Description:FIELD OF INVENTION
[0001] Embodiments of a present disclosure relate to maximizing sales revenue, and more particularly to a system and method for artificial intelligence driven productivity enhancement for sales management.
BACKGROUND
[0002] Sales management is basically a process of organizing and optimizing sales of a business for maximizing the sales efficiency of the business. Conventionally, in the case of the real estate industry, either a real estate specialist or a Telesales agent is allocated to a lead as it enters a sales system from numerous sources, such as digital, offline marketing sources, channel partners, referrals, etc. This person engages with the lead to understand their needs. The lead is classified as interested once it has been determined that the requirement has been comprehended and that the customer actually intends to buy a home. After that, the prospective client pays a site visit to the property. The lead negotiates and books the house after finishing the site inspection. In this process, there is a significant lead inflow at the beginning, and by the time the home booking occurs, the lead volume from the beginning is rapidly decreasing. The majority of leads are lost between lead generation and site visits, which is the real estate lifecycle.
[0003] Hence, there is a need for an improved system and method for artificial intelligence driven productivity enhancement for sales management which addresses the aforementioned issues.
BRIEF DESCRIPTION
[0004] In accordance with one embodiment of the disclosure, a system for artificial intelligence driven productivity enhancement for sales management is provided. The system includes a processing subsystem hosted on a server. The processing subsystem is configured to execute on a network to control bidirectional communications among a plurality of modules. The processing subsystem includes a lead classification module. The lead classification module is configured to identify one or more success characteristics that assisted one or more clients to complete a preferred purchase from a preferred seller, by analyzing one or more client behavioral characteristics corresponding to the corresponding one or more clients using artificial intelligence. The lead classification module is also configured to generate a prospect quality scoring model by superimposing the corresponding one or more success characteristics onto a plurality of lead details corresponding to one or more leads of the preferred seller, in real-time using machine learning. The lead classification module is further configured to generate a prospect quality score corresponding to a prediction of a probability of successfully converting the one or more leads into one or more future clients, using the prospect quality scoring model. Further, the lead classification module is also configured to classify the one or more leads under a preferred lead category based on the prospect quality score associated with the corresponding one or more leads. The processing subsystem also includes an agent classification module operatively coupled to the lead classification module. The agent classification module is configured to analyze one or more agent behavioral characteristics corresponding to one or more sales agents associated with the preferred seller using artificial intelligence, based on agent historic data corresponding to the corresponding one or more sales agents, upon classifying the one or more leads. The agent classification module is also configured to generate an agent score corresponding to a performance and a profile of the one or more sales agents, using an artificial intelligence-based model, based on the analysis of the one or more agent behavioral characteristics. Further, the agent classification module is also configured to classify the one or more sales agents under a preferred agent category based on the agent score associated with the corresponding one or more sales agents. The processing subsystem also includes a lead allocation module operatively coupled to the agent classification module. The lead allocation module is configured to generate a lead allocation model in real-time, using machine learning based on at least one of lead historic data and the classification of the one or more sales agents. The lead allocation module is also configured to allocate a predefined count of the one or more sales agents for dealing with the one or more leads using the lead allocation model, based on the prospect quality score corresponding to the corresponding one or more leads and the agent score corresponding to the corresponding one or more sales agents. Further, the processing subsystem also includes a lead reviving module operatively coupled to the lead allocation module. The lead reviving module is configured to generate one or more propensity models in real-time, based on analysis of at least one of one or more structured parameters, one or more unstructured parameters, and one or more features using artificial intelligence, when a specific count of the one or more leads fail to reach a final stage of one or more stages of the sales funnel. The lead reviving module is configured to identify one or more potential leads having a potential to get revived from a predetermined list of one or more failed leads, to a next stage in the one or more stages of the sales funnel, based on the one or more propensity models, using sentiment analysis and data pre-processing, thereby facilitating the lead behavior analysis for the sales management.
