Claims:We Claim:
1. A processor implemented method, comprising:
obtaining, via one or more hardware processors, an input corresponding to a use case scenario from a user (202);
querying, a database via the one or more hardware processors, for matching content specific to the input (204);
obtaining, via the one or more hardware processors, one or more contextual inputs from the user, if the matching content is not found (206);
querying, the database via the one or more hardware processors, specific to the one or more contextual inputs (208);
performing (210), via the one or more hardware processors:
providing one or more relevant results based on the one or more queried contextual inputs, wherein the one or more relevant results serve as at least one knowledge asset (210a); or
generating, via the one or more hardware processors, one or more contextual terms based on the one or more contextual inputs obtained from the user, wherein the one or more contextual terms serve as a candidate for creation of the at least one knowledge asset (210b);
analysing, via the one or more hardware processors, the at least one knowledge asset to obtain an analysed knowledge asset (212);
automatically generating, via the one or more hardware processors, one or more specific keywords and one or more tags corresponding to the analysed knowledge asset based on content comprised therein (214);
identifying, via the one or more hardware processors, at least one of (i) one or more similar assets, and (ii) one or more specific assets based on the one or more specific keywords and the one or more tags respectively (216),
wherein the one or more keywords are obtained from a keyword glossary comprised in the database, wherein the keyword glossary comprises a plurality of keywords obtained from one or more sources, and wherein the one or more sources comprise at least one of matching content not found, one or more market intelligence reports, one or more analysis reports, one or more request for proposals, and crowd sourcing; and
updating, via the one or more hardware processors, the keyword glossary based on the at least one of (i) the one or more similar assets, and (ii) the one or more specific assets being identified (218).

2. The processor implemented method of claim 2, further comprising performing one or more of:
obtaining additional content based on the updated keyword glossary; and
categorizing (i) the one or more similar assets, and (ii) the one or more specific assets based on the one or more specific keywords and the one or more tags respectively.

3. The processor implemented method of claim 2, further comprising:
categorizing the plurality of keywords comprised in the updated keyword glossary, using one or more categorization techniques, to obtain one or more set of categorical keywords, wherein one or more keywords with spelling errors and one or more keywords with ambiguous terms are categorized using a machine learning technique;
automatically generating a word cloud for each set of categorical keywords from the one or more set of categorical keywords; and
automatically generating a description with summary and one or more individual tag clouds based on the generated word cloud for each set of categorical keywords to determine a decision impact and improvement in a searchability.

4. The processor implemented method of claim 2, further comprising:
obtaining, a request for proposal (RFP) document from one or more users;
analysing the RFP document and identifying one or more relevant key terms from the RFP document; and
automatically recommending one or more knowledge assets based on the one or more identified relevant key terms, wherein the one or more recommended knowledge assets serve as one of one or more case studies or one or more case references.

5. The processor implemented method of claim 4, further comprising
identifying one or more emerging terms from the one or more recommended knowledge assets, that are not found in the updated keyword glossary; and
triggering for content creation based on the one or more emerging terms being not found in the updated keyword glossary.

6. A system (100), comprising:
a memory (102) storing instructions;
one or more communication interfaces (106); and
one or more hardware processors (104) coupled to the memory (102) via the one or more communication interfaces (106), wherein the one or more hardware processors (104) are configured by the instructions to:
obtain an input corresponding to a use case scenario from a user;
query a database for matching content specific to the input;
obtain one or more contextual inputs from the user, if the matching content is not found;
query the database specific to the one or more contextual inputs;
perform:
providing one or more relevant results based on the one or more queried contextual inputs, wherein the one or more relevant results serve as at least one knowledge asset; or
generating, via the one or more hardware processors, one or more contextual terms based on the one or more contextual inputs obtained from the user, wherein the one or more contextual terms serve as a candidate for creation of the at least one knowledge asset;
analyse the at least one knowledge asset to obtain an analysed knowledge asset;
automatically generate one or more specific keywords and one or more tags corresponding to the analysed knowledge asset based on content comprised therein;
identify at least one of (i) the one or more similar assets, and (ii) the one or more specific assets based on the one or more specific keywords and the one or more tags respectively,
wherein the one or more keywords are obtained from a keyword glossary comprised in the database, wherein the keyword glossary comprises a plurality of keywords obtained from one or more sources, and wherein the one or more sources comprise at least one of matching content not found, one or more market intelligence reports, one or more analysis reports, one or more request for proposals, and crowd sourcing; and
update the keyword glossary based on the at least one of (i) the one or more similar assets, and (ii) the one or more specific assets being identified.

7. The system of claim 6, wherein the one or more hardware processors are further configured by the instructions to:
perform one or more of:
obtain additional content based on the updated keyword glossary; and
categorize (i) the one or more similar assets, and (ii) the one or more specific assets based on the one or more specific keywords and the one or more tags respectively.

8. The system of claim 7, wherein the one or more hardware processors are further configured by the instructions to:
categorize the plurality of keywords comprised in the updated keyword glossary, using one or more categorization techniques, to obtain one or more set of categorical keywords, wherein one or more keywords with spelling errors and one or more keywords with ambiguous terms are categorized using a machine learning technique;
automatically generate a word cloud for each set of categorical keywords from the one or more set of categorical keywords; and
automatically generate a description with summary and one or more individual tag clouds based on the generated word cloud for each set of categorical keywords to determine a decision impact and improvement in a searchability.

9. The system of claim 7, wherein the one or more hardware processors are further configured by the instructions to:
obtain a request for proposal (RFP) document from one or more users;
analyse the RFP document and identifying one or more relevant key terms from the RFP document; and
automatically recommend one or more knowledge assets based on the one or more identified relevant key terms, wherein the one or more recommended knowledge assets serve as one of one or more case studies or one or more case references.

10. The system of claim 9, wherein the one or more hardware processors are further configured by the instructions to:
identify one or more emerging terms from the one or more recommended knowledge assets, that are not found in the updated keyword glossary; and
trigger for content creation based on the one or more emerging terms being not found in the updated keyword glossary.

