Method and Apparatus for Charging Using Vehicle Travel Distance Data Verification

Abstract

The present disclosure relates to a vehicle mileage-based billing system, and more specifically, to a method for determining a reliable standard mileage by mutually verifying a plurality of independent mileage data and billing based thereon, and a server device for performing the same. A billing method using verification of vehicle driving distance data according to an embodiment of the present specification for achieving the above-described objective may include: (i) obtaining a plurality of driving distance parameters including a first movement displacement calculated from a geospatial location specification module, (ii) a second movement displacement measured from a measurement system of the vehicle, and (iii) a third movement displacement estimated based on a predefined path profile; a step of analyzing the correlation between the driving distance parameters and determining a standard driving distance that serves as a reference for billing according to a preset judgment logic; and a step of calculating a final billing amount by applying a unit rate to the determined standard driving distance and initiating a payment transaction for the calculated billing amount.

Description

Technology Field

[0001] The present disclosure relates to a vehicle mileage-based billing system, and more specifically, to a method for determining a reliable standard mileage by mutually verifying a plurality of independent mileage data and billing based thereon, and a server device for performing the same. Background Technology

[0002] With the growth of the vehicle-based service industry, various billing systems based on accurately measuring vehicle mileage are emerging. Representative examples include pay-as-you-drive insurance, mileage-based vehicle rental services, settlement of electric vehicle charging and maintenance costs, and toll or road usage fee settlement systems. Since these services commonly calculate fees based on data regarding the actual distance traveled by vehicles, the accuracy and reliability of mileage data are considered key factors directly linked to the fairness of billing.

[0003] Conventionally, driving distance has been measured by relying on a single means of measurement devices inside the vehicle, such as tire rotation-based odometers or GPS-based location tracking systems. However, these single-resource measurement systems are vulnerable to various disturbances. For instance, GPS-based systems may experience unstable signal reception and increased errors in tunnels, densely populated high-rise areas, or adverse weather conditions. In the case of tire rotation-based measurement, values ​​that differ from the actual driving distance may be measured due to factors such as tire wear, changes in air pressure, and wheel slip. These factors can be caused not only by equipment errors but also by intentional user manipulation, data loss, or communication errors, posing a significant obstacle to accurate billing.

[0004] Furthermore, while a large amount of vehicle-related data is currently being transmitted in real-time to cloud servers via networks, factors such as packet loss, network latency, and data synchronization failures during this process also compromise data integrity. Accordingly, service providers are required to adopt a complex approach that generates reference data through mutual verification and complementarity by securing multiple data sources, rather than relying entirely on a single source.

[0005] Moreover, existing systems rely on simple threshold comparisons or history-based filtering to determine anomalies in mileage measurement data, which poses a risk of making incorrect judgments based on fixed standards and failing to respond flexibly to various driving environments. For example, applying the same standards to urban driving and highway driving can be unreasonable and may lead to billing errors or user dissatisfaction. Accordingly, there is an increasing need for technology capable of multi-facetedly analyzing mileage data by comprehensively considering various sensor information, vehicle operation patterns, and external environmental data.

[0006] The aforementioned background technology is technical information that the inventor possessed for the derivation of the present disclosure or acquired during the process of deriving the present disclosure, and it cannot be considered technology that was disclosed to the general public prior to the filing of the present disclosure. The problem to be solved

[0007] The present specification aims to calculate a more reliable standard mileage through mutual verification using mileage data collected from different sources, thereby enabling accurate and fair billing. In particular, it aims to provide a billing system that effectively excludes outlier data and can respond flexibly to driving environments. means of solving the problem

[0008] A billing method using verification of vehicle driving distance data according to an embodiment of the present specification for achieving the above-described objective may include: (i) obtaining a plurality of driving distance parameters including a first movement displacement calculated from a geospatial location specification module, (ii) a second movement displacement measured from a measurement system of the vehicle, and (iii) a third movement displacement estimated based on a predefined path profile; a step of analyzing the correlation between the driving distance parameters and determining a standard driving distance that serves as a reference for billing according to a preset judgment logic; and a step of calculating a final billing amount by applying a unit rate to the determined standard driving distance and initiating a payment transaction for the calculated billing amount.

[0009] In the step of determining the standard driving distance, mutual deviations between the first, second, and third moving displacements are each calculated and a multilateral comparative analysis is performed. If there is one pair of moving displacements among the calculated mutual deviations that is below a preset threshold value, the remaining moving displacements not included in that pair are determined as outliers and excluded, and the standard driving distance can be determined according to a predefined priority among the two moving displacements constituting the pair.

