FORM 2
THE PATENTS ACT, 1970
(39 of 1970)
&
THE PATENT RULES, 2003
COMPLETE SPECIFICATION
(See Section 10 and Rule 13)
Title of invention:
METHOD AND SYSTEM FOR VEHICLE SERVICE SCHEDULING
Applicant
Tata Consultancy Services Limited
A company Incorporated in India under the Companies Act, 1956
Having address:
Nirmal Building, 9th floor,
Nariman point, Mumbai 400021,
Maharashtra, India
Preamble to the description:
The following specification particularly describes the invention and the manner in which it is to be performed.
2
TECHNICAL FIELD
[001]
The disclosure herein generally relates to vehicle maintenance, and, more particularly, to a method and system for vehicle service scheduling.
BACKGROUND 5
[002]
Vehicle service plays a vital role in keeping vehicle health and performance thereby, keeping the vehicle in good working condition. The vehicle owners service the vehicle as per the pre-defined rules set by Original Equipment Manufacturer (OEM) or service stations. Most of the times vehicle servicing depends on the availability of vehicles and free slots in service stations. The vehicle 10 owners may not be aware of the current health of the vehicle to handover the vehicle to the service station for on time service and the free slots available at the service station. Service stations also need to manage their bandwidth in order to achieve efficiency. State of the art practices in this domain fail to determine a service schedule considering such parameters. Traditional systems often do not 15 account for real-time changes in vehicle usage or customer schedules. Existing systems usually rely on static service intervals, not considering the actual condition or usage of the vehicle. Many current systems do not fully integrate different data types (like telematics and weather data) for service scheduling. Conventional scheduling often leads to uneven distribution of workloads in service centers. 20 Existing systems may not prioritize customer convenience, leading to scheduling conflicts.
SUMMARY
[003]
Embodiments of the present disclosure present technological 25 improvements as solutions to one or more of the above-mentioned technical problems recognized by the inventors in conventional systems. For example, in one embodiment, a processor implemented method is provided. The method includes: receiving, via one or more hardware processors, vehicle details (T1), vehicle journey details (T2), vehicle mapped locations (T3), vehicles telematics data (T4), 30 weather data (T5), and vehicle service records (T6), associated with a plurality of
3
vehicles,
as input data; deriving, by processing the input data via the one or more hardware processors, a plurality of usage statistics of the plurality of vehicles, wherein the plurality of usage statistics comprising one or more of journey patterns, journey trends, correlation between the vehicle and location of the vehicle, and anomaly data; extracting, via the one or more hardware processors, a first set of 5 features comprising a) vehicles type, b) location, c) one or more driving patterns, and d) one or more telematics driven health indicators, from the vehicle details (T1), the vehicle map location (T3), and the vehicle telematics data (T4), respectively, of each of the plurality of vehicles; extracting, via the one or more hardware processors, a second set of features comprising a) impact of weather on vehicle 10 performance and service needs, b) relationship between journey patterns and service frequency, c) vehicle journey timeslots, and d) inference on how past service records relate to future maintenance requirements, from the vehicle journey details (T2), the weather data (T5), and the vehicle service records (T6), respectively, of each of the plurality of vehicles; determining, via the one or more 15 hardware processors, a vehicle rank associated with each of the plurality of vehicles, by categorizing the plurality of vehicles into a plurality of pre-defined profiles, based on a determined similarity in terms of the extracted first set of features and the extracted second set of features of each of the plurality of vehicles; generating, via the one or more hardware processors, a first rank matrix, by 20 applying one or more similarity metrics on a) similar vehicle ranks from among the determined vehicle ranks, b) the first set of features, and c) the second set of features, wherein the first rank matrix quantifies extent of similarity between the plurality of vehicles in terms of the first set of features and the second set of features; generating, via the one or more hardware processors, a second rank matrix, 25 for the vehicles having the extent of similarity within a common window of similarity, wherein the second rank matrix correlates the similarity of the first set of features and the second set of features between the plurality of vehicles; and predicting, via the one or more hardware processors, vehicle availability for service on a plurality of days, by correlating at least one of the first rank matrix and the 30 second rank matrix with historical vehicle service data.
4
[004]
In an embodiment of the method, a) the vehicle details comprises of vehicle purchase date, model year, variant, powertrain, and gearbox details, b) the vehicle journey details comprises of drive frequency, duration, and types of trips, c) the vehicle mapped location comprises of geographical patterns in vehicle use, d) the vehicles telematics data comprises of real-time data gathered from an 5 onboard system of the plurality of vehicles, e) the weather data comprises of local weather information, and f) the vehicle service records consists of historical vehicle maintenance and service data.
[005]
In an embodiment of the method, deriving the plurality of usage statistics by applying statistical method comprises: applying descriptive statistics 10 on the input data to measure mean, median, mode and standard deviation to summarize a central tendency and spread data; determining relationship between different parameters of the plurality of vehicles by applying correlation analysis; obtaining one or more of the journey trends and the journey patterns over a selected time period by applying a time series analysis on the input data; identifying the 15 anomaly data indicating any pre-defined unusual vehicle usage or potential data errors; applying one or more visualization techniques on the input data to interpret data and visually explore graphs and charts; and reducing dimensionality of the input data, wherein by reducing the dimensionality of the input data, features influencing one or more vehicle serving needs are identified, and wherein, the 20 central tendency and spread data, the determined relationship between the different parameters, the obtained one or more of the journey trends and the journey patterns, the identified anomaly data, data interpreted by applying the one or more visualization techniques, and the features identified as influencing the one or more vehicle serving needs, form the plurality of usage statistics. 25
[006]
In an embodiment of the method, predicting the vehicle availability for service on the plurality of days comprises of applying one or more machine learning algorithms trained on historical service data, on at least one of the first ranking matrix and the second ranking matrix.
[007]
In an embodiment of the method, the input data is collected for the 30 plurality of vehicles which have provided consent for data collection.