Dated this 04th Day of March 2022

Tata Consultancy Services Limited
By their Agent & Attorney

(Adheesh Nargolkar)
of Khaitan & Co
Reg No IN-PA-1086
, Description:FORM 2

THE PATENTS ACT, 1970
(39 of 1970)
&
THE PATENT RULES, 2003

COMPLETE SPECIFICATION
(See Section 10 and Rule 13)

Title of invention:

CONTEXTUAL INPUTS-BASED RETRIEVAL OF RELEVANT KNOWLEDGE ASSETS FOR RECOMMENDATION AND PROCESS DRIVEN KEYWORD IDENTIFICATION

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.
TECHNICAL FIELD
[001] The disclosure herein generally relates to search and recommendation techniques, and, more particularly, to contextual inputs-based retrieval of relevant knowledge assets and recommendation thereof.

BACKGROUND
[002] In entities such as small and corporate organizations, customers need information or associates from the organizations need knowledge assets to address customer requirements. However, the external website or internal content management solution of such entities needs more capabilities for searching and recommending knowledge assets. There are a few challenges in terms of: (i) associates who are in communication with customer are sometimes not aware of customer intent and interest, (ii) even if the associate is aware of the intent and/or interest, the associate may not be able to get appropriate support from content management system within his/her organization, (iii) when associate attempts for a relevant information search, he/she most of the times leaves with no results founds for a list of associated queries, (iv) further the keyword based, old generation search engine may display irrelevant results, and do not meet the associate’s demands thus failing to meet the customer intent and/or interest, and (iv) voice based search, though implemented may not result in effective outcomes. Other challenges further include analysis of large number of unresolved customer queries is insufficient to understand and relate to the intent and interest of the customer. Further, as the time passes by, the associate may end up with querying for same information in the content management system as the relevant content is not made available. Furthermore, due of lack of insights, search improvement initiatives tend to be inefficient. Such above challenges may result into an unexpected result and eventually leads to a disengagement of the associate from various platforms. There are various existing techniques/approaches available in the market to address customer intent and/or interest. However, these are not customized to address specific organization requirements and cannot replace a recommendation strategy.