[0010] In addition, if the calculated multiple mutual deviations all exceed the threshold value, the entire driving section may be divided into multiple analysis sections, and a multilateral comparative analysis may be performed again for each analysis section to identify normal sections and non-normal sections. Then, an alternative correction logic may be applied only to the non-normal sections to calculate the corrected displacement, and the displacement of the normal section and the corrected displacement may be summed to determine the final standard driving distance. At this time, the alternative correction logic may include calculating the displacement through dead reckoning using sensor data from an inertial measurement unit (IMU) mounted on the vehicle.

[0011] The above priority can be dynamically reset based on a reliability index calculated for each movement displacement (first, second, and third) at preset unit times. The reliability index can be calculated based on at least one of (i) a satellite signal reception quality index for the first movement displacement, (ii) a validity or continuity index of vehicle internal communication network data for the second movement displacement, and (iii) an average separation distance index between the vehicle location and a predefined path profile for the third movement displacement, and can be corrected by additionally reflecting context data such as real-time traffic information, weather information, and road type information.

[0012] Alternatively, the step of determining the standard driving distance may utilize a regression-based machine learning model. This model receives the first, second, and third displacements as input, assigns dynamic confidence weights to each displacement based on previously learned error patterns for driving situations, and calculates a weighted average standard driving distance by applying the assigned weights.

[0013] A server according to one embodiment of the present specification for achieving the above-described objective may include a processor; and a memory for loading instructions executed by said processor. Effects of the invention

[0014] According to the present disclosure, inaccurate billing can be prevented by ensuring the reliability of driving distance data through multi-party analysis, and it is possible to adapt to various driving situations through reliability-based priority setting and correction logic linked with real-time environmental information. In addition, the intelligence and scalability of the system are enhanced through automated standard distance calculation using regression-based machine learning. Brief explanation of the drawing

[0015] FIG. 1 is a conceptual diagram illustrating a driving distance verification-based billing system according to one embodiment of the present invention. FIG. 2 is a flowchart illustrating a mileage verification-based billing method according to an embodiment of the present invention. FIG. 3 is a flowchart illustrating the process of determining a standard driving distance according to an embodiment of the present invention. FIG. 4 is a flowchart illustrating the process of correcting the standard driving distance when a discrepancy occurs according to an embodiment of the present invention. FIG. 5 is a flowchart illustrating the process of calculating a reliability index for dynamic priority setting according to an embodiment of the present invention. FIG. 6 is a conceptual diagram illustrating an alternative correction logic for an inconsistency section according to one embodiment of the present invention. FIG. 7 is a graph showing the change in reliability index over time according to one embodiment of the present invention. FIG. 8 is a conceptual diagram illustrating a reliability index correction process using context data according to an embodiment of the present invention. FIG. 9 is a conceptual diagram illustrating the process of calculating a standard driving distance using a machine learning model according to an embodiment of the present invention. FIG. 10 is a block diagram illustrating the internal configuration of a server device according to one embodiment of the present invention. Specific details for implementing the invention

[0016] The present disclosure may be modified in various ways and may have various embodiments; specific embodiments are illustrated in the drawings and described in detail in the detailed description. The effects and features of the present disclosure and the methods for achieving them will become clear by referring to the embodiments described below in detail together with the drawings. However, the present disclosure is not limited to the embodiments disclosed below and may be implemented in various forms.

[0017] Each logical block may represent a module, segment, or part of code containing one or more executable instructions for executing a specific logical function. It should be noted that in one embodiment, the functions mentioned for each block may be executed in a different order than described. For example, even if two blocks are described in succession, the functions described for each block may be performed substantially simultaneously or in reverse order depending on the execution conditions or environment. In the following embodiments, singular expressions include plural expressions unless the context clearly indicates otherwise.

[0018] In the following examples, terms such as "include" or "have" mean that the features or components described in this specification are present, and do not exclude the possibility that one or more other features or components may be added.

[0019] Instructions executed through a processor of a computer or other programmable data processing equipment can generate means to perform each function described with reference to a flowchart or block diagram. The instructions can generate processes that are loaded on a computer, etc. and executed on the computer, etc. to perform a series of operational steps.

[0020] In this embodiment, the term "~part" refers to a component that performs a specific function performed by software or hardware such as an FPGA (Field Programmable Gate Array) or an ASIC (Application Specific Integrated Circuit). However, "~part" is not limited to being performed by software or hardware. "~part" may exist in the form of data stored on an addressable storage medium, or one or more processors may be configured to execute a specific function.