5
[008]
In another embodiment, a system is provided. The system includes one or more hardware processors; a communication interface; and a memory storing a plurality of instructions. The plurality of instructions cause the one or more hardware processors to: receive vehicle details (T1), vehicle journey details (T2), vehicle mapped locations (T3), vehicles telematics data (T4), weather data (T5), 5 and vehicle service records (T6), associated with a plurality of vehicles, as input data; derive, by processing the input data, a plurality of usage statistics of the plurality of vehicles, wherein the plurality of usage statistics comprising one or more of journey patterns, journey trends, correlation between the vehicle and location of the vehicle, and anomaly data; extract a first set of features comprising 10 a) vehicles type, b) location, c) one or more driving patterns, and d) one or more telematics driven health indicators, from the vehicle details (T1), the vehicle map location (T3), and the vehicle telematics data (T4), respectively, of each of the plurality of vehicles; extract a second set of features comprising a) impact of weather on vehicle performance and service needs, b) relationship between the one 15 or more journey patterns and service frequency, c) vehicle journey timeslots, and d) inference on how past service records relate to future maintenance requirements, from the vehicle journey details (T2), the weather data (T5), and the vehicle service records (T6), respectively, of each of the plurality of vehicles; determine a vehicle rank associated with each of the plurality of vehicles, by categorizing the plurality 20 of vehicles into a plurality of pre-defined profiles, based on a determined similarity in terms of the extracted first set of features and the extracted second set of features of each of the plurality of vehicles; generate a first rank matrix, by applying one or more similarity metrics on a) similar vehicle ranks from among the determined vehicle ranks, b) the first set of features, and c) the second set of features, wherein 25 the first rank matrix quantifies extent of similarity between the plurality of vehicles in terms of the first set of features and the second set of features; generate a second rank matrix, for the vehicles having the extent of similarity within a common window of similarity, wherein the second rank matrix correlates the similarity of the first set of features and the second set of features between the plurality of 30 vehicles; and predict vehicle availability for service on a plurality of days, by
6
correlating at least one of the first rank matrix and the second rank matrix with a
historical vehicle service data.
[009]
In an embodiment of the system, a) the vehicle details comprises of vehicle purchase date, model year, variant, powertrain, and gearbox details, b) the vehicle journey details comprises of drive frequency, duration, and types of trips, 5 c) the vehicle mapped location comprises of geographical patterns in vehicle use, d) the vehicles telematics data comprises of real-time data gathered from an onboard system of the plurality of vehicles, e) the weather data comprises of local weather information, and f) the vehicle service records consists of historical vehicle maintenance and service data. 10
[010]
In another embodiment of the system, the one or more hardware processors are configured to derive the plurality of usage statistics by applying statistical method, by: applying descriptive statistics on the input data to measure mean, median, mode and standard deviation to summarize a central tendency and spread data; determining relationship between different parameters of the plurality 15 of vehicles by applying correlation analysis; obtaining one or more of the journey trends and the journey patterns over a selected time period by applying a time series analysis on the input data; identifying the anomaly data, indicating any pre-defined unusual vehicle usage or potential data errors; applying one or more visualization techniques on the input data to interpret data and visually explore graphs and charts; 20 and reducing dimensionality of the input data, wherein by reducing the dimensionality of the input data, features influencing one or more vehicle serving needs are identified, and wherein, the central tendency and spread data, the determined relationship between the different parameters, the obtained one or more of the journey trends and the journey patterns, the identified anomaly data, data 25 interpreted by applying the one or more visualization techniques, and the features identified as influencing the one or more vehicle serving needs, form the plurality of usage statistics.
[011]
In another embodiment of the system, the one or more hardware processors are configured to predict the vehicle availability for service on a plurality 30 of days by applying one or more machine learning algorithms trained on historical
7
service data
, on at least one of the first ranking matrix and the second ranking matrix.
[012]
In another embodiment of the system, the input data is collected for the plurality of vehicles which have provided consent for data collection.
[013]
In yet another aspect, a non-transitory computer readable medium is 5 provided. The non-transitory computer readable medium includes a plurality of instructions, which when executed, cause one or more hardware processors to: receive vehicle details (T1), vehicle journey details (T2), vehicle mapped locations (T3), vehicles telematics data (T4), weather data (T5), and vehicle service records (T6), associated with a plurality of vehicles, as input data; derive, by processing the 10 input data, a plurality of usage statistics of the plurality of vehicles, wherein the plurality of usage statistics comprising one or more of journey patterns, journey trends, correlation between the vehicle and location of the vehicle, and anomaly data; extract a first set of features comprising a) vehicles type, b) location, c) one or more driving patterns, and d) one or more telematics driven health indicators, 15 from the vehicle details (T1), the vehicle map location (T3), and the vehicle telematics data (T4), respectively, of each of the plurality of vehicles; extract a second set of features comprising a) impact of weather on vehicle performance and service needs, b) relationship between journey patterns and service frequency, c) vehicle journey timeslots, and d) inference on how past service records relate to 20 future maintenance requirements, from the vehicle journey details (T2), the weather data (T5), and the vehicle service records (T6), respectively, of each of the plurality of vehicles; determine a vehicle rank associated with each of a plurality of vehicles, by categorizing the plurality of vehicles into a plurality of pre-defined profiles, based on a determined similarity in terms of the extracted first set of features and 25 the extracted second set of features of each of the plurality of vehicles; generate a first rank matrix, by applying one or more similarity metrics on a) similar vehicle ranks from among the determined vehicle ranks, b) the first set of features, and c) the second set of features, wherein the first rank matrix quantifies extent of similarity between the plurality of vehicles in terms of the first set of features and 30 the second set of features; generate a second rank matrix, for the vehicles having
8
the extent of similarity within a common window of similarity, wherein the second
rank matrix correlates the similarity of the first set of features and the second set of features between the plurality of vehicles; and predict vehicle availability for service on a plurality of days, by correlating at least one of the first rank matrix and the second rank matrix with a historical vehicle service data. 5
[014]
In an embodiment of the non-transitory computer readable medium, a) the vehicle details comprises of vehicle purchase date, model year, variant, powertrain, and gearbox details, b) the vehicle journey details comprises of drive frequency, duration, and types of trips, c) the vehicle mapped location comprises of geographical patterns in vehicle use, d) the vehicles telematics data comprises of 10 real-time data gathered from an onboard system of the plurality of vehicles, e) the weather data comprises of local weather information, and f) the vehicle service records consists of historical vehicle maintenance and service data.
[015]
In an embodiment of the non-transitory computer readable medium, deriving the plurality of usage statistics by applying statistical method comprises: 15 applying descriptive statistics on the input data to measure mean, median, mode and standard deviation to summarize a central tendency and spread data; determining relationship between different parameters of the plurality of vehicles by applying correlation analysis; obtaining one or more of the journey trends and the journey patterns over a selected time period by applying a time series analysis 20 on the input data; identifying the anomaly data indicating any pre-defined unusual vehicle usage or potential data errors; applying one or more visualization techniques on the input data to interpret data and visually explore graphs and charts; and reducing dimensionality of the input data, wherein by reducing the dimensionality of the input data, features influencing one or more vehicle serving 25 needs are identified, and wherein, the central tendency and spread data, the determined relationship between the different parameters, the obtained one or more of the journey trends and the journey patterns, the identified anomaly data, data interpreted by applying the one or more visualization techniques, and the features identified as influencing the one or more vehicle serving needs, form the plurality 30 of usage statistics.