SUMMARY
[003] 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 aspect, there is provided a processor implemented method for contextual inputs-based retrieval of one or more relevant assets and recommendation thereof. The method comprises obtaining, via one or more hardware processors, an input corresponding to a use case scenario from a user; querying, a database via the one or more hardware processors, for matching content specific to the input; obtaining, via the one or more hardware processors, one or more contextual inputs from the user, if the matching content is not found; querying, the database via the one or more hardware processors, specific to the one or more contextual inputs; performing: providing one or more relevant results based on the one or more contextual inputs, wherein the one or more relevant results serve as at least one knowledge asset; or generating, via the one or more hardware processors, one or more contextual terms based on the one or more contextual inputs obtained from the user, wherein the one or more contextual terms serve as a candidate for creation of the at least one knowledge asset; analysing the at least one knowledge asset to obtain an analysed knowledge asset; automatically generating one or more specific keywords and one or more tags corresponding to the analysed knowledge asset based on content comprised therein; identifying at least one of (i) one or more similar assets, and (ii) one or more specific assets based on the one or more specific keywords and the one or more tags respectively, wherein the one or more keywords are obtained from a keyword glossary comprised in the database, wherein the keyword glossary comprises a plurality of keywords obtained from one or more sources, and wherein the one or more sources comprise at least one of matching content not found, one or more market intelligence reports, one or more analysis reports, one or more request for proposals, and crowd sourcing; and updating the keyword glossary based on the at least one of (i) the one or more similar assets, and (ii) the one or more specific assets being identified.
[004] In an embodiment, the method further comprises performing one or more of: obtaining additional content based on the updated keyword glossary; and categorizing (i) the one or more similar assets, and (ii) the one or more specific assets based on the one or more specific keywords and the one or more tags respectively.
[005] In an embodiment, the method further comprises categorizing the plurality of keywords comprised in the updated keyword glossary, using one or more categorization techniques, to obtain one or more set of categorical keywords, wherein one or more keywords with spelling errors and one or more keywords with ambiguous terms are categorized using a machine learning technique; automatically generating a word cloud for each set of categorical keywords from the one or more set of categorical keywords; and automatically generating a description with summary and one or more individual tag clouds based on the generated word cloud for each set of categorical keywords to determine a decision impact and improvement in a searchability.
[006] In an embodiment, the method further comprises obtaining, a request for proposal (RFP) document from a user; analysing the RFP document and identifying one or more relevant key terms from the RFP document; and automatically recommending one or more knowledge assets based on the one or more identified relevant key terms, wherein the one or more recommended knowledge assets serve as one of one or more case studies or one or more case references.
[007] In an embodiment, the method further comprises identifying one or more emerging terms from the one or more recommended knowledge assets, that are not found in the updated keyword glossary; and triggering for content creation based on the one or more emerging terms being not found in the updated keyword glossary.
[008] In another aspect, there is provided a processor implemented system for contextual inputs-based retrieval of one or more relevant assets and recommendation thereof. The system comprises: a memory storing instructions; one or more communication interfaces; and one or more hardware processors coupled to the memory via the one or more communication interfaces, wherein the one or more hardware processors are configured by the instructions to: obtain an input corresponding to a use case scenario from a user; query, a database, for matching content specific to the input; obtain one or more contextual inputs from the user, if the matching content is not found; query, the database via the one or more hardware processors, specific to the one or more contextual inputs; perform: provide one or more relevant results based on the one or more contextual inputs, wherein the one or more relevant results serve as at least one knowledge asset; or generate one or more contextual terms based on the one or more contextual inputs obtained from the user, wherein the one or more contextual terms serve as a candidate for creation of the at least one knowledge asset; and analyse the at least one knowledge asset to obtain an analysed knowledge asset; automatically generate one or more specific keywords and one or more tags corresponding to the analysed knowledge asset based on content comprised therein; identify at least one of (i) one or more similar assets, and (ii) one or more specific assets based on the one or more specific keywords and the one or more tags respectively, wherein the one or more keywords are obtained from a keyword glossary comprised in the database, wherein the keyword glossary comprises a plurality of keywords obtained from one or more sources, and wherein the one or more sources comprise at least one of matching content not found, one or more market intelligence reports, one or more analysis reports, one or more request for proposals, and crowd sourcing; and update the keyword glossary based on the at least one of (i) the one or more similar assets, and (ii) the one or more specific assets being identified.
[009] In an embodiment, the one or more hardware processors are further configured by the instructions to perform one or more of: obtain additional content based on the updated keyword glossary; and categorize (i) the one or more similar assets, and (ii) the one or more specific assets based on the one or more specific keywords and the one or more tags respectively.
[010] In an embodiment, the one or more hardware processors are further configured by the instructions to categorize the plurality of keywords comprised in the updated keyword glossary, using one or more categorization techniques, to obtain one or more set of categorical keywords, wherein one or more keywords with spelling errors and one or more keywords with ambiguous terms are categorized using a machine learning technique; automatically generate a word cloud for each set of categorical keywords from the one or more set of categorical keywords; and automatically generate a description with summary and one or more individual tag clouds based on the generated word cloud for each set of categorical keywords to determine a decision impact and improvement in a searchability.
[011] In an embodiment, the one or more hardware processors are further configured by the instructions to obtain, a request for proposal (RFP) document from a user; analysing the RFP document and identify one or more relevant key terms from the RFP document; and automatically recommend one or more knowledge assets based on the one or more identified relevant key terms, wherein the one or more recommended knowledge assets serve as one of one or more case studies or one or more case references.
[012] In an embodiment, the one or more hardware processors are further configured by the instructions to identify one or more emerging terms from the one or more recommended knowledge assets, that are not found in the updated keyword glossary; and trigger for content creation based on the one or more emerging terms being not found in the updated keyword glossary.
[013] In yet another aspect, there are provided one or more non-transitory machine-readable information storage mediums comprising one or more instructions which when executed by one or more hardware processors cause contextual inputs-based retrieval of one or more relevant assets and recommendation thereof, by: obtaining an input corresponding to a use case scenario from a user; querying, a database, for matching content specific to the input; obtaining one or more contextual inputs from the user, if the matching content is not found; querying, the database, specific to the one or more contextual inputs; performing: providing one or more relevant results based on the one or more contextual inputs, wherein the one or more relevant results serve as at least one knowledge asset; or generating one or more contextual terms based on the one or more contextual inputs obtained from the user, wherein the one or more contextual terms serve as a candidate for creation of the at least one knowledge asset; analysing the at least one knowledge asset to obtain an analysed knowledge asset; automatically generating one or more specific keywords and one or more tags corresponding to the analysed knowledge asset based on content comprised therein; identifying at least one of (i) one or more similar assets, and (ii) one or more specific assets based on the one or more specific keywords and the one or more tags respectively, wherein the one or more keywords are obtained from a keyword glossary comprised in the databased, wherein the keyword glossary comprises a plurality of keywords obtained from one or more sources, and wherein the one or more sources comprise at least one of matching content not found, one or more market intelligence reports, one or more analysis reports, one or more request for proposals, and crowd sourcing; and updating the keyword glossary based on the at least one of (i) the one or more similar assets, and (ii) the one or more specific assets being identified.
[014] In an embodiment, the one or more instructions which when executed by the one or more hardware processors further cause performing one or more of: generating additional content based on the updated keyword glossary; and categorizing (i) the one or more similar assets, and (ii) the one or more specific assets based on the one or more specific keywords and the one or more tags respectively.
[015] In an embodiment, the one or more instructions which when executed by the one or more hardware processors further cause categorizing the plurality of keywords comprised in the updated keyword glossary, using one or more categorization techniques, to obtain one or more set of categorical keywords, wherein one or more keywords with spelling errors and one or more keywords with ambiguous terms are categorized using a machine learning technique; automatically generating a word cloud for each set of categorical keywords from the one or more set of categorical keywords; and automatically generating a description with summary and one or more individual tag clouds based on the generated word cloud for each set of categorical keywords to determine a decision impact and improvement in a searchability.
[016] In an embodiment, the one or more instructions which when executed by the one or more hardware processors further cause obtaining, a request for proposal (RFP) document from a user; analysing the RFP document and identifying one or more relevant key terms from the RFP document; and automatically recommending one or more knowledge assets based on the one or more identified relevant key terms, wherein the one or more recommended knowledge assets serve as one of one or more case studies or one or more case references.
[017] In an embodiment, the one or more instructions which when executed by the one or more hardware processors further cause identifying one or more emerging terms from the one or more recommended knowledge assets, that are not found in the updated keyword glossary; and triggering for content creation based on the one or more emerging terms being not found in the updated keyword glossary and previously available knowledge assets.
[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.

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:
[020] FIG. 1 depicts an exemplary system for contextual inputs-based retrieval of one or more relevant knowledge assets and recommendation thereof, in accordance with an embodiment of the present disclosure.
[021] FIG. 2 depict an exemplary high level block diagram of the system for contextual inputs-based retrieval of one or more relevant knowledge assets and recommendation thereof, in accordance with an embodiment of the present disclosure.
[022] FIG. 3 depicts an exemplary flow chart illustrating a method for contextual inputs-based retrieval of one or more relevant knowledge assets and recommendation thereof, using the systems of FIGS. 1-2, in accordance with an embodiment of the present disclosure.
[023] FIG. 4 depicts a flow diagram illustrating a method of analysing keywords for which matching content is not found, in accordance with an embodiment of the present disclosure.
[024] FIG. 5 depicts a flow diagram illustrating a method of creation of knowledge asset/content, in accordance with an embodiment of the present disclosure.
[025] FIG. 6 depicts a flow diagram illustrating a method of analysing market intelligence reports, in accordance with an embodiment of the present disclosure.