[0021] In the drawings, the size of components may be exaggerated or reduced for convenience of explanation. For example, the size and thickness of each component shown in the drawings are depicted arbitrarily for convenience of explanation, and therefore the present disclosure is not necessarily limited to what is illustrated. Furthermore, in the present disclosure, expressions such as "greater than" or "less than" are used to determine whether a specific condition is satisfied or fulfilled; however, this is merely for the purpose of expressing an example and does not exclude descriptions of "greater than" or "less than." Conditions described as "greater than" may be replaced with "greater than," conditions described as "less than" with "less than," and conditions described as "greater than and less than" with "greater than and less than." Terms such as "first," "second," etc., may be used to describe various components, but the components should not be limited by said terms. The above terms are used solely for the purpose of distinguishing one component from another. Software may include computer programs, code, instructions, or a combination of one or more of these, and may configure a processing unit to operate as desired or instruct the processing unit independently or collectively. Software and / or data may be permanently or temporarily embodied in any type of machine, component, physical device, virtual equipment, computer storage medium or device, or transmitted signal wave in order to be interpreted by the processing unit or to provide instructions or data to the processing unit. Software may be distributed over networked computer systems and may be stored or executed in a distributed manner. Software and data may be stored on one or more computer-readable recording media.

[0022] In the present disclosure, a pre-trained model may refer to an artificial intelligence model that has been trained in advance using a large dataset. Such a model may be used directly for a specific task or utilized as a base model to optimize performance through additional training or fine-tuning to meet the requirements of a specific application field. Through the pre-training process, the model learns general features or patterns of the data. In the present disclosure, such a pre-trained model may be utilized in the stages of text cleaning, summarization, translation, and image generation.

[0023] FIG. 1 is a conceptual diagram illustrating a driving distance verification-based billing system according to one embodiment of the present invention.

[0024] Referring to FIG. 1, a mileage verification-based billing system (10) may be configured to include a vehicle (110), a billing server (120), and an external server (130). The vehicle (110), the billing server (120), and the external server (130) may be connected via a network (20).

[0025] The vehicle (110) is a moving object subject to billing and can perform the role of generating a plurality of heterogeneous data to calculate the driving distance and transmitting them to the billing server (120). The vehicle (110) may include a geospatial positioning module, a measurement system, and an inertial measurement unit. The geospatial positioning module can periodically collect position information through a satellite navigation system, for example, a GPS (Global Positioning System) or GNSS (Global Navigation Satellite System) receiver, and calculate a first displacement based thereon. The measurement system can measure a second displacement by obtaining pulse signals or accumulated driving distance values ​​from the vehicle's speed sensor or odometer through a vehicle internal communication network, for example, a CAN (Controller Area Network). The inertial measurement unit (IMU) can perform dead reckoning to track the vehicle's movement in a specific section using sensor data such as an accelerometer and a gyroscope.

[0026] The billing server (120) is the entity that performs the core operations of the present invention. The billing server (120) can receive a plurality of driving distance parameters, such as a first driving displacement and a second driving displacement, from the vehicle (110). Additionally, the billing server (120) can obtain a third driving displacement based on a predefined path profile from a user terminal (140) or an external server (130). The billing server (120) compares and analyzes the mutual deviations between the collected plurality of driving distance parameters and determines a standard driving distance that serves as a reference for billing according to a preset judgment logic. A unit rate is applied to the determined standard driving distance to calculate the final billing amount, and the billing server (120) can perform the function of initiating a payment transaction for the calculated billing amount or notifying the user terminal (140) of billing information.

[0027] The external server (130) may serve to provide context data to increase the accuracy of determining the standard driving distance. The external server (130) may be a server that provides real-time traffic information, weather information, or map information including information such as the type of road, tunnel, or underpass. The billing server (120) may use the context data received from the external server (130) to correct the reliability of each driving distance parameter and reflect this in the process of determining the standard driving distance.

[0028] A user terminal (140) is a device that provides an interface between a user and a system. The user terminal (140) may be a smartphone, a tablet PC, or an infotainment system built into a vehicle. Through the user terminal (140), the user can set a driving route or check real-time driving distance and estimated billing amount. Additionally, the user terminal (140) can receive the final billing details from the billing server (120), display them to the user, and perform the function of processing the billing amount payment through integration with a payment application.

[0029] FIG. 2 is a flowchart illustrating a mileage verification-based billing method according to an embodiment of the present invention.

[0030] Referring to FIG. 2, the billing server can obtain driving distance parameters in step S210. A plurality of driving distance parameters may include a first moving displacement calculated from a geospatial location-specific module, a second moving displacement measured from a vehicle's measurement system, and a third moving displacement estimated based on a predefined path profile.

[0031] In step S220, a billing server according to one embodiment can analyze the correlation between acquired parameters and determine the driving distance to be the standard for billing according to the judgment logic. The specific process for determining the standard driving distance will be described below with reference to the drawings.

