DESC: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 CONTEXTUAL DATA VISUALIZATION

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
The following specification particularly describes the invention and the manner in which it is to be performed.

CROSS-REFERENCE TO RELATED APPLICATIONS AND PRIORITY
[001] The present application claims priority from Indian patent application no. (201821013257), filed on 06th April, 2018 the complete disclosure of which, in its entirety is herein incorporated by reference.
TECHNICAL FIELD
[002] The disclosure herein generally relates to data visualization and, more particularly, to method and system for contextual data visualization to predict optimal visualization pattern.
BACKGROUND
[003] In recent trends, data collected from many distinct areas help data scientists to find correlations that may exist between the data. Enterprise businesses rely on analytics and computing techniques to identify patterns, detect variances, and to collect tangible insights from the large volumes of complex datasets. However, existing techniques for charting data are limited in their capability to render a plurality of different data types within a single chart in an intuitive and meaningful way. Data processed using cognitive techniques and machine learning algorithms generates eminent results and limits in understanding visual patterns and insight for complex data sets. Therefore, it can be difficult to provide visualized insights of the data based on requested cognitive user in a single or multiple charts and managing these data in a progressive information graphics.
[004] Most of the conventional methods, provides visualized datasets for analyzing complex data in user requested form. The data being represented has one or more unbounded dimensions which requires analytical algorithms for analyzing complex datasets. However, these system limits in analyzing the complex data sets along with the cognitive capabilities of the requested user and providing the visualization chart dynamically in the manner user understands.
SUMMARY
[005] Embodiments of the present disclosure present technological 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 system for predicting optimal visualization pattern is provided. The system includes a processor, an Input/output (I/O) interface and a memory coupled to the processor is capable of executing programmed instructions stored in the processor in the memory to pre-process, to receive a request from a user wherein the request comprises a query for data visualization associated with a domain of user interest. The received request is processed by the processor by simultaneously performing to analyze the query to obtain a plurality of visualization features for the query using a visualization model. The plurality of visualization features comprises a chart type, a color with its theme, a type of navigation, an interactivity, collaboration and a visualization mode. Further, a user persona is generated for the user based on a plurality of user parameters using a Machine Learning (ML) model. Further, the system matches the plurality of visualization features and the user persona in accordance with a matching threshold defined for a preset matching technique. Then, maps the user into one of the contextual user group or into the non-contextual user group using the ML model. Further, the optimal data visualization is provided to the user as a response to the user query by predicting an optimal visualization pattern, using a visualization model, for the domain of user interest in accordance with the contextual user group.
[006] In another aspect, a method for predicting optimal visualization pattern is provided. The method includes a processor, an Input/output (I/O) interface and a memory coupled to the processor is capable of executing programmed instructions stored in the processor in the memory to receive a request from a user wherein the request comprises a query for data visualization associated with a domain of user interest. The received request is processed by the processor by simultaneously performing to analyze the query to obtain a plurality of visualization features for the query using a visualization model. The plurality of visualization features comprises a chart type, a color with its theme, a type of navigation, an interactivity, collaboration and a visualization mode. Further, a user persona is generated for the user based on a plurality of user parameters using a Machine Learning (ML) model. Further, the system matches the plurality of visualization features and the user persona in accordance with a matching threshold defined for a preset matching technique. Then, maps the user into one of the contextual user group or into the non-contextual user group using the ML model. Further, the optimal data visualization is provided to the user as an response to the user query by predicting an optimal visualization pattern, using a visualization model, for the domain of user interest in accordance with the contextual user group.
[007] 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.
BRIEF DESCRIPTION OF THE DRAWINGS
[008] 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:
[009] FIG. 1 illustrates an exemplary block diagram of a system for contextual data visualization to predict optimal visualization pattern, in accordance with some embodiments of the present disclosure.
[010] FIG. 2 is a flow diagram illustrating the method for contextual data visualization to predict optimal visualization pattern, in accordance with some embodiments of the present disclosure.
[011] FIG. 3a & 3b is an example architecture of the system FIG. 1 and FIG.2 implemented for processing a user query to provide contextual data visualization by predicting optimal visualization pattern for the user, in accordance with some embodiments of the present disclosure.