DETAILED DESCRIPTION OF EMBODIMENTS
[026] 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 scope of the disclosed embodiments.
[027] As mentioned earlier, customers need information or associates from the organizations need knowledge assets to address customer requirements. There are existing techniques/approaches available in the market to address customer intent and/or interest. However, these are constrained with several challenges as mentioned earlier and are not customized to address specific organization requirements and cannot replace a recommendation strategy. Embodiments of the present disclosure (also referred as present application and interchangeably used herein) provide systems and methods for contextual inputs-based retrieval of one or more relevant assets and recommendation thereof. More specifically, embodiments of the present disclosure provide an asset retrieval and recommendation system that also enables for sustenance of keywords addition wherein identified keywords are used for identifying keywords for content addition. Further, when the search results are not found for contextual input queries, the search terms/keywords which are queried by end-user are analysed using natural language processing (NLP) techniques and categorized wherein the classification of such search terms/keywords are done using machine learning (ML) models. Such analysis of keywords and categorization (where search results are not found) enables the system and method of the present disclosure to suggest on how to improve searchability. For instance, if the content is created and added back to the system, keywords/key terms are identified using NLP for subsequent queries, which are then compared with any previous request for proposal (RFP) documents and relevant/appropriate recommendations are made accordingly. The recommendations may further include case-based reasoning on how and why it is relevant to a current contextual input/query. The system of the present disclosure further arranges results in a manner most suitable for RFP analysis by finding (also referred as identifying and interchangeably used herein) the context for a given keyword. Such analysis report can be further used as a checklist for RFP submission during a potential engagement.
[028] Referring now to the drawings, and more particularly to FIGS. 1 through 6, 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.
[029] FIG. 1 depicts an exemplary system 100 for contextual inputs-based retrieval of one or more relevant knowledge assets and recommendation thereof, in accordance with an embodiment of the present disclosure. In an embodiment, the system 100 may also be referred as one of: asset retrieval and recommendation system (ARRS), a recommendation system, an analytics system, content management system (CMS), and the like and may be interchangeably used herein. In an embodiment, the system 100 includes one or more hardware processors 104, communication interface device(s) or input/output (I/O) interface(s) 106 (also referred as interface(s)), and one or more data storage devices or memory 102 operatively coupled to the one or more hardware processors 104. The one or more processors 104 may be one or more software processing components 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/are 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 (e.g., smartphones, tablet phones, mobile communication devices, and the like), workstations, mainframe computers, servers, a network cloud, and the like.
[030] The I/O interface device(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.
[031] 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, a database 108 is comprised in the memory 102, wherein the database 108 comprises information pertaining to search queries such as contextual inputs/keywords/search terms, and the like. The database 108 further comprises various assets such as knowledge assets, documents, matching content for the contextual inputs, search queries, and the like. Furthermore, the database 108 comprises (i) content added by one or more users, (ii) content generated by the system 100 via one or more user inputs, and the like. For example, content added by the users may be relevant to one or more business or engagement contexts. The database 108 further comprises analysed knowledge assets, specific keywords and one or more tags corresponding to the analysed knowledge assets, one or more similar assets corresponding to the tags, and specific keywords. The database 108 further comprises a keyword glossary wherein the keyword glossary is periodically updated with new search terms/contextual inputs provided by users. The database 108 further comprises one or more categories or a catalogue which include category specific assets (e.g., identical assets, similar assets, or near-similar assets). The term asset and knowledge asset may be interchangeably used herein. The expression ‘knowledge asset’ may refer to a document, or a written description that is searchable/retrieval by the system 100 for a given input query/contextual input.
[032] The memory 102 further comprises one or more analysis technique(s), natural language processing (NLP) technique(s), machine learning technique(s)/model(s), artificial intelligence technique(s), as known in the art that when executed by the system of the present disclosure, enables to perform the method described herein. The memory 102 further comprises (or may further comprise) information pertaining to input(s)/output(s) of each step performed by the systems and methods of the present disclosure. In other words, input(s) fed at each step and output(s) generated at each step are comprised in the memory 102 and can be utilized in further processing and analysis.
[033] FIG. 2 depict an exemplary high level block diagram of the system 100 for contextual inputs-based retrieval of one or more relevant knowledge assets and recommendation thereof, in accordance with an embodiment of the present disclosure.
[034] FIG. 3 depicts an exemplary flow chart illustrating a method for contextual inputs-based retrieval of one or more relevant knowledge assets and recommendation thereof, using the systems of FIGS. 1-2, in accordance with an embodiment of the present disclosure. In an embodiment, the system(s) 100 comprises one or more data storage devices or the memory 102 operatively coupled to the one or more hardware processors 104 and is configured to store instructions for execution of steps of the method by the one or more processors 104. The steps of the method of the present disclosure will now be explained with reference to components of the system 100 of FIG. 1, the block diagram of the system 100 depicted in FIG. 2, and the flow diagram as depicted in FIG. 3.
[035] In an embodiment, at step 202 of the present disclosure, the one or more hardware processors 104 receive an input corresponding to a use case scenario from a user. Various customer touchpoints may be available in the Organization (e.g., customer relation management (CRM) system, Event Management System, Organizations Website, Project Management system that gather’s customer feedback, executive briefing center, Competitor/Customer Information system, etc. In addition, Organization may be partnered with other third-party companies to purchase data about Organization’s customer. This customer data can provide important insights about the customer’s business and can open doors of opportunities. For instance, a use case scenario may include, say customer X leaves an intent and interest on company’s portal. He/she reads an article (intent). He downloads a white paper (interest) and further uses contact me link and provides his/her interest in the form of comments. Further touchpoints may include, but are not limited to, one or more events attended by him, feedback about an Organization after visiting an executing briefing center, feedback provided for Organization's project, meeting next week on specific agenda, and the like.
[036] In an embodiment, at step 204 of the present disclosure, the one or more hardware processors 104 query the database 108 for matching content specific to the input corresponding to the use case scenario. For instance, for the above various touchpoints captured, and based on the inputs provided by the user (e.g., say various search terms/keywords fed by the user as inputs), the database 108 is queried to determine for any matching content specific to the use case scenario.
[037] It is assumed by the system 100 that there is no matching content available. With this assumption, at step 206 of the present disclosure, the one or more hardware processors 104 obtain one or more contextual inputs from the user if (or when) the matching content is not found. In other words, other additional inputs are obtained from the user when there is no matching content (or similar content/results) available in the database 108. Since there is no matching content is available for the input received at step 202, the system 100 further requests the user to provide further details on the information requested. In such scenarios, focused keywords/search terms or focused contextual inputs are provided by the user to the system 100. For instance, additional specific inputs/contextual inputs, may include, but are not limited to, ‘customer experience enhancement using modern technology’, ‘augmented reality/virtual reality (AR/VR)’, ‘Organization case studies related to customer experience’, ‘Industry name in which service is needed’, and the like. It is to be understood by a person having ordinary skill in the art or person skilled in the art that such additional contextual inputs shall not be construed as limiting the scope of the present disclosure.
[038] Based on the additional contextual inputs, at step 208 of the present disclosure, the one or more hardware processors 104 query the database 108 specific to the above mentioned one or more focused contextual inputs.
[039] At step 210 of the present disclosure, the one or more hardware processors 104 performing one or more steps. For instance, at step 210a, the one or more hardware processors 104 provide one or more relevant results based on the one or more queried contextual inputs. For example, now based on the focused contextual inputs, the system 100 may have found matching content or similar content that corresponding to the focused contextual inputs. Such relevant results may include knowledge asset. In other words, the relevant results serve as knowledge asset(s). At step 210b, the one or more hardware processors 104 generate one or more contextual terms based on the one or more contextual inputs obtained from the user. The one or more contextual terms serve as a candidate for creation of knowledge asset(s), in an example embodiment of the present disclosure. The steps 202 till 210 (including 210a and 210b) may be iteratively performed by the system 100. For instance, if the results are still not found related to extra specific input (e.g., focused contextual inputs) of query then the system 100 automatically generates certain (business/key) terms from extra specific inputs and query and for these additional terms content addition is triggered with respect to the requirements of the user.
[040] Alternatively, once the contextual terms are identified from the contextual inputs, one or more knowledge assets may be created by one or more subject matter experts. For instance, the one or more subject matter experts may include other users who have knowledge and experience in the same segment/domain/industry. The one or more subject matter experts may also include users from other segment/domain(s)/industries who have previously contributed to content creation and/or addition. Subject matter experts may also be an entity/person(s) who have prior experience and/or has sufficient knowledge about the market, customer interaction/engagements, and the like, but may be a first timer to create content for addition to the database 108 as knowledge assets. To enable content creation and addition to the database 108, textual description using crowdsourcing may be provided. In an embodiment, say automatic generated (business/key) terms for content addition may be collected and diverted by the system 100 to various teams/stakeholders (e.g., say marketing team) automatically for getting the content generated from various users (e.g., subject matter experts) of those areas/domain/industries.
[041] Once the one or more knowledge assets are added based on their availability as provided by SMEs, or available in the system 100, the system 100 generates a real-time notification which is communicated to the user, wherein the real-time notification indicates that the knowledge asset, the user is looking for is created and stored in the database 108. Such notifications enable the user to be periodically updated with information available to him/her for effective engagements with various stakeholders (e.g., team members, marketing teams, customer, and the like).
[042] In an embodiment, at step 212 of the present disclosure, the one or more hardware processors 104 analyse the one or more knowledge assets to obtain one or more analysed knowledge assets. For instance, say there is at least one created knowledge asset available to the user. This created knowledge asset is analysed by the system 100 to determine its accuracy, relevancy, and the like for the user. The analysis outcome results in an analysed knowledge asset. The analysis by the system 100 also includes indexing the created knowledge asset for easy retrieval for subsequent input queries.
[043] In an embodiment, the step 214 of the present disclosure, the one or more hardware processors 104 automatically generate one or more specific keywords and one or more tags corresponding to the analysed knowledge asset based on content comprised therein. The specific keywords and tags are also indexed in the database 108. Below Table 1 illustrates a knowledge asset that is created and for which specific keywords and tags are generated, tagged, and indexed accordingly.
Table 1
Asset_title Content in asset Themes/Keywords Tags
Indian Bank Gets Consolidated HR Administration System HR transformation journey to consolidate multiple legacy application systems. Solution leverages Agile methodology and Artificial Intelligence to introduce innovative HR Practices for the modern bank. ['HR Transformation', 'Governance', 'Legacy Modernization', 'Delivery', 'Agile Transformation', 'Analytics and Insights', 'Reporting', 'Alliance and Partnerships', 'Automation', 'Modernization', 'Delivery Assurance', 'Government', 'Methodology'] ['data', 'product', 'business', 'helped', 'application', 'plans', 'source', 'system', 'effort', 'legacy', 'created', 'client', 'existing', 'reduced', 'solution', 'administration', 'system', 'modern', 'consolidate', 'time', 'correction', 'sprints', 'automation', 'monitoring', 'processes', 'backlogs', 'knowledge', 'sauce', 'dashboards', 'agile', 'consulting', 'accuracy', 'bid', 'transformation', 'internal', 'provider', 'methodology', 'leverage']

