DESC:FORM 2

THE PATENTS ACT, 1970
[39 of 1970]

&
THE PATENTS RULES, 2003

COMPLETE SPECIFICATION

(Section 10; Rule 13)

EXPERT FEEDBACK SYSTEM AND METHOD TO ENHANCE SERVICES OF INDIAN RAILWAYS

Name of the Applicant: Institute of Aeronautical Engineering
An Indian Institution

Address:
Institute of Aeronautical Engineering
Dundigal, Hyderabad – 500 043
Telangana, India

The following specification particularly describes the application and the manner in which it is to be performed.
FIELD OF INVENTION

[001] The present invention in general relates to system and method to analyze social sentiments. In particular, the present invention relates to an Expert Feedback System and method to enhance decision making in Indian Railways services by analyzing passenger’s opinion displayed in social network.

BACKGROUND OF INVENTION

[002] India is the second largest populated country and Indian railways are one amongst the largest network and employment provider in the World. Majority of the Indian people travel needs and freight requirements are fulfilled by the Indian Railways. Biggest challenges in front of the Indian railways are meeting the growing demand in passenger and freight segment, service quality, safety and pricing. Though Indian railways is the unique service provider in such segments, these days it can foresee the competition in terms of premium passenger segments with air/luxury road travel. Additionally increase of air freight and plans to enhance cargo on waters are the real challenges in near future.

[003] Customer satisfaction and retention are key determinants to measure the quality of services of any organization. Last few years brought biggest change in people expectations in terms of service availability, quality of the service and safety. Customers are willing to spend more for better quality and additional services and for their safety. Railways can leverage the better pricing by meeting these customer expectations. The assessment of the quality of services and enhancement of services is a burning challenge for transportation sector like Indian Railways. The sentiment analysis of the passengers is also important to the policy makers of Railways in order to address the problems and fulfill the satisfaction of the passengers.

[004] In present practice, the Indian Railways rely on individual sources such as the traditional feedback system, trusted web sites, surveys and social things (such as Facebook, twitter {hashtags}, etc.). To process this data, railways will need to have a team and infrastructure to segregate the collected data from said social things as actionable items and process improvement categories using semi-automated processes. The main challenges in this process are the interconnection of infrastructure and the data communication medium, trust worthiness, scalability, security and fast response of the data. So the present available techniques are inadequate for solving challenging issues such as relevance, search, semi-structured data processing, and analyze the voluminous data. Also to develop location-based analysis on passenger behavior about visiting plans in terms of duration and place of visit and identification of the pattern of trips is difficult to achieve from present systems and techniques.

[005] The convergence of the IoT and the social network, a new paradigm known as Social Internet of Things (SIoT) is recognized as an intelligent platform in the present digital world to gather the relevant data, efficient storage, and automated process. It is been found that Expert feedback system for computing Big Data analytics is remarkably significant for enhancement of passenger opinions analysis in the specific fields of Indian Railway Service quality improvement and service enhancement.

[006] Accordingly, it is desirable to develop an Expert System which provides effective passenger feedback and behavior information by processing text using natural language processing, social graph clustering and Big Data analytics to.

OBJECT OF THE INVENTION

[007] The principal object of the invention is to overcome the disadvantages/drawbacks of the prior art.

[008] Another object of the present invention is to develop a framework for expert feedback system on the social internet of things using the combination of big data analytics and sentiment analysis.

[009] Another object of the present invention is to establish an build social internet of things (SoT) architecture by integrating connected multiple social things data sources into a central repository of collected data at cloud, Remote/local server for establishing expert feedback system to improve service quality of Indian railways

[0010] Yet another object of this invention is to build a dynamic model to group multiple themes of social data by using graph clustering techniques.

[0011] Further object of the present invention is to design an expert system for doing both categorization of data and sentiment analysis by using advanced machine learning algorithms for quick response as well as service quality improvement, assessment and enhancement.

SUMMARY OF THE INVENTION

[0012] The following summary is provided to facilitate an understanding of some of the innovative features unique to the disclosed description and is not intended to be a full description.