[0032] In step S220, a billing server according to one embodiment can calculate a final billing amount by applying a unit rate to a determined standard driving distance. The billing server (120) can initiate a payment transaction for the calculated billing amount or transmit billing information to a user terminal (140).

[0033] FIG. 3 is a flowchart illustrating the process of determining a standard driving distance according to an embodiment of the present invention.

[0034] Referring to FIG. 3, the billing server (120) can perform a multilateral comparative analysis using the acquired first movement displacement, second movement displacement, and third movement displacement at step S310. Specifically, the billing server (120) calculates a plurality of mutual deviation values ​​including (i) a deviation between the first movement displacement and the second movement displacement, (ii) a deviation between the first movement displacement and the third movement displacement, and (iii) a deviation between the second movement displacement and the third movement displacement.

[0035] In one embodiment, the billing server can identify, at step S320, whether there is one pair among the calculated deviations that is below a preset threshold. If there is one pair below the threshold, the billing server proceeds to step S330, and if there is not one pair below the threshold, the billing server proceeds to step S350.

[0036] In one embodiment, the billing server may exclude the remaining displacement not included in the pair by determining it as an outlier at step S330. Accordingly, the billing server (120) may consider the single displacement as a statistical outlier at step S330 and exclude it during the subsequent standard driving distance determination process. After the outlier is excluded, two displacements whose mutual consistency has been verified remain. Subsequently, at step S340, the billing server (120) may select the displacement among the two remaining displacements that is determined to have higher reliability according to a priority policy defined in the system in advance and determine it as the final standard driving distance.

[0037] In step S340, a billing server according to one embodiment may determine one displacement as a standard driving distance according to a predefined priority among pairs determined to be normal.

[0038] In step S350, a billing server according to one embodiment can identify whether there are zero pairs among the calculated deviations that are below a preset threshold. If there are zero pairs below the threshold, the billing server can proceed to step S360. Or, if there are not zero pairs below the threshold, the billing server can proceed to step S370.

[0039] A billing server according to one embodiment may perform inconsistency section processing logic at step S360. This will be described in more detail below in FIG. 4.

[0040] In step S370, a billing server according to one embodiment may determine one of the movement displacements as a standard driving distance based on priority. The billing server may select the movement displacement with the highest predefined priority among the three movement displacements as a representative value and determine it as the standard driving distance.

[0041] FIG. 4 is a flowchart illustrating the process of correcting the standard driving distance when a discrepancy occurs according to an embodiment of the present invention. The operation of the billing server in FIG. 4 corresponds to step S360 in FIG. 3.

[0042] Referring to FIG. 4, if a data discrepancy is detected in a macroscopic comparative analysis of the entire driving section at step S410, the billing server (120) may divide the entire driving section into multiple analysis sections according to a predefined unit to localize a specific section that is the cause of the error. The analysis sections may be divided into fixed time intervals, for example, in units of 1 minute, or fixed distances, for example, in units of 1 kilometer, and this may function as a parameter for determining the precision of subsequent analysis.

[0043] According to one embodiment, the billing server may perform a multilateral comparative analysis for each analysis segment in step S420. The billing server may re-perform the multilateral comparative analysis for each divided analysis segment. Specifically, the billing server (120) calculates a first displacement, a second displacement, and a third displacement for each analysis segment, and calculates the mutual deviations between them.

[0044] In step S430, a billing server according to one embodiment can identify a normal section and an inconsistent section. A normal section may refer to a section where the reliability of the data is secured by the mutual deviation between a plurality of movement displacements calculated within the analysis section converging within a preset first threshold. On the other hand, an inconsistent section may refer to a section where the mutual deviation still exceeds the threshold and data inconsistency is continuously observed. For example, a tunnel section where satellite signal reception is difficult or a section where a temporary failure occurs in the vehicle's internal communication network may be identified as an inconsistent section.

[0045] In step S440, a billing server according to one embodiment may apply correction logic to the discrepancy section. Substitute correction logic for correcting driving distance data is applied only to the identified discrepancy section, and the corrected displacement can be calculated through this. According to one embodiment of the present invention, the substitute correction logic may include recalculating the displacement of the discrepancy section through dead reckoning using sensor data from an inertial measurement unit (IMU) mounted on a vehicle (110). Although dead reckoning has the problem of cumulative error, by applying it only to relatively short sections such as the discrepancy section, the impact of the error can be minimized and reliable substitute data can be generated.

[0046] A billing server according to one embodiment may determine a standard driving distance in step S450. This is determined by summing the displacement of all normal sections identified in step S430 and the corrected displacement of all inconsistencies calculated through the alternative correction logic of step S440. The displacement of a normal section may be a weighted average value of a parameter or multiple parameters judged to have the highest reliability in that section.