[012] FIG.4 is an architecture of a visualization model of the system for obtaining visualization features to process the user query, in accordance with some embodiments of the present disclosure.
[013] FIG.5 is an architecture of a Machine Learning (ML) model for generating user persona of the user to process the user query, in accordance with some embodiments of the present disclosure.
DETAILED DESCRIPTION OF EMBODIMENTS
[014] 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 described herein, modifications, adaptations, and other implementations are possible without departing from the spirit and scope of the disclosed embodiments. It is intended that the following detailed description be considered as exemplary only, with the true scope and spirit being indicated by the following claims.
[015] The embodiments herein provides a method and system for contextual data visualization to predict optimal visualization pattern. The proposed method and the system enables a user to provide a query to a system. The user can provide a query to the system using any display device that includes a laptop, mobile device or a bot. Here, the system may be alternatively referred as data visualization system. The query provided by the user to the system may be a natural language text query or a voice query. The system may then processes the user query to predict an optimal visualization pattern to the user based on a user persona and a plurality of visualization features. The proposed system provides an eminent visualization pattern for the user query by exploring data of user choice for patterns and outliers. The system is capable of analyzing cognitive behavioral patterns of the user to recommend the user by providing best analysis visualization pattern that can be represented and experienced. The proposed system can be easily integrated into any business enterprises with existing reporting tools which provides an extension to supplement visualization. Additionally, the system has the capability to engage with the end user in the natural language text or into the voice based conversation, allowing the user to interact with data and analytics.
[016] Referring now to the drawings, and more particularly to FIG. 1 through FIG.5, where similar reference characters denote corresponding features 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.
[017] FIG. 1 illustrates an exemplary block diagram of a system for contextual data visualization to predict optimal visualization pattern, in accordance with some embodiments of the present disclosure. In an embodiment, the visualization system 100 includes processor (s) 104, communication interface device(s), alternatively referred as or input/output (I/O) interface(s) 106, and one or more data storage devices or memory 102 operatively coupled to the processor (s) 104. The processor (s), alternatively referred as one or more processors 104 may be one or more software processing modules and/or hardware processors. In an embodiment, the hardware processors can be implemented as one or more microprocessors, microcomputers, microcontrollers, digital signal processors, central processing units, state machines, logic circuitries, and/or any devices that manipulate signals based on operational instructions. Among other capabilities, the processor(s) is configured to fetch and execute computer-readable instructions stored in the memory. In an embodiment, the system 100 can be implemented in a variety of computing systems, such as laptop computers, notebooks, hand-held devices, workstations, mainframe computers, servers, a network cloud and the like.
[018] The I/O interface(s) 106 can include a variety of software and hardware interfaces, for example, a web interface, a graphical user interface, and the like and can facilitate multiple communications within a wide variety of networks N/W and protocol types, including wired networks, for example, LAN, cable, etc., and wireless networks, such as WLAN, cellular, or satellite. In an embodiment, the I/O interface device(s) can include one or more ports for connecting a number of devices to one another or to another server.
[019] The memory 102 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 embodiment, the memory 102, may include a repository 110. The repository 110 may store the workflow resource patterns generated from the task. The repository 110 may also record the plurality of attributes for the workflow resource pattern mapping to the corresponding queuing modes. The memory 102 may further comprise information pertaining to input(s)/output(s) of each step performed by the system 100 and methods of the present disclosure.
[020] FIG. 2 is a flow diagram illustrating the method 200 for contextual data visualization to predict optimal visualization pattern, in accordance with some embodiments of the present disclosure. The steps of the method 200 of the flow diagram will now be explained with reference to the components or blocks of the system 100 in conjunction with the example architecture of the system as depicted in FIG.3. In an embodiment, the system 100 comprises one or more data storage devices or the memory 102 operatively coupled to the one or more processors 104 and is configured to store instructions for execution of steps of the method 200 by the one or more processors 104. Although process steps, method steps, techniques or the like may be described in a sequential order, such processes, methods and techniques may be configured to work in alternate orders. In other words, any sequence or order of steps that may be described does not necessarily indicate a requirement that the steps be performed in that order. The steps of processes described herein may be performed in any order practical. Further, some steps may be performed simultaneously.
