly probability score is determined by the following formula:
wherein, Represent the firstThe anomaly probability calculated by the data verification strategy; Represent the first Reliability weights of the individual data verification policies; Representing the number of data verification policies used.
Optionally, the method further comprises:
determining the vehicle state consistency corresponding to the vehicle state factors;
Adjusting the authenticity score or adjusting the correction function based on the vehicle state consistency;
wherein the vehicle state consistency is determined by the following formula:
wherein, Representing vehicle state consistency; Represent the first Actual status of individual rental events; Represent the first Expected states of the lease events are analyzed according to historical data; And Respectively representing a maximum value and a minimum value of the state; Representing a number of rental events; is a coefficient for adjusting the influence degree of the external influence factors; Represent the first A weight coefficient of each external influence factor; Represent the first The degree of influence of the individual external influencing factors on the consistency of the vehicle state.
Optionally, 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:
wherein, Representing the adjusted authenticity score(s),A coefficient indicating a degree of influence of adjusting the consistency of the vehicle state,Representing vehicle state consistency;
the adjusted correction function is determined by the following formula:
wherein, Representing the modified correction function after the adjustment,A coefficient indicating a degree of influence of adjusting the consistency of the vehicle state,Indicating vehicle state consistency.
In a second aspect, an embodiment of the present application provides a vehicle rental data correction system based on an intelligent AI, including:
The system comprises an acquisition module, a data processing module and a data processing module, wherein the acquisition module is used for acquiring at least two vehicle lease records from different data sources, and each record contains a plurality of lease events;
the identification module is used for analyzing lease events in each record by utilizing the intelligent AI and identifying potential data abnormal items;
The determining module is used for determining the authenticity and the accuracy of each lease event through a multi-factor verification algorithm based on the data abnormal item;
the adjusting module is used for adjusting data abnormal items in the at least two vehicle lease records from different data sources according to the authenticity and the accuracy so as to ensure the consistency of the data;
The determining module is specifically configured to calculate an authenticity score of each rental event through a multi-factor verification algorithm based on the data abnormal item and in combination with the obtained geographic positioning information factor, the obtained timestamp factor and the obtained vehicle state factor in the rental event; and evaluating the accuracy of the leasing event according to the authenticity score, and generating a correction suggestion.
In a third aspect, embodiments of the present application provide 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 operable to be invoked and executed by the processing component to implement a smart AI-based vehicle rental data correction method as in any one of the first aspects.
In a fourth aspect, an embodiment of the present application provides a computer storage medium storing a computer program, where the computer program when executed by a computer implements a vehicle rental data correction method based on an intelligent AI as set forth in any one of the first aspects.
In the embodiment of the application, at least two vehicle leasing records from different data sources are obtained, and each record contains a plurality of leasing events; analyzing lease events in each record by using an intelligent AI, and identifying potential data abnormal items; based on the data abnormal items, determining the authenticity and accuracy of each lease event through a multi-factor verification algorithm; and adjusting data abnormal items in the at least two vehicle lease records from different data sources according to the authenticity and the accuracy so as to ensure the consistency of the data. The technical scheme provided by the application can improve the efficiency of correcting the abnormal data and improve the accuracy and consistency of the vehicle lease record data.
These and other aspects of the application will be more readily apparent from the following description of the embodiments.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are some embodiments of the present application, and other drawings can be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flowchart of a vehicle rental data correction method based on an intelligent AI according to an embodiment of the present application;
FIG. 2 is a schematic diagram of a vehicle rental data correction system based on an intelligent AI according to an embodiment of the present application;
fig. 3 is a schematic structural diagram of a computing device according to an embodiment of the present application.
Detailed Description
In order to enable those skilled in the art to better understand the present application, the following description will make clear and complete descriptions of the technical solutions according to the embodiments of the present application with reference to the accompanying drawings.