9
[016]
In an embodiment of the non-transitory computer readable medium, predicting the vehicle availability for service on the plurality of days comprises of applying one or more machine learning algorithms trained on historical service data, on at least one of the first ranking matrix and the second ranking matrix.
[017]
In an embodiment of the non-transitory computer readable medium, 5 the input data is collected for the plurality of vehicles which have provided consent for data collection.
[018]
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the invention, as claimed. 10
BRIEF DESCRIPTION OF THE DRAWINGS
[019]
The accompanying drawings, which are incorporated in and constitute a part of this disclosure, illustrate exemplary embodiments and, together with the description, serve to explain the disclosed principles: 15
[020]
FIG. 1 illustrates an exemplary system for vehicle service scheduling, according to some embodiments of the present disclosure.
[021]
FIG. 2 is a flow diagram depicting steps involved in the process of vehicle service scheduling, by the system of FIG. 1, according to some embodiments of the present disclosure. 20
[022]
FIG. 3 is a flow diagram depicting steps involved in the process of deriving a plurality of usage statistics by applying statistical method, using the system of FIG. 1, in accordance with some embodiments of the present disclosure.
DETAILED DESCRIPTION OF EMBODIMENTS 25
[023]
Exemplary embodiments are described with reference to the accompanying drawings. In the figures, the left-most digit(s) of a reference number identifies the figure in which the reference number first appears. Wherever convenient, the same reference numbers are used throughout the drawings to refer to the same or like parts. While examples and features of disclosed principles are 30
10
described herein, modifications, adaptations, and other implementations are
possible without departing from the scope of the disclosed embodiments.
[024]
Vehicle service plays a vital role in keeping the vehicle healthy and in a good working condition. The vehicle owners service their vehicle as per the pre-defined rules set by OEM or service stations. Most of the times vehicle 5 servicing depends on the availability of the vehicle and free slots in service stations. The vehicle owners are not aware of the current health of the vehicle to handover the vehicle to the service station for on time service and the free slots available in the service station. Service stations also need to manage their bandwidth in order to achieve efficiency. State of the art practices in this domain fail to determine a 10 service schedule considering such parameters.
[025]
In order to address these challenges, a method and system of vehicle service scheduling are provided. The method includes the following steps. Initially, vehicle details (T1), vehicle journey details (T2), vehicle mapped locations (T3), vehicles telematics data (T4), weather data (T5), and vehicle service records (T6), 15 associated with a plurality of vehicles, are received as input data. Further, a plurality of usage statistics of the plurality of vehicles are derived by processing the input data, wherein the plurality of usage statistics may comprise one or more of journey patterns, journey trends, correlation between the vehicle and location of the vehicle, and anomaly data. Further, a first set of features may comprise a) vehicles type, b) 20 location, c) one or more driving patterns, and d) one or more telematics driven health indicators, may be extracted from the vehicle details (T1), the vehicle map location (T3), and the vehicle telematics data (T4), respectively, of each of the plurality of vehicles. Further, a second set of features comprising a) impact of weather on vehicle performance and service needs, b) relationship between journey 25 patterns and service frequency, c) vehicle journey timeslots, and d) inference on how past service records relate to future maintenance requirements, may be extracted from the vehicle journey details (T2), the weather data (T5), and the vehicle service records (T6), respectively, of each of the plurality of vehicles. Further, a vehicle rank associated with each of the plurality of vehicles may be 30 determined by categorizing the plurality of vehicles into a plurality of pre-defined
11
profiles, based on a determined similarity in terms of the extracted first set of
features and the extracted second set of features of each of the plurality of vehicles. Further, a first rank matrix may be generated by applying one or more similarity metrics on a) similar vehicle ranks from among the determined vehicle ranks, b) the first set of features, and c) the second set of features, wherein the first rank matrix 5 quantifies extent of similarity between the plurality of vehicles in terms of the first set of features and the second set of features. Further, a second rank matrix may be generated for the plurality of vehicles having the extent of similarity within a common window of similarity, wherein the second rank matrix correlates the similarity of the first set of features and the second set of features between the 10 plurality of vehicles. Further, vehicle availability for service on a plurality of days may be predicted by correlating at least one of the first rank matrix and the second rank matrix with historical vehicle service data.
[026]
Referring now to the drawings, and more particularly to FIG. 1 through FIG. 3, where similar reference characters denote corresponding features 15 consistently throughout the figures, there are shown preferred embodiments and these embodiments are described in the context of the following exemplary system and/or method.
[027]
FIG. 1 illustrates an exemplary system for vehicle service scheduling, according to some embodiments of the present disclosure. The system 20 100 includes or is otherwise in communication with hardware processors 102, at least one memory such as a memory 104, an I/O interface 112. The hardware processors 102, memory 104, and the Input /Output (I/O) interface 112 may be coupled by a system bus such as a system bus 108 or a similar mechanism. In an embodiment, the hardware processors 102 can be one or more hardware processors. 25
[028]
The I/O interface 112 may include a variety of software and hardware interfaces, for example, a web interface, a graphical user interface, and the like. The I/O interface 112 may include a variety of software and hardware interfaces, for example, interfaces for peripheral device(s), such as a keyboard, a mouse, an external memory, a printer and the like. Further, the I/O interface 112 30
12
may enable the system 100 to communicate with other devices, such as web servers,
and external databases.
[029]
The I/O interface 112 can facilitate multiple communications within a wide variety of networks and protocol types, including wired networks, for example, local area network (LAN), cable, etc., and wireless networks, such as 5 Wireless LAN (WLAN), cellular, or satellite. For the purpose, the I/O interface 112 may include one or more ports for connecting several computing systems with one another or to another server computer. The I/O interface 112 may include one or more ports for connecting several devices to one another or to another server.