[0005] In accordance with another embodiment, a method for artificial intelligence driven productivity enhancement for sales management is provided. The method includes identifying one or more success characteristics that assisted one or more clients to complete a preferred purchase from a preferred seller, by analyzing one or more client behavioral characteristics corresponding to the corresponding one or more clients using artificial intelligence. The method also includes generating a prospect quality scoring model by superimposing the corresponding one or more success characteristics onto a plurality of lead details corresponding to one or more leads of the preferred seller, in real-time using machine learning. Further, the method also includes generating a prospect quality score corresponding to a prediction of a probability of successfully converting the one or more leads to one or more future clients, using the prospect quality scoring model. Furthermore, the method also includes classifying the one or more leads under a preferred lead category based on the prospect quality score associated with the corresponding one or more leads. The method further includes analyzing one or more agent behavioral characteristics corresponding to one or more sales agents associated with the preferred seller using artificial intelligence, based on agent historic data corresponding to the corresponding one or more sales agents, upon classifying the one or more leads. The method also includes generating an agent score corresponding to a performance and a profile of the one or more sales agents, using an artificial intelligence-based model, based on the analysis of the one or more agent behavioral characteristics. Subsequently, the method also includes classifying the one or more sales agents under a preferred agent category based on the agent score associated with the corresponding one or more sales agents. In addition, the method also includes generating a lead allocation model in real-time, using machine learning based on at least one of lead historic data and the classification of the one or more sales agents. The method further includes allocating a predefined count of the one or more sales agents for dealing with the one or more leads using the lead allocation model, based on the prospect quality score corresponding to the corresponding one or more leads and the agent score corresponding to the corresponding one or more sales agents. The method also includes generating one or more propensity models in real-time, based on analysis of at least one of one or more structured parameters, one or more unstructured parameters, and one or more features using artificial intelligence, when a specific count of the one or more leads fail to reach a final stage of one or more stages of sales funnel. Further, the method includes identifying one or more potential leads having a potential to get revived from a predetermined list of one or more failed leads, to a next stage in the one or more stages of the sales funnel, based on the one or more propensity models, using sentiment analysis and data pre-processing, thereby facilitating the lead behavior analysis for the sales management.
[0006] To further clarify the advantages and features of the present disclosure, a more particular description of the disclosure will follow by reference to specific embodiments thereof, which are illustrated in the appended figures. It is to be appreciated that these figures depict only typical embodiments of the disclosure and are therefore not to be considered limiting in scope. The disclosure will be described and explained with additional specificity and detail with the appended figures.
BRIEF DESCRIPTION OF THE DRAWINGS
The disclosure will be described and explained with additional specificity and detail with the accompanying figures in which:
[0007] FIG. 1 is a block diagram representation of a system for artificial intelligence driven productivity enhancement for sales management in accordance with an embodiment of the present disclosure;
[0008] FIG. 2 is a block diagram representation of an exemplary embodiment of the system for artificial intelligence driven productivity enhancement for sales management of FIG. 1 in accordance with an embodiment of the present disclosure;
[0009] FIG. 3 is a block diagram of a sales management computer or a sales management server in accordance with an embodiment of the present disclosure;
[0010] FIG. 4 (a) is a flow chart representing steps involved in a method for artificial intelligence driven productivity enhancement for sales management in accordance with an embodiment of the present disclosure; and
[0011] FIG. 4 (b) is a flow chart representing continued steps involved in a method of FIG. 4 (a) in accordance with an embodiment of the present disclosure.
[0012] Further, those skilled in the art will appreciate that elements in the figures are illustrated for simplicity and may not have necessarily been drawn to scale. Furthermore, in terms of the construction of the device, one or more components of the device may have been represented in the figures by conventional symbols, and the figures may show only those specific details that are pertinent to understanding the embodiments of the present disclosure so as not to obscure the figures with details that will be readily apparent to those skilled in the art having the benefit of the description herein.
DETAILED DESCRIPTION
[0013] For the purpose of promoting an understanding of the principles of the disclosure, reference will now be made to the embodiment illustrated in the figures and specific language will be used to describe them. It will nevertheless be understood that no limitation of the scope of the disclosure is thereby intended. Such alterations and further modifications in the illustrated system, and such further applications of the principles of the disclosure as would normally occur to those skilled in the art are to be construed as being within the scope of the present disclosure.
[0014] The terms "comprises", "comprising", or any other variations thereof, are intended to cover a non-exclusive inclusion, such that a process or method that comprises a list of steps does not include only those steps but may include other steps not expressly listed or inherent to such a process or method. Similarly, one or more devices or sub-systems or elements or structures or components preceded by "comprises... a" does not, without more constraints, preclude the existence of other devices, sub-systems, elements, structures, components, additional devices, additional sub-systems, additional elements, additional structures or additional components. Appearances of the phrase "in an embodiment", "in another embodiment" and similar language throughout this specification may, but not necessarily do, all refer to the same embodiment.
[0015] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this disclosure belongs. The system, methods, and examples provided herein are only illustrative and not intended to be limiting.
[0016] In the following specification and the claims, reference will be made to a number of terms, which shall be defined to have the following meanings. The singular forms “a”, “an”, and “the” include plural references unless the context clearly dictates otherwise.