[0047] FIG. 5 is a flowchart illustrating the process of calculating a reliability index for dynamic priority setting according to an embodiment of the present invention. The purpose of this process is to dynamically improve the accuracy and reliability of determining the standard driving distance by moving away from a static priority system and reflecting the driving environment and data collection status that change in real time.

[0048] Referring to FIG. 5, the billing server (120) can determine whether a preset unit time has elapsed in step S510 to determine whether the reliability index update cycle has arrived. The unit time may be set as a fixed time interval, such as 10 seconds or 30 seconds, for example, or may be set as a variable time interval that is triggered non-periodically by a specific driving event, such as the start of high-speed driving above a certain speed, a change in road type, or the detection of abnormal data signs.

[0049] When it is determined that a unit time has elapsed, the billing server (120) can obtain a reliability index, which is a basic indicator for quantitatively evaluating the reliability of each of the first movement displacement, the second movement displacement, and the third movement displacement, at step S520.

[0050] Specifically, the reliability indicator for the first displacement may be a reception quality indicator of satellite signals collected by a geospatial position-specific module during the corresponding unit time. Such an indicator may include the number of received satellites, the signal-to-noise ratio (SNR) of individual satellite signals, or the degree of positional degradation (DOP).

[0051] The reliability indicator for the second displacement may be an indicator of the validity or continuity of data received from the vehicle's internal communication network. Such an indicator may include the loss rate of data packets related to vehicle speed or odometer values, discontinuity of timestamps, or the frequency with which measured values ​​deviate from a preset normal range.

[0052] The reliability indicator for the third displacement may be the average deviation distance between the vehicle's real-time position and a predefined path profile during the corresponding unit time. Since a larger deviation distance indicates a higher likelihood that the driver has deviated from the planned path, the reliability of the third displacement may be evaluated as low.

[0053] In step S530, the billing server (120) may obtain context data from an external server (130) to correct the reliability index by obtaining objective information about the driving environment. The context data may include real-time traffic information, weather information such as rain or snow, and information on road types, tunnels, underpasses, overpasses, or urban shaded areas included in map information.

[0054] In step S540, the billing server (120) can correct each reliability index obtained in step S520 based on the context data obtained in step S530 and calculate the final reliability index of each movement displacement. The correction may be performed according to a predefined correction rule or function. For example, if the context data indicates entry into a tunnel section, the billing server (120) may forcibly adjust the reliability index of the first movement displacement to the lowest value because satellite signal reception is impossible. Additionally, if adverse weather information such as heavy rain is received, the reliability index of the first movement displacement may be adjusted downward by applying a specific attenuation weight to it, taking into account the possibility of satellite signal attenuation.

[0055] Finally, at step S550, the billing server (120) can compare the final reliability indices calculated at step S540 to dynamically reset the priority for each movement displacement. For example, the movement displacement with the highest reliability index may be given the highest priority, and the remaining movement displacements may be assigned sequential priorities in proportion to their reliability indices. The priority reset in real-time at each unit time in this way can be used as an objective criterion for selecting one of a plurality of valid movement displacements in the standard driving distance determination process of FIG. 3.

[0056] FIG. 6 is a conceptual diagram illustrating an alternative correction logic for an inconsistency section according to one embodiment of the present invention.

[0057] Referring to FIG. 6, the billing server (120) can identify a mismatch section (610) in which the mutual deviations between the first displacement, the second displacement, and the third displacement all exceed a preset threshold. Such a mismatch section (610) may occur, for example, in a tunnel where satellite signal reception is difficult, an underground parking lot, or a shaded urban area where high-rise buildings are dense, or it may occur due to a temporary error in the vehicle's internal sensors.

[0058] For the discrepancy section (610), it is difficult to determine a reliable standard driving distance using only the existing three displacement parameters. Therefore, the billing server (120) may apply an independent fourth displacement calculation method to the identified discrepancy section (610). To this end, the billing server (120) may receive sensor data, such as acceleration and angular velocity measured during the section, from an inertial measurement device mounted on the vehicle (110).

[0059] The billing server (120) performs a dead reckoning algorithm using the sensor data of the received inertial measurement device. Dead reckoning is a method of calculating the relative position change over time by integrating continuous acceleration and angular velocity data based on the starting point position of the mismatch section (610). The billing server (120) can determine the corrected displacement (620) calculated through this dead reckoning as the driving distance of the mismatch section (610).

[0060] Finally, the billing server (120) can calculate the final standard driving distance for the entire driving distance by summing the confirmed movement displacement in the normal sections of the entire driving section and the corrected movement displacement (620) calculated through the alternative correction logic in the inconsistency section (610).

[0061] FIG. 7 is a graph showing the change in reliability index over time according to one embodiment of the present invention.