In some of the flows described in the specification and claims of the present application and in the foregoing figures, a plurality of operations occurring in a particular order are included, but it should be understood that the operations may be performed out of order or performed in parallel, with the order of operations such as 101, 102, etc., being merely used to distinguish between the various operations, the order of the operations themselves not representing any order of execution. In addition, the flows may include more or fewer operations, and the operations may be performed sequentially or in parallel. It should be noted that, the descriptions of "first" and "second" herein are used to distinguish different messages, devices, modules, etc., and do not represent a sequence, and are not limited to the "first" and the "second" being different types.
The following description of the embodiments of the present application will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to fall within the scope of the application.
Fig. 1 is a flowchart of a vehicle rental data correction method based on intelligent AI according to an embodiment of the present application, and as shown in fig. 1, the method includes:
101. acquiring at least two vehicle rental records from different data sources, each record containing a plurality of rental events;
in this step, acquiring at least two vehicle rental records from different data sources means that data is collected from two or more independent sources. These data sources may be databases of different vehicle rental companies, vehicle GPS tracking system records, third party paymate transaction records, and the like. Each record contains a plurality of rental events, meaning that each data record represents a particular rental activity, e.g., a vehicle is rented out at a time and returned at a later time.
In the embodiment of the application, we assume that there are two data sources: one is an internal database (System A) of a car rental company, and the other is a partner of the company, a third party platform (System B) providing vehicle location tracking services. The two systems each store information about the rental of the vehicle. To ensure the comprehensiveness and consistency of the data, we will acquire all lease records from System A for a specified period of time, and also acquire records from System B for the same period of time regarding the usage of the vehicle.
Specific examples are as follows:
System A data Source example:
lease ID:001;
vehicle ID:12345;
Lease time: 2024-09-0108:00 AM;
Return time: 2024-09-0106:00 PM;
Lease location: central Station Branch;
System B data Source example:
vehicle ID:12345;
GPS records time: 2024-09-0108:05 AM;
GPS position: central Station, city;
The next recording time: 2024-09-0106:03 PM;
in this process, we may also encounter terms of art such as GPS (Global Positioning System, GPS), which is a global positioning system used to determine the exact coordinates of any location on the earth. By obtaining information from these two different data sources, we can perform further data analysis and anomaly detection.
102. Analyzing lease events in each record by using an intelligent AI, and identifying potential data abnormal items;
Optionally, the analyzing the rental events in each record with the intelligent AI in step 102 includes: analyzing lease events in each record by adopting a preconfigured AI model, wherein the AI model is trained by using a plurality of data verification strategies; and marking out the leasing event with abnormality according to the AI model analysis result, and calculating the abnormality probability score of each leasing event.
In this step, analyzing rental events in each record using the smart AI refers to analyzing the vehicle rental records obtained from different data sources using artificial intelligence techniques in order to identify anomalous data that may be present therein. "Smart AI" as referred to herein generally refers to a trained machine learning model or deep learning network that can predict the behavior or characteristics of new unknown data based on existing data patterns. "data anomalies" refer to those data points that do not conform to normal patterns, and may be due to input errors, system failures, or other abnormal causes.
The concepts involved in the above steps are explained:
preconfigured AI model: refers to a machine learning model that has been trained, which may be a supervised learning, an unsupervised learning, or a semi-supervised learning model, for detecting anomalies in the data. In the model training process, various data verification strategies, such as cross-validation (CV), K-fold cross-validation (KFCV) and other methods, are used to ensure the generalization capability and accuracy of the model.
A variety of data validation strategies: refers to different technical approaches taken to evaluate model performance, such as dividing the data set into a training set, a validation set, and a test set, in order to continuously optimize model parameters during training while preventing overfitting.
Anomaly probability score: refers to a set of values that represent the degree of deviation of each rental event from normal behavior. The higher this score, the more likely the event is abnormal.
In the embodiment of the application, we assume that an anomaly detection model based on deep learning has been trained, and the model is trained by using various data verification strategies. The following are specific examples:
Data preprocessing: first, the vehicle rental records obtained from different data sources are cleaned and formatted to ensure standardization and consistency of the data. For example, all timestamps are converted to a uniform time format.