[021] At step 202 of the method 200, the processor 104 is configured to receive a request, wherein the request comprises a query for data visualization associated with a domain of user interest. The step 202 is explained considering an example in conjunction with FIG.3a &3B. The Fig.3a & 3b is an example architecture of the system FIG. 1 and FIG.2 implemented for processing a user query to provide contextual data visualization by predicting optimal visualization pattern for the user, in accordance with some embodiments of the present disclosure. Here, the user requests for a data visualization report as for obtaining a sales report of an enterprise as a query to the system using a input device. The query received from the user may be a natural language text or a voice. The user may provide his request as query through any input device which is coupled to the system. The user input device may be a web based application, a mobile device, a laptop, a desktop or the bot. The input device may transmit the user query to the system in real time or through an interface coupled to the system. Further, the user is authenticated with valid credentials for entering his query into the system. The user credentials may be user login and password for accessing the system to process user query.
[022] At step 204 of the method 200, the processor 104 is configured to simultaneously perform two actions. First action comprises analysis of the query to obtain a plurality of visualization features for the query using a visualization model. The plurality of visualization features comprises a chart type, a color with its theme, a type of navigation, an interactivity, collaboration and a visualization mode. The first action of the step 204 of the method 200 is explained in conjunction with FIG.4. The FIG.4 is an architecture of a visualization model of the system for obtaining visualization features to process the user query, in accordance with some embodiments of the present disclosure. Once the user is authenticated, the processor (104) processes the natural language text query obtained using a User Interface (UI) such as a bot. In an embodiment the query can be a voice query and is analyzed known using speech analysis techniques. Further, from the query, the system extracts the plurality of visualization features using the visualization model, wherein the visualization model is a trained model. The natural language text query is processed to extract semantics for obtaining a plurality of visualization features. The model is trained using a training dataset, a plurality of rules from a rules repository and a plurality of input parameters. The plurality of input parameters comprises number of dimensions, measures, type of analysis, type of use case, type of data, data volume, visualization pre-requisites, data latency, data granularity, interactive features, collaboration features, user preferences extracted from the user persona to provide a best-fit chart type, an optimal visualization mode and a personalized color with the theme for the user interface (UI).
[023] To train the visualization model the visualization repository obtains the training dataset are obtained manually from the subject matter expert and pre-stores the training dataset. The training dataset are inputted as visualization features for training the visualization model. The rules repository has a plurality of pre-defined rules or patterns based on the learner rule. Further, the rule learner is utilized for tuning the visualization model for updating the plurality of visualization parameters while processing the natural language text query for extracting the plurality of visualization features. The tuned parameters are then fed into the model for deployment. The trained visualization model obtains based on the plurality of visualization features for the user query the best fit chart type, the optimal visualization mode and the UI/UX personalized theme.
[024] In an embodiment, a second action at step 204 comprises generating a user persona of the user for based on a plurality of user parameters using a Machine Learning (ML) model. This step is depicted in conjunction with FIG.5. The FIG.5 is an architecture of a Machine Learning (ML) model for generating user persona of the user to process the user query, in accordance with some embodiments of the present disclosure The basic profile of the user is obtained from the plurality of user parameters, wherein the plurality of user parameters comprises a user role, a type of user, user age and a user device. The user persona of the user is generated using the trained machine learning model. The machine learning model is trained to generate user persona by extracting a plurality of user features from the plurality of user parameters. The user characteristics are identified by descriptive traits to categorize the users into groups. The plurality of user features are processed to create a user vector corresponding to the plurality of user parameters and updating each user vector based on the prior searches of the user. Further, each user vector is used for classifying the user in the user person among a plurality of users based on a similarity profiling technique which is known in the art
[025] At step 206 of the method 200, the processor 104 is configured to matching, the plurality of visualization features and the user persona in accordance with a matching threshold defined for a preset matching technique. The plurality of obtained visualization features and the generated user persona are matched with the preset matching technique to process the user query. The combined analysis results of the plurality of visualization features and the user persona is greater than matching threshold of the preset matching technique, the system maps the user into one of the contextual user group to predict optimal data visualization pattern. The matching threshold is obtained from the test dataset based on the query of the user depending on domain specific, where the subject matter expert pre-sets the matching threshold. For example, for the enterprise domain the matching threshold may be 75% which later varies depending on the ratio of user diversity to the total number of enterprise users.