[0017] Embodiments of the present disclosure relate to a system for artificial intelligence driven productivity enhancement for sales management. As used herein, the term “lead” refers to an individual or organization that has expressed interest in buying what a business is selling. Further, as used herein, the term “lead behavior analysis” refers to analyzing and understanding a behavior of leads using certain techniques. Furthermore, as used herein, the term “sales management” refers to a process of organizing and optimizing sales of a business for maximizing the sales efficiency of the business. Moreover, the behavior of one or more leads of the business has a huge impact on the sales efficiency of the business. Thus, the system described hereafter in FIG. 1 is the system for facilitating the lead behavior analysis for the sales management.
[0018] FIG. 1 is a block diagram representation of a system (10) for artificial intelligence driven productivity enhancement for sales management in accordance with an embodiment of the present disclosure. The system (10) includes a processing subsystem (20) hosted on a server (30). In one embodiment, the server (30) may include a cloud server. In another embodiment, the server (30) may include a local server. The processing subsystem (20) is configured to execute on a network (not shown in FIG. 1) to control bidirectional communications among a plurality of modules. In one embodiment, the network may include a wired network such as a local area network (LAN). In another embodiment, the network may include a wireless network such as wireless fidelity (Wi-Fi), Bluetooth, Zigbee, near field communication (NFC), infra-red communication, or the like.
[0019] Basically, when a lead approaches a seller, the lead is generally assigned to a sales agent who interacts with the lead to understand their requirements for a purchase. In one embodiment, the lead may also be assigned to a call centre agent. Once the requirements are understood and the lead is having a genuine home buying intent customer, the lead is categorized as interested. Post this, in case of a real estate industry, a potential customer visits a property for a site visit. Once the site visit is done by the lead, the lead enters into negotiation and books the house.
[0020] Therefore, the approaching of one or more users to one or more sellers may correspond to a generation of one or more leads. Upon generation of the one or more leads, some of the one or more leads may be willing to just check for price difference and not make an actual purchase, some may be actually interested in purchasing but may have financial restrictions, some may be both interested and financially sound for making the purchase, or the like. Thus, for analyzing a behavior of the one or more leads, the corresponding one or more leads may initially have to be classified.
[0021] Therefore, the processing subsystem (20) includes a lead classification module (40). However, prior to classifying the one or more leads, details corresponding to the one or more leads may have to be collected. Therefore, in an embodiment, the processing subsystem (20) may also include a data collection module (as shown in FIG. 2) operatively coupled to the lead classification module (40). The data collection module may be configured to extract and record a plurality of lead details corresponding to the one or more leads of a preferred seller, upon generation of the one or more leads via a plurality of sources.
[0022] In one exemplary embodiment, the plurality of lead details may include at least one of a plurality of personal details of the one or more leads, a plurality of project details corresponding to one or more projects the one or more leads are willing to make a deal with, one or more features corresponding to the one or more leads, and the like. In one embodiment, the plurality of personal details may include at least one of name, contact details, budget details, type of purchase interested in, and the like corresponding to the one or more leads. In another embodiment, the plurality of project details may include at least one of a project name, location, one or more activities performed by the one or more leads in association with the one or more projects, and the like. In yet another embodiment, the one or more features may include at least one of mobile operator, mobile phone circle, time of lead creation, email domain, a project for which the lead is generated, micro market, a ticket size of the project, amenities of the project, and the like.
[0023] Further, in an embodiment, the plurality of lead details may be stored in a database of the system (10). The database may include a local database or a cloud database. In a specific embodiment, the preferred seller may be a real estate seller, a contractor, a builder, a real estate agent, business-to-business (B2B) companies, and the like. Furthermore, in an embodiment, the plurality of sources of the generation of the one or more leads may include at least one of digital marketing, offline mediums, tour channel partners, through customer referrals, through loyalty customers, advertising, affiliates, and the like.
[0024] Further, the lead classification module (40) is configured to identify one or more success characteristics that assisted one or more clients to complete a preferred purchase from the preferred seller, by analyzing one or more client behavioral characteristics corresponding to the corresponding one or more clients using artificial intelligence (AI). In an embodiment, the one or more clients may correspond to the one or more leads that have agreed to make a purchase of one or more products, or one or more services provided by the preferred seller. In one embodiment, the one or more products or the one or more services may include real estate property, a plot, an independent house, an apartment, a field, or the like. Moreover, in an embodiment, the preferred purchase may correspond to the one or more products or the one or more services.