[030]
The one or more hardware processors 102 may be implemented as 10 one or more microprocessors, microcomputers, microcontrollers, digital signal processors, central processing units, node machines, logic circuitries, and/or any devices that manipulate signals based on operational instructions. Among other capabilities, the one or more hardware processors 102 is configured to fetch and execute computer-readable instructions stored in the memory 104. 15
[031]
The memory 104 may include any computer-readable medium known in the art including, for example, volatile memory, such as static random-access memory (SRAM) and dynamic random-access memory (DRAM), and/or non-volatile memory, such as read only memory (ROM), erasable programmable ROM, flash memories, hard disks, optical disks, and magnetic tapes. In an 20 embodiment, the memory 104 includes a plurality of modules 106.
[032]
The plurality of modules 106 include programs or coded instructions that supplement applications or functions performed by the system 100 for executing different steps involved in the process of optimal placement of blocks across worker nodes in a distributed computing environment. The plurality of 25 modules 106, amongst other things, can include routines, programs, objects, components, and data structures, which performs particular tasks or implement particular abstract data types. The plurality of modules 106 may also be used as, signal processor(s), node machine(s), logic circuitries, and/or any other device or component that manipulates signals based on operational instructions. Further, the 30 plurality of modules 106 can be used by hardware, by computer-readable
13
instructions executed by the one or more hardware processors 102, or by a
combination thereof. The plurality of modules 106 can include various sub-modules (not shown). The plurality of modules 106 may include computer-readable instructions that supplement applications or functions performed by the system 100 for the optimal placement of blocks across worker nodes in a distributed computing 5 environment.
[033]
The data repository (or repository) 110 may include a plurality of abstracted pieces of code for refinement and data that is processed, received, or generated as a result of the execution of the plurality of modules in the module(s) 106. 10
[034]
Although the data repository 110 is shown internal to the system 100, it will be noted that, in alternate embodiments, the data repository 110 can also be implemented external to the system 100, where the data repository 110 may be stored within a database (repository 110) communicatively coupled to the system 100. The data contained within such external database may be periodically updated. 15 For example, new data may be added into the database (not shown in FIG. 1) and/or existing data may be modified and/or non-useful data may be deleted from the database. In one example, the data may be stored in an external system, such as a Lightweight Directory Access Protocol (LDAP) directory and a Relational Database Management System (RDBMS). Functions of the components of the 20 system 100 are now explained with reference to steps in flow diagrams in FIG. 2 and FIG. 3.
[035]
FIGS. 2A and FIG. 2B (collectively referred to as FIG. 2) depict a flow diagram depicting steps involved in the process of vehicle service scheduling, by the system 100 of FIG. 1, according to some embodiments of the present 25 disclosure. At step 202 of method 200 of FIG. 2, the system 100 receives, via the one or more hardware processors 102, vehicle details (T1), vehicle journey details (T2), vehicle mapped locations (T3), vehicles telematics data (T4), weather data (T5), and vehicle service records (T6), associated with a plurality of vehicles, as input data. The vehicle details comprises of vehicle specification data such as but 30 not limited to vehicle purchase date, model year, variant, powertrain, and gearbox
14
details
. The vehicle journey details comprises of vehicle usage patterns data including, but not limited to, drive frequency, duration, and types of trips. The vehicle mapped location includes geographical patterns in vehicle use. The vehicles telematics data includes real-time data gathered from the vehicles onboard system. The weather data comprises of local weather information, i.e., weather data in the 5 location of the vehicle, and f) the vehicle service records consists of historical vehicle maintenance and service data. In an embodiment, the input data is collected for vehicles which have provided consent for data collection.
[036]
Further, at step 204 of the method 200, the system 100 derives, by processing the input data via the one or more hardware processors 102, a plurality 10 of usage statistics of the plurality of vehicles. The plurality of usage statistics may include one or more of journey patterns, journey trends, correlation between the vehicle and location of the vehicle, and anomaly data. Various steps in the process of deriving the usage statistics are depicted in method 300 in FIG. 3, and are explained hereafter. At step 302 of the method 300, the system 100 applies 15 descriptive statistics on the input data to measure mean, median, mode and standard deviation to summarize a central tendency and spread data. Mean, mode, and standard deviation are some examples of the descriptive statistics. Mean (Average): This calculates the average daily mileage of vehicles. By understanding the average distance vehicles travel, the scheduling system can better predict service needs 20 based on wear and tear associated with mileage. Median: This identifies the middle value of daily mileage data. It's useful for understanding typical vehicle use, particularly in datasets with extreme values (very high or very low mileage) that might skew the average. Mode: This represents the most frequently occurring daily mileage. It helps identify the most common usage pattern among the vehicles, 25 which can be crucial for planning routine services. Standard Deviation: This measures the variance in daily mileage. A high standard deviation indicates a wide range of vehicle usage, which can imply varying service needs across the fleet. These statistical methods help in analyzing vehicle usage data, providing insights necessary for efficient and effective service scheduling. 30
15
[037]
Similarly, Central Tendency refers to the measure that represents a center or typical value in a dataset. In vehicle usage data, this could be the average (mean) or most typical (median) daily mileage. It helps in identifying what is 'normal' for the majority of vehicles. The ‘Spread of data’ indicates range and distribution of data values. In terms of vehicle usage, this could involve assessing 5 how much individual vehicle mileage varies from the average (standard deviation). This helps in understanding the diversity in vehicle usage patterns, crucial for tailoring the service schedule.
[038]
Further, at step 304 of the method 300, the system 100 determines relationship between different parameters of the plurality of vehicles by applying 10 correlation analysis. The correlation analysis helps in understanding interplay between different factors affecting a vehicle's maintenance needs, enhancing the system's ability to schedule services proactively and efficiently. Some Examples of the relationships that were explored through correlation analysis include:
- Mileage vs. Service Frequency: Analyzing how the total mileage correlates with 15 the frequency of service requirements. Higher mileage might strongly correlate with more frequent maintenance needs.
- Weather Conditions vs. Vehicle Wear: Examining the relationship between adverse weather conditions and increased wear on vehicle parts. For instance, vehicles in colder, wetter climates might require more frequent servicing. 20
- Vehicle Usage Frequency vs. Availability: Analyzing the relationship between how often a vehicle is used and its availability for servicing. Frequent usage might correlate with less availability during weekdays.
- Historical Service Patterns vs. Future Availability: Examining past service records to predict future availability, assuming vehicles follow similar service 25 patterns over time.
16
- Seasonal Factors vs. Availability: Identifying how seasons or weather conditions affect vehicle usage, and in turn, service availability. For example, vehicles might be less available during winter in regions with heavy snowfall.