Characteristic engineering: and extracting key characteristics of each lease record, such as lease time, return time, lease place and the like. These features will serve as inputs to the model.
Model application: the extracted features are input into a preconfigured AI model. The model is a deep neural network, and can identify common abnormal modes after a large number of lease record training.
Abnormality detection: the model outputs an anomaly probability score for each rental event. For example, for a record, the model may output the following:
lease ID:001
Anomaly probability score: 0.85 (indicating that this record has a 85% probability of being abnormal)
Marking abnormality: rental events that are likely to have anomalies are marked based on a set threshold (e.g., anomaly probability score greater than 0.7). For the records in the above example, the anomaly probability score is 0.85, which exceeds the set threshold, and therefore will be marked as a potential anomalous rental event.
In this way, the intelligent AI can be used to effectively identify abnormal items in the data, and provide basis for further data cleaning and consistency verification.
103. Based on the data abnormal items, determining the authenticity and accuracy of each lease event through a multi-factor verification algorithm;
Optionally, the determining, based on the data anomaly, the authenticity and accuracy of each rental event by a multi-factor verification algorithm in step 103 includes: based on the data abnormal items, and combining the obtained geographic positioning information factors, the obtained timestamp factors and the obtained vehicle state factors in the leasing events, calculating the authenticity score of each leasing event through a multi-factor verification algorithm; and evaluating the accuracy of the leasing event according to the authenticity score, and generating a correction suggestion.
Wherein the authenticity score is determined by the following formula:
wherein, Representing an authenticity score; Represent the first The weight coefficient of each factor; representing the first of the rental events The degree of agreement of the individual factors with the historical data; Representing a number of factors in the rental event; Representing an anomaly probability score; And Is a coefficient for adjusting the degree of influence of the score of the probability of abnormality and the authenticity; Represent the first A weight coefficient of each external influence factor; Represent the first The degree of influence of the individual external influencing factors on the rental event; representing the number of external influencing factors; is a coefficient for adjusting the degree of influence of an external influence factor.
In the step, based on the data abnormal items, and combined with the obtained geographic positioning information factors, the obtained timestamp factors and the obtained vehicle state factors in the leasing events, the authenticity score of each leasing event is calculated through a multi-factor verification algorithm. The "multi-factor verification algorithm" herein refers to the integrated assessment of the authenticity and accuracy of each rental event in combination with information in multiple dimensions. By the method, the credibility of the data can be more comprehensively known, so that more accurate data correction suggestions can be made.
Specifically, the authenticity score is determined by the following formula:
wherein, Representing an authenticity score; Represent the first The weight coefficient of each factor; representing the first of the rental events The degree of agreement of the individual factors with the historical data; Representing a number of factors in the rental event; Representing an anomaly probability score; And Is a coefficient for adjusting the degree of influence of the score of the probability of abnormality and the authenticity; Represent the first A weight coefficient of each external influence factor; Represent the first The degree of influence of the individual external influencing factors on the rental event; representing the number of external influencing factors; is a coefficient for adjusting the degree of influence of an external influence factor.
In the embodiment of the application, we assume that a specific rental event needs to be evaluated for authenticity and accuracy, and the specific embodiment is as follows:
Data preparation: we obtain a lease record from different data sources, record lease time, return time, lease place, etc. information, and mark anomaly probability score through intelligent AI model 。
And (3) factor analysis:
Geolocation information factors: it is checked whether the actual return location of the vehicle is identical to the recorded location.
Timestamp factor: checking whether the lease time and the return time are reasonable or not, and whether a logic error exists in time or not.
Vehicle state factors: it is checked whether status data of the vehicle during rental, such as driving distance, fuel consumption, etc., meet expectations.