[0013] The present invention discloses a computer implemented intelligent feedback system to analyze customer feedback from social networks which are connected with railways or related organization comprising; Customer Feedback Module 10 for receiving customer feedback from plurality of social networks; Social Internet of Things Module for processing customer feedback received using a processing means; a Distributed Module for storing and analyzing customer feedback through parallel computing, Social Clustering and expert system. The said invention helps in automating collection of feedbacks from existing various internet/cellular network based feedback system, thereby providing a precise and accurate customer opinions resulting to reduction of time in decision making by respective stockholders on different issues existing in any service sector.

[0014] The present invention addresses the problems mentioned in the prior-art by distributed computing method with workable components such as parallel processing of big data sources using Hadoop technology; graph clustering for theme based grouping, advanced natural language processing techniques for sentiment analysis, and advanced machine learning algorithms for the feedback categorization process.

[0015] According to the present invention, the data is explored from social things (such as mobile devices, sensors,etc.). The said useful data is extracted using various data mining techniques. The present invention exploits the correlation among different attribute of the data and facilitates the understanding and defining human behavior using Big Data Analytics. The present disclosed system also tackles the challenge of understanding by providing feedback to the users that offer them the chance to improve their behaviors by using alert messaging technique.

[0016] According to the present invention, disclosed method to enhance passenger’s opinion using Expert feedback system comprises of:

Step 1: Establishing SIoT environment and extracting data from social things (such as websites, social networks, posts, interesting views, shares, opinions, and ratings). After getting this voluminous data from multiple sources, the distributed computing techniques are established for supporting parallel processing by several nodes. The useful data will be extracted using distributed computing.

Step 2: Using Data pre-processing and tokenization process to extract relevant contents, filter out unwanted constituents like embedded emoticons and URLs, and tokenize them into n-grams for further processing. Feature extraction and social network generation identifies significant key terms from the tweets and use them to model the tweets as a social network. Finally, clustering is applied on the generated social network to crystallize it into various clusters. The aim of clustering analysis is that to find the number of clusters and explore the clusters effectively for unlabeled data. Now the data is grouped according to related themes.

Step 3: In each cluster, the data is segregated into two categories: Actionable items for improvement of quality of service and process improvements as suggestions. This is implemented by expert self-learning system.

[0017] According to the present embodiment, an Expert feedback system comprises of: Social Internet of Things Server(SIoT), distributed system implemented with big data analytics, parallel processing system, system for social graph clustering, expert system with machine learning, system to convert deliverables as actionable items/processes, and expert decision making System

[0018] In the present embodiment of the invention, the Social Internet of Things server is developed for volumetric data source by searching with hash tags and keywords related to Indian railways. The pre-process is performed on data to remove noisy data and unrelated items. The social graph clustering is implemented to group the theme based text into a collected data. Expert system with machine learning is implemented to categorize the passenger data as actionable items or process implements.

[0019] The embodiment of the present invention is even though intended to Indian Railways to analyze passenger’s opinion; the application of the invention can also be used to analyze opinion for all services oriented systems viz. aviation, public road transport systems, industries, educational institutes etc. with mere change in the embodiments.

BRIEF DESCRIPTION OF THE DRAWINGS
[0020] A more complete appreciation of aspects of the disclosure and many of the attendant advantages thereof will be readily obtained as the same becomes better understood by reference to the following detailed description when considered in connection with the accompanying drawings which are presented solely for illustration and not limitation of the disclosure, and in which:

[0021] Fig. 1 shows flowchart illustrating working of the Social IoT based Expert feedback device.

[0022] Fig. 2 depict an architecture of expert feedback system in Social IoT based Expert feedback device in railways consistent with various embodiments of the disclosed technology.

DETAILED DESCRIPTION OF THE INVENTION
[0023] Various aspects are disclosed in the following description and related drawings. Alternate aspects may be devised without departing from the scope of the disclosure. Additionally, well-known elements of the disclosure will not be described in detail or will be omitted so as not to obscure the relevant details of the disclosure.

[0024] The words “exemplary” and/or “example” are used herein to mean “serving as an example, instance, or illustration.” Any aspect described herein as “exemplary” and/or “example” is not necessarily to be construed as preferred or advantageous over other aspects. Likewise, the term “aspects of the disclosure” does not require that all aspects of the disclosure include the discussed feature, advantage or mode of operation.