[0062] Referring to FIG. 7, the horizontal axis of the graph represents the flow of time, and the vertical axis represents the reliability index calculated for each displacement parameter. The graph shows the change trends of the reliability index of the first displacement (710), the reliability index of the second displacement (720), and the reliability index of the third displacement (730).

[0063] The billing server (120) can continuously calculate and monitor the reliability index of each movement displacement at preset unit times. The reliability index of each movement displacement may fluctuate in real time depending on the driving environment and data collection status. For example, when a vehicle enters a tunnel, the satellite signal is lost, and the reliability index (710) of the first movement displacement may drop sharply. On the other hand, if a temporary error occurs in the vehicle's internal communication network, the reliability index (720) of the second movement displacement may decrease, and if the driver deviates significantly from the planned route, the reliability index (730) of the third movement displacement may decrease.

[0064] Based on the real-time change of these reliability indices, the billing server (120) can identify the movement displacement having the highest reliability index for each time interval and dynamically assign the highest priority to the movement displacement. For example, in a specific interval A of FIG. 7, the reliability index (710) of the first movement displacement is the highest, so the first movement displacement can be used as the priority criterion for determining the standard driving distance. However, in subsequent interval B, the reliability index (710) of the first movement displacement decreases and the reliability index (720) of the second movement displacement becomes the highest, so the priority can be dynamically switched to the second movement displacement.

[0065] FIG. 8 is a conceptual diagram illustrating a reliability index correction process using context data according to an embodiment of the present invention.

[0066] Referring to FIG. 8, the billing server (120) may include a reliability correction module (830). The reliability correction module (830) receives two types of data. The first input is a basic reliability index (810) based on raw data characteristics of each moving displacement, such as satellite signal quality and data validity. The second input is context data (820) containing objective information about the vehicle's driving environment, collected from an external server (130), etc. The context data (820) may include real-time traffic information, weather information, map information including road types, etc.

[0067] The reliability correction module (830) performs an operation to correct the basic reliability index (810) by reflecting the input context data (820). The correction may be based on predefined rules or functions. For example, if the context data (820) includes 'tunnel' information, the reliability correction module (830) may apply a rule to forcibly adjust the basic reliability index (810) of the first movement displacement (GPS-based) to a value close to zero. Additionally, if 'heavy rain' weather information is included, the value may be lowered by multiplying the basic reliability index (810) of the first movement displacement by a specific attenuation coefficient, taking into account the possibility of satellite signal attenuation.

[0068] Through this correction process, the reliability correction module (830) outputs a final reliability index (840) that is calculated more precisely by comprehensively considering the surrounding conditions. The billing server (120) can improve the accuracy of determining the standard driving distance by using the final reliability index (840) calculated in this way as the final criterion for determining the priority of each moving displacement.

[0069] FIG. 9 is a conceptual diagram illustrating the process of calculating a standard driving distance using a machine learning model according to an embodiment of the present invention.

[0070] Referring to FIG. 9, the billing server (120) may include a regression-based pre-trained machine learning model (930). The machine learning model (930) may be designed to receive a plurality of input features and output a single standard driving distance value.

[0071] In the learning phase of the machine learning model (930), the billing server (120) may use a database of previously learned error patterns for each driving situation that includes past driving data. The database stores pairs of values ​​for a first displacement, a second displacement, and a third displacement, and a ground truth value obtained through verification, for various driving situations, such as highway driving, city driving, and tunnel passing. The machine learning model (930) learns this data to internalize the pattern and trend of the error represented by each displacement in a specific driving situation.

[0072] In the actual billing calculation step, the billing server (120) provides the first displacement (911), the second displacement (913), and the third displacement (915) obtained in the current driving section as input values ​​to the machine learning model (930). The machine learning model (930) assigns dynamic confidence weights to each input displacement in real time based on an internalized error pattern. These weights are values ​​indicating the degree to which each displacement contributes to the final result.

[0073] The billing server (120) can calculate a weighted average by applying the weights assigned by the machine learning model (930) to each movement displacement and calculate the result as the final standard driving distance (940). Unlike a rule-based method that simply selects a single movement displacement, this method comprehensively reflects information on all movement displacements according to reliability, thereby enabling a more robust and precise calculation of the standard driving distance.

[0074] FIG. 10 is a block diagram illustrating the internal configuration of a billing server device according to one embodiment of the present invention.

[0075] The billing server is illustrated as including memory (1010), a communication unit (1020), and a processor (1030), but is not necessarily limited thereto. For example, the memory (1010), the communication unit (1020), and the processor (1030) may each exist as physically independent components.