[0025] For example, suppose a characteristic of the one or more leads of asking too many questions corresponding to the purchase to be made, has assisted the one or more leads in successfully making the purchase based on preferred terms of the one or more leads. Therefore, of the one or more client behavioral characteristics, certain characteristics that are directly responsible for converting the one or more leads to the one or more clients may be corresponding to the one or more success characteristics. Further, as used herein, the term “artificial intelligence” is defined as the simulation of human intelligence processes by machines, especially computer systems.
[0026] The lead classification module (40) is also configured to generate a prospect quality scoring model by superimposing the corresponding one or more success characteristics onto the plurality of lead details corresponding to the one or more leads of the preferred seller, in real-time using machine learning (ML). As used herein, the term “machine learning” is defined as a subfield of artificial intelligence, which is broadly defined as the capability of a machine to imitate intelligent human behavior.
[0027] The lead classification module (40) is further configured to generate a real-time prospect quality score corresponding to a prediction of a probability of successfully converting the one or more leads to one or more future clients, using the prospect quality scoring model. Further, the lead classification module (40) is also configured to classify the one or more leads under a preferred lead category based on the prospect quality score associated with the corresponding one or more leads. In one embodiment, the preferred category may include a Platinum category, a regular category, or the like.
[0028] In one exemplary embodiment, the Platinum category may include the one or more leads having the prospect quality score greater than or equal to a threshold quality score. In another embodiment, the regular category may include the one or more leads having the prospect quality score less than the threshold quality score. Further, the one or more leads belonging to the Platinum category may be given more attention by one or more sales agents, as such one or more leads are more likely to convert to the one or more clients. However, the one or more leads belonging to the regular category may be given a little less attention as such one or more leads are less likely to convert to the one or more clients.
[0029] Subsequently, the processing subsystem (20) also includes an agent classification module (50) operatively coupled to the lead classification module (40). Prior to classifying the one or more sales agents, details corresponding to the one or more sales agents may have to be collected by the system (10). Therefore, in an embodiment, the data collection module may also be configured to extract agent historic data corresponding to the one or more sales agents responsible for working on converting the one or more leads to the one or more clients for the preferred seller. In one embodiment, the agent historic data may include at least one of past interactions of the one or more sales agents with the one or more leads, an outcome of such past interactions, call recordings, feedback about the corresponding one or more sales agents, and the like. In one embodiment, the agent historic data may be extracted from the database of the system (10).
[0030] Later, the agent classification module (50) is configured to analyze one or more agent behavioral characteristics corresponding to the one or more sales agents associated with the preferred seller using AI, based on the agent historic data corresponding to the corresponding one or more sales agents, upon classifying the one or more leads. The agent classification module (50) is also configured to generate an agent score corresponding to a performance and a profile of the one or more sales agents, using an AI-based model, based on the analysis of the one or more agent behavioral characteristics. Further, the agent classification module (50) is also configured to classify the one or more sales agents under a preferred agent category based on the agent score associated with the corresponding one or more sales agents.
[0031] In one exemplary embodiment, the preferred agent category may include a top category, a medium category, a bottom category, and the like. In one embodiment, the top category may include the one or more sales agents having the agent score greater than or equal to a first threshold agent score. In another embodiment, the medium category may include the one or more sales agents having the agent score less than the first threshold agent score but greater than or equal to a second threshold agent score. In yet another embodiment, the low category may include the one or more sales agents having the agent score less than the second threshold agent score.
[0032] In addition, the processing subsystem (20) also includes a lead allocation module (60) operatively coupled to the agent classification module (50). The lead allocation module (60) is configured to generate a lead allocation model in real-time, using ML based on at least one of lead historic data and the classification of the one or more sales agents. In one embodiment, the lead historic data may include at least one of the plurality of lead details, the one or more client behavioral characteristics, the prospect quality score, the preferred lead category to which the one or more leads belong, how the one or more leads have progressed in a sales funnel, all information captured by the one or more sales agents about the corresponding one or more leads, and the like. As used herein, the term “sales funnel” is defined as the visual representation of the customer journey, depicting the sales process from awareness to action.
[0033] The lead allocation module (60) is also configured to allocate a predefined count of the one or more sales agents for dealing with the one or more leads using the lead allocation model, based on the prospect quality score corresponding to the corresponding one or more leads and the agent score corresponding to the corresponding one or more sales agents. In one embodiment, the one or more sales agents with a higher agent score may be allocated with the one or more leads with a higher prospect quality score. In such embodiment, of the predefined count of the one or more sales agents, a first agent may have a highest score, a reason for allocating the predefined count of the one or more sales agents may be to make sure that the one or more leads are continuously contacted even in absence of the first agent.