[039]
These relationships help in fine-tuning the prediction of vehicle availability for more efficient service scheduling. 5
[040]
Further, at step 306 of the method 300, the system 100 obtains one or more of the journey trends and the journey patterns over a selected time period by applying a time series analysis on the input data. The journey trends and patterns refer to regularities and commonalities in how and when a vehicle is used. This includes information like the most frequent routes taken, typical distances travelled, 10 times of day when the vehicle is most and least used, and variations in usage between weekdays and weekends. Analyzing these trends helps in understanding a vehicle's operational profile, which is crucial for predicting its availability for servicing and maintenance.
[041]
Further, at step 308 of the method 300, the system 100 identifies the 15 anomaly data in the input data, indicating any pre-defined unusual vehicle usage or potential data errors. The anomalies in vehicle usage data, which in turn forms the anomaly data, are identified using one or more statistical techniques and machine learning models. The process involves: 1. Establishing a Baseline: First, usage patterns that represent expected/normal behavior or working condition of the 20 vehicle are established based on historical data. This includes typical mileage, routes, and times of use. 2. Statistical Analysis: Data points that significantly deviate from this established norm are flagged. Here, ‘significant deviation’ maybe determined with respect to comparison with a defined threshold. The anomaly detection could involve analyzing variations in mileage, unusual times of operation, 25 or unexpected routes. 3. Machine Learning Models: Advanced models like anomaly detection algorithms (Isolation Forest, K-Means Clustering, DBSCAN, One Class SVM) may be used at this stage to identify outliers in the data being processed. These models are trained using standard training approaches to recognize patterns and can alert when there's a departure from these patterns. 4. Continuous 30
17
Monitoring: The system
100 continuously monitors and updates its understanding of ‘normal’ to accommodate gradual changes in usage patterns. Based on these anomalies, the system 100 can better understand irregularities in vehicle use, which is important for accurate service scheduling.
[042]
Further, at step 310 of the method 300, the system 100 applies one 5 or more visualization techniques on the input data to interpret data and visually explore graphs and charts. Further, at step 312 of the method 300, the system 100 reduces dimensionality of the input data to identify features influencing one or more vehicle serving needs. Some of the visualization techniques that maybe used by the system are: 10
1.
Heat Maps: To show areas with the highest frequency of vehicle usage or service needs.
2.
Line Graphs: Useful for visualizing trends over time, like changes in vehicle usage patterns.
3.
Bar Charts: For comparing different types of service requirements across 15 vehicle models or time periods.
4.
Scatter Plots: To identify correlations between different variables, such as mileage and service frequency.
[043]
The system 100 is configured to interpret these visualizations using appropriate algorithms that analyze patterns and anomalies. In an embodiment, the 20 system 100 may facilitate, through appropriate user interface, user interpretation of the generated visualization patterns, especially for complex scenarios or to provide context that the system might not capture.
[044]
The system 100 may achieve the dimensionality reduction using techniques such as but not limited to Principal Component Analysis (PCA). PCA 25 works by identifying and keeping only those features which have been determined as most relevant features, from the input data, which significantly reduces the number of data points the system needs to process. This streamlined data still retains the essential information needed for accurate predictions and analyses but is much simpler and more efficient for the system to handle. By reducing dimensionality, 30 the system 100 can focus on key variables that most influence service needs and
18
availability, improving performance and reducing computational load. For
example, consider that the system 100 collects various data points for each vehicle: daily mileage, average speed, frequency of stops, engine temperature, and tire pressure. This high dimensionality (many variables) can complicate analysis. By applying the PCA, patterns in the data are identified and are re-expressed in terms 5 of principal components, which are new variables created as combinations of the original ones. These principal components capture the most significant variance in the data with fewer variables. For instance, the first principal component might combine aspects of daily mileage, average speed, and frequency of stops because they vary together in a way that represents a large part of the total variance in the 10 data set. By focusing analysis on these principal components, the system 100 efficiently captures most of the important information with less data, simplifying and speeding up the process of predicting service schedules.
[045]
The central tendency and spread data, the determined relationship between the different parameters, the obtained one or more of the journey trends 15 and the journey patterns, the identified anomaly data, data interpreted by applying the one or more visualization techniques, and the features identified as influencing the one or more vehicle serving needs, form the plurality of usage statistics.
[046]
Referring back to the method 200, at step 206 of the method 200, the system 100 extracts, via the one or more hardware processors 102, a first set of 20 features comprising a) vehicles type, b) location, c) one or more driving patterns, and d) one or more telematics driven health indicators, from the vehicle details (T1), the vehicle map location (T3), and the vehicle telematics data (T4), respectively, for each of the plurality of vehicles. Extracting the first set of features from vehicle details, location, and telematics data involves several areas: 25
1. Vehicle Type (from Vehicle Details - T1): The system 100 categorizes vehicles based on specifications like model, size, engine type, etc., which are part of the vehicle details data.
2. Location (from Vehicle Mapped Location - T3): Utilizing GPS data or location 30 tracking, the system 100 identifies common locations or routes for each vehicle.
19
3. Driving Patterns (from Vehicle Telematics Data - T4): The system 100 analyzes telematics data for driving and journey behaviors, such as speed patterns, braking habits, frequent start-stop cycles, and journey patterns.
4. Telematics Driven Health Indicators (from Vehicle Telematics Data - T4): The system 100 assesses vehicle health based on telematics data, such as engine 5 performance, battery status, or tire pressure.
[047]
These features are compiled and processed by the system 100 to understand each vehicle’s characteristics and behavior for the service scheduling.
[048]
Further, at step 208 of the method 200, the system 100 extracts, via the one or more hardware processors 102, a second set of features comprising a) 10 impact of weather on vehicle performance and service needs, b) relationship between the one or more journey patterns and service frequency, c) vehicle journey timeslots, and d) inference on how past service records relate to future maintenance requirements, from the vehicle journey details (T2), the weather data (T5), and the vehicle service records (T6), respectively, of each of the plurality of vehicles. 15 Extracting the second set of features involves the following areas:
1. Impact of Weather on Vehicle Performance and Service Needs (from Weather Data - T5): The system 100 determines, by analyzing collected historical data, how different weather conditions (like rain, snow, heat) affect vehicle performance. This 20 is done by correlating weather data with reports of vehicle issues or increased service requests during specific weather conditions.
2. Relationship Between Journey Patterns and Service Frequency (from Vehicle Journey Details - T2 and Vehicle Service Records - T6): By comparing journey data (like route frequency, distances) with service records, the system identifies 25 patterns, such as more frequent services for vehicles on longer or rougher routes.