[0076] Memory (1010) is a computer-readable recording medium and may include a non-perishable permanent mass storage device such as RAM (random access memory), ROM (read only memory), and a disk drive. Additionally, an operating system and at least one program code may be stored in memory (1010). These software components may be loaded from a computer-readable recording medium separate from memory (1010) using a drive mechanism. This separate computer-readable recording medium may include a computer-readable recording medium such as a floppy drive, disk, tape, DVD / CD-ROM drive, or memory card. Memory (1010) may store computer executable instructions.

[0077] The memory (1010) stores an operating system (OS) for overall operation of the billing server (120) and one or more computer programs, which are sets of instructions for executing a billing method based on mileage verification according to one embodiment of the present invention. Specifically, the memory (1010) may include (i) a module for acquiring mileage parameters, (ii) a module for analyzing mutual deviations between acquired parameters and determining a standard mileage, (iii) a module for calculating and correcting a real-time reliability index, (iv) a module for performing alternative correction logic for discrepancies, and (v) a module for calculating a final billing amount and processing a payment transaction.

[0078] Additionally, the memory (1010) serves as a workspace for the processor (1030) and permanently or temporarily stores various data used in the computation process.

[0079] The data to be stored may include first and second movement displacement data received from the vehicle (110), inertial measurement device sensor data, context data received from an external server (130), unit rates required for a billing policy, threshold values ​​used in judgment logic, parameters of a pre-trained machine learning model (930), and mutual deviations generated during the calculation process, reliability index, final confirmed standard driving distance and final billing amount.

[0080] The communication unit (1020) performs data reception and transmission functions under the control of the processor (1030). As a reception function, the communication unit (1020) can receive time-series GPS coordinate data constituting the first movement displacement from the vehicle (110), vehicle internal communication network data constituting the second movement displacement, and inertial measurement unit sensor data to be used in the alternative correction logic. In addition, it can receive context data such as real-time traffic, weather, and map information required for reliability correction from an external server (130), and receive basis data for calculating the third movement displacement, such as a predefined path profile, from a user terminal (140). As a transmission function, the communication unit (1020) can perform the role of transmitting the final billing amount information and detailed details calculated by the processor (1030) to the user terminal (140) or transmitting a payment transaction request to an external payment system.

[0081] The processor (1030) comprehensively controls the overall operation of the billing server (120) and can perform the core information processing operation of the present disclosure by decoding and executing instructions of the operating system and application programs stored in memory (1010).

[0082] Specifically, the processor (1030) can load a billing method execution program stored in memory (1010) and perform the following functions. The processor (1030) controls the communication unit (1020) to obtain a plurality of driving distance parameters and stores the obtained parameters in a specific area of ​​memory (1010).

[0083] Subsequently, the processor (1030) performs complex logical operations to determine the standard driving distance. For example, the processor (1030) loads the displacement from memory (1010) and calculates the mutual deviation through arithmetic operations that calculate the difference between them. It performs a logical operation that compares the calculated deviation value with a threshold value stored in memory (1010), and controls the execution flow of the program by branching according to the result.

[0084] Additionally, the processor (1030) may perform periodic operations for dynamic priority setting. The processor (1030) determines the elapsed time of a unit using an internal timer or external time information, and executes an operation to calculate a final reliability index according to a predefined correction rule or function by receiving reliability indicators and context data at each unit time. This process may include real number operations and weight application operations.

[0085] When a mismatch occurs and the alternative correction logic is called, the processor (1030) applies a dead reckoning algorithm to the inertial measurement unit sensor data.

[0086] The processor (1030) performs operations according to the structure of the machine learning model (930) loaded into the memory (1010). The processor (1030) infers dynamic confidence weights by executing a series of operations defined in the model, such as matrix multiplication and the application of activation functions, on the input displacements, and finally calculates the standard driving distance by calculating the weighted average.

[0087] The processor (1030) calculates the final charge amount by loading the unit rate from the memory (1010) and multiplying it by the standard driving distance, and controls the transmission of this result value to an external device through the communication unit (1020). In this way, the processor (1030) functions as the actual operation entity that implements the technical concept of the present invention.

[0088] The processor (1030) may be implemented as a digital signal processor (DSP) that processes digital signals, a microprocessor, or a time controller (TCON). However, it is not limited thereto, and may include or be defined by one or more of a central processing unit (CPU), a micro controller unit (MCU), a micro processing unit (MPU), a controller, an application processor (AP), a communication processor (CP), or an ARM processor. Additionally, the processor may be implemented as a System on Chip (SoC) or large-scale integration (LSI) with built-in processing algorithms, or in the form of a Field Programmable Gate Array (FPGA). Furthermore, the processor (1030) may include a Neural Processing Unit (NPU), a Graphics Processing Unit (GPU), and a Tensor Processing Unit (TPU).