[0034] During one or more stages of the sales funnel of the one or more leads, most of the one or more leads fail to reach a final stage and get classified as one or more failed leads at different stages of the one or more stages. However, such one or more failed leads can be revived. Therefore, the processing subsystem (20) also includes a lead reviving module (70) operatively coupled to the lead allocation module (60). In one embodiment, the lead reviving module (70) may not be operatively coupled to the lead allocation module (60). In such an embodiment, the lead reviving module may be operatively coupled to the the lead classification module (40) and is accountable to focus on the one or more leads that may be revived and may be moved up the ladder based on the client’s behaviour using AI. It must be noted that in such an embodiment the said one or more leads may be defined as those leads that fail due to multiple reasons in the one or more stages. In one embodiment, the one or more stages may include a lead stage, an interested qualified lead stage, after site visit stage, booking stage and the like.
[0035] The lead reviving module (70) is configured to generate one or more propensity models in real-time, based on analysis of at least one of one or more structured parameters, one or more unstructured parameters, and the one or more features using AI, when a specific count of the one or more leads fail to reach a final stage of one or more stages of the sales funnel. In one exemplary embodiment, the one or more structured parameters may include at least one of the lead historic data, the agent historic data, a performance of the one or more sales agents, a behavior of the one or more leads, and the like. In another exemplary embodiment, the one or more unstructured data may include comments, notes, and the like corresponding to the one or more leads and the one or more sales agents.
[0036] The lead reviving module (70) is configured to identify one or more potential leads having a potential to get revived from a predetermined list of the one or more failed leads, to a next stage in the one or more stages of the sales funnel, based on the one or more propensity models, using sentiment analysis and data pre-processing, thereby facilitating the lead behavior analysis for the sales management. As used herein, the term “sentiment analysis” is defined as the process of computationally identifying and categorizing opinions expressed in a piece of text, especially in order to determine whether the writer's attitude towards a particular topic, product, etc. is positive, negative, or neutral.
[0037] Further, upon allocating the predefined count of the one or more sales agents for dealing with the one or more leads, the corresponding one or more sales agents may have to contact the corresponding one or more leads. Therefore, in an embodiment, the processing subsystem (20) may also include a suggestion module (as shown in FIG. 2) operatively coupled to the lead reviving module (70). The suggestion module is configured to generate a first suggestion for the one or more sales agents to contact the one or more leads for a first preferred count, based on the preferred lead category under which the corresponding one or more leads are classified. In one exemplary embodiment, the first preferred count may be higher if the preferred lead category may be the platinum category. In another exemplary embodiment, the first preferred count may be lower if the preferred lead category may be the regular category.
[0038] Later, upon reviving the one or more potential leads from the predetermined list of the one or more failed leads, the preferred seller may have to modify an approach in which the corresponding one or more potential leads may be contacted. Therefore, in an embodiment, the suggestion module may be configured to generate a second suggestion for the one or more sales agents to contact the one or more potential leads for a second preferred count, based on the corresponding one or more stages of the sales funnel during which the one or more potential leads are identified. Also, in an embodiment, the suggestion module may suggest the preferred seller to change the one or more sales agents who are contacting the corresponding one or more leads or the one or more potential leads.
[0039] Later, in an embodiment, the processing subsystem (20) may also include an agent feedback module (as shown in FIG. 2) operatively coupled to the lead reviving module (70). The agent feedback module may be configured to generate a feedback for the one or more sales agents in real-time, based on analysis of a conversion rate of the one or more leads to the one or more clients allocated to the corresponding one or more sales agents using AI. In one exemplary embodiment, the feedback may include a reward a plan for improving the performance and the profile of the one or more sales agents.
[0040] Subsequently, in an embodiment, the processing subsystem (20) may further include a failed lead categorization module (as shown in FIG. 2) operatively coupled to the lead reviving module (70). The failed lead categorization module may be configured to categorize the one or more failed leads under one or more stage-based lead categories, based on a generation of the one or more failed leads at the corresponding one or more stages of the sales funnel. In one exemplary embodiment, in case of the real estate industry, the one or more stage-based lead categories may include will fail to reach an interested category, will be interested but not visit the site, will be interested, and will have at least one site visit but will not book and purchase the site, and the likes.