3. Vehicle Journey Timeslots (from Vehicle Journey Details - T2): The system 100 identifies common times when the vehicle is used (morning commute, afternoon commute, evening commute, weekend trips) to predict optimal service scheduling times. 30
20
4. Inference on How Past Service Records Relate to Future Maintenance Requirements (from Vehicle Service Records - T6): Using historical service data, the system 100 forecasts future maintenance needs, spotting trends like certain parts needing replacement after specific intervals.
[049]
This process involves advanced data processing and pattern 5 recognition to enhance the scheduling and maintenance prediction capabilities of the system.
[050]
Further, at step 210 of the method 200, the system 100 determines, via the one or more hardware processors 102, a vehicle rank associated with each of the plurality of vehicles. In order to determine the vehicle rank, the system 100 10 categorizes the plurality of vehicles into a plurality of pre-defined profiles, based on a determined similarity in terms of the extracted first set of features and the extracted second set of features of each of the plurality of vehicles. Each of the pre-defined profiles may be formed of certain combination of features, with each profile having different weightages of different parameters. Depending on which profile 15 matches with the first and second set of features of the vehicle is determined as the profile the vehicle is to be categorized into. The "rank of a vehicle" in the context of the embodiments disclosed herein signifies predicted service needs and availability, based on the vehicle’s match to a specific profile. This rank is derived from analyzing various data points like usage patterns, maintenance history, and 20 vehicle type. A vehicle’s rank guides the system 100 in predicting the optimal times for maintenance and servicing, tailored to that vehicle's unique operational profile and historical data. This ranking facilitates more accurate and efficient service scheduling, tailored to each vehicle's specific requirements and usage patterns. Sub-steps involved in this process are: 25
1. Profile Creation: Profiles are established based on various factors such as vehicle type, usage patterns, maintenance history, etc. Various profiles may be pre-defined and configured with the system 100, wherein each profile may be formed with a unique combination of parameters, and/or with unique values of selected set of parameters. 30
21
2. Matching Vehicles to Profiles: Each vehicle is evaluated and matched to a profile that most closely represents its characteristics and usage data.
3. Rank Determination: The rank of a vehicle is determined based on how closely it aligns with its matched profile. This involves comparing specific characteristics of the vehicle against the defining features of the profile. 5 Hence the vehicle rank is with respect to each profile the vehicle being compared to, and based on extent of similarity, the vehicle may have different ranks with respect to different profiles. The rank of a vehicle essentially indicates its predicted maintenance needs, availability for service, and other service-related predictions. A specific rank might suggest 10 a certain frequency of maintenance, types of services needed, and the best times for scheduling services, based on the profile it aligns with. Each pre-defined profile may have an associated vehicle service characteristic. Hence, ranking indicates closeness/similarity of the vehicle to each profile, and this in turn represents service requirements of the vehicle. 15
[051]
Further, at step 212 of the method 200, the system 100 generates, via the one or more hardware processors 102, a first rank matrix, by applying one or more similarity metrics on a) similar vehicle ranks from among the determined vehicle ranks, b) the first set of features, and c) the second set of features. The first rank matrix quantifies extent of similarity between the plurality of vehicles in terms 20 of first set of features and the second set of features. Generating the first rank matrix involves:
1. Applying similarity metrics: The system 100 uses metrics like Euclidean distance or cosine similarity to measure how similar each vehicle is to others 25 based on the extracted features.
2. Matrix Construction: In this matrix, each row and column represents a vehicle. The intersection of a row and column contains the similarity score between those two vehicles.
22
3. Quantifying Similarity: Higher scores indicate greater similarity. The matrix quantifies these similarities across all vehicles, based on their ranks and features.
Example Representation:
Consider a simplified matrix with three vehicles (V1, V2, V3): 5
V1
V2
V3
V1
1.0
0.8
0.3
V2
0.8
1.0
0.4
V3
0.3
0.4
1.0
[052]
Here, 1.0 represents complete similarity (a vehicle with itself), while other values show similarity with other vehicles, with a higher number indicating more similarity and lower number indicating less similarity.
[053]
Further, at step 214 of the method 200, the system 100 generates, 10 via the one or more hardware processors 102, a second rank matrix, for the vehicles having the extent of similarity within a common window of similarity. The second rank matrix correlates the similarity of the first set of features and the second set of features between the plurality of vehicles.
[054]
The generation of the second rank matrix by the system 100 15 involves:
1. Selection of Similar Vehicles: The system 100 first identifies vehicles that fall within a defined common similarity window based on the first rank matrix. This means selecting vehicles with similarity scores above a certain threshold. 20
2. Feature Correlation: For these selected vehicles, the system 100 then examines the correlations between their features (both from the first and second set of features). This involves looking at how features like driving patterns, service history, and weather impacts are related among these similar vehicles. 25
3. Matrix Construction: In the second rank matrix, each row and column again represents a vehicle. However, this time, the matrix focuses only on
23
vehicles within the similarity window. The values in the matrix represent the degree of feature correlation between pairs of vehicles.
[055]
Example Representation: Consider a simplified matrix with vehicles V1, V2, and V3, all within the similarity window:
V1
V2
V3
V1
1.0
0.7
0.6
V2
0.7
1.0
0.5
V3
0.6
0.5
1.0
5
[056]
Here, the matrix shows how closely related the features of these vehicles are. For instance, V1 and V2 have a correlation score of 0.7, indicating a strong similarity in their features.
[057]
Further, at step 216 of the method 200, the system 100 predicts, via the one or more hardware processors 102, vehicle availability for service on a 10 plurality of days, by correlating at least one of the first rank matrix and the second rank matrix with historical vehicle service data. Predicting the vehicle availability for service on a plurality of days comprises of applying one or more trained machine learning algorithms on at least one of the first ranking matrix and the second ranking matrix, wherein the one or more machine learning models are trained on historical 15 service data.
[058]
Prediction of the vehicle availability for service using the one or more machine learning models involves analysis of similar Vehicles. The system 100 uses the second rank matrix (from step 214) to understand similarities in features between vehicles. This involves analyzing vehicles with comparable 20 characteristics and service histories. In step 216, the system 100 employs a detailed approach, integrating both long-term usage patterns and predictive analytics:
a.
Analysis of 6-Month Vehicle Usage Data: The system 100 assesses vehicle usage patterns over the past six months. This includes daily and weekly usage trends, identifying periods of high and low 25 activity.