[026] At step 208 of the method 200, the processor 104 is configured to mapping the user into a contextual user group, among a plurality of contextual groups if the matching is above the matching threshold or into a non- contextual group, if the matching is below the matching threshold using a machine learning model. The machine learning model is trained by obtaining, a training data set, wherein the training dataset comprises pre-defined users matching the user persona and the visualization features into one of the contextual user group. The training data set are mapped into the mapping table that comprises the contextual user groups and each contextual user group is mapped to a visualization feature vector. Each visualization vectors are then mapped based on the query, for obtaining a plurality of recommended visualization parameters for each visualization feature vector.
[027] At step 210 of the method 200, the processor 104 is configured to providing, the data visualization by predicting an optimal visualization pattern, using a visualization model, for the domain of user interest in accordance with the contextual user group. The optimal visualization pattern for the contextual group is in accordance to a predefined pattern for the contextual group. The predefined pattern provides linking of the contextual group to a set of visualization feature vectors and a set of recommended visualization. Further, the optimal visualization pattern provides a best-fit chart type, an optimal visualization mode and a personalized color with the theme for the User Interface (UI) patterns. The system re-trains the ML model by creating a new entry into the contextual user group if the user is mapped into the non-contextual group. The users mapped into the non -contextual group, the domain and intent classification is done using domain ontology and ML techniques for extracting the visualization features which is then rendered. For the user request, the system, recommends the most optimal method of visualization and the viewing so that the users find it most convenient in 2-D, 3-D on laptop or mobile device, or in increased field of view, augmented reality, limited field of view in mobile device, mixed reality with increased field of view with HMD and then into virtual reality unbounded view. This decision is driven by multiple factors which include the analytics use case, type of data, patterns/trends that are required, number of dimensions, best chart type, data volume, data granularity, data latency, interactivity and collaboration etc. needed to get fruitful insights and results. The system recommends the best choice of chart types to suit the specific use case/data analysis needs along with the creative, user-centric UX/UI themes and personalization.
[028] Use case: In an embodiment, considering the user case in most organizations, there are a number of different user “personalities”, or personas, with distinct needs. The system understands the user query using machine learning techniques to understand these personas and transforms the user query into personalized data visualization experience. The system understand each user specific query and provides the user a customized data visualization through interactive interaction. The use cases below depict two different user profiles, their needs and expectations and the obtained optimal data visualization pattern.
Use Case 1
Demographics: Name: John, Role: CEO, Age: 45, Gender: Male, Skills: Master’s degree, Location: Urban
User query:
1. Increase business revenue and profit
2. Reduce cost
3. Identify and mitigate risks
4. New areas and opportunities
5. Manage a competitive edge through innovation and technology
User expected response from the query:
1. Data driven business insights and not just meetings
2. Performance measurement
3. Save time online with quick & efficient analysis and productive outcomes
4. High level visibility into the health of the business at finger tips, actionable insights to improve business.
The machine learning model for generating user persona classifies the plurality of user parameters by extracting the profile of user as, ‘John’ as a CEO user persona based on the demographics, goals and expectations. Further, based on John’s query to the system,
John’s User Query -- “How close/far are we from meeting our objectives?”
The bot engages in an interactive dialog to extract the intent and context. “The CEO has a remote business performance & operations review meeting with the Executive management and Business Heads”. Accordingly, the business performance entities, KPIs, dimension and other reporting vocabulary parameters are extracted from natural language user query, and translated into a database query. The datasets returned are converted to contextual visualizations /infographics/dashboards on-the-fly. The system predicts and renders personalized visualization based on the particular user persona as mentioned below,
1. Dashboards / Infographics with a high-level view of business operations
2. Overview of strategic KPIs at organizational level using KPI/Single value indicator charts
3. Quick trends and thresholds/alerts
4. Ability to drill down and interact with data
5. Clear and concise visualizations, not overwhelming / confusing to interpret
6. Devices/Modes: Collaborative virtual reality
7. UX/UI aligned with brand guidelines and goals.
John the user and other users enter in the same Virtual Arena, ready to interact with the same dashboard to draw insights.