[0041] FIG. 2 is a block diagram representation of an exemplary embodiment of the system (10) for artificial intelligence driven productivity enhancement for sales management of FIG. 1 in accordance with an embodiment of the present disclosure. Consider a non-limiting example in which a person ‘X’ (80) is willing to purchase a property, but is not sure how to make a choice, as a real estate market has multiple property options for multiple customers (90) willing to purchase one. To receive assistance for decision making, the person ‘X’ (80) decides to use the system (10) and visits a dashboard of the system (10) via a personal mobile phone (100), and performs one or more activities such as, but not limited to, browses a few properties of certain types, checks for properties with specific price ranges, searches for particular localities, and the like. The system (10) includes the processing subsystem (20) hosted on a cloud server (110). The system (10) basically includes the lead classification module (40), the agent classification module (50), the lead allocation module (60), and the lead reviving module (70) operatively coupled with each other.
[0042] As the person ‘X’ (80) is performing the one or more activities, the system (10) generates a prospect quality score for the person ‘X’ (80) and classifies the person ‘X’ (80) under a preferred lead category via the lead classification module (40). For the system (10) to be able to classify the person ‘X’ (80), details of the person ‘X’ (80) need to be extracted from a cloud database (120) of the system (10). This is done via the data collection module (130) based on the one or more activities performed by the person ‘X’ (80). Then, the person ‘X’ (80) raises a request to communicate with the one or more specific sales agents (140) of a preferred seller ‘Y’ (150) having properties located at street ‘Z’ (160). Further, the preferred seller ‘Y’ (150) has hired or authorized or empanelled to the one or more specific sales agents (140) to provide service to the customers (90) and is also using the system (10) via a dashboard on a personal seller mobile phone (165). A behavior, a profile and a performance of the one or more specific sales agents (140) is continuously analyzed via the agent classification module (50), and a corresponding agent score is generated for each of the one or more specific sales agents (140), and each of the one or more specific sales agents (140) are also classified under a preferred agent category. For the system (10) to be able to analyze the behavior of the one or more specific sales agents (140), the system (10) may have to extract the agent historic data from the cloud database (120) of the system (10), which is done via the data collection module (130).
[0043] Suppose a sales agent ‘W’ (170) has been allocated to the person ‘X’ (80) via the lead allocation module (60) based on the lead historic data and the classification of the one or more specific sales agents (140). Suppose the person ‘X’ (80) is classified under a regular category via the lead classification module (40), and the sales agent ‘W’ (170) is a perfect match for dealing with the person ‘X’ (80). Therefore, the sales agent ‘W’ (170) is suggested to contact the person ‘X’ (80) for least number of times say one time a day via the suggestion module (180). In other words, the sales agent ‘W’ is suggested to contact the person ‘X’ frequently based on the sale process. Then, the sales agent ‘W’ (170) communicates with the person ‘X’ (80) and understands requirements of the person ‘X’ (80). The sales agent ‘W’ (170) can contact the person ‘X’ (80) using a personal agent mobile phone (190).
[0044] Further, suppose after communicating with the sales agent ‘W’ (170), next time the person ‘X’ (80) doesn’t show any further interest in visiting the site. Hence, the person ‘X’ (80) gets classified under the one or more failed leads. Similarly, suppose the customers (90) who visited the system (10) have got classified under the one or more failed leads at different stages of the sales funnel, and only a few have reached a final stage. So, the system (10) also identifies one or more potential leads that can be revived from the one or more failed leads via the lead reviving module (70). Later, the preferred seller ‘Y’ (150) is suggested to contact the person ‘X’ (80) and other customers (90) again, via the suggestion module (180). In one embodiment, if the preferred seller ‘Y’ (150) is not a builder, then the seller ‘Y’ can choose to change the one or more specific sales agents (140) who will be contacting the customers (90).
[0045] Furthermore, as this process of communication between the customers (90) and the one or more specific sales agents (140) continues, the one or more specific sales agents (140) are also provided with a feedback via the agent feedback module (200). Also, the one or more failed leads are classified under the one or more stage-based lead categories, via the failed lead categorization module (205) based on the generation of the one or more failed leads at the corresponding one or more stages of the sales funnel. This is how the system (10) facilitates the lead behavior analysis for the sales management of the preferred seller ‘Y’ (150).
[0046] FIG. 3 is a block diagram of a sales management computer or a sales management server (210) in accordance with an embodiment of the present disclosure. The sales management server (210) includes processor(s) (220), and memory (230) operatively coupled to a bus (240). The processor(s) (220), as used herein, means any type of computational circuit, such as, but not limited to, a microprocessor, a microcontroller, a complex instruction set computing microprocessor, a reduced instruction set computing microprocessor, a very long instruction word microprocessor, an explicitly parallel instruction computing microprocessor, a digital signal processor, or any other type of processing circuit, or a combination thereof.