Weighting score:
Setting a weight coefficient of each factor For example, geolocation informationTime stamp factorVehicle state factor。
Calculating the degree of coincidence of each factor with the historical dataFor example, geolocation informationTime stamp factorVehicle state factor。
Setting an anomaly probability score。
Taking into account external influencing factorsFor example weather conditionsTraffic conditionsAssume that weather conditions affect the extent of an eventDegree of influence of traffic conditions on events。
Calculating an authenticity score:
Setting an adjustment coefficient 。
Substituting the above values into the formula:
evaluation and correction advice: according to the calculated authenticity score The accuracy of evaluating the rental event is low. Based on this evaluation, corresponding correction suggestions are generated, such as further verifying geolocation information, recalibration time stamps, etc., to ensure consistency and accuracy of the data.
Through the steps, the authenticity and the accuracy of each leasing event can be effectively evaluated, and specific correction measures are provided accordingly, so that the overall quality of data is improved.
104. And adjusting data abnormal items in the at least two vehicle lease records from different data sources according to the authenticity and the accuracy so as to ensure the consistency of the data.
Optionally, the adjusting of the data anomalies in the at least two vehicle rental records from different data sources according to the authenticity and the accuracy in step 104 includes: defining a correction function; adjusting data anomaly items in the at least two vehicle rental records from different data sources based on the correction function and the authenticity score and anomaly probability score for each rental event;
wherein the correction function The method comprises the following steps:
wherein, Representing the correction value; representing observed rental event values; Representing a reference value, i.e., an average of normal rental events in the historical data; Representing an authenticity score; Representing an anomaly probability score; Is a small positive number for preventing zero removal errors; Is a coefficient for adjusting the degree of influence of the anomaly probability score; Represent the first An adjustment coefficient of the correction value by the external influence factors; Represent the first The degree of influence of the individual external influencing factors on the rental event; Is a coefficient for adjusting the degree of influence of the external influence factor on the correction value; representing the number of external influencing factors;
Wherein the anomaly probability score is determined by the following formula:
wherein, Represent the firstThe anomaly probability calculated by the data verification strategy; Represent the first Reliability weights of the individual data verification policies; Representing the number of data verification policies used.
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, data anomalies in at least two vehicle rental records from different data sources are adjusted to ensure consistency of the data. This process aims to quantify and correct anomalies in the data by means of a mathematical model, thereby improving the data quality.
Correction function: This is a mathematical expression for adjusting data anomalies that decides how to correct the data based on authenticity and accuracy.
Observed lease event value: This refers to the actual rental recorded values obtained from different data sources.
Reference value: I.e., the average of normal rental events in the historical data, is used as a comparison benchmark.
Authenticity score: And reflects the comprehensive evaluation of the authenticity and accuracy of the lease event.
Anomaly probability score: Reflecting the size of the likelihood of an abnormality in the rental event.
Small positive number: For preventing zero removal errors and ensuring stability in the formula calculation process.
Adjustment coefficient: For adjusting the degree of influence of the anomaly probability score on the correction value.
Adjustment coefficient of external influence factor: The degree of influence of different external factors on the correction value is reflected.
Degree of influence of external influence factor: Indicating the magnitude of the impact of the external factors on the rental event.
Coefficient for adjusting influence degree of external influence factor: For adjusting the degree of influence of external factors on the correction value.
In the embodiment of the application, it is assumed that we have lease records of two data sources, and data abnormal items in the lease records need to be adjusted according to authenticity and accuracy. Specific examples are as follows:
data preparation:
And obtaining a lease record from the two data sources, wherein the lease record comprises lease time, return time, driving mileage and other information.
Defining a correction function：
Wherein, For an actual observed rental event value, for example, an actual mileage of 200 km; As a reference value, assume that the average value of the normal driving mileage in the history data is 150 km; For the authenticity score, 0.364 is assumed; The value is 0.001; The value is 0.5; An anomaly probability score of 0.8 is assumed; the value is 0.2; the number of external influencing factors is assumed to be 2; the adjustment coefficients for the external influencing factors are assumed to be 0.5 and 0.5, respectively; the degree of influence of the external influence factors is assumed to be 0.1 and 0.2, respectively;
Calculating correction value ：
Adjusting data abnormal items:
According to the calculated correction value The exception data in the original record may be adjusted. For example, if the actual driving distance is 200 km, it can be adjusted to 150 km+ 129.223 km based on the correction valueKilometers. Of course, in practical application, the actual meaning of the correction value needs to be adjusted according to specific situations.