[044] In the above Table 1, asset (e.g., Indian Bank Gets Consolidated HR Administration System) is mentioned in asset_title. In the present example, say asset is a presentation created by Marketing Teams in collaboration with Subject Matter Experts. Commentary is mentioned in the notes section of presentation. It is to be understood by a person having ordinary skill in the art or person skilled in the art that asset can also be any other media content or multimedia content and such examples of asset shall not be construed as limiting the scope of the present disclosure. For instance, an asset (also referred as knowledge asset) may also be a video session of senior leadership team in various conferences, and the like. Here, content (speech to text) needs to be extracted. Other assets may include, say a statistical report related to market requirement is generated every quarter by marketing team, ongoing trends, and future trends, wherein these assets are to be analyzed automatically from quarter to quarter or whenever they are generated, and new trends should be identified. Further, tags may be generated based on those analysis from the asset. In an embodiment, the asset is analyzed based on the content comprised therein. Themes (also referred as keywords and interchangeably used herein) and tags are accordingly generated (e.g., using a python program known in the art) for each asset using matching words. In other words, the keywords, and tags generation by the system 100 may include user fed keywords which get added to the keyword glossary (e.g., also referred as business glossary and interchangeably used herein). Some keywords may be obtained by crowdsourcing. Such keywords generation may either happen offline, real-time or near-real-time, in an embodiment of the present disclosure. Themes/keywords are picked up from a keyword glossary. These themes and tags help the system 100 to return asset accurately.
[045] Other knowledge assets (or similar assets) that are generated/created and stored in the database 108 are depicted in Table 2 as shown below:
Table 2
Asset_title Content in asset Themes/Keywords Tags
Car Manufacturer Implements End-to-End Data Quality Solution for Enhanced Productivity and real-time quality monitoring The company developed a comprehensive end-to-end quality assurance solution to ensure data consistency and generation of error free reports, which led to productivity improvement. This solution uses patented data quality solution. ['Digital Transformation', 'Governance', 'India', 'Delivery', 'Analytics and Insights', 'Reporting', 'Automation', 'Decision Making', 'Quality Assurance', 'Delivery Assurance', 'Database Management', 'automobile'] ['data', 'reports', 'test', 'quality', 'solution', 'database', 'testing', 'company', 'productivity', 'bits', 'based', 'discrepancies', 'led', 'team', 'internal', 'enabled', 'process', 'cases', 'error', 'decision', 'mining', 'ensure', 'transformation', 'end', 'rows', 'executed', 'increased', 'schedule', 'management', 'ensured', 'making', 'detection', 'pre', 'assurance', 'mapping', 'analysis', 'automation', 'generated', 'factors', 'technology', 'landscape', 'jobs', 'realtime', 'powered', 'improved', 'monitor', 'area', 'number', 'scheduling', 'sql', 'wanted', 'etl', 'created', 'automated', 'load', 'server', 'issues', 'leverage', 'shore', 'identified', 'project', 'updates', 'changes', 'stakeholder', 'India', 'extract', 'cols', 'refreshed', 'underlying', 'advance', 'cycle', 'underwent', 'software', 'set', 'life', 'sap', 'columns', 'application', 'prepared', 'supplement', 'quicken', 'services', 'sync', 'committee', 'steering', 'engagement', 'charts', 'site', 'resolve', 'executions', 'monitoring']