[0047] Computer memory elements may include any suitable memory device(s) for storing data and executable program, such as read only memory, random access memory, erasable programmable read only memory, electrically erasable programmable read only memory, hard drive, removable media drive for handling memory cards and the like. Embodiments of the present subject matter may be implemented in conjunction with program modules, including functions, procedures, data structures, and application programs, for performing tasks, or defining abstract data types or low-level hardware contexts. Executable program stored on any of the above-mentioned storage media may be executable by the processor(s) (220).
[0048] The memory (230) includes a plurality of subsystems stored in the form of executable program which instructs the processor(s) (220) to perform method steps illustrated in FIG. 1. The memory (230) includes a processing subsystem (20) of FIG 1. The processing subsystem (20) further has following modules: a lead classification module (40), an agent classification module (50), a lead allocation module (60), a lead reviving module (70), a data collection module (130), a suggestion module (180), an agent feedback module (200), and a failed lead categorization module (205).
[0049] The lead classification module (40) is configured to identify one or more success characteristics that assisted one or more clients to complete a preferred purchase from a preferred seller, by analyzing one or more client behavioral characteristics corresponding to the one or more clients using artificial intelligence. The lead classification module (40) is also configured to generate a prospect quality scoring model by superimposing the corresponding one or more success characteristics onto a plurality of lead details corresponding to one or more leads of the preferred seller, in real-time using machine learning. The lead classification module (40) is also configured to generate a prospect quality score corresponding to a prediction of a probability of successfully converting the one or more leads to one or more future clients, using the prospect quality scoring model. The lead classification module (40) is also configured to classify the one or more leads under a preferred lead category based on the prospect quality score associated with the corresponding one or more leads.
[0050] The agent classification module (50) is configured to analyze one or more agent behavioral characteristics corresponding to one or more sales agents associated with the preferred seller using artificial intelligence, based on agent historic data corresponding to the corresponding one or more sales agents, upon classifying the one or more leads. The agent classification module (50) is also configured to generate an agent score corresponding to a performance and a profile of the one or more sales agents, using an artificial intelligence-based model, based on the analysis of the one or more agent behavioral characteristics. The agent classification module (50) is also configured to classify the one or more sales agents under a preferred agent category based on the agent score associated with the corresponding one or more sales agents.
[0051] The lead allocation module (60) is configured to generate a lead allocation model in real-time, using machine learning based on at least one of lead historic data and the classification of the one or more sales agents. The lead allocation module (60) is also configured to allocate a predefined count of the one or more sales agents for dealing with the one or more leads using the lead allocation model, based on the prospect quality score corresponding to the corresponding one or more leads and the agent score corresponding to the corresponding one or more sales agents.
[0052] The lead reviving module (70) is configured to generate one or more propensity models in real-time, based on analysis of at least one of one or more structured parameters, one or more unstructured parameters, and one or more features using artificial intelligence, when a specific count of the one or more leads fail to reach a final stage of one or more stages of sales funnel. The lead reviving module (70) is also configured to identify one or more potential leads having a potential to get revived from a predetermined list of one or more failed leads, to a next stage in the one or more stages of the sales funnel, based on the one or more propensity models, using sentiment analysis and data pre-processing, thereby facilitating the lead behavior analysis for the sales management.
[0053] The data collection module (130) is configured to extract and record the plurality of lead details corresponding to the one or more leads of the preferred seller, upon generation of the one or more leads via a plurality of sources. The data collection module (130) is also configured to extract the agent historic data corresponding to the one or more sales agents responsible for working on converting the one or more leads to the one or more clients for the preferred seller.
[0054] The suggestion module (180) is configured to generate a first suggestion for the one or more sales agents to contact the one or more leads for a first preferred count, based on the preferred lead category under which the corresponding one or more leads are classified. The suggestion module (180) is also configured to generate a second suggestion for the one or more sales agents to contact the one or more potential leads for a second preferred count, based on the corresponding one or more stages of the sales funnel during which the one or more potential leads are identified.
[0055] The agent feedback module (200) is configured to generate a feedback for the one or more sales agents in real-time, based on analysis of a conversion rate of the one or more leads to the one or more clients allocated to the corresponding one or more sales agents using artificial intelligence.
[0056] The failed lead categorization module (205) is configured to categorize the one or more failed leads under one or more stage-based lead categories, based on a generation of the one or more failed leads at the corresponding one or more stages of the sales funnel.