Through the steps, abnormal items in the data can be adjusted based on the authenticity and the accuracy, and the consistency and the accuracy of the data are ensured, so that the quality of the whole data is improved.
Optionally, the method further comprises:
determining the vehicle state consistency corresponding to the vehicle state factors;
Adjusting the authenticity score or adjusting the correction function based on the vehicle state consistency;
wherein the vehicle state consistency is determined by the following formula:
wherein, Representing vehicle state consistency; Represent the first Actual status of individual rental events; Represent the first Expected states of the lease events are analyzed according to historical data; And Respectively representing a maximum value and a minimum value of the state; Representing a number of rental events; is a coefficient for adjusting the influence degree of the external influence factors; Represent the first A weight coefficient of each external influence factor; Represent the first The degree of influence of the external influencing factors on the consistency of the vehicle state; Representing the number of external influencing factors.
Wherein adjusting the authenticity score or adjusting the correction function based on the vehicle state consistency comprises:
The adjusted authenticity score is determined by the following formula:
wherein, Representing the adjusted authenticity score(s),A coefficient indicating a degree of influence of adjusting the consistency of the vehicle state,Representing vehicle state consistency;
the adjusted correction function is determined by the following formula:
wherein, Representing the modified correction function after the adjustment,A coefficient indicating a degree of influence of adjusting the consistency of the vehicle state,Indicating vehicle state consistency.
In this step, the vehicle state consistency corresponding to the vehicle state factor is determined:
wherein, Representing vehicle state consistency, reflecting whether the actual state of the vehicle during rental complies with expectations of historical data; Represent the first Actual status of individual rental events; Represent the first Expected states of the lease events are analyzed according to historical data; And Respectively representing a maximum value and a minimum value of the state; Representing a number of rental events; is a coefficient for adjusting the influence degree of the external influence factors; Represent the first A weight coefficient of each external influence factor; Represent the first The degree of influence of the individual external influencing factors on the consistency of the vehicle state.
Adjusting the authenticity score or adjusting the correction function based on the vehicle state consistency:
adjusted authenticity score Representing the addition of adjustments to the consistency of the vehicle state based on the original authenticity score.
Modified correction functionIndicating the addition of adjustments to the consistency of the vehicle state based on the original correction function.
A coefficient indicating a degree of influence in adjusting the consistency of the vehicle state.
A coefficient indicating the degree of influence on the correction function in adjusting the consistency of the vehicle state.
In the embodiment of the application, the consistency of the vehicle state is determined：
Assuming we have a set of rental event data, we need to determine vehicle state consistency：
Assume a commonA rental event;
Actual state of each event Respectively is；
Expected state from historical data analysisRespectively [0.8,0.7,0.9,0.7,0.6];
Maximum value of state State minimum；
External influencing factorsThe weighting coefficients are assumed to be weather conditions and traffic conditions respectivelyAndThe degree of influence is respectivelyAnd；
Adjustment coefficient；
Calculating vehicle state consistency：
Adjusting an authenticity score：
Assuming a known authenticity scoreAnomaly probability scoreExternal influencing factorsWeight coefficientAndDegree of influenceAndAdjusting the coefficientAdjusting the coefficient。
Calculating an adjusted authenticity score：
Adjusting correction functions：
Assume that observed rental event values are knownReference valueAdjusting the coefficientAdjusting the coefficient。
Calculating an adjusted correction function：
Through the steps, the authenticity score and the correction function can be adjusted based on the consistency of the vehicle states, so that the consistency and the accuracy of the data are further improved.