24
b.
Weekly Availability Prediction for 30 Days: Using this data, the system 100 predicts the vehicle's availability over the next 30 days, focusing on a weekly basis (Monday through Friday).
c.
Color-Coded Availability: The system 100 categorizes predicted availability into three categories - 'Red' (likely unavailable/busy), 5 'Amber' (possibly available/less busy), and 'Green' (highly available/free). This color coding provides a clear, at-a-glance understanding of when a vehicle is likely to be available for servicing. It is to be understood by a person having ordinary skill in the art or person skilled in the art that the above method of 10 categorizing into Red, Amber, Green is one of different ways (e.g., other ways include providing a numeral reference such as 1), 2), and 3), etc. each depicting a specific category), and such categorization method shall not be construed as limiting the scope of the present disclosure. 15
d.
Machine Learning Enhancement: The system 100 uses ML models, that are trained on historical data using standard ML training approaches, to refine the predictions. They analyze the nuanced interplay of past servicing intervals, recent usage patterns, and similar vehicle profiles to accurately forecast availability. 20
[059]
The written description describes the subject matter herein to enable any person skilled in the art to make and use the embodiments. The scope of the subject matter embodiments is defined by the claims and may include other modifications that occur to those skilled in the art. Such other modifications are intended to be within the scope of the claims if they have similar elements that do 25 not differ from the literal language of the claims or if they include equivalent elements with insubstantial differences from the literal language of the claims.
[060]
The embodiments of present disclosure herein address unresolved problem of vehicle service scheduling. The embodiment, thus provides a mechanism for determining ranks of each vehicle based on a profile the vehicle has 30
25
been determined as belonging to
. Moreover, the embodiments herein further provide a mechanism for predicting vehicle availability for a plurality of days.
[061]
It is to be understood that the scope of the protection is extended to such a program and in addition to a computer-readable means having a message therein; such computer-readable storage means contain program-code means for 5 implementation of one or more steps of the method, when the program runs on a server or mobile device or any suitable programmable device. The hardware device can be any kind of device which can be programmed including e.g., any kind of computer like a server or a personal computer, or the like, or any combination thereof. The device may also include means which could be e.g., hardware means 10 like e.g., an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or a combination of hardware and software means, e.g., an ASIC and an FPGA, or at least one microprocessor and at least one memory with software processing components located therein. Thus, the means can include both hardware means and software means. The method embodiments described herein 15 could be implemented in hardware and software. The device may also include software means. Alternatively, the embodiments may be implemented on different hardware devices, e.g., using a plurality of CPUs.
[062]
The embodiments herein can comprise hardware and software elements. The embodiments that are implemented in software include but are not 20 limited to, firmware, resident software, microcode, etc. The functions performed by various components described herein may be implemented in other components or combinations of other components. For the purposes of this description, a computer-usable or computer readable medium can be any apparatus that can comprise, store, communicate, propagate, or transport the program for use by or in 25 connection with the instruction execution system, apparatus, or device.
[063]
The illustrated steps are set out to explain the exemplary embodiments shown, and it should be anticipated that ongoing technological development will change the manner in which particular functions are performed. These examples are presented herein for purposes of illustration, and not limitation. 30 Further, the boundaries of the functional building blocks have been arbitrarily
26
defined herein for the convenience of the description.
Alternative boundaries can be defined so long as the specified functions and relationships thereof are appropriately performed. Alternatives (including equivalents, extensions, variations, deviations, etc., of those described herein) will be apparent to persons skilled in the relevant art(s) based on the teachings contained herein. Such 5 alternatives fall within the scope of the disclosed embodiments. Also, the words “comprising,” “having,” “containing,” and “including,” and other similar forms are intended to be equivalent in meaning and be open ended in that an item or items following any one of these words is not meant to be an exhaustive listing of such item or items, or meant to be limited to only the listed item or items. It must also be 10 noted that as used herein and in the appended claims, the singular forms “a,” “an,” and “the” include plural references unless the context clearly dictates otherwise.
[064]
Furthermore, one or more computer-readable storage media may be utilized in implementing embodiments consistent with the present disclosure. A computer-readable storage medium refers to any type of physical memory on which 15 information or data readable by a processor may be stored. Thus, a computer-readable storage medium may store instructions for execution by one or more processors, including instructions for causing the processor(s) to perform steps or stages consistent with the embodiments described herein. The term “computer-readable medium” should be understood to include tangible items and exclude 20 carrier waves and transient signals, i.e., be non-transitory. Examples include random access memory (RAM), read-only memory (ROM), volatile memory, nonvolatile memory, hard drives, CD ROMs, DVDs, flash drives, disks, and any other known physical storage media.
[065]
It is intended that the disclosure and examples be considered as exemplary only, with a true scope of disclosed embodiments being indicated by the following claims.
We Claim:
1. A processor implemented method (200), comprising:
receiving (202), via one or more hardware processors, vehicle details (T1), vehicle journey details (T2), vehicle mapped locations (T3), vehicles telematics data (T4), weather data (T5), and vehicle service records (T6), associated with a plurality of vehicles, as input data;
deriving (204), by processing the input data via the one or more hardware processors, a plurality of usage statistics of the plurality of vehicles, wherein the plurality of usage statistics comprising one or more of journey patterns, journey trends, correlation between the vehicle and location of the vehicle, and anomaly data;
extracting (206), via the one or more hardware processors, a first set of features comprising a) vehicles type, b) location, c) one or more driving patterns, and d) one or more telematics driven health indicators, from the vehicle details (T1), the vehicle map location (T3), and the vehicle telematics data (T4), respectively, of each of the plurality of vehicles; extracting (208), via the one or more hardware processors, a second set of features comprising a) impact of weather on vehicle performance and service needs, b) relationship between the one or more journey patterns and service frequency, c) vehicle journey timeslots, and d) inference on how past service records relate to future maintenance requirements, from the vehicle journey details (T2), the weather data (T5), and the vehicle service records (T6), respectively, of each of the plurality of vehicles;
determining (210), via the one or more hardware processors, a vehicle rank associated with each of the plurality of vehicles, by categorizing the plurality of vehicles into a plurality of pre-defined profiles, based on a determined similarity in terms of the extracted first set of features and the extracted second set of features of each of the plurality of vehicles; generating (212), via the one or more hardware processors, a first rank matrix, by applying one or more similarity metrics on a) similar vehicle ranks from among the determined vehicle ranks, b) the first set of features,

and c) the second set of features, wherein the first rank matrix quantifies extent of similarity between the plurality of vehicles in terms of the first set of features and the second set of features;
generating (214), via the one or more hardware processors, a second rank matrix, for the plurality of vehicles having the extent of similarity within a common window of similarity, wherein the second rank matrix correlates the similarity of the first set of features and the second set of features between the plurality of vehicles; and
predicting (216), via the one or more hardware processors, vehicle availability for service on a plurality of days, by correlating at least one of the first rank matrix and the second rank matrix with historical vehicle service data.