Use Case 2
Demographics: Name: Simon, Role: Customer Marketing/Sales Rep, Age: 33, Gender: Male, Skills: Bachelor’s degree, Location: Urban
User Query
1. Insights from sales data, trends, and metrics to set targets and forecast future sales performance
2. Demand/Pipeline management
3. Campaign execution/co-ordination
4. Wants to connect with customers with contextual offerings, Next Best actions for a customer
User Profile
1. Engaging in business partnerships with clients
2. Staying ahead of industry standards and trends
3. Business Development, promoting products and services
The system classifies Simon as a Customer Sales/Marketing Rep user persona based on the demographics, goals/expectations. Simon has an upcoming client meeting and requests the bot for personalized set of offerings that can up sell/cross sell to the customer. The bot fetches back the contextual, personalized visualizations in the optimal mode recommended based on the particular user persona and scenario as below:
1. Alerts/thresholds on cross-sell/up-sell opportunities and issues
2. Artistic, modern, visually rich dashboards/infographics
3. Real time, Ad-hoc reports/dashboards
4. Ability to drill down and interact with data, sharing/collaborating on data/insights
5. Devices/Modes: Tablet/Mobile/Desktop
6. UX/UI aligned with brand guidelines and goals.
[029] The embodiments of the present disclosure herein addresses unresolved problem contextual data visualization to predict optimal visualization pattern. The system enables providing a rebuilt charting library & components that are configurable and completely customizable. The system provides a self-service for business users to generate a quick data visualizations and visualize, interact and explore data of their choice for trends, patterns and outliers. The system also provides a guided conversation with end users leveraging cognitive and machine learning abilities. The system can be easily integrated within existing landscape, new features /visualizations and can be added, enhanced or customized. The system is capable of analyzing complex data sets for performing any data visualization model in the virtual and mixed reality mode to enhance user experience. The system has the capability to engage with the end user in a text or voice based conversation, allowing them to interact with data and analytics in the most natural way as humans are comfortable with through natural language, thus making it more user friendly, appealing and effortless. The system understands cognitive behavior and the query of the user that learns from different behavioral patterns and analysis traits of user and recommends user specific next best analysis that can be performed. The system also recommends the next best move based on behavioral trends and/or best practices guiding the user to the desired analytics outcome, further enriching the user experience and adoption of analytics.
[030] 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 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.
[031] 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 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 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 modules located therein. Thus, the means can include both hardware means and software means. The method embodiments described herein 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.
[032] The embodiments herein can comprise hardware and software elements. The embodiments that are implemented in software include but are not limited to, firmware, resident software, microcode, etc. The functions performed by various modules described herein may be implemented in other modules or combinations of other modules. 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 connection with the instruction execution system, apparatus, or device.
[033] 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. Further, the boundaries of the functional building blocks have been arbitrarily 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 alternatives fall within the scope and spirit 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 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.
[034] 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 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 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.
[035] It is intended that the disclosure and examples be considered as exemplary only, with a true scope and spirit of disclosed embodiments being indicated by the following claims.
,CLAIMS:1. A processor (104) implemented method for contextual data visualization, wherein the method comprises:
receiving, by a processor (104), a request from a user, wherein the request comprises a query for data visualization associated with a domain of user interest (202);
simultaneously, performing by the processor (104),
analysis, of the query to obtain a plurality of visualization features for the query using a visualization model, wherein the plurality of visualization features comprises a chart type, a color with its theme, a type of navigation, an interactivity, collaboration and a visualization mode; and
generation, of a user persona of the user, based on a plurality of user parameters using a Machine Learning (ML) model;
matching, the plurality of visualization features and the user persona in accordance with a matching threshold defined for a preset matching technique;
mapping, using the ML model, the user into one of:
a contextual user group, among a plurality of contextual groups if the matching is above the matching threshold; and
a non- contextual group, if the matching is below the matching threshold; and
providing, the data visualization by predicting an optimal visualization pattern, using a visualization model, for the domain of user interest in accordance with the contextual user group,
wherein, the optimal visualization pattern for the contextual group is in accordance to a predefined pattern for the contextual group, wherein, the predefined pattern provides linking of the contextual group to a set of visualization feature vectors and a set of recommended visualization, and
wherein, the optimal visualization pattern provides a best-fit chart type, an optimal visualization mode and a personalized color with the theme for the User Inteface (UI) patterns.