Fig. 2 is a schematic structural diagram of a vehicle rental data correction system based on intelligent AI according to an embodiment of the present application, and as shown in fig. 2, the system includes:
An acquisition module 21 for acquiring at least two vehicle rental records from different data sources, each record containing a plurality of rental events;
An identification module 22 for analyzing the rental events in each record using the intelligent AI to identify potential data anomalies;
a determining module 23 for determining the authenticity and accuracy of each rental event by a multi-factor verification algorithm based on the data anomaly;
an adjustment module 24, configured to adjust data abnormal items in the at least two vehicle rental records from different data sources according to the authenticity and the accuracy, so as to ensure consistency of the data;
the determining module 23 is specifically configured to calculate an authenticity score of each rental event through a multi-factor verification algorithm based on the data anomaly item and in combination with the obtained geolocation information factor, the timestamp factor, and the vehicle status factor in the rental event; and evaluating the accuracy of the leasing event according to the authenticity score, and generating a correction suggestion.
The intelligent AI-based vehicle rental data correction system described in fig. 2 may execute the intelligent AI-based vehicle rental data correction method described in the embodiment shown in fig. 1, and its implementation principle and technical effects are not described again. The specific manner in which the various modules, units, and operations of the intelligent AI-based vehicle rental data correction system of the above-described embodiments are performed has been described in detail in connection with the embodiments of the method, and will not be described in detail herein.
In one possible design, the smart AI-based vehicle rental data correction system of the embodiment of fig. 2 may be implemented as a computing device, which may include a storage component 31 and a processing component 32, as shown in fig. 3;
the storage component 31 stores one or more computer instructions for execution by the processing component 32.
The processing component 32 is configured to: acquiring at least two vehicle rental records from different data sources, each record containing a plurality of rental events; analyzing lease events in each record by using an intelligent AI, and identifying potential data abnormal items; based on the data abnormal items, determining the authenticity and accuracy of each lease event through a multi-factor verification algorithm; and adjusting data abnormal items in the at least two vehicle lease records from different data sources according to the authenticity and the accuracy so as to ensure the consistency of the data.
Wherein the processing component 32 may include one or more processors to execute computer instructions to perform all or part of the steps of the methods described above. Of course, the processing component may also be implemented as 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 elements for executing the methods described above.
The storage component 31 is configured to store various types of data to support operations at the terminal. The memory component may be implemented by any type or combination of volatile or nonvolatile memory devices 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 or optical disk.
Of course, the computing device may necessarily include other components as well, such as input/output interfaces, display components, communication components, and the like.
The input/output interface provides an interface between the processing component and a peripheral interface module, which may be an output device, an input device, etc.
The communication component is configured to facilitate wired or wireless communication between the computing device and other devices, and the like.
The computing device may be a physical device or an elastic computing host provided by the cloud computing platform, and at this time, the computing device may be a cloud server, and the processing component, the storage component, and the like may be a base server resource rented or purchased from the cloud computing platform.
The embodiment of the application also provides a computer storage medium, which stores a computer program, and the computer program can realize the intelligent AI-based vehicle rental data correction method in the embodiment shown in the figure 1 when being executed by a computer.
It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, which are not repeated herein.
The system embodiments described above are merely illustrative, wherein the elements illustrated as separate elements may or may not be physically separate, and the elements shown as elements may or may not be physical elements, may be located in one place, or may be distributed over a plurality of network elements. 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 will understand and implement the present invention without undue burden.
From the above description of the embodiments, it will be apparent to those skilled in the art that the embodiments may be implemented by means of software plus necessary general hardware platforms, or of course may be implemented by means of hardware. Based on this understanding, the foregoing technical solution may be embodied essentially or in a part contributing to the prior art in the form of a software product, which may be stored in a computer readable storage medium, such as ROM/RAM, a magnetic disk, an optical disk, etc., including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method described in the respective embodiments or some parts of the embodiments.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present application, and are not limiting; although the application has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present application.