[046] Once the keywords, and tags are generated, at step 216 of the present disclosure, the one or more hardware processors 104 identify at least one of (i) one or more similar assets, and (ii) one or more specific assets based on the one or more specific keywords and the one or more tags respectively.
[047] Such keywords are used for are updating the keyword glossary based on the at least one of (i) the one or more similar assets, and (ii) the one or more specific assets being identified. In other words, at step 218 of the present disclosure, the one or more hardware processors 104 update the keyword glossary based on the keywords obtained from similar or specific assets. Below Table 3 depicts an exemplary keyword glossary illustrating keywords updation in the keyword glossary.
Table 3
Industry Services Industry Specific Solution Current Solution Offerings NextGen Solution Offerings
Communications Media & Technology Cognitive Business Operations Divestiure Business Resilience Artificial Intelligence
HiTech Conversational Experiences Payments CRM Augmented Reality
Life Sciences & Healthcare Engineering & Industrial Services Merger and Acquisition Customer Experience Management Connected Products
Public Services Cloud Apps Open Banking Legacy Modernization Digital Channels
Travel Transportation & Hospitality Microservices & API Patient Experience Risk Management Internet of Things
Consumer Goods & Distribution Cyber Security Market Research Supply Chain Management Neural Manufacturing
Energy Resources & Utilities Company Interactive unit Core Banking CRM Remote Working
… … … … …
Insurance Analytics and Insights Clinical Trials Reporting Research and Development

