DESC:RESERVATION OF RIGHTS
[0001] A portion of the disclosure of this patent document contains material, which is subject to intellectual property rights such as but are not limited to, copyright, design, trademark, integrated circuit (IC) layout design, and/or trade dress protection, belonging to Jio Platforms Limited (JPL) or its affiliates (hereinafter referred as owner). The owner has no objection to the facsimile reproduction by anyone of the patent document or the patent disclosure, as it appears in the Patent and Trademark Office patent files or records, but otherwise reserves all rights whatsoever. All rights to such intellectual property are fully reserved by the owner.

FIELD OF INVENTION
[0002] The embodiments of the present disclosure generally relate to systems and methods for retrieval of business related information using various tools. More particularly, the present disclosure relates to a system and a method for presenting business relevant news to corporates.

BACKGROUND
[0003] The following description of the related art is intended to provide background information pertaining to the field of the disclosure. This section may include certain aspects of the art that may be related to various features of the present disclosure. However, it should be appreciated that this section is used only to enhance the understanding of the reader with respect to the present disclosure, and not as admissions of the prior art.
[0004] Corporates/organizations having specific businesses require news coverage. In addition, businesses also incorporate sentiments and trends across news covering them to ensure that the business is highlighted in a positive perspective among media. Further, businesses may take any preventive or corrective measures in case the business is highlighted in a wrong perspective. In many instances, businesses lack resources for investigating authenticity of the available news received from/provided by different sources.
[0005] There is, therefore, a need in the art to provide a system and a method that can mitigate the problems associated with the prior arts.

OBJECTS OF THE INVENTION
[0006] Some of the objects of the present disclosure, which at least one embodiment herein satisfies are listed herein below.
[0007] It is an object of the present disclosure to provide a system and a method to enable businesses to systematically analyse news information in mainstream media.
[0008] It is an object of the present disclosure to provide a system and a method that uses Artificial Intelligence (AI) assisted models to retrieve relevant news articles, add supplementary information against each news article, and rank the articles based on relevance.
[0009] It is an object of the present disclosure to provide a system and a method that helps corporates to receive news relevant articles and extract information valuable to their businesses.
[0010] It is an object of the present disclosure to provide a system and a method that generates a trending score based on news articles by analysing the sentiment associated with corporates.

SUMMARY
[0011] This section is provided to introduce certain objects and aspects of the present disclosure in a simplified form that are further described below in the detailed description. This summary is not intended to identify the key features or the scope of the claimed subject matter.
[0012] In an aspect, the present disclosure relates to a system for generating business relevant information. The system includes a processor and a memory operatively coupled with the processor, where said memory stores instructions which, when executed by the processor, cause the processor to receive information associated with one or more entities via a knowledge graph (KG). The processor generates one or more scores associated with one or more new entities based on the one or more entities. The processor receives one or more articles from one or more publishers. The processor matches the one or more articles with the one or more scores to generate an entity relevance score. The processor generates a trending relevance score based on one or more views associated with the one or more articles by a user. The processor generates a sentiment relevance score based on a sentiment of the one or more new entities among the one or more articles. The processor generates an overall relevance score associated with the one or more articles based on the entity relevance score, the trending relevance score, and the sentiment relevance score.
[0013] In an embodiment, the processor may generate the one or more scores based on an old score associated with an entity among the one or more entities and a weight corresponding to the old score.
[0014] In an embodiment, the processor may generate the one or more scores based on one or more aggregated scores associated with the one or more entities and one or more weights corresponding to the one or more aggregated scores.
[0015] In an embodiment, the processor may generate the trending relevance score by being configured to determine one or more views associated with the one or more articles for a predetermined period. The processor may be configured to categorize the one or more articles into a trending profile based on the one or more views for the predetermined period. The processor may be configured to determine a trending score associated with the one or more articles based on the trending profile and generate the trending relevance score associated with the one or more articles.
[0016] In an embodiment, the processor may generate the sentiment relevance score by being configured to generate an entity sentiment profile based on the sentiment of the one or more new entities. The processor may be configured to compute a differential sentiment for the one or more new entities based on the entity sentiment profile among the one or more articles. The processor may be configured to aggregate the differential sentiment to generate a final differential sentiment score among the one or more articles. The processor may be configured to generate the sentiment relevance score based on the aggregated differential sentiment of the one or more new entities among the one or more articles.
[0017] In an embodiment, the processor may be configured to receive one or more feedback inputs associated with the one or more articles based on the overall relevance score. The processor may be configured to determine the sentiment associated with the one or more entities based on the one or more feedback inputs to update the entity sentiment profile. The processor may be configured to determine one or more relationships associated with the one or more new entities among the one or more articles based on the one or more feedback inputs. The processor may be configured to determine one or more attributes associated with the one or more articles based on the one or more feedback inputs. The processor may be configured to update the KG based on the one or more relationships and the one or more attributes.
[0018] In an embodiment, the KG may include one or more defined relationships among the one or more entities. The one or more defined relationships may be based on an importance score assigned to the one or more entities.
[0019] In an aspect, the present disclosure relates to a method for generating business relevant information. The method includes receiving information, by a processor configured with a system, associated with one or more entities via a KG. The method includes generating, by the processor, one or more scores associated with one or more new entities based on the one or more entities. The method includes receiving, by the processor, one or more articles from one or more publishers. The method includes matching, by the processor, the one or more articles with the one or more scores to generate an entity relevance score. The method includes generating, by the processor, a trending relevance score based on one or more views associated with the one or more articles by a user. The method includes generating, by the processor, a sentiment relevance score based on a sentiment of the one or more new entities among the one or more articles. The method includes generating, by the processor, an overall relevance score associated with the one or more articles based on the entity relevance score, the trending relevance score, and the sentiment relevance score.
[0020] In an embodiment, the method may include generating, by the processor, the one or more scores based on an old score associated with an entity among the one or more entities and a weight corresponding to the old score.
[0021] In an embodiment, the method may include generating, by the processor, the one or more scores based on one or more aggregated scores associated with the one or more entities and one or more weights corresponding to the one or more aggregated scores.
[0022] In an embodiment, the method may include generating, by the processor, the trending relevance score by determining the one or more views associated with the one or more articles for a predetermined period. The method may include generating the trending relevance score by categorizing, by the processor, the one or more articles into a trending profile based on the one or more views for the predetermined period. The method may include generating the trending relevance score by determining, by the processor, a trending score associated with the one or more articles based on the trending profile and generating the trending relevance score associated with the one or more articles.
[0023] In an embodiment, the method may include generating, by the processor, the sentiment relevance score by generating an entity sentiment profile based on the sentiment of the one or more new entities. In an embodiment, the method may include generating, by the processor, the sentiment relevance score by computing a differential sentiment for the one or more new entities based on the entity sentiment profile among the one or more articles. In an embodiment, the method may include generating, by the processor, the sentiment relevance score by aggregating the differential sentiment to generate a final differential sentiment score among the one or more articles. In an embodiment, the method may include generating, by the processor, the sentiment relevance score based on the aggregated differential sentiment of the one or more new entities among the one or more articles.
[0024] In an embodiment, the method may include receiving, by the processor, one or more feedback inputs associated with the one or more articles based on the overall relevance score. In an embodiment, the method may include determining, by the processor, the sentiment associated with the one or more entities based on the one or more feedback inputs for updating the entity sentiment profile. In an embodiment, the method may include determining, by the processor, one or more relationships associated with the one or more new entities among the one or more articles based on the one or more feedback inputs. In an embodiment, the method may include determining, by the processor, one or more attributes associated with the one or more articles based on the one or more feedback inputs. In an embodiment, the method may include updating, by the processor, the KG based on the one or more relationships and the one or more attributes.
[0025] In an embodiment, the KG may include one or more defined relationships among the one or more entities. The one or more defined relationships may be based on an importance score assigned to the one or more entities.

BRIEF DESCRIPTION OF DRAWINGS
[0026] The accompanying drawings, which are incorporated herein, and constitute a part of this disclosure, illustrate exemplary embodiments of the disclosed methods and systems which like reference numerals refer to the same parts throughout the different drawings. Components in the drawings are not necessarily to scale, emphasis instead being placed upon clearly illustrating the principles of the present disclosure. Some drawings may indicate the components using block diagrams and may not represent the internal circuitry of each component. It will be appreciated by those skilled in the art that disclosure of such drawings includes the disclosure of electrical components, electronic components, or circuitry commonly used to implement such components.
[0027] FIG. 1 illustrates an example network architecture (100) for implementing a proposed system (108), in accordance with an embodiment of the present disclosure.
[0028] FIG. 2 illustrates an example block diagram (200) of a proposed system (108), in accordance with an embodiment of the present disclosure.
[0029] FIGs. 3A-3B illustrate example flow diagrams (300A, 300B) of a trending score computation module, in accordance with an embodiment of the present disclosure.
[0030] FIG. 4 illustrates an example flow diagram (400) of a sentiment computation module, in accordance with an embodiment of the present disclosure.
[0031] FIG. 5 illustrates an example flow diagram (500) of a differential sentiment computation module, in accordance with an embodiment of the present disclosure.
[0032] FIG. 6 illustrates an example flow diagram (600) of a news profile article processing module, in accordance with an embodiment of the present disclosure.
[0033] FIG. 7 illustrates an example block diagram (700) of a display module, in accordance with an embodiment of the present disclosure.
[0034] FIG. 8 illustrates an example flow diagram (800) of a relevance score computation module, in accordance with an embodiment of the present disclosure.
[0035] FIG. 9 illustrates an example flow diagram (900) of a feedback module, in accordance with an embodiment of the present disclosure.
[0036] FIG. 10 illustrates an example system architecture (1000), of the proposed system (108), in accordance with an embodiment of the present disclosure.
[0037] FIG. 11 illustrates an example computer system (1100) in which or with which embodiments of the present disclosure may be implemented.
[0038] The foregoing shall be more apparent from the following more detailed description of the disclosure.

DEATILED DESCRIPTION
[0039] In the following description, for the purposes of explanation, various specific details are set forth in order to provide a thorough understanding of embodiments of the present disclosure. It will be apparent, however, that embodiments of the present disclosure may be practiced without these specific details. Several features described hereafter can each be used independently of one another or with any combination of other features. An individual feature may not address all of the problems discussed above or might address only some of the problems discussed above. Some of the problems discussed above might not be fully addressed by any of the features described herein.
[0040] The ensuing description provides exemplary embodiments only and is not intended to limit the scope, applicability, or configuration of the disclosure. Rather, the ensuing description of the exemplary embodiments will provide those skilled in the art with an enabling description for implementing an exemplary embodiment. It should be understood that various changes may be made in the function and arrangement of elements without departing from the spirit and scope of the disclosure as set forth.
[0041] Specific details are given in the following description to provide a thorough understanding of the embodiments. However, it will be understood by one of ordinary skill in the art that the embodiments may be practiced without these specific details. For example, circuits, systems, networks, processes, and other components may be shown as components in block diagram form in order not to obscure the embodiments in unnecessary detail. In other instances, well-known circuits, processes, algorithms, structures, and techniques may be shown without unnecessary detail to avoid obscuring the embodiments.
[0042] Also, it is noted that individual embodiments may be described as a process that is depicted as a flowchart, a flow diagram, a data flow diagram, a structure diagram, or a block diagram. Although a flowchart may describe the operations as a sequential process, many of the operations can be performed in parallel or concurrently. In addition, the order of the operations may be re-arranged. A process is terminated when its operations are completed but could have additional steps not included in a figure. A process may correspond to a method, a function, a procedure, a subroutine, a subprogram, etc. When a process corresponds to a function, its termination can correspond to a return of the function to the calling function or the main function.
[0043] The word “exemplary” and/or “demonstrative” is used herein to mean serving as an example, instance, or illustration. For the avoidance of doubt, the subject matter disclosed herein is not limited by such examples. In addition, any aspect or design described herein as “exemplary” and/or “demonstrative” is not necessarily to be construed as preferred or advantageous over other aspects or designs, nor is it meant to preclude equivalent exemplary structures and techniques known to those of ordinary skill in the art. Furthermore, to the extent that the terms “includes,” “has,” “contains,” and other similar words are used in either the detailed description or the claims, such terms are intended to be inclusive in a manner similar to the term “comprising” as an open transition word without precluding any additional or other elements.
[0044] Reference throughout this specification to “one embodiment” or “an embodiment” or “an instance” or “one instance” means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the present disclosure. Thus, the appearances of the phrases “in one embodiment” or “in an embodiment” in various places throughout this specification are not necessarily all referring to the same embodiment. Furthermore, the particular features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.
[0045] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the disclosure. As used herein, the singular forms “a”, “an”, and “the” are intended to include the plural forms as well, unless the context indicates otherwise. It will be further understood that the terms “comprises” and/or “comprising,” when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof. As used herein, the term “and/or” includes any and all combinations of one or more of the associated listed items.
[0046] The present disclosure may aid corporates in receiving relevant news articles and provide information valuable to their businesses. The present disclosure provides a system and a method that extracts keywords and entities related to businesses. Businesses may be required to provide seed information like company name, key person names, and operating industries as input to the system. A knowledge graph may be utilized to enrich the keywords and the entities specific to a corporate, competitors, and industry. The system may calculate relevance of a news article associated with the corporates, the competitors and the industry. Further, the system may provide sentiment around the corporates, the competitors, and the industry, and generate a trending score on the news articles.
[0047] Various embodiments of the present disclosure will be explained in detail with reference to FIGs. 1-11.
[0048] FIG. 1 illustrates an example network architecture (100) for implementing a proposed system (108), in accordance with an embodiment of the present disclosure.
[0049] As illustrated in FIG. 1, the network architecture (100) may include a system (108). The system (108) may be connected to one or more entities (102-1, 102-2…102-N) via one or more computing devices (104-1, 104-2…104-N). It may be appreciated that the one or more computing devices (104-1, 104-2…104-N) may be interchangeably referred as computing devices (104) throughout the disclosure. The computing devices (104) may be connected to the system (108) via a network (106). The one or more entities (102-1, 102-2…102-N) may be interchangeably mentioned as entities (102) throughout the disclosure. The entities (102) may include corporates from different verticals such as, but not limited to, telecommunication based corporate, agriculture based corporate, and pharmaceutical based corporate.
[0050] In an embodiment, the computing devices (104) may include, but not be limited to, a mobile, a laptop, etc. Further, the computing devices (104) may include a smartphone, virtual reality (VR) devices, augmented reality (AR) devices, a general-purpose computer, a desktop, a personal digital assistant, a tablet computer, and a mainframe computer. Additionally, input devices for receiving input from the one or more entities (102) such as a touch pad, a touch-enabled screen, an electronic pen, and the like may be used. A person of ordinary skill in the art will appreciate that the computing devices (104) may not be restricted to the mentioned devices and various other devices may be used.
[0051] In an embodiment, the network (106) may include, by way of example but not limitation, at least a portion of one or more networks having one or more nodes that transmit, receive, forward, generate, buffer, store, route, switch, process, or a combination thereof, etc. one or more messages, packets, signals, waves, voltage or current levels, some combination thereof, or so forth. The network (106) may also include, by way of example but not limitation, one or more of a wireless network, a wired network, an internet, an intranet, a public network, a private network, a packet-switched network, a circuit-switched network, an ad hoc network, an infrastructure network, a Public-Switched Telephone Network (PSTN), a cable network, a cellular network, a satellite network, a fiber optic network, or some combination thereof.
[0052] In an embodiment, the system (108) may receive information associated with one or more entities (102) via a knowledge graph (KG). The KG may include one or more defined relationships among the one or more entities (102). The one or more defined relationships may be based on an importance score assigned to the one or more entities (102) in the KG. The system (108) may generate one or more scores associated with one or more new entities based on the one or more entities (102). The system (108) may generate the one or more scores based on an old score associated with an entity among the one or more entities (102) and a weight corresponding to the old score. The system (108) may generate the one or more scores based one or more aggregated scores associated with the one or more entities (102) and one or more weights corresponding to the one or more aggregated scores.
[0053] In an embodiment, the system (108) may receive one or more articles from one or more publishers. The system (108) may match the one or more articles with the one or more scores to generate an entity relevance score.
[0054] In an embodiment, the system (108) may generate a trending relevance score based on one or more views of a user associated with the one or more articles. The system (108) may determine the one or more views associated with the one or more articles for a predetermined period. The system (108) may categorize the one or more articles into a trending profile based on the one or more views for the predetermined period. The system (108) may determine a trending score associated with the one or more articles based on the trending profile and generate the trending relevance score associated with the one or more articles.
[0055] In an embodiment, the system (108) may generate a sentiment relevance score based on a sentiment of the one or more new entities among the one or more articles. The system (108) may generate an entity sentiment profile based on the sentiment of the one or more new entities. The system (108) may compute a differential sentiment for the one or more new entities based on the entity sentiment profile among the one or more articles. The system (108) may aggregate the differential sentiment to generate a final differential sentiment score among the one or more articles. The system (108) may generate the sentiment relevance score based on the aggregated differential sentiment of the one or more new entities among the one or more articles.
[0056] In an embodiment, the system (108) may generate an overall relevance score associated with the one or more articles based on the entity relevance score, the trending relevance score, and the overall relevance score.
[0057] In an embodiment, the system (108) may receive one or more feedback inputs associated with the one or more articles based on the overall relevance score. The system (108) may determine the sentiment associated with the one or more entities (102) based on the one or more feedback inputs to update the entity sentiment profile. The system (108) may determine one or more relationships associated with the one or more new entities among the one or more articles based on the one or more feedback inputs. The system (108) may determine one or more attributes associated with the one or more articles based on the one or more feedback inputs. The system (108) may update the KG based on the one or more relationships and the one or more attributes.
[0058] In an embodiment, corporates may provide information on seed entities that may include name of the corporate/company, working industries, and key people. Seed entities along with an importance score may be received from the corporates. The importance score may be a numeric or a categorical value. As an example, the importance score may include values as high, medium, and low with numeric values as 3, 2, and 1, respectively. Further, an interface to facilitate filling of this information may also be provided. The KG may include a graph in which multiple entity nodes may be connected using the edges for defining relationships among the multiple entity nodes. As an example, a relationship node ‘Is_CEO_of’ between ‘Satya Nadela’ and ‘Microsoft’ may be established. There may be multiple entities matching each of the names provided by the corporates. Disambiguation may be performed based on the information provided by the corporates. If required, additional information may be collected from the corporates using a user interface. As an example, consider a case in which a company name “xyz” and CEO name as “Bob” may be entered by an organization. “Bob” may correspond to multiple people in the KG. “Bob” may be considered as entities which may be sufficiently close to the company “xyz” (and any other information provided by the organization). The closeness may be defined by direct or indirect edge relationships between two entities. All the entities that are retrieved as “Bob” may be displayed with additional information like photograph for providing further inputs from the organizations. This may aid in visually identifying and selecting appropriate entities.
[0059] In an embodiment, organizations/corporates may select the correct entity or may reject all the entities retrieved. In case, all the entities found may not be relevant to an organization. Hence, relevant information may be inserted in the KG. Also, more information (e.g., area of work, founders, location, board members, etc.) may be required from the organization to generate appropriate relationships (both first and higher level) which may be required for further enhancing the scope of the search. For example, when searching for a company name, KG may also be searched for the relationships like ‘Subsidiaries’, ‘Founders’, and other associated persons. For a person type of entity, the extracted entities may involve ‘spouse’, ‘kids’, ‘parents’, etc. Each of the relationship (or an edge) may be defined with a multiplication factor. Score of a new entity may be found through an old entity and a pre-defined relationship may be based on multiplication of the old entity score and relationship score. As shown in Table 1, relationships among entities may be assigned with a specific weight.

Relationship Name Example weight
{Person}Is_CEO_of{Organization} 1
{Person}Is_Investor_in{Organization} 0.6
{Person}Is_Spouse_of{Person} 0.6
{Organization}Is_Subsidiary_of{Organization} 0.9
{Product}Is_Product_of{Organization} 0.7
Table 1
Further, a score associated with an entity among the one or more entities may be generated as defined below in equation (1):
….equation (1)
[0060] In an embodiment, if the new entity is discovered through multiple old entities and relationships, then an aggregation function may be used to derive the final score. A maximum aggregation function, with minimum, average and other aggregation functions may also be used based on the application as defined below in equation (2):
…equation (2)
[0061] All the discovered entities in the order of relevance may be presented to the corporates for further verification. An algorithm for calculating the order of relevance may be based on the score as defined in equations (1) and (2). A list of final verified entities may be created for further processing and creation of rules.
[0062] Although FIG. 1 shows exemplary components of the network architecture (100), in other embodiments, the network architecture (100) may include fewer components, different components, differently arranged components, or additional functional components than depicted in FIG. 1. Additionally, or alternatively, one or more components of the network architecture (100) may perform functions described as being performed by one or more other components of the network architecture (100).
[0063] FIG. 2 illustrates an example block diagram (200) of a proposed system (108), in accordance with an embodiment of the present disclosure.
[0064] Referring to FIG. 2, the system (108) may include one or more processor(s) (202) that may be implemented as one or more microprocessors, microcomputers, microcontrollers, digital signal processors, central processing units, logic circuitries, and/or any devices that process data based on operational instructions. Among other capabilities, the one or more processor(s) (202) may be configured to fetch and execute computer-readable instructions stored in a memory (204) of the system (108). The memory (204) may be configured to store one or more computer-readable instructions or routines in a non-transitory computer readable storage medium, which may be fetched and executed to create or share data packets over a network service. The memory (204) may include any non-transitory storage device including, for example, volatile memory such as random-access memory (RAM), or non-volatile memory such as erasable programmable read only memory (EPROM), flash memory, and the like.
[0065] In an embodiment, the system (108) may include an interface(s) (206). The interface(s) (206) may comprise a variety of interfaces, for example, interfaces for data input and output (I/O) devices, storage devices, and the like. The interface(s) (206) may also provide a communication pathway for one or more components of the system (108). Examples of such components include, but are not limited to, processing engine(s) (208) and a database (210), where the processing engine(s) (208) may include, but not be limited to, a data ingestion engine (212) and other engine(s) (214). In an embodiment, the other engine(s) (214) may include, but not limited to, a data management engine, an input/output engine, and a notification engine.
[0066] In an embodiment, the processing engine(s) (208) may be implemented as a combination of hardware and programming (for example, programmable instructions) to implement one or more functionalities of the processing engine(s) (208). In examples described herein, such combinations of hardware and programming may be implemented in several different ways. For example, the programming for the processing engine(s) (208) may be processor-executable instructions stored on a non-transitory machine-readable storage medium and the hardware for the processing engine(s) (208) may comprise a processing resource (for example, one or more processors), to execute such instructions. In the present examples, the machine-readable storage medium may store instructions that, when executed by the processing resource, implement the processing engine(s) (208). In such examples, the system (108) may comprise the machine-readable storage medium storing the instructions and the processing resource to execute the instructions, or the machine-readable storage medium may be separate but accessible to the system (108) and the processing resource. In other examples, the processing engine(s) (208) may be implemented by electronic circuitry.
[0067] In an embodiment, the processor (202) may receive information via the data ingestion engine (212). The information may be associated with one or more entities (102) and received via a KG). The processor (202) may store the information in the database (210). The KG may include one or more defined relationships among the one or more entities (102). The one or more defined relationships may be based on an importance score assigned to the one or more entities (102) in the KG. The processor (202) may generate one or more scores associated with one or more new entities based on the one or more entities (102). The processor (202) may generate the one or more scores based on an old score associated with an entity among the one or more entities (102) and a weight corresponding to the old score. The processor (202) may generate the one or more scores based one or more aggregated scores associated with the one or more entities (102) and one or more weights corresponding to the one or more aggregated scores.
[0068] In an embodiment, the processor (202) may receive one or more articles from one or more publishers. The processor (202) may match the one or more articles with the one or more scores to generate an entity relevance score.
[0069] In an embodiment, the processor (202) may generate a trending relevance score based on one or more views of a user associated with the one or more articles. The processor (202) may determine the one or more views associated with the one or more articles for a predetermined period. The processor (202) may categorize the one or more articles into a trending profile based on the one or more views for the predetermined period. The processor (202) may determine a trending score associated with the one or more articles based on the trending profile and generate the trending relevance score associated with the one or more articles.
[0070] In an embodiment, the processor (202) may generate a sentiment relevance score based on a sentiment of the one or more new entities among the one or more articles. The processor (202) may generate an entity sentiment profile based on the sentiment of the one or more new entities. The processor (202) may compute a differential sentiment for the one or more new entities based on the entity sentiment profile among the one or more articles. The processor (202) may aggregate the differential sentiment of the one or more new entities to generate a final differential sentiment score among the one or more articles. The processor (202) may generate the sentiment relevance score based on the aggregated differential sentiment of the one or more new entities among the one or more articles.
[0071] In an embodiment, the processor (202) may generate an overall relevance score associated with the one or more articles based on the entity relevance score, the trending relevance score, and the overall relevance score.
[0072] In an embodiment, the processor (202) may receive one or more feedback inputs associated with the one or more articles based on the overall relevance score. The processor (202) may determine the sentiment associated with the one or more entities (102) based on the one or more feedback inputs to update the entity sentiment profile. The processor (202) may determine one or more relationships associated with the one or more new entities among the one or more articles based on the one or more feedback inputs. The processor (202) may determine one or more attributes associated with the one or more articles based on the one or more feedback inputs. The processor (202) may update the KG based on the one or more relationships and the one or more attributes.
[0073] Although FIG. 2 shows exemplary components of the system (108), in other embodiments, the system (108) may include fewer components, different components, differently arranged components, or additional functional components than depicted in FIG. 2. Additionally, or alternatively, one or more components of the system (108) may perform functions described as being performed by one or more other components of the system (108).
[0074] FIGs. 3A-3B illustrate example flow diagrams (300A, 300B) of a trending score computation module, in accordance with an embodiment of the present disclosure.
[0075] In an embodiment, the system (108) may generate the trending score to provide the articles that are more trending currently. Articles that are trending more may require immediate response. Further, the system (108) may use a decay function for calculating the trending score for news articles. The decay function approach may be based on recency and the number of views.
[0076] As illustrated in FIG. 3A, in an embodiment, the system (108) may fetch all new interactions based on a given timestamp range and filter eventType from an analytics database (DB) and put the new interactions into an interaction queue (302) to be picked by the trending profile. Further, the system (108) may pick all the recent documents in the interaction queue (302), add to the documents in the trending profile, and check if that pair of contentId and contentType already exists. Based on a positive determination, the system (108) may increment the viewsTillNow and set updatedAt column to a current timestamp (304). Based on a negative determination, the system (108) may insert that interaction as a new document (trending_score = 1 and viewTillNow = 1) in the trending profile. Further, the system (108) may run a separate script to determine multiply viewsTillNow with a configurable decay function (306), where the decay function (306) = (number of views) * (1 - Alpha) ^ (1 + (Current_Time – Created_At)/3600) to get the trending score. The system (108) may update the decay function for the all documents from the trending profile every 10 or 15 minutes based on the average count of documents in the trending profile. Here, Alpha may be a configurable parameter.
[0077] In an embodiment, the system (108) may set the trending score as 0 (308) if the document in trending profile is older than 48 hours and remove the document from the trending profile if the document is older than 72 hours. The system (108) may run a separate script to pick all the documents from the trending profile (310) and push them into a separate queue (here pub/sub). This may help in updating the trending score in a postgres table used by a user Interface (UI), where the UI may update an application programming interface (API).
[0078] As illustrated in FIG. 3B, in an embodiment, the system (108) may receive articles from a producer (312). The system (108) may store the articles in a pub-sub (314). Further, the system (108) may arrange the articles in a queue (316). The system (108) may present the articles to a consumer (318). Further, the system (108) may store all the articles in a postgres database (320).
[0079] FIG. 4 illustrates an example flow diagram (400) of a sentiment computation module, in accordance with an embodiment of the present disclosure.
[0080] In an embodiment, the sentiment computation module may determine the sentiment of a headline (text) in the news article with respect to a specific keyword (aspect). For example, a telecommunications company may receive a feedback from the consumer. For example, the feedback may include a message saying that the service is great, but the network was bad. This may be an aspect based sentiment where the “service” may be assigned a positive 0.924 value and the network may be assigned a negative 0.997 value.
[0081] As illustrated in FIG. 4, in an embodiment, the system (108) may receive inputs from a DB (402) and an aspects DB (404). The system (108) may generate news article text (406) from the DB (402) and corporate aspects (including network, service) (408) from the aspects DB (404). Further, the system (108) may generate a pre-trained sentiment model (410) based on the news article text (406) and the corporate aspects (408). The system (108) may further generate an output (412) based on the pre-trained sentiment model (408).
[0082] In an embodiment, a feedback may be received about the telecommunications company that describes the telecommunications company service as great, but the network was bad. Further, the aspect based sentiment may include values related to services. A positive response for service with a value 0.924 and negative response for network with a value 0.997. Every corporate may provide a list of aspects/keywords on which the sentiment may be calculated. Some of the keywords may include a name of person, a name of subsidiary, or generic aspects like petrol, diesel, or gas.
[0083] In an embodiment, the telecommunications based corporate may include network and services. Further, an agriculture based corporate may include services related to for example, but not limited to, hand cultivators, harrows, spades, budding. Also, a pharmaceutical based corporate may include services related to for example, but not limited to, allergy, bacteria, and Covid vaccines.
[0084] In an embodiment, the system (108) may include a multi-aspect sentiment profile based on a word count of different aspects in the article text, the sentiment details along with a score, summary of articles based on aspect sentiments.
[0085] FIG. 5 illustrates an example flow diagram (500) of a differential sentiment computation module, in accordance with an embodiment of the present disclosure.
[0086] In an embodiment, the system (108) may generate a differential sentiment of an entity. The differential sentiment may be the sentiment of the entity in an article with respect to the sentiment of the news article in other articles in which the same entity appeared. The differential sentiment may be calculated over a long-term, intra-day, intra-publisher, or an intra-event.
[0087] In an embodiment, the system (108) may compute a long term differential sentiment where a profile of each entity may be calculated. The profile may consist of a distribution of sentiment scores across different sentiment score bins. An example profile with bin size 0.1 for an entity “xyz” may be “xyz”: [(-1:-0.9): 1%, (-0.3, -0.2): 10%, (-0.2, -0.1): 20%, (-0.1, 0): 25%, (0, 0.1): 17 %,…). Based on an assumption over a long term, each sentiment profile may follow a Gaussian distribution with a mean and standard deviation. Any news with the sentiment deviation more than a threshold (two standard deviations from the mean) may be treated as of very high importance. At the same time, the system (108) may use a function to calculate the differential positive or a negative score. This score may be used in the final relevance calculation.
[0088] In an embodiment, the system (108) may compute an intra-day, intra-publisher, or intra-event differential sentiment. These may be calculated in a similar manner as the long-term differential sentiment, but a profile may be created according to the view (e.g., day, publisher, or event). Finally, the article level differential sentiment may be calculated from each of the entity level differential sentiment in the article. An aggregation function like Max of the polarity of differential sentiment for any of entities may be used.
[0089] As illustrated in FIG. 5, in an embodiment, the system (108) may include the following steps:
[0090] At step 502: The system (108) may receive news articles from a news article database.
[0091] At step 504: The system (108) may perform sentiment computation for entities.
[0092] At step 506: The system (108) may generate entity versus sentiment.
[0093] At step 508: The system (108) may send this information to a sentiment profiling module.
[0094] At step 510: A sentiment profiling module may process the information and send an output.
[0095] At step 512: The system (108) may receive the output and perform differential sentiment computation for all the entities.
[0096] At step 514: The system (108) may receive news articles.
[0097] At step 516: The system (108) may determine the entity in the news article and go to step 512.
[0098] At step 518: The system (108) may perform an aggregation function for differential sentiment of the article.
[0099] At step 520: The system (108) may generate a final differential sentiment score based on the aggregation function.
[00100] In an embodiment, the system (108) may include a re-ranking module where the articles may be ranked based on recency, the trending score, the differential sentiment score, and the negative sentiment score based on the entities present in the article.
[00101] FIG. 6 illustrates an example flow diagram (600) of a news profile article processing module, in accordance with an embodiment of the present disclosure.
[00102] As illustrated in FIG. 6, in an embodiment, the system (108) may receive articles from a producer (602). The system (108) may send the articles to a pub-sub (604) for processing. The system (108) may generate a queue (606) of the articles based on the processing. The system (108) may present the articles to a consumer (608) and store the articles in the postgres database (610). The system (108) may further send the articles received from the consumer to an analytic module (612). The articles may include article headlines and a keyword list. The analytic module (612) may process the articles and send the output back to the consumer (608). The output may include an overall sentiment of the articles, and keyword sentiments associated with the articles.
[00103] FIG. 7 illustrates an example flow diagram (700) of a display module, in accordance with an embodiment of the present disclosure.
[00104] As illustrated in FIG. 7, in an embodiment, the display module may include a React web application (702) that may receive inputs from a state manager module (704), screens module (706), and an API wrapper (708).
[00105] FIG. 8 illustrates an example flow diagram (800) of a relevance score computation module, in accordance with an embodiment of the present disclosure.
[00106] As illustrated in FIG. 8, in an embodiment, the system (108) may receive inputs from the KG (802) and generate an entity relevance score (804) based on the inputs from the KG (802). The system (108) may generate a differential sentiment score and a negative sentiment score (806) based on the articles and generate a sentiment relevance score (808) based on the differential sentiment score and the negative sentiment score (806). Further, the system (108) may generate a trending news score (810) based on the trending articles in the trending profile and generate a trending relevance score (812) based on the trending news score (810). Further, the system (108) may generate an overall relevance score (814) based on the entity relevance score (804), the sentiment relevance score (806), and the trending relevance score (812). The overall relevance score (814) may be considered as a weighted average of the entity relevance score (804), the sentiment relevance score (806), and the trending relevance score (812). The weights for the three scores may be determined as per need of a domain depending on relevance of the article, a negative sentiment associated with the article, and a determination based on the article trending or not.
[00107] FIG. 9 illustrates an example flow diagram (900) of a feedback module, in accordance with an embodiment of the present disclosure.
[00108] In an embodiment, the system (108) may receive the feedback from the corporates in the form of signals that may include but not limited to a click rate of the article, a condition if the corporate has liked the article or not, a read/watch time of the article, and a condition if the article has been added to a read list by the consumer. These signals with some thresholds may provide the feedback to an entity discovery scoring module. The entity discovery scoring module may determine if the weightages set up for the entity relationships require any change. For example, if the corporates are not interested in reading the articles based on who the investors are for the company, weightage of {Person}_Is_investor_In {Organization} may be reduced. Hence, these articles may receive a lesser entity discovery score and a relevance score. Similarly, the feedback system may be provided for retraining the sentiment module, based on whether the corporate considers the entity’s sentiment negative or positive.
[00109] As illustrated in FIG. 9, in an embodiment, articles may be displayed to the corporate based on the overall relevance score (902). A sample article (904) among the articles may be used by the system (108) and include feedback from the corporates. The system (108) may generate various attributes/signals that may include a click rate (906), a watch/read time (908), an add to read list (910), and like the article (912) based on the sample article (904). The system (108) may determine if the signal values are less than a threshold. Further, the system (108) may also determine entities and relations (914) associated with the sample article (904). Hence, the system (108) may change the weightage of the relations of the entities in the KG based on the positive determination and the entities and relations (914). Similarly, the system (108) may determine if the entity sentiment (916) is positive or negative as per corporate based on the sample article (904). Further, the system (108) may generate sentiment feedback data (918) based on the entity sentiment (916) and retain the sentiment model (920) based on the feedback data.
[00110] In an embodiment, the system (108) may check if the signal values are less than threshold (922) based on the click rate (906), the watch/read time (908), the add to read list (910), and like the article (912). The system (108) may change the weightage of the relations of the entities in the KG (924) based on the entities and relation (914) and checking of the signal values being less than threshold (922).
[00111] FIG. 10 illustrates an example system architecture (1000), of the proposed system (108), in accordance with an embodiment of the present disclosure.
[00112] As illustrated in FIG. 10, in an embodiment, the system (108) may include the following steps:
[00113] At step 1002: The system (108) may use a KG.
[00114] At step 1004: The system (108) may generate entities discovery and scoring based on the KG.
[00115] At step 1006: The system (108) may receive an explicit feedback from corporates.
[00116] At step 1008: The system (108) may identify important entities and scores based on the entities discovery and scoring.
[00117] At step 1010: The system (108) may generate a corporate feedback on entity scores.
[00118] At step 1012: The system (108) may generate final verified entities and scores based on the corporate feedback on entity scores.
[00119] At step 1014: The system (108) may receive articles from various publishers (1014) (publisher 1, publisher 2…publisher N).
[00120] At step 1016: The system (108) may use a news aggregation service for processing the articles.
[00121] At step 1018: The system (108) may generate a news corpus via the news aggregation service.
[00122] At step 1020: The system (108) may receive the final verified entities and scores and provide this information to an entity matching and scoring engine.
[00123] At step 1022: The system (108) may generate the matched articles and the entity scores.
[00124] At step 1024: The system (108) may use a news application.
[00125] At step 1026: The system (108) may generate user interaction events from the news application.
[00126] At step 1028: The system (108) may generate a trending score calculation based on the user interaction events and the matched articles and entity scores.
[00127] At step 1030: The system (108) may provide the matched articles and entity scores to an entity based sentiment module.
[00128] At step 1032: The system (108) may receive information from the entity based sentiment module and provide this information to a differential sentiment scoring module.
[00129] At step 1034: The system (108) may generate a relevance score computation via the entity based sentiment module and the differential sentiment scoring module.
[00130] At step 1036: The system (108) may provide the relevance score computation to a display module.
[00131] At step 1038: The system (108) may provide the relevance score computation to corporates via the display module.
[00132] At step 1040: The system (108) may receive a feedback from corporates via the display module.
[00133] At step 1042: The system (108) may generate an entity discovery scoring algorithm optimization based on the feedback received from corporates.
[00134] At step 1044: The system (108) may provide the sentiment model retraining based on the feedback received from corporates.
[00135] FIG. 11 illustrates an exemplary computer system (1100) in which or with which embodiments of the present disclosure may be implemented.
[00136] As shown in FIG. 11, the computer system (1100) may include an external storage device (1110), a bus (1120), a main memory (1130), a read-only memory (1140), a mass storage device (1150), a communication port(s) (1160), and a processor (1170). A person skilled in the art will appreciate that the computer system (1100) may include more than one processor and communication ports. The processor (1170) may include various modules associated with embodiments of the present disclosure. The communication port(s) (1160) may be any of an RS-232 port for use with a modem-based dialup connection, a 10/100 Ethernet port, a Gigabit or 10 Gigabit port using copper or fiber, a serial port, a parallel port, or other existing or future ports. The communication ports(s) (1160) may be chosen depending on a network, such as a Local Area Network (LAN), Wide Area Network (WAN), or any network to which the computer system (1100) connects.
[00137] In an embodiment, the main memory (1130) may be Random Access Memory (RAM), or any other dynamic storage device commonly known in the art. The read-only memory (1140) may be any static storage device(s) e.g., but not limited to, a Programmable Read Only Memory (PROM) chip for storing static information e.g., start-up or basic input/output system (BIOS) instructions for the processor (1170). The mass storage device (1150) may be any current or future mass storage solution, which can be used to store information and/or instructions. Exemplary mass storage solutions include, but are not limited to, Parallel Advanced Technology Attachment (PATA) or Serial Advanced Technology Attachment (SATA) hard disk drives or solid-state drives (internal or external, e.g., having Universal Serial Bus (USB) and/or Firewire interfaces).
[00138] In an embodiment, the bus (1120) may communicatively couple the processor(s) (1170) with the other memory, storage, and communication blocks. The bus (1120) may be, e.g., a Peripheral Component Interconnect (PCI)/PCI Extended (PCI-X) bus, Small Computer System Interface (SCSI), USB, or the like, for connecting expansion cards, drives, and other subsystems as well as other buses, such a front side bus (FSB), which connects the processor (1170) to the computer system (1100).
[00139] In another embodiment, operator and administrative interfaces, e.g., a display, keyboard, and cursor control device may also be coupled to the bus (1120) to support direct operator interaction with the computer system (1100). Other operator and administrative interfaces can be provided through network connections connected through the communication port(s) (1160). Components described above are meant only to exemplify various possibilities. In no way should the aforementioned exemplary computer system (1100) limit the scope of the present disclosure.
[00140] While considerable emphasis has been placed herein on the preferred embodiments, it will be appreciated that many embodiments can be made and that many changes can be made in the preferred embodiments without departing from the principles of the disclosure. These and other changes in the preferred embodiments of the disclosure will be apparent to those skilled in the art from the disclosure herein, whereby it is to be distinctly understood that the foregoing descriptive matter is to be implemented merely as illustrative of the disclosure and not as a limitation.

ADVANTAGES OF THE INVENTION
[00141] The present disclosure provides a system and a method that helps businesses to get a list of relevant articles in a timely manner from a list of multiple articles published by different publishers across globe.
[00142] The present disclosure provides a system and a method that facilitates additional information, including different kinds of sentiment on news articles for generating an overall relevance score from the list of multiple articles.
[00143] The present disclosure provides a system and a method that provides timely coverage of relevant news articles about their business, people involved in the business, competitors, and industry in general.

,CLAIMS:1. A system (108) for generating business relevant information, the system (108) comprising:
a processor (202); and
a memory (204) operatively coupled with the processor (202), wherein said memory (204) stores instructions which, when executed by the processor (202), cause the processor (202) to:
receive information associated with one or more entities (102) via a knowledge graph (KG);
generate one or more scores associated with one or more new entities based on the one or more entities (102);
receive one or more articles from one or more publishers;
match the one or more articles with the one or more scores to generate an entity relevance score;
generate a trending relevance score based on one or more views associated with the one or more articles by a user;
generate a sentiment relevance score based on a sentiment of the one or more new entities among the one or more articles; and
generate an overall relevance score associated with the one or more articles based on the entity relevance score, the trending relevance score, and the sentiment relevance score.
2. The system (108) as claimed in claim 1, wherein the processor (202) is to generate the one or more scores based on an old score associated with an entity among the one or more entities (102) and a weight corresponding to the old score.
3. The system (108) as claimed in claim 1, wherein the processor (202) is to generate the one or more scores based on one or more aggregated scores associated with the one or more entities (102) and one or more weights corresponding to the one or more aggregated scores.
4. The system (108) as claimed in claim 1, wherein the processor (202) is to generate the trending relevance score by being configured to:
determine one or more views associated with the one or more articles for a predetermined period;
categorize the one or more articles into a trending profile based on the one or more views for the predetermined period; and
determine a trending score associated with the one or more articles based on the trending profile and generate the trending relevance score associated with the one or more articles.
5. The system (108) as claimed in claim 1, wherein the processor (202) is to generate the sentiment relevance score by being configured to:
generate an entity sentiment profile based on the sentiment of the one or more new entities;
compute a differential sentiment for the one or more new entities based on the entity sentiment profile among the one or more articles;
aggregate the differential sentiment of the one or more new entities to generate a final differential sentiment score among the one or more articles; and
generate the sentiment relevance score based on the aggregated differential sentiment of the one or more new entities among the one or more articles.
6. The system (108) as claimed in claim 5, wherein the processor (202) is configured to:
receive one or more feedback inputs associated with the one or more articles based on the overall relevance score;
determine the sentiment associated with the one or more entities based on the one or more feedback inputs to update the entity sentiment profile;
determine one or more relationships associated with the one or more new entities among the one or more articles based on the one or more feedback inputs;
determine one or more attributes associated with the one or more articles based on the one or more feedback inputs; and
update the KG based on the one or more relationships and the one or more attributes.
7. The system (108) as claimed in claim 1, wherein the KG comprises one or more defined relationships among the one or more entities (102), and wherein the one or more defined relationships are based on an importance score assigned to the one or more entities (102).
8. A method for generating business relevant information, the method comprising:
receiving information, by a processor (202) configured with a system (108), associated with one or more entities (102) via a knowledge graph (KG);
generating, by the processor (202), one or more scores associated with one or more new entities based on the one or more entities;
receiving, by the processor (202), one or more articles from one or more publishers;
matching, by the processor (202), the one or more articles with the one or more scores to generate an entity relevance score;
generating, by the processor (202), a trending relevance score based on one or more views of a user associated with the one or more articles;
generating, by the processor (202), a sentiment relevance score based on a sentiment of the one or more new entities among the one or more articles; and
generating, by the processor (202), an overall relevance score associated with the one or more articles based on the entity relevance score, the trending relevance score, and the overall relevance score.
9. The method as claimed in claim 8, comprising generating, by the processor (202), the one or more scores based on an old score associated with an entity among the one or more entities (102) and a weight corresponding to the old score.
10. The method as claimed in claim 8, comprising generating, by the processor (202), the one or more scores based one or more aggregated scores associated with the one or more entities (102) and one or more weights corresponding to the one or more aggregated scores.
11. The method as claimed in claim 8, comprising generating, by the processor (202), the trending relevance score by:
determining, by the processor (202), the one or more views associated with the one or more articles for a predetermined period;
categorizing, by the processor (202), the one or more articles into a trending profile based on the one or more views for the predetermined period; and
determining, by the processor (202), a trending score associated with the one or more articles based on the trending profile and generate the trending relevance score associated with the one or more articles.
12. The method as claimed in claim 8, comprising generating, by the processor (202), the sentiment relevance score by:
generating, by the processor (202), an entity sentiment profile based on the sentiment of the one or more new entities;
computing, by the processor (202), a differential sentiment for the one or more new entities based on the entity sentiment profile among the one or more articles;
aggregating, by the processor (202), the differential sentiment to generate a final differential sentiment score among the one or more articles; and
generating, by the processor (202), the sentiment relevance score based on the aggregated differential sentiment of the one or more new entities among the one or more articles.
13. The method as claimed in claim 8, comprising:
receiving, by the processor (202), one or more feedback inputs associated with the one or more articles based on the overall relevance score;
determining, by the processor (202), the sentiment associated with the one or more new entities based on the one or more feedback inputs for updating the entity sentiment profile;
determining, by the processor (202), one or more relationships associated with the one or more new entities among the one or more articles based on the one or more feedback inputs;
determining, by the processor (202), one or more attributes associated with the one or more articles based on the one or more feedback inputs; and
updating, by the processor (202), the KG based on the one or more relationships and the one or more attributes.
14. The method as claimed in claim 8, wherein the KG comprises one or more defined relationships among the one or more entities (102), and wherein the one or more defined relationships are based on an importance score assigned to the one or more entities (102).