Claims (9)
1. A vehicle rental data correction method based on intelligent AI, comprising:
Acquiring at least two vehicle rental records from different data sources, each record containing a plurality of rental events;
analyzing lease events in each record by using an intelligent AI, and identifying potential data abnormal items;
Based on the data abnormal items, determining the authenticity and accuracy of each lease event through a multi-factor verification algorithm;
according to the authenticity and the accuracy, adjusting data abnormal items in the at least two vehicle lease records from different data sources so as to ensure the consistency of the data;
the determining the authenticity and accuracy of each rental event by a multi-factor verification algorithm based on the data anomaly, comprising:
Based on the data abnormal items, and combining the obtained geographic positioning information factors, the obtained timestamp factors and the obtained vehicle state factors in the leasing events, calculating the authenticity score of each leasing event through a multi-factor verification algorithm;
and evaluating the accuracy of the leasing event according to the authenticity score, and generating a correction suggestion.
2. The method of claim 1, wherein analyzing the rental events in each record using the intelligent AI comprises:
analyzing lease events in each record by adopting a preconfigured AI model, wherein the AI model is trained by using a plurality of data verification strategies;
and marking out the leasing event with abnormality according to the AI model analysis result, and calculating the abnormality probability score of each leasing event.
3. The method of claim 1, wherein the authenticity score is determined by the following formula:
；
wherein, Representing an authenticity score; Represent the first The weight coefficient of each factor; representing the first of the rental events The degree of agreement of the individual factors with the historical data; Representing a number of factors in the rental event; Representing an anomaly probability score; And Is a coefficient for adjusting the degree of influence of the score of the probability of abnormality and the authenticity; Represent the first A weight coefficient of each external influence factor; Represent the first The degree of influence of the individual external influencing factors on the rental event; representing the number of external influencing factors; is a coefficient for adjusting the degree of influence of an external influence factor.
4. The method of claim 1, wherein said adjusting data anomalies in the at least two vehicle rental records from different data sources based on the authenticity and the accuracy comprises:
defining a correction function;
Adjusting data anomaly items in the at least two vehicle rental records from different data sources based on the correction function and the authenticity score and anomaly probability score for each rental event;
wherein the correction function The method comprises the following steps:
；
wherein, Representing the correction value; representing observed rental event values; Representing a reference value, i.e., an average of normal rental events in the historical data; Representing an authenticity score; Representing an anomaly probability score; Is a small positive number for preventing zero removal errors; Is a coefficient for adjusting the degree of influence of the anomaly probability score; Represent the first An adjustment coefficient of the correction value by the external influence factors; Represent the first The degree of influence of the individual external influencing factors on the rental event; Is a coefficient for adjusting the degree of influence of the external influence factor on the correction value; representing the number of external influencing factors;
Wherein the anomaly probability score is determined by the following formula:
；
wherein, Represent the firstThe anomaly probability calculated by the data verification strategy; Represent the first Reliability weights of the individual data verification policies; Representing the number of data verification policies used.
5. The method as recited in claim 4, further comprising:
determining the vehicle state consistency corresponding to the vehicle state factors;
Adjusting the authenticity score or adjusting the correction function based on the vehicle state consistency;
wherein the vehicle state consistency is determined by the following formula:
；
wherein, Representing vehicle state consistency; Represent the first Actual status of individual rental events; Represent the first Expected states of the lease events are analyzed according to historical data; And Respectively representing a maximum value and a minimum value of the state; Representing a number of rental events; is a coefficient for adjusting the influence degree of the external influence factors; Represent the first A weight coefficient of each external influence factor; Represent the first The degree of influence of the external influencing factors on the consistency of the vehicle state; Representing the number of external influencing factors.
6. The method of claim 5, wherein the adjusting the authenticity score or adjusting the correction function based on the vehicle state consistency comprises:
The adjusted authenticity score is determined by the following formula:
；
wherein, Representing the adjusted authenticity score(s),A coefficient indicating a degree of influence of adjusting the consistency of the vehicle state,Representing vehicle state consistency;
the adjusted correction function is determined by the following formula:
；
wherein, Representing the modified correction function after the adjustment,A coefficient indicating a degree of influence of adjusting the consistency of the vehicle state,Indicating vehicle state consistency.