[048] The one or more keywords are obtained from a keyword glossary comprised in the database 108. The keyword glossary comprises a plurality of keywords obtained from one or more sources, wherein the one or more sources comprise at least one of matching content not found, one or more market intelligence reports, one or more analyst reports, one or more request for proposals, and crowd sourcing. For instance, when a matching content is not found during an iterative search query and results retrieval process, such stage/process serve as a source from which keywords/key terms are extracted/identified, in an example embodiment of the present disclosure. Other instances of keyword identification from various sources include data from organization(s), list of technologies published by technology unit(s) in the organizations every year (or on a periodic basis), and the like. Further, these identified keywords may also be compared with latest technologies published on the internet such as Wikipedia® which may serve as another source. In the above table 2, there are new terms (e.g., neural manufacturing, and the like), for which assets are not available. A process is set to add content for these keywords. Visibility of these keywords is provided to unit marketing teams for prioritization. In other words, the one or more hardware processors 104 generate additional content based on the updated keyword glossary, and categorize (i) the one or more similar assets, and (ii) the one or more specific assets based on the one or more specific keywords and the one or more tags respectively.
[049] Analysis of keywords for which matching content is not found is described herein. The keywords from the search not found outcome (or matching content not found) are identified by the system 100 and accordingly stored in the database 108. Such keywords where matching content is not available, may be categorized and labeled accordingly for further processing. The keyword glossary consists of important key terms details such as keywords/themes and categories. ‘Search not found’ analysis uses this to categorize each query depending on content. Both keywords identified from matching content not found, and the keyword glossary fed as input to the system 100 which uses an NLP technique as known in the art/text search to output results into most suitable category for the query. In case of insufficient term, NLP is used to identify suitable category. In an embodiment, a confidence score (e.g., say x%) may be used to threshold suitable category. In the present disclosure, a confidence score of 80% match was used as threshold to choose suitable category. Such confidence score shall not be construed as limiting the scope of the present disclosure. The search category is then identified accordingly. For instance, in an example, category may include search category found, and/or a blank category indicating that category for the search term/keyword is not found. Categorisation is performed using NLP technique as known in the art which enables auto categorization of a specific query based on the keyword glossary. For instance, keywords/search terms are categorized based on a fuzzy search technique as known in the art. These search terms may be transferred to category of search bucket. Further, summary analysis or word cloud generation is performed wherein the summary analysis provides a broad understanding of all search terms/keywords. For instance, such analysis provides insights on what are the users searching for? What is the percentage of queries related to customer? How many queries are related to Industry/technology/Process/specific geography? etc. On the other hand, the word cloud helps visualize data. Once the summary analysis and word cloud are generated, actionable insights are generated which may enable users for efficient search. For instance, says users are searching for technology, then the system 100 makes offerings searchable. The system 100 further enables changes to configuration of long queries. It can be observed that search queries can be as short as one word of 3-4 characters and as long as multiple words with more than x characters (e.g., say 50 characters). The system 100 encourages users to use long queries as these long queries tend to have more context such as industry, geography, technology, offerings, etc. that help generate relatively accurate search results. During categorization of “search not found” queries, say the system 100 may identify query with more than y characters (e.g., say 35 characters) as a long query. Based on data analysis in future, if the system 100 finds that queries with more than 20 characters also provide accurate results, configuration of character values may be performed to identify these more than 20 characters queries as long queries. This helps Product Owners to focus on those query terms that need attention. The above description may be better understood by way of following example. For instance, say query such as include “smart meetings for modern workspace powered by Microsoft® teams” may be 40+ characters. “Smart meetings”, “Microsoft® teams” shall definitely return knowledge assets. Either synonyms are not present, or search engine configuration parameters need to be tweaked for fuzzy search. Another query may include say “Company X point of view on purpose themes sustainability industry deep dives” which may have 40+ characters. “Purpose themes”, “sustainability” related keywords may have corresponding knowledge assets available in the database already. So, the system 100 may find in future that even queries with 20+ characters may provide similar accurate results by tweaking search engine parameters, then the definition of long query may be changed to 20, in configuration file wherein the configuration file is stored in the memory 102. This further helps Product Owners to focus on those query terms that need attention.
[050] Referring to categorization, if the category remains blank or no category specified even after using fuzzy logic, then the keyword glossary is accordingly updated or query specific clarification is obtained from the user (e.g., using appropriate interface – such as a conversation interface or a user recommendation API). If after obtaining the query specific clarification from the user there are no results found, then creation for content is triggered accordingly. Assuming that “robotics in medical”, “nutraceuticals”, “electric vehicles” are some of the terms identified in user (e.g., BRM) search that was carried out a few months ago, for which content was not found. Even if clarification is obtained from users on these queries, accurate results may not be returned. It is highly likely that content/knowledge asset itself is not available as these concepts are new and emerging. Case studies may not have been created so far. For these terms, content addition needs to be triggered, wherein ranking of these terms plays a critical role. Therefore, the system 100 may receive inputs on the ranking wherein (BRMs) provide rank to these keywords based on respective priorities and highly ranked terms may be picked up for content addition (or creation of knowledge asset), in one example embodiment. The above description of analysis of keywords for which matching content is not found can be realized by way of FIG. 4. More specifically, FIG. 4, with reference to FIGS. 1 through 3, depicts a flow diagram illustrating a method of analysing keywords for which matching content is not found, in accordance with an embodiment of the present disclosure.
[051] The content creation process may involve several steps as described herein. For instance, analysis of at least one of (i) the one or more market intelligence reports, (ii) search/matching content not found, (iii) crowdsourcing, (iv) RFP, and (v) analyst report(s) serve as an input to the system 100 for enabling content creation (e.g., creation of knowledge asset).
[052] Market intelligence reports (also referred as market analysis reports or market intelligence analysis reports) are generated from market research teams periodically with different statistics and market growth opportunities in near future. These reports are analyzed automatically by the system 100 wherein emerging technology / process concepts are shared with the users (e.g., business relationship managers (BRMs)) for review and its relevance, and then content is considered for addition as knowledge asset and relevant terms are added to the keyword glossary (e.g., refer FIG. 6). More specifically, FIG. 6, with reference to FIGS. 1 through 5, depicts a flow diagram illustrating a method of analysing market intelligence reports, in accordance with an embodiment of the present disclosure.
[053] Search/matching content not found analysis is performed on queries that do not result into any content from database 108 or across different database.
[054] As user (BRM) is aware of customer queries related to new concepts/terminologies, and are further aware of unmet requirements, these requirements can be collected from BRM automatically using an appropriate interface via crowdsourcing wherein customer details may not be specified for privacy concerns as it may be construed as sensitive data.
[055] More specifically, the process of crowdsourcing is triggered for contents creation, related to query from different departments of organization, other social networks, media networks, web engines etc. These topics shall be consolidated automatically by the system. The crowdsourcing option when selected by the system 100 assumes that the user submitting the input query for matching content is required to do minimum amount of work to provide inputs. In such scenarios, the user (e.g., say in this case BRM) provides his intent and interest through search box. In addition, he should be given opportunity to vote and rank new concepts for which he would like to see content. The topics may depend on requirements provided by customer or his/her organization and his topics of interest where he would like to get content created - customer provides those topics and notifies the priority. From the database 108, his/her (e.g., customer) industry may be populated. The topics are analyzed using known in the art NLP techniques. Existing topics in keyword glossary may be removed. Topics are sorted by priority and number of occurrences. In a similar way, topic gathered from social media, Media Networks etc., may be processed by the system 100 and further be shared with the BRM for ranking and voting. Shortlisted terms are distributed to unit marketing teams or crowdsourced for content creation. Content is created by SMEs in respective units. Notification is sent to BRM (e.g., via various communication channels available and known in the art such as email, message on mobile device, notification on a desktop application) when the content he requested is published to content management system, wherein the notification is a near real-time notification.
[056] Similarly, there can be analysis of RFP which can reveal certain terms not covered in the keyword glossary. This analysis outcome may also serve as a source for adding content. The analyst report analysis may involve analysis from various sources/analysts as known in the art (e.g., Gartner / Forrester) which can depict emerging trends, thus serve as an additional source for adding content. All these analysis outputs serve as input for content addition governance, approval, and tracking wherein addition of content is monitored (e.g., monitoring via user inputs – say a set of team members). Analytical Reports/Triggers help them to monitor periodically, in an example embodiment of the present disclosure. While this team monitors progress, the identification of keywords is automatically done by the system 100. All the above trigger the content addition process into the database 108. The process may be followed by a review wherein a dedicated review team may be identified (e.g., unit marketing teams), wherein the content addition leading to knowledge asset creation is published and coordinated with one or more stakeholders (e.g., SMEs, and the like). The request for asset creation/addition may be made wherein appropriate SME may be contacted via various networks. The asset is then published, and keyword glossary is updated with new keywords/search terms/key terms being identified based on the knowledge asset being created or added. The step of knowledge asset creation as described can be better understood and realized as depicted in FIG. 5. More specifically, FIG. 5, with reference to FIGS. 1 through 4, depicts a flow diagram illustrating a method of creation of knowledge asset/content, in accordance with an embodiment of the present disclosure.
[057] Referring to step of FIG. 3, once (i) the keyword glossary is updated, and (ii) the one or more similar assets, and the one or more specific assets are identified, the one or more hardware processors 104 generate additional content based on the updated keyword glossary, and categorize (i) the one or more similar assets, and (ii) the one or more specific assets based on the one or more specific keywords and the one or more tags respectively.
[058] The one or more hardware processors 104 are further configured by the instructions to categorize the plurality of keywords comprised in the updated keyword glossary, using one or more categorization techniques, to obtain one or more set of categorical keywords; automatically generate a word cloud for each set of categorical keywords from the one or more set of categorical keywords; and automatically generate a description with summary and one or more individual tag clouds based on the generated word cloud for each set of categorical keywords to determine a decision impact and improvement in a searchability. In an embodiment, keyword(s) with spelling errors and keyword(s) with ambiguous terms are categorized using a machine learning technique as known in the art.
[059] The one or more hardware processors 104 are further configured by the instructions to obtain a request for proposal (RFP) document from a user; analyse the RFP document and identifying one or more relevant key terms from the RFP document; and automatically recommend one or more knowledge assets based on the one or more identified relevant key terms. The one or more recommended knowledge assets serve as one of one or more case studies or one or more case references for the various users (e.g., BRM, marketing team, and the like). In other words, the RFP is received, it is analysed by the system 100 with the help of the keyword glossary (e.g., either the initial keyword glossary or the updated keyword glossary) to identify industry/industries, geography/ies, technologies, etc. Further, the keyword search helps in identifying key terms in the RFP, wherein the system 100 invokes (i) one or more ML technique(s) to categorize the keywords/terms with spelling errors or keyword(s) with ambiguous terms. For instance, “Digital transformn” is correctly identified as “Digital Transformation”, and the like, using dense neural network, in an example embodiment of the present disclosure. It is to be understood by a person having ordinary skill in the art or person skilled in the art that such example of neural network shall not be construed as limiting the scope of the present disclosure. In other words, other neural networks such as Convolution neural network (CNN,) Recurrent neural network (RNN), Long short-term memory (LSTM), Gated recurrent units (GRU) may also be implemented herein by the system 100. Alternatively, fuzzy logic algorithm(s) may be used by the system 100, in another example embodiment of the present disclosure Since the system 100 has identified repeating ambiguous term, this data serves as additional knowledge or input for correctly identifying keywords using machine learning.
[060] The one or more hardware processors 104 further automatically generate a word cloud for each set of categorical keywords from the one or more set of categorical keywords. In an embodiment, the word cloud (also referred as keyword cloud) may be generated using internal topics of the organization. For instance, keywords that are relating to emerging technologies, popularity, frequently used terms may be highlighted and be appearing in sufficiently large font in the word cloud. Other ways of depicting such keywords may also be represented by various color coding as known in the art. It shall be understood by a person having ordinary skill in the art or person skilled in the art such depicts of keywords shall not be construed as limiting the scope of the present disclosure.
[061] The one or more hardware processors 104 further automatically generate a description with summary and one or more individual tag clouds based on the generated word cloud for each set of categorical keywords to determine a decision impact and improvement in a searchability. Below Table 4 depicts description with summary being generated by the system, illustrated by way of example:
Table 4
Search terms Percentage rounded off to get a Birds eye view
Company X internal topics 3.09%
Insufficient and incomplete terms 72.8%
Prominent categories such as Industry and Function Transformation and Technology 10.5%
Natural Language Query 2.45%
Customers and Offerings Analysts and Associates 3.09%