[0025] Further, many aspects are described in terms of sequences of actions to be performed by, for example, elements of a computing device. It will be recognized that various actions described herein can be performed by specific circuits (e.g., an application specific integrated circuit (ASIC)), by program instructions being executed by one or more processors, or by a combination of both. Additionally, these sequence of actions described herein can be considered to be embodied entirely within any form of computer readable storage medium having stored there in a corresponding set of computer instructions that upon execution would cause an associated processor to perform the functionality described herein. Thus, the various aspects of the disclosure may be embodied in a number of different forms, all of which have been contemplated to be within the scope of the claimed subject matter. In addition, for each of the aspects described herein, the corresponding form of any such aspects may be described herein as, for example, “logic configured to” perform the described action.

[0026] As used herein, the term “Internet of Things (IoT) device” is used to refer to any object (e.g., an appliance, a sensor, etc.) that has an addressable interface (e.g., an Internet protocol (IP) address, a Bluetooth identifier (ID), a near-field communication (NFC) ID, etc.) and can transmit information to one or more other devices over a wired or wireless connection. An IoT device may have a passive communication interface, such as a quick response (QR) code, a radio-frequency identification (RFID) tag, an NFC tag, or the like, or an active communication interface, such as a modem, a transceiver, a transmitter-receiver, or the like. An IoT device can have a particular set of attributes (e.g., a device state or status, such as whether the IoT device is on or off, open or closed, idle or active, available for task execution or busy, and so on, a cooling or heating function, an environmental monitoring or recording function, a light-emitting function, a sound-emitting function, etc.) that can be embedded in and/or controlled/monitored by a central processing unit (CPU), microprocessor, ASIC, or the like, and configured for connection to an IoT network such as a local ad-hoc network or the Internet. For example, IoT devices may include, but are not limited to, refrigerators, toasters, ovens, microwaves, freezers, dishwashers, dishes, hand tools, clothes washers, clothes dryers, furnaces, air conditioners, thermostats, televisions, light fixtures, vacuum cleaners, sprinklers, electricity meters, gas meters, etc., so long as the devices are equipped with an addressable communications interface for communicating with the IoT network. IoT devices may also include cell phones, desktop computers, laptop computers, tablet computers, personal digital assistants (PDAs), etc. Accordingly, the IoT network may be comprised of a combination of “legacy” Internet-accessible devices (e.g., laptop or desktop computers, cell phones, etc.) in addition to devices that do not typically have Internet-connectivity (e.g., dishwashers, etc.).

[0027] The term ‘Social Internet of Things’ refers to a platform for worldwide interconnected objects to establish social relationship by sacrificing their individuality to common interest and better service to users.

[0028] Referring to Fig 1 is a block diagram illustrating social feedback system. The customer feedback module 10 receives customer feedback from social networks. This said customer feedback 10 is then used as input for implementation of Social IoT Module 20 for development of expert feedback system. Social internet of things (SIoT) 20 is one of the multi attribute component, which is established with identified social sensors incorporated in respective service. During the implementation of SIoT the said input is transferred to a distribution system module 30 for storage and further processing using big data ecosystem. The said data distribution system module 30 depict the distributed environment, which will establish connected social things. The said things may communicate each other and connected with either server or cloud through internet / cellular network. From the connected social element, the data extraction is performed from respective collected things by using Application Program Interface (API’s) from the remote server and stores in any one of these as local machine / remote server or cloud for further processing. In addition to the text, the crawler also retrieves various users and tweets related structural features and stores them in a structured format. After the processing of the input data in the distribution system, the combined information will be undergoing parallel computing 40 for implementation of pre-process for data analytics using collected data. An analytical tool (such as IBM SPSS Statistics, R programming, etc.) may be used to perform preprocess on social data to standardize the analysis. The text in social posts nature is initially unstructured and informal nature, hence it contains along with text, special characters, emoticons, URLs etc. associated with text, images and videos, specially spelled words has more significance in terms of feedback. Those posts are highly expressive in the present sense as strong complaint or suggestion. The posts includes any of this associated information may be stored in metadata to process further. The extracted data during parallel processing requires data cleansing to make required input precise and accurate. The said extracted data undergoes social graph clustering (50) for identification of major themes in customer's post. The graph clustering techniques (such as Markov clustering) is applied on the generated social network to crystallize it into various clusters. Each cluster signifies with a unique theme hidden in text data. The statistical model of texts (such as LDA model) is used to identify significant key terms for tweets representation using the vector-space model. A social network generation method is used to the model's tweets as a weighted graph in which the weight of an edge represents the topical similarity of the tweets. The graph clustering is used to crystallize the social network into various clusters, each one representing a particular event. Feature extraction and social network generation identifies significant key terms from the tweets using statistical model of texts and use them to model the tweets as a social network.

[0029] The data obtained through social clustering is sent for further processing in Expert system 60. The said expert system (fig. 3) uses machine learning techniques to classify the data into different deliverables of feedback data 70. The said expert system further classifies the processed said deliverables into actionable data feedback items 80 and non-actionable data feedback items 90. The said actionable data feedback items 80 are stored in the system logs and are printable 120 for taking a proper decision 110 by the users on any case. The remaining non-actionable data feedback items will be stored in the system log 100 and are printable as reports 120 by user as a reference in decision making process on any specific situations and scenarios.

For example:
[0030] In Indian railway passenger feedback system includes different things to consider passenger feedbacks. The main focus is to establish a distributed and parallel computing model which extract railway passengers opinions like feedback, suggestions, complements, opinion on newly introduced practices or rules like swatchrail, digital transactions etc., from website feedback, mobile messages, twitter tweets etc. from social sensors.

[0031] Refering to Fig. 2, the implementation of said system with the existing social internet of things related devices will capture feedbacks from different stakeholders and social network of Indian railways. The said raw data obtained from the customer is stored at local/remote servers or cloud. This said raw data is processed through various data cleansing methods for getting a precise and accurate data as per the requirement of any division's officials. The said processed data further segregated into multiple themes using various data clustering techniques. The extracted data in each theme is further classified as actionable and non-actionable items in Expert feedback system using machine learning techniques. The both actionable and non-actionable items/ processes are stored in system logs. The actionable items are processed by Expert system for a proper decision making by respective official in Indian railways. The results obtained during the process can be taken printable reports for further actions by respective stakeholders. ,CLAIMS:We Claim
1. A computer implemented intelligent feedback system to analyze customer feedback from social networks which are connected with railways or related organization comprising;
a. Customer Feedback Module 1 for receiving customer feedback from plurality of social networks;
b. Social Internet of Things Module 2 for processing customer feedback received using a processing means;
a Distributed Module for storing and analyzing customer feedback through parallel computing, Social Clustering and expert system.

2. A computer implemented method for analyzing customer feedback from social networks which are connected with railways or related organization comprising; said method comprising steps of
a. Receiving said customer feedback using Customer feedback module
b. Processing of Customer feedback received from social media from step (a) using customer feedback Module;
c. Storing and Analyzing customer feedback through parallel computing, Social Clustering and expert system on receiving said feedback from step (b) using Distributed Module

3. The method as claimed in claim 3, wherein said data may be stored in the repository of distributed module and can be available in local/remote server, filers or cloud.

4. The method as claimed in claim 3, wherein the said data stored in distributed module is cleaned in Big Data Enterprise Ecosystem with all active social components, accessible by passengers.

5. The method of claim 4, wherein said data will processed and clustered in the form of actionable and Non-actionable data feedback items on the basis of sentiment scores

6. The method of claim 1- 4, wherein the said data undergoes conditional action and processing by experts if feedback data come under actionable,

7. The method of claim 1- 4, wherein the said data is stored and available for assessment by experts if feedback data comes under non actionable item.

8. The method of claim 1- 4, wherein the said data is used to generate reports on deliverable feedback along with related statistics & assessments for purpose of implementation by users and clients.

Dated this on 28th day of June, 2018

Subhajit Saha
Patent Agent (IN/PA-1937)
Agent for the applicant