2. The processor implemented method as claimed in claim 1, wherein a) the vehicle details comprises of vehicle purchase date, model year, variant, powertrain, and gearbox details, b) the vehicle journey details comprises of drive frequency, duration, and types of trips, c) the vehicle mapped location comprises of geographical patterns in vehicle use, d) the vehicles telematics data comprises of real-time data gathered from an onboard system of the plurality of vehicles, e) the weather data comprises of local weather information, and f) the vehicle service records consists of historical vehicle maintenance and service data.
3. The processor implemented method as claimed in claim 1, wherein deriving the plurality of usage statistics by applying a statistical method comprises:
applying (302) descriptive statistics on the input data to measure mean, median, mode and standard deviation to summarize a central tendency and spread data;
determining (304) relationship between different parameters of the plurality of vehicles by applying correlation analysis;

obtaining (306) one or more of the journey trends and the journey patterns over a selected time period by applying a time series analysis on the input data;
identifying (308) the anomaly data indicating any pre-defined unusual vehicle usage or potential data errors;
applying (310) one or more visualization techniques on the input data to interpret data and visually explore graphs and charts; and reducing (312) dimensionality of the input data, wherein by reducing the dimensionality of the input data, features influencing one or more vehicle serving needs are identified, and wherein, the central tendency and spread data, the determined relationship between the different parameters, the obtained one or more of the journey trends and the journey patterns, the identified anomaly data, data interpreted by applying the one or more visualization techniques, and the features identified as influencing the one or more vehicle serving needs, form the plurality of usage statistics.
4. The processor implemented method as claimed in claim 1, wherein predicting the vehicle availability for service on the plurality of days comprises of applying one or more machine learning algorithms trained on historical service data, on at least one of the first ranking matrix and the second ranking matrix.
5. The processor implemented method as claimed in claim 1, wherein the input data is collected for the plurality of vehicles which have provided consent for data collection.
6. A system (100), comprising:
one or more hardware processors (102);
a communication interface (112); and
a memory (104) storing a plurality of instructions, wherein the plurality of
instructions cause the one or more hardware processors to:

receive vehicle details (T1), vehicle journey details (T2), vehicle mapped locations (T3), vehicles telematics data (T4), weather data (T5), and vehicle service records (T6), associated with a plurality of vehicles, as input data;
derive, by processing the input data, a plurality of usage statistics of the plurality of vehicles, wherein the plurality of usage statistics comprising one or more of journey patterns, journey trends, correlation between the vehicle and location of the vehicle, and anomaly data;
extract a first set of features comprising a) vehicles type, b) location, c) one or more driving patterns, and d) one or more telematics driven health indicators, from the vehicle details (T1), the vehicle map location (T3), and the vehicle telematics data (T4), respectively, of each of the plurality of vehicles;
extract a second set of features comprising a) impact of weather on vehicle performance and service needs, b) relationship between the one or more journey patterns and service frequency, c) vehicle journey timeslots, and d) inference on how past service records relate to future maintenance requirements, from the vehicle journey details (T2), the weather data (T5), and the vehicle service records (T6), respectively, of each of the plurality of vehicles;
determine a vehicle rank associated with each of the plurality of vehicles, by categorizing the plurality of vehicles into a plurality of pre-defined profiles, based on a determined similarity in terms of the extracted first set of features and the extracted second set of features of each of the plurality of vehicles;
generate a first rank matrix, by applying one or more similarity metrics on a) similar vehicle ranks from among the determined vehicle ranks, b) the first set of features, and c) the second set of features, wherein the first rank matrix quantifies extent of similarity

between the plurality of vehicles in terms of the first set of features
and the second set of features;
generate a second rank matrix, for the plurality of vehicles having
the extent of similarity within a common window of similarity,
wherein the second rank matrix correlates the similarity of the first
set of features and the second set of features between the plurality
of vehicles; and
predict vehicle availability for service on a plurality of days, by
correlating at least one of the first rank matrix and the second rank
matrix with historical vehicle service data.
7. The system as claimed in claim 6, wherein a) the vehicle details comprises of vehicle purchase date, model year, variant, powertrain, and gearbox details, b) the vehicle journey details comprises of drive frequency, duration, and types of trips, c) the vehicle mapped location comprises of geographical patterns in vehicle use, d) the vehicles telematics data comprises of real-time data gathered from an onboard system of the plurality of vehicles, e) the weather data comprises of local weather information, and f) the vehicle service records consists of historical vehicle maintenance and service data.
8. The system as claimed in claim 6, wherein the one or more hardware processors are configured to derive the plurality of usage statistics by applying a statistical method, by:
applying descriptive statistics on the input data to measure mean,
median, mode and standard deviation to summarize a central
tendency and spread data;
determining relationship between different parameters of the
plurality of vehicles by applying correlation analysis;
obtaining one or more of the journey trends and the journey patterns
over a selected time period by applying a time series analysis on the
input data;

identifying the anomaly data indicating any pre-defined unusual
vehicle usage or potential data errors;
applying one or more visualization techniques on the input data to
interpret data and visually explore graphs and charts; and
reducing dimensionality of the input data, wherein by reducing the
dimensionality of the input data, features influencing one or more
vehicle serving needs are identified, and wherein,
the central tendency and spread data, the determined relationship
between the different parameters, the obtained one or more of the
journey trends and the journey patterns, the identified anomaly data,
data interpreted by applying the one or more visualization
techniques, and the features identified as influencing the one or more
vehicle serving needs, form the plurality of usage statistics.
9. The system as claimed in claim 6, wherein the one or more hardware processors are configured to predict the vehicle availability for service on the plurality of days by applying one or more machine learning algorithms trained on historical service data, on at least one of the first ranking matrix and the second ranking matrix.
10. The system as claimed in claim 6, wherein the one or more hardware processors are configured to collect the input data for the plurality of vehicles which have provided consent for data collection.