2. The method as claimed in claim 1, wherein the method further comprises re-training the ML model by creating a new entry into the contextual user group if the user is mapped into the non-contextual group.
3. The method as claimed in claim 1, wherein the visualization model for obtaining the optimal visualization pattern is trained using a training dataset, a plurality of rules from a rules repository and a plurality of input parameters,
wherein, the plurality of input parameters comprises number of dimensions, measures, type of analysis, type of use case, type of data, data volume, visualization pre-requisites, data latency, data granularity, interactive features, collaboration features, user preferences extracted from the user persona to provide a best-fit chart type, an optimal visualization mode and a personalized color with the theme for the user interface (UI).
4. The method as claimed in claim 1, wherein training the ML model for generating the user persona comprises:
obtaining, the plurality of user parameters associated with a profile of the user, wherein the plurality of user parameters comprises a user role, a type of user, user age and a user device;
extracting, a plurality of user features based on the plurality of user parameters;
creating, a user vector corresponding to the plurality of user features and updating the user vector based on the historical searches; and
classifying, the user in a user persona among a plurality of user personas based on a similarity profiling technique.
5. A system (100) for contextual data visualization, the system (100) comprising:
a memory (102) storing instructions;
one or more Input/Output (I/O) interfaces (106);
and one or more processors (104) coupled to the memory (102) via the one or more I/O interfaces (106), wherein the processor (104) is configured by the instructions to:
receive, a request from a user, wherein the request comprises a query for data visualization associated with a domain of user interest;
simultaneously perform,
analysis, of the query to obtain a plurality of visualization features for the query using a visualization model, wherein the plurality of visualization features comprises a chart type, a color with its theme, a type of navigation, an interactivity, collaboration and a visualization mode; and
generation, of a user persona of the user, based on a plurality of user parameters using a Machine Learning (ML) model;
match, the plurality of visualization features and the user persona in accordance with a matching threshold defined for a preset matching technique;
map, using the ML model, the user into one of:
a contextual user group, among a plurality of contextual groups if the matching is above the matching threshold; and
a non- contextual group, if the matching is below the matching threshold; and
provide, the data visualization by predicting an optimal visualization pattern, using a visualization model, for the domain of user interest in accordance with the contextual user group,
wherein, the optimal visualization pattern for the contextual group is in accordance to a predefined pattern for the contextual group, wherein, the predefined pattern provides linking of the contextual group to a set of visualization feature vectors and a set of recommended visualization, and
wherein, the optimal visualization pattern provides a best-fit chart type, an optimal visualization mode and a personalized color with the theme for the User Inteface (UI) patterns.
6. The system (100) as claimed in claim 5, wherein the method further comprises re-training the ML model by creating a new entry into the contextual user group if the user is mapped into the non-contextual group.
7. The system (100) as claimed in claim 5, wherein the visualization model for obtaining the optimal visualization pattern is trained using a training dataset, a plurality of rules from a rules repository and a plurality of input parameters,
wherein, the plurality of input parameters comprises number of dimensions, measures, type of analysis, type of use case, type of data, data volume, visualization pre-requisites, data latency, data granularity, interactive features, collaboration features, user preferences extracted from the user persona to provide a best-fit chart type, an optimal visualization mode and a personalized color with the theme for the user interface (UI).
8. The system (100) as claimed as claimed in claim 5, wherein training the ML model for generating the user persona comprises:
obtaining, the plurality of user parameters associated with a profile of the user, wherein the plurality of user parameters comprises a user role, a type of user, user age and a user device;
extracting, a plurality of user features based on the plurality of user parameters;
creating, a user vector corresponding to the plurality of user features and updating the user vector based on the historical searches; and
classifying, the user in a user persona among a plurality of user personas based on a similarity profiling technique.