Over 162 Queries analysed for July 2021.
[062] The decision for the system 100 that is taken may include, but not limited to, (i) make offerings searchable, for instance, in one of the reports, lot of offering searches were seen where no results were returned, (ii) tweak parameters in search engine/system wherein it was found that content is available still search results are not returned. This issue was resolved after tweaking parameters in search engine, and the like.
[063] Once the relevant key terms are identified, the system 100 automatically recommend one or more knowledge assets present in the database 108. Emerging terms/keyword s from the one or more recommended knowledge assets, not found in the keyword glossary are identified and content creation is triggered for these keywords. For instance, emerging technologies are extracted from a source (e.g., refer https://en.wikipedia.org/wiki/List_of_emerging_technologies), wherein some of them shall be relevant for the system 100 to perform analysis. In customer RFP, one of the technologies is found included say “Domed City”. Content/Knowledge asset shall not be available in the system 100. However, Domed City shall be available in the keyword glossary comprised in the database 108. Since there is in the customer RFP but content is not available, this keyword “Domed City” serves as a candidate for content addition (or creation of knowledge asset) and users (e.g., BRMs) can rank it as per process (or requirement) accordingly.
[064] Embodiments of the present disclosure/present application provide system that implements a method for contextual inputs-based retrieval of relevant knowledge assets and recommendations thereof. More specifically, system and method of the present disclosure focus on providing better support for various stakeholders in an organization or an entity as applicable (e.g., users such as Business Relationship Managers (BMRs) who frequently uses case studies for Request for Proposal (RFP) Support OR Customer Presentations). Conventional approaches requited Subject Matter Experts (SMEs) who can convince customer about the Organization's capabilities to execute Growth and Transformation (G&T) initiatives. The present disclosure reduces dependency on SME and accordingly provides smart (relevant and contextual) recommendations as well as fast and accurate search. This is achieved by capturing data at every customer touch point. Different customer touch points can be: Company Portal, Event, Executive Briefing Center and Feedback provided for Organization's project, meeting with BRM scheduled using CRM system. Data generated at Customer touch point is mostly textual data, which is analysed by implementing NLP techniques, to provide purpose driven recommendations based on these customer touch points. Further, conventional approach which involves querying of dataset using various search logics as known in the art, which may be inaccurate and inefficient in providing results pertaining to user requirements. Embodiments of the present disclosure not only provide contextual inputs-based knowledge assets, but enable (i) addition of new keywords, (ii) analysis for search/keyword/matching content not found, (iii) take decisions to improve searchability, and (iv) context specific recommendations and notification. In traditional approaches, search not found analysis is typically a manual effort. In the present disclosure, the search not found analysis is an automated and holistic approach that enables categorization, bucketing, predicting search keywords and mapping of queries for different search requests. This enables improvement in the way keyword search is performed or keywords/inputs are queries and the entire knowledge assets retrieval process is made easier and efficient.
[065] 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.
[066] 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 processing components 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.
[067] 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 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 connection with the instruction execution system, apparatus, or device.
[068] 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 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.
[069] 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.
[070] 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.