7. A vehicle rental data correction system based on intelligent AI, comprising:
The system comprises an acquisition module, a data processing module and a data processing module, wherein the acquisition module is used for acquiring at least two vehicle lease records from different data sources, and each record contains a plurality of lease events;
the identification module is used for analyzing lease events in each record by utilizing the intelligent AI and identifying potential data abnormal items;
The determining module is used for determining the authenticity and the accuracy of each lease event through a multi-factor verification algorithm based on the data abnormal item;
the adjusting module is used for adjusting data abnormal items in the at least two vehicle lease records from different data sources according to the authenticity and the accuracy so as to ensure the consistency of the data;
The determining module is specifically configured to calculate an authenticity score of each rental event through a multi-factor verification algorithm based on the data abnormal item and in combination with the obtained geographic positioning information factor, the obtained timestamp factor and the obtained vehicle state factor in the rental event; and evaluating the accuracy of the leasing event according to the authenticity score, and generating a correction suggestion.
8. 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 configured to be invoked and executed by the processing component to implement the intelligent AI-based vehicle rental data correction method of any one of claims 1-6.
9. A computer storage medium storing a computer program which, when executed by a computer, implements a vehicle rental data correction method based on an intelligent AI as claimed in any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411406343.8A CN118916824A (en) | 2024-10-10 | 2024-10-10 | Vehicle lease data correction method and system based on intelligent AI |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411406343.8A CN118916824A (en) | 2024-10-10 | 2024-10-10 | Vehicle lease data correction method and system based on intelligent AI |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN118916824A true CN118916824A (en) | 2024-11-08 |
Family
ID=93296357
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202411406343.8A Pending CN118916824A (en) | 2024-10-10 | 2024-10-10 | Vehicle lease data correction method and system based on intelligent AI |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118916824A (en) |
-
2024
- 2024-10-10 CN CN202411406343.8A patent/CN118916824A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| TW201941058A (en) | Anomaly detection method and device | |
| CN113590429B (en) | Server fault diagnosis method and device and electronic equipment | |
| EP3613003B1 (en) | System and method for managing detection of fraud in a financial transaction system | |
| JP6641112B2 (en) | Guarantee cost estimation based on calculation of expected failure number of product | |
| US20180307218A1 (en) | System and method for allocating machine behavioral models | |
| CN111858108A (en) | Hard disk fault prediction method and device, electronic equipment and storage medium | |
| CN117237126B (en) | Insurance platform and insurance data processing method | |
| CN117170915A (en) | Data center equipment fault prediction method and device and computer equipment | |
| KR20140051678A (en) | Apparatus and method for fault management of smart devices | |
| CN111798246A (en) | Financial risk grade assessment method and device | |
| US20220245492A1 (en) | Constructing a statistical model and evaluating model performance | |
| Luijten et al. | Faster defect resolution with higher technical quality of software | |
| CN118916824A (en) | Vehicle lease data correction method and system based on intelligent AI | |
| WO2023061209A1 (en) | Method for predicting memory fault, and electronic device and computer-readable storage medium | |
| CN112346995B (en) | Banking industry-based test risk prediction model construction method and device | |
| CN115795312A (en) | Method for generating test data, method for evaluating flow mining algorithm, and medium | |
| Lyu et al. | Assessing the maturity of model maintenance techniques for AIOps solutions | |
| CN116304935A (en) | Abnormal data detection method and device and electronic equipment | |
| CN110334518B (en) | Trusted computing platform-based measurement policy verification method and device | |
| CN118396737B (en) | Intelligent wind control decision system for credit business | |
| CN117993616A (en) | Carbon emission data analysis management method, device, equipment and storage medium | |
| CN112990767B (en) | Vertical consumption medical SaaS production data calculation method, system, terminal and medium | |
| CN117611115A (en) | Salary generation method, system, storage medium and processor | |
| CN114676936A (en) | Method for predicting default time and related device | |
| Wang et al. | Network Abnormality Location Algorithm Based on Greedy Monte Carlo Tree |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication |