DESC:TECHNICAL FIELD
[0001] The invention of the present disclosure relates to the field of generating one or more recommendations using data from a plurality of sources. More specifically, the embodiment of the present disclosure relates to a system and method for the generation of one or more recommendations of leads for an entity.
BACKGROUND
[0002] This section is intended to provide information relating to the general state of the art and thus any approach/functionality described herein below should not be assumed to be qualified as prior art merely by its inclusion in this section.
[0003] In every field, it is crucial to timely identify potential leads that may be relevant to the operations of an entity, be it a person, a group or an organization. For an entity, a potential lead may be any relevant person, group or organization that may be interested in the operations of the entity, be it a product, a service, research or any other operation.
[0004] As a result, a failure to timely identify one or more potential leads may be detrimental to the operations of the entity and may even lead to a loss of competitive advantage. On the contrary, a timely recognition of potential leads may aid an entity to successfully utilize the opportunities available to it. For example, a timely and successful identification of potential leads may aid a research organization to connect with a research fund in a timely manner. Similarly, a timely identification of potential leads may aid a company engaged in construction services to find and connect with a potential point of contact associated with a desirable project before competitors.
[0005] However, conventional methods of identifying potential leads are performed through reliance on manual processes and traditional methods, wherein identification and generation of leads involves physically reading and filtering articles and other sources of information for relevant content, manually recording information and manual distribution of the filtered information to relevant people for conducting actions on the identified leads. The existing solutions, as described herein, come with certain drawbacks.
[0006] Firstly, manual reading and processing of different sources of information is a time consuming and resource intensive task that may require hiring of dedicated professionals. However, this may introduce subjectivity into the processing of information. As a result of this subjectivity, there may also be a difficulty in distinguishing and segregating leads into ‘priority’ leads that may have a higher likelihood of acquiring the entities products and/or services, and therefore require prioritization. Further, the hiring and training of professionals requires significant financial resources, and yet the model is limited in scalability because it might not be possible for an entity to hire a greater number of professionals for such operations with the ever-increasing volumes and complexity of available data.
[0007] Secondly, information from which potential leads may be identified might not be available in widely known and understood languages, i.e., English. This leads to a large pool of leads published in regional and/or foreign languages being rendered inaccessible by interested entities, as a person manually filtering through sources of information cannot be proficient in all of the languages that the leads may be published in.
[0008] Overall, the existing known solutions are limited by the limitations described herein, and therefore fall short of delivering consistent and real-time identification and generation of leads. As a result, entities may not gain access to various potential leads, and/or may not get them in a time-bound or resource efficient manner, thereby resulting in a loss of potential opportunities.
[0009] It may be noted that this section is not intended to identify an exhaustive list of drawbacks present in the state of the art, but to give a general picture of some of the major limitations associated with the state of the art, and as such, the scope of the present disclosure is not limited to the solution of the aforementioned limitations only.
OBJECTS OF THE INVENTION
[0010] 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 description:
[0011] In order to overcome at least a few problems associated with the known solutions as provided in the previous section, an object of the invention is to significantly reduce the limitations and drawbacks of the prior arts are described hereinabove.
[0012] Another object of the present disclosure is to automate the process of collection of data from different sources.
[0013] Another object of the present disclosure is to increase the time-efficiency for the analysis of data from different sources.
[0014] Another object of the present disclosure is to convert generic sources of information into potential leads that are relevant for an entity.
[0015] Another object of the present disclosure is to improve the scalability of lead identification operations for entities across different verticals and geographical locations.
[0016] Another object of the present disclosure is to enable multi-lingual analysis of data for the generation of recommendations of leads.
[0017] Yet another object of the invention is to blend relevant public data with proprietary entity data of the entity for the identification of potential leads.
SUMMARY
[0018] An aspect of the present disclosure relates to a method for generating one or more recommendations of leads for an entity. The method comprises retrieving one or more sets of data from at least one data source. Thereafter, the method further comprises extracting at least one relevant information from the one or more sets of data and managing the at least one relevant information on the basis of a predetermined set of criteria. Thereafter, the method further comprises determining, a person of interest associated with one or more leads on the basis of an analysis of the at least one relevant information, and then identifying, from a database, at least one connection to the person of interest. Thereafter, the method comprises generating one or more recommendations of leads, on the basis of at least one relevant information and at least one connection to the person of interest.
[0019] In an exemplary aspect of the present disclosure, the method further comprises identifying one or more gaps from the database.
[0020] In an exemplary aspect of the present disclosure, the method further comprises rectifying the one or more gaps in the database via a set of rectification actions.
[0021] In an exemplary aspect of the present disclosure, the predetermined set of criteria comprises one or more plans, trends, reports, goals or requirements associated with the operations of the entity.
[0022] In an exemplary aspect of the present disclosure, wherein the person of interest associated with one or more leads comprises at least one of a person, a group or an organization interested in the one or more operations of the entity.
[0023] In an exemplary aspect of the present disclosure, the identification of at least one connection to the person of interest is performed using one or more artificial intelligence (AI) models.
[0024] In an exemplary aspect of the present disclosure, the extraction, management and the analysis of the at least one relevant information comprises the use of one or more Natural Language Processing (NLP) techniques.
[0025] In an exemplary aspect of the present disclosure, the database comprises a customer relationship management (CRM) database.
[0026] In an exemplary aspect of the present disclosure, the one or more recommendations of leads comprises a summarized compilation of the at least one relevant information and the at least one connection to the person of interest associated with one or more leads.
[0027] In an exemplary aspect of the present disclosure, the at least one relevant information is translated from a non-preferred language to a preferred language.
[0028] In an exemplary aspect of the present disclosure, the translation of the at least one relevant information from a non-preferred language to a preferred language is performed using one or more AI models.
[0029] In an exemplary aspect of the present disclosure, the one or more recommendations of leads are displayed via one or more graphical interfaces.
[0030] In an exemplary aspect of the present disclosure, the method is performed in response to one or more inputs provided by a user via a chat interface.
[0031] In an exemplary aspect of the present disclosure, the one or more inputs are used to define a set of parameters to retrieve the one or more sets of data from at least one data source.
[0032] Another aspect of the present disclosure relates to a system for generating one or more recommendations of leads for an entity. The system comprises a processor configured to retrieve, one or more sets of data from at least one data source. The processor is further configured to extract at least one relevant information from the one or more sets of data and manage the at least one relevant information on the basis of a predetermined set of criteria. Thereafter, the processor is further configured to determine, a person of interest associated with one or more leads on the basis of an analysis of the at least one relevant information, and identify, from a database, at least one connection to the person of interest. Thereafter, the processor is configured to generate, one or more recommendation of leads, on the basis of at least one relevant information, at least one connection to the person of interest and the set of rectification actions.
BRIEF DESCRIPTION OF DRAWINGS
[0033] The accompanying drawings, which are incorporated herein, constitute a part of this disclosure. 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 disclosure of electrical components or circuitry commonly used to implement such components. Although exemplary connections between sub-components have been shown in the accompanying drawings, it will be appreciated by those skilled in the art, that other connections may also be possible, without departing from the scope of the invention. All sub-components within a component may be connected to each other, unless otherwise indicated.
[0034] FIG. 1 illustrates an exemplary block diagram of a system for generating one or more recommendations for an entity, in accordance with an exemplary implementation of the present disclosure.
[0035] FIG. 2 illustrates an exemplary method flow diagram for generating one or more recommendation of leads for an entity, in accordance with an exemplary implementation of the present disclosure.
[0036] FIG. 3 illustrates an exemplary chat-based interface for providing one or more user inputs for retrieving one or more sets of data, in accordance with an exemplary implementation of the present disclosure.
DETAILED DESCRIPTION
[0037] In the following description, for the purposes of explanation, various specific details are set forth in order to provide a thorough understanding of the embodiments of the present invention. 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 any 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. Example embodiments of the present disclosure are described below, as illustrated in various drawings.
[0038] 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.
[0039] 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 in order to avoid obscuring the embodiments.
[0040] Also, it is noted that individual embodiments may be described as a process which 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.
[0041] 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.
[0042] As used herein, a ‘processing unit” or a “processor” includes processing unit, wherein processor refers to any logic circuitry for processing instructions. The processor may be a general-purpose processor, a special purpose processor, a conventional processor, a digital signal processor (DSP), a plurality of microprocessors, one or more microprocessors in association with a DSP core, a controller, a microcontroller, Application Specific Integrated Circuits (ASIC), Field Programmable Gate Array circuits (FPGA), any other type of integrated circuits, etc. The processor may perform signal coding, data processing, input/output processing, and/or any other functionality that enables the working of the system according to the present disclosure. More specifically, the processor is a hardware processor.
[0043] Further, as used herein, “Storage” refers to a machine or computer-readable medium including any mechanism for storing information including but not limited to text, images, audio, and video files in a form readable by a computer or similar machine. For example, a computer-readable medium includes read-only memory (“ROM”), random access memory (“RAM”), magnetic disk storage media, optical storage media, flash memory devices or other types of machine-accessible storage media. The storage unit stores at least the data that may be required by one or more units of the server/system/user device to perform their respective functions.
[0044] Further, as used herein, “entity” refers to a person, or a group of persons or an organization for which the one or more recommendations of leads are generated.
[0045] As discussed in the background section, the current known solutions have shortcomings. The present disclosure aims to overcome the shortcomings shortcomings discussed above and other existing problems in the field of generation of one or more recommendations of leads for an entity. The present disclosure provides a technically advanced system and method for analysing data from a plurality of sources. The present disclosure also enables efficient identification of one or more persons of interest to generate one or more recommendations of leads for an entity. Furthermore, the present disclosure automates the process of procurement, management, analysis, summarisation and consolidation of data to increase time-efficiency and accuracy of identification of potential leads for an entity. The present disclosure also allows for a highly scalable approach to generate recommendations of relevant leads. Additionally, the present disclosure also offers a technically advanced solution that facilitates a multi-lingual management and analysis of data, by enabling real-time translation of the data into a preferred language, thereby ensuring timely identification of potential leads for an entity.
[0046] Hereinafter, exemplary embodiments of the present disclosure will be described in detail with reference to the accompanying drawings so that those skilled in the art can easily carry out the solution provided by the current disclosure.
[0047] Referring now to FIG. 1, an exemplary block diagram of system [100] for generation of one or more recommendation of leads for an entity, in accordance with an exemplary implementation of the present disclosure. As illustrated, the system [100] comprises at least one of the following components, namely, a processor [102], a data unit [104], an AI Controller [106], a storage [108], and an interface unit [110]. As used herein, all components/units of the system [100] shall be assumed to be inter-connected and working in conjunction with each other to generate one or more recommendations of leads for an entity, unless explicitly stated otherwise. Further, the scope of the present disclosure encompasses that the system [100] may be configured with more than one of each component/unit/module, however, only one instance of each is shown in FIG.1 for clarity and brevity.
[0048] It may be understood by a person ordinarily skilled in the art that the system [100] may comprise any other configuration of one or more components, units and/or modules as may be required to implement the features of the present disclosure, and the present description is not intended to limit the scope of the present disclosure. In one example, the system [100] may comprise only one or more of processor [102] that may be configured to implement the features of the present disclosure independently.
[0049] Further, to generate one or more recommendations of leads for an entity, the system [100] may be implemented in a wide variety of computer electronic devices that may be configured to host one or more databases, or may be connected and configured to access one or more databases, such as a hosting server, a laptop, a desktop, a tablet etc. In an exemplary implementation, the system [100] may be implemented in other computer system configurations, including hand-held devices, multiprocessor systems, microprocessor based or programmable consumer electronics, network personal computers, minicomputers, mainframe computers, and the like.
[0050] In another exemplary implementation, the system [100] may be implemented on a computing device that may be remotely connected to a hosting server/device. The computing device on which the system [100] is implemented may be connected via wired connection, such as ethernet, USB, fiber optic and the like. In another example, the connection may be a wireless connection using any wireless communication technology as may be known by a person skilled in the art, e.g., wide area networks (WAN), such as internet, 4G or 5G networks etc, or a local area network (LAN), such as Wi-Fi, Li-Fi, Bluetooth, etc.
[0051] In yet another exemplary implementation, the system [100] may be implemented as a plug-in for legacy systems, wherein one or more features of the system [100] may be implemented on the hardware of existing systems of an entity.
[0052] It may be understood that the aforementioned description is only to illustrate the features of system [100] and is not intended to limit the scope of the present disclosure, and as such, the system [100] may be implemented on any computing device as may be known to a person ordinarily skilled in the art, and using any mode of communication as may be known by a person ordinarily skilled in the art.
[0053] In operation, the processor [102] of the system [100] may be configured to retrieve, via the data unit [104], one or more sets of data from a plurality of data sources. In an exemplary implementation, the plurality of data sources may comprise one or more of websites, articles, databases, journals, reports, blogs and digital archives.
[0054] It may be understood by a person ordinarily skilled in the art that the aforementioned list of data sources is not intended to limit the scope of the present disclosure, and hence, it may be understood that the list of data sources is inclusive in nature.
[0055] In another exemplary implementation, the processor [102] may retrieve the one or more sets of data from a single source of data. For example, in one scenario, a plurality of potential leads may be made available in a single database or website via large sets of data, and therefore, the processor [102] may determine that no additional data sources may be required to generate the one or more recommendations of leads. In another exemplary implementation, the number and/or types of data sources to be searched for the retrieval of data may be configured by one or more users of the system [100]. Additionally, the system [100] may also enable the one or more users to dictate specific sources of data from which the one or more sets of data may be retrieved.
[0056] It may be noted that the one or more users may comprise users that may be associated with an entity for which the system [100] is generating the one or more recommendations of leads.
[0057] Further, in an exemplary implementation, the processor [102] may be further configured to retrieve the one or more sets of data via the use of AI Controller [106] in addition to the data unit [104]. The system [100] may utilize one or more large language models (LLMs) and/or one or more machine learning (ML) models to retrieve the one or more sets of data. The one or more LLMs/ ML models may be trained to identify relevant information from the one or more sets of data, including, but not limited to, relevant words, phrases, contexts, and contacts associated with potential leads that the entity may be interested in.
[0058] In yet another exemplary implementation, the processor [102] may be further configured to store the one or more sets of data in the storage [108]. The one or more sets of data may be stored in the storage [108] temporarily, until the one or more recommendations of leads for the entity have been generated. Thereafter, the one or more sets of data may be removed from the storage [108].
[0059] Alternatively, in another exemplary implementation, the one or more sets of data may be stored in the storage [108] for a pre-configured period of time, as may be defined by the one or more users associated with the entity.
[0060] Herein, the one or more sets of data may comprise, but are not limited to, listings of requirements for products, services or operations that may be relevant to the entity, reports of one or more events that may create a relevant opportunity for the entity, and observations relating to trends and patterns that may indicate a relevant opportunity for the products, services or operations of the entity.
[0061] Returning to the operation of the system [100], thereafter, the processor [102] may extract at least one relevant information from the one or more sets of data. Further, the processor [102] may be configured to manage the at least one relevant information extracted from the one or more sets of data. The extraction of the at least one relevant information, and the management of the same may be performed on the basis of a set of predetermined criteria. As used herein, the predetermined set of criteria may include, but is not limited to, one or more plans, trends, reports, goals or requirements associated with the operations of the entity.
[0062] For example, for an entity involved in operations associated with financial transactions, the predetermined set of criteria may comprise expansion plans, mergers & acquisitions, hiring trends and financial health.
[0063] Further, the management of the at least one relevant information may include, but is not limited to, sorting, grouping, ungrouping, and arrangement of the relevant information. For example, the arrangement of relevant information may comprise arranging the relevant information in a hierarchical order based on the determined relevancy of the information.
[0064] In an exemplary implementation, the processor [102] may be further configured to detect if the any of the relevant information extracted is in a language other than a preferred language that may have been configured in the system [100]. In an event, wherein a relevant information exists in a language other than a preferred language of operation, the processor [102] may translate the relevant information into the preferred language of operation before management. In one exemplary implementation, the processor [102] may perform the translation operation via the AI Controller [106], with the use of one or more large language models (LLMs).
[0065] For example, an entity may be involved in global operations, however, the preferred language of operation for the entity may be English, and therefore the preferred language of operation may be set to English, wherein the system [100] will operate using English and generate recommendations of leads in English. Any language other than English, i.e., Hindi, Marathi or French will comprise a language other than the preferred language of operation. Therefore, any data collected from a plurality of sources of data that is published in a language other than the preferred language of operation will be translated into the preferred language of operation, i.e., English, and thereafter the further processing and generation of outcomes of the method of the present disclosure will be in the preferred language of operation.
[0066] In another example, wherein a relevant information is extracted from the one or more data sources that may be published in Mandarin, and the relevant information is associated with a potential lead in China, the system [100] may recognize the same and translate the relevant information from Mandarin to English for the generation of one or more recommendations of leads for the entity.
[0067] Returning to the operation of the system [100], thereafter, the processor [102] may be configured to analyze the at least one relevant information, and on the basis of the analysis, the processor [102] may determine a person of interest associated with one or more leads, from the at least one relevant information.
[0068] As used herein, a person of interest may comprise a person, a group or an organization that may be interested in the one or more operations of the entity. As such, a person of interest may be a potential customer, point of contact in any organization that may require any product, services or operations of the entity, or a group of the same. Additionally, the person of interest may also be an organization itself.
[0069] In an exemplary implementation, the processor [102] may further determine one or more contact and designation information associated with the person of interest, if available. In another exemplary implementation, the one processor [102] may perform the extraction, management and the analysis of the at least one relevant information, via the AI Controller, wherein, one or more Natural Language Processing (NLP) techniques may be employed to perform each or any of the aforementioned actions. It may be understood that the one or more NLP techniques used herein may comprise any NLP techniques as may be known to a person ordinarily skilled in the art.
[0070] Returning to the operation of the system [100], the processor [102] may then identify a connection to the person of interest associated with one or more leads, from a database.
[0071] In an exemplary implementation, a database may comprise a database storing connection information for one or more persons associated with the entity and the one or more persons of interest. A connection may simply comprise an existing contact information, and/or link to the person of interest. Additionally, a connection may comprise a recorded relationship and network with the person of interest, via one or more persons associated with the entity. Herein, the database, may be a proprietary database of the entity, or a database associated with a service employed by the entity for storage and management of data. In another exemplary implementation, the database may be stored in the storage [108].
[0072] For example, in one scenario, the database may be a customer relationship management (CRM) database, wherein, records of previous engagement of one or more persons associated with the entity, with customers of the entity may be stored. Here, any of the customers may be a person of interest, and ideally, the database may be configured to store contact information for each of the customers.
[0073] In another exemplary implementation, the identification of the connection with a person of interest may be performed via the AI Controller [106], using one or more artificial intelligence (AI) models, as may be known to a person skilled in the art. For example, a Large Language Model (LLM) may be employed to enhance the accuracy of identification of existing connections to a person of interest, from the database.
[0074] In one scenario, the identification of a connection to the person of interest may result in identification of one or more gaps in the database. Herein, the one or more gaps may comprise an absence of existing relationship with the person of interest, a missing contact or a lack of record. In an event of identification of one or more gaps in the database, the processor [102] may be further configured to rectify the one or more gaps via a set of rectification actions. As used herein, a set of rectification actions may include, but are not limited to, flagging the one or more gaps for rectification by the one or more users, and retrieving requisite information for rectification of the one or more gaps from a second proprietary database of the entity, or any other data source that may be accessible to the system [100] to perform the rectification of one or more gaps.
[0075] For example, wherein, a gap corresponding to lack of contact information for a person of interest, e.g., a potential vendor for products of the entity, is identified, the system [100] may attempt a search and retrieval operation for the contact information from an alternative data source to rectify the gap.
[0076] Returning to the operation of the system [100], thereafter, the processor [102] may generate one or more recommendations of leads for the entity. Here, the generation of the of the one or more recommendations may be based on the at least one relevant information and connection to the person of interest. The one or more recommendations of leads generated by the system [100] may comprise one or more detailed reports, one or more analytical insights, one or more actionable insights etc., that may comprise the at least one relevant information, and are presented in a summarized format. Additionally, the one or more recommendations may indicate a level of priority of action for the potential leads identified. In another implementation, the recommendations may also comprise the relevant information related to the person of interest associated with the one or more leads, to enable action against the one or more leads.
[0077] Further, in an exemplary implementation, one or more recommendations of leads may be displayed to the one or more users via the interface unit [110], using a graphical user interface. In another exemplary implementation, the recommendations may be displayed via more than one graphical user interface, wherein a different graphical user interface may be used to display the recommendations, based on the type of recommendations and the user.
[0078] Furthermore, an implementation of the present disclosure encompasses that the system [100] may be configured to perform the generation of one or more recommendation of leads in response to the provision of one or more inputs by a user, wherein the one or more inputs may define a set of parameters for the retrieval of the one or more sets of data from the at least one data source. Herein, the parameters defined by one or more inputs may comprise, but are not limited to, type and scope of data sources for retrieval, type of data to be retrieved, preferred language of data, a preferred geographical location associated with the data, translation parameters and age of data, i.e., the data range in which the data may have been published. Further, in another exemplary implementation, the one or more inputs may be provided to the system [100] via a chat interface, using the AI Controller [106].
[0079] Referring now to FIG. 2, an exemplary flow diagram of the method for generating one or more recommendation of leads for an entity, in accordance with the exemplary implementation of the present invention is shown. As illustrated, the method [200] may begin at step [202].
[0080] Next, at step [204], the method [200] may comprise retrieving, one or more sets of data from at least one data source.
[0081] In an exemplary implementation, the method [200] may further comprise generating the one or more recommendation of leads in response to the provision of one or more inputs by a user, wherein the one or more inputs may define a set of parameters for the retrieval of the one or more sets of data from the at least one data source.
[0082] In another exemplary implementation, the method [200] may further comprise one or more inputs may be provided via a chat interface.
[0083] Next at step [206], the method [200] may comprise extracting at least one relevant information from the one or more sets of data and managing the at least one relevant information on the basis of a predetermined set of criteria.
[0084] As used herein, the predetermined set of criteria may include, but is not limited to, one or more plans, trends, reports, goals or requirements associated with the operations of the entity.
[0085] In an exemplary implementation, method [200] may further comprise detecting the language of the extracted relevant information. Further, the method [200] may comprise translating the relevant information into the preferred language of operation, in an event any of the extracted relevant information is in a language other than a configured preferred language, before managing extracted relevant information.
[0086] In another exemplary implementation, the method [200] may further comprise translating the at least one relevant information useing of one or more large language models (LLMs).
[0087] Next, at step [208], the method [200] may comprise determining, a person of interest associated with one or more leads on the basis of an analysis of the at least one relevant information.
[0088] A person of interest may comprise a person, a group or an organization that may be interested in the one or more operations of the entity. Likewise, a person of interest may be a potential customer, point of contact in any organization that may require any product, services or operations of the entity, or a group of the same.
[0089] In an exemplary implementation, the actions of extracting, managing and analyzing the at least one relevant information may be performed via one or more Natural Language Processing (NLP) techniques. It may be understood that the one or more NLP techniques used herein may comprise any NLP techniques as may be known to a person ordinarily skilled in the art.
[0090] Next, at step [210], the method [200] may comprise identifying, from a database, at least one connection to the person of interest. In an exemplary implementation, the database may be a customer relationship management (CRM) database.
[0091] In an exemplary implementation, the method [200] may further comprise identifying at least one connection to a person of interest using one or more artificial intelligence (AI) models, as may be known to a person skilled in the art. In one example, the connection to the person of interest may be identified using a large language model (LLM).
[0092] In another exemplary implementation, identifying a connection to the person of interest may further comprise identifying one or more gaps in the database. Herein, the one or more gaps may comprise an absence of existing relationship with the person of interest, a missing contact or a lack of record.
[0093] In yet another exemplary implementation, the method [200] may further comprise rectifying the one or more gaps via a set of rectification actions, in an event of identification of one or more gaps in the database.
[0094] Next, at step [212], the method [200] may comprise generating, one or more recommendation of leads, on the basis of at least one relevant information and at least one connection to the person of interest.
[0095] In an exemplary implementation, the method [200] may further comprise generating the one or more recommendations based on the at least one relevant information and connection to the person of interest.
[0096] The one or more recommendations of leads may comprise one or more detailed reports, one or more analytical insights, one or more actionable insights etc., derived from the at least one relevant information, and are presented in a summarized format. Additionally, the one or more recommendations may indicate a level of priority of action for the potential leads identified. In another implementation, the recommendations may also comprise the relevant information related to the person of interest associated with the one or more leads, to enable action against the one or more leads.
[0097] In another exemplary implementation, the one or more recommendations of leads may comprise a summarized compilation of the at least one relevant information and the at least one connection to the person of interest associated with one or more leads.
[0098] In yet another exemplary implementation, the method [200] may comprise displaying the one or more recommendations of leads to the one or more users, using a graphical user interface. In another exemplary implementation, the recommendations may be displayed via more than one graphical user interface, wherein a different graphical user interface may be used to display the recommendations, based on the type of recommendations and the user.
[0099] Thereafter, at step [214], the method [200] terminates.
[00100] Referring now to FIG. 3, an exemplary chat interface is shown, in accordance with an exemplary implementation of the present disclosure. As illustrated, the system [100] may provide a chat-based interface to enable a user to provide one or more inputs comprising parameters that may be used to guide the retrieval of one or more sets of data for generating one or more recommendations for an entity. For example, as illustrated, a user may provide inputs in natural language, such as category/type of data, preferred geographical location of the data, and a preferred age of the data.
[00101] As is evident from the paragraphs above, the present disclosure provides a technically advanced solution for generating one or more recommendations of leads for an entity. Thus in view of the above, the system and method are cost and time-efficient, easy to scale and allow users to process large volume of data from a plurality of sources to identify potential leads in short amount of time. The present solution also facilitates a resource friendly approach to identifying potential leads from large data sets, and presenting them in an easy to read recommendation-based formats.
[00102] While considerable emphasis has been placed herein on the disclosed implementations, it will be appreciated that many implementations can be made and that many changes can be made to the implementations without departing from the principles of the present disclosure. These and other changes in the implementations of the present disclosure will be apparent to those skilled in the art, whereby it is to be understood that the foregoing descriptive matter to be implemented is illustrative and non-limiting.
,CLAIMS:
1. A method [200] for generating one or more recommendations of leads for an entity, the method comprising:
retrieving, one or more sets of data from at least one data source;
extracting at least one relevant information from the one or more sets of data and managing the at least one relevant information on the basis of a predetermined set of criteria;
determining, a person of interest associated with one or more leads on the basis of an analysis of the at least one relevant information;
identifying, from a database, at least one connection to the person of interest; and
generating, one or more recommendation of leads, on the basis of at least one relevant information and at least one connection to the person of interest.
2. The method [200] as claimed in claim 1, wherein the method further comprises identifying one or more gaps from the database.
3. The method [200] as claimed in claim 1 and claim 2, wherein the method further comprises rectifying the one or more gaps in the database via a set of rectification actions.
4. The method [200] as claimed in claim 1, wherein the predetermined set of criteria comprises one or more plans, trends, reports, goals or requirements associated with the operations of the entity.
5. The method [200] as claimed in claim 1, wherein the person of interest associated with one or more leads comprises at least one of a person, a group or an organization interested in the one or more operations of the entity.
6. The method [200] as claimed in claim 1, wherein the identification of at least one connection to the person of interest is performed using one or more artificial intelligence (AI) models.
7. The method [200] as claimed in claim 1, wherein the extraction, management and the analysis of the at least one relevant information comprises the use of one or more Natural Language Processing (NLP) techniques.
8. The method [200] as claimed in claim 1, wherein the database comprises a customer relationship management (CRM) database.
9. The method [200] as claimed in claim 1, wherein the one or more recommendations of leads comprises a summarized compilation of the at least one relevant information and the at least one connection to the person of interest associated with one or more leads.
10. The method [200] as claimed in claim 1, wherein the at least one relevant information is translated from a non-preferred language to a preferred language.
11. The method [200] as claimed in claim 1 and 10, wherein the translation of the at least one relevant information from a non-preferred language to a preferred language is performed using one or more AI models.
12. The method [200] as claimed in claim 1, wherein the one or more recommendations of leads are displayed via one or more graphical interfaces.
13. The method [200] as claimed in claim 1, wherein the method is performed in response to one or more inputs provided by a user via a chat interface.
14. The method [200] as claimed in claim 1 and 13, wherein the one or more inputs are used to define a set of parameters to retrieve the one or more sets of data from at least one data source.
15. A system [100] for generating one or more recommendations of leads for an entity, the system comprising:
a processor [102] configured to,
retrieve, one or more sets of data from at least one data source;
extract at least one relevant information from the one or more sets of data and manage the at least one relevant information on the basis of a predetermined set of criteria;
determine, a person of interest associated with one or more leads on the basis of an analysis of the at least one relevant information;
identify, from a database, at least one connection to the person of interest; and
generate, one or more recommendation of leads, on the basis of at least one relevant information, at least one connection to the person of interest.
16. The system [100] as claimed in claim 15, wherein the processor is further configured to identify one or more gaps from the database.
17. The system [100] as claimed in claim 15 and claim 16, wherein the processor is further configured to rectify the one or more gaps in the database via a set of rectification actions.
18. The system [100] as claimed in claim 15, wherein the predetermined set of criteria comprises one or more plans, trends, reports, goals or requirements associated with the operations of the entity.
19. The system [100] as claimed in claim 15, wherein the person of interest associated with one or more leads comprises one or more leads comprises at least one of a person, a group or an organization interested in the one or more operations of the entity.
20. The system [100] as claimed in claim 15, wherein the identification of at least one connection to the person of interest is performed using one or more artificial intelligence (AI) models.
21. The system [100] as claimed in claim 15, wherein the extraction, management and the analysis of the at least one relevant information comprises the use of one or more Natural Language Processing (NLP) techniques.
22. The system [100] as claimed in claim 15, wherein the database comprises a customer relationship management (CRM) database.
23. The system [100] as claimed in claim 15, wherein the one or more recommendations of leads comprises a summarized compilation of the at least one relevant information and the at least one connection to the person of interest associated with one or more leads.
24. The system [100] as claimed in claim 15, wherein the at least one relevant information is translated from a non-preferred language to a preferred language.
25. The system [100] as claimed in claim 15 and 24, wherein the translation of the at least one relevant information from a non-preferred language to a preferred language is performed using one or more AI models.
26. The system [100] as claimed in claim 15, wherein the one or more recommendations of leads are displayed via one or more graphical interfaces.
27. The system [100] as claimed in claim 15, wherein the method is performed in response to one or more inputs provided by a user via a chat interface.
28. The system [100] as claimed in claim 15 and 27, wherein the one or more inputs are used to define a set of parameters to retrieve the one or more sets of data from at least one data source.