[0089] Although the embodiments have been described above with reference to limited examples and drawings, those skilled in the art can make various modifications and variations from the description above. For example, suitable results may be achieved even if the described techniques are performed in a different order than described, and / or if the components of the described system, structure, device, circuit, etc. are combined or assembled in a form different from described, or replaced or substituted by other components or equivalents. In other embodiments consistent with the principles of this disclosure, the order of these operations may be changed. Also, non-dependent operations may be performed in parallel.

[0090] Therefore, other implementations, one embodiment, and equivalents to the claims also fall within the scope of the claims set forth below. Explanation of the symbols

[0092] 10: Mileage Verification-Based Billing System 110: Vehicle 120: Billing Server 130: External server 140: User terminal 20: Network 610: Inconsistency section 620: Moving displacement 710: Reliability Index of the First Moving Displacement 720: Reliability Index of the Second Displacement 730: Reliability Index of the Third Moving Displacement 810: Basic Reliability Indicators 820: Context data 830: Reliability Correction Module 840: Final reliability index 911: 1st displacement 913: Second displacement 915: Third displacement 930: Machine learning model 940: Standard mileage

Claims

Claim 1 A billing method using verification of vehicle mileage data, comprising: a step of obtaining a plurality of mileage parameters derived from heterogeneous sources, wherein the plurality of mileage parameters include (i) a first displacement calculated from a geospatial location specification module, (ii) a second displacement measured from a measurement system of the vehicle, and (iii) a third displacement estimated based on a predefined path profile; a step of analyzing the correlation between the mileage parameters and determining a standard mileage that serves as a reference for billing according to a preset judgment logic; and a step of calculating a final billing amount by applying a unit rate to the determined standard mileage and initiating a payment transaction for the calculated billing amount. Claim 2 A driving distance verification-based billing method according to claim 1, characterized by comprising: a step of performing a multilateral comparative analysis by calculating mutual deviations between the first moving displacement, the second moving displacement, and the third moving displacement, respectively; and a step of, if there is one pair of moving displacements among the calculated mutual deviations that is below a preset threshold value, determining the remaining moving displacement not included in the pair as an outlier and excluding it, and determining a standard driving distance according to a predefined priority among the two moving displacements constituting the pair. Claim 3 A driving distance verification-based billing method according to claim 2, wherein the step of determining the standard driving distance comprises: a step of dividing the entire driving section into a plurality of analysis sections when all of the calculated multiple mutual deviations exceed the threshold value; a step of re-performing the multilateral comparison analysis for each analysis section to identify a normal section in which the mutual deviation is within a first threshold value and a mismatch section in which the mutual deviation exceeds the threshold value; and a step of applying an alternative correction logic only to the mismatch section to calculate a corrected displacement, and summing the displacement of the normal section and the corrected displacement to determine the final standard driving distance. Claim 4 A driving distance verification-based billing method according to claim 3, wherein the alternative correction logic calculates the displacement of the mismatch section through dead reckoning using sensor data of an inertial measurement device mounted on the vehicle. Claim 5 A driving distance verification-based billing method according to claim 2, wherein the priority is characterized by calculating a reliability index for each of the first movement displacement, the second movement displacement, and the third movement displacement at preset unit times, and dynamically resetting the priority based on the calculated reliability index. Claim 6 A driving distance verification-based billing method according to claim 5, wherein the reliability index calculated for each unit time is calculated based on at least one of: (i) a reception quality index of a satellite signal collected during the corresponding unit time for the first moving displacement; (ii) a validity or continuity index of data received from an in-vehicle communication network during the corresponding unit time for the second moving displacement; and (iii) an average separation distance index between the vehicle position and a predefined path profile during the corresponding unit time for the third moving displacement. Claim 7 A driving distance verification-based billing method according to claim 6, wherein the step of calculating the reliability index includes the step of correcting the reliability index by additionally reflecting context data, and wherein the context data includes at least one of real-time traffic information, weather information, and road type information included in map information. Claim 8 A billing method based on driving distance verification according to claim 2, wherein the step of determining the standard driving distance is characterized by using a regression-based machine learning model that receives the first moving displacement, the second moving displacement, and the third moving displacement as input, assigns a dynamic confidence weight to each moving displacement based on a previously learned error pattern for each driving situation, and calculates a weighted average standard driving distance by applying the assigned weight. Claim 9 A server comprising a processor; and a memory loaded with instructions that, when executed by said processor, cause to execute a mileage verification-based billing method described in any one of claims 1 to 8. Claim 10 A computer-readable recording medium having a computer program recorded thereon, comprising instructions for a computer to execute a mileage verification-based billing method described in any one of paragraphs 1 through 8.

Images