[0057] The bus (240) as used herein refers to be internal memory channels or computer network that is used to connect computer components and transfer data between them. The bus (240) includes a serial bus or a parallel bus, wherein the serial bus transmits data in a bit-serial format and the parallel bus transmits data across multiple wires. The bus (240) as used herein, may include but not limited to, a system bus, an internal bus, an external bus, an expansion bus, a frontside bus, a backside bus, and the like.
[0058] FIG. 4 (a) is a flow chart representing steps involved in a method (250) for artificial intelligence driven productivity enhancementfor sales management in accordance with an embodiment of the present disclosure. FIG. 4 (b) is a flow chart representing continued steps involved in the method (250) of FIG. 4 (a) in accordance with an embodiment of the present disclosure. The method (250) includes identifying one or more success characteristics that assisted one or more clients to complete a preferred purchase from a preferred seller, by analyzing one or more client behavioral characteristics corresponding to the corresponding one or more clients using artificial intelligence in step 260. In one embodiment, identifying the one or more success characteristics may include identifying the one or more success characteristics via a lead classification module (40).
[0059] The method (250) also includes generating a prospect quality scoring model by superimposing the corresponding one or more success characteristics onto a plurality of lead details corresponding to one or more leads of the preferred seller, in real-time using machine learning in step 270. In one embodiment, generating the prospect quality scoring model may include generating the prospect quality scoring model via the lead classification module (40).
[0060] In one exemplary embodiment, the method (250) may include extracting and recording the plurality of lead details corresponding to the one or more leads of the preferred seller, upon generation of the one or more leads via a plurality of sources. In such embodiment, extracting and recording the plurality of lead details may include extracting and recording the plurality of lead details via a data collection module (130).
[0061] Further, the method (250) includes generating a prospect quality score corresponding to a prediction of a probability of successfully converting the one or more leads to one or more future clients, using the prospect quality scoring model in step 280. In one embodiment, generating the prospect quality score may include generating the prospect quality score via the lead classification module (40).
[0062] Furthermore, the method (250) also includes classifying the one or more leads under a preferred lead category based on the prospect quality score associated with the corresponding one or more leads in step 290. In one embodiment, classifying the one or more leads under the preferred lead category may include classifying the one or more leads under the preferred lead category via the lead classification module (40).
[0063] The method (250) further includes analyzing one or more agent behavioral characteristics corresponding to one or more sales agents associated with the preferred seller using artificial intelligence, based on agent historic data corresponding to the corresponding one or more sales agents, upon classifying the one or more leads in step 300. In one embodiment, analyzing the one or more agent behavioral characteristics may include analyzing the one or more agent behavioral characteristics via an agent classification module (50).
[0064] In one exemplary embodiment, the method (250) may include extracting the agent historic data corresponding to the one or more sales agents responsible for working on converting the one or more leads to the one or more clients for the preferred seller. In such embodiment, extracting the agent historic data may include extracting the agent historic data via the data collection module (130).
[0065] The method (250) also includes generating an agent score corresponding to a performance and a profile of the one or more sales agents, using an artificial intelligence-based model, based on the analysis of the one or more agent behavioral characteristics in step 310. In one embodiment, generating the agent score may include generating the agent score via the agent classification module (50).
[0066] Subsequently, the method (250) also includes classifying the one or more sales agents under a preferred agent category based on the agent score associated with the corresponding one or more sales agents in step 320. In one embodiment, classifying the one or more sales agents under the preferred agent category may include classifying the one or more sales agents under the preferred agent category via the agent classification module (50).
[0067] In addition, the method (250) also includes generating a lead allocation model in real-time, using machine learning based on at least one of lead historic data and the classification of the one or more sales agents in step 330. In one embodiment, generating the lead allocation model may include generating the lead allocation model via a lead allocation module (60).
[0068] The method (250) further includes allocating a predefined count of the one or more sales agents for dealing with the one or more leads using the lead allocation model, based on the prospect quality score corresponding to the corresponding one or more leads and the agent score corresponding to the corresponding one or more sales agents in step 340. In one embodiment, allocating the predefined count of the one or more sales agents for dealing with the one or more leads may include allocating the predefined count of the one or more sales agents for dealing with the one or more leads via the lead allocation module (60).
[0069] The method (250) also includes generating one or more propensity models in real-time, based on analysis of at least one of one or more structured parameters, one or more unstructured parameters, and one or more features using artificial intelligence, when a specific count of the one or more leads fail to reach a final stage of one or more stages of sales funnel in step 350. In one embodiment, generating the one or more propensity models may include generating the one or more propensity models via a lead reviving module (70).
[0070] Further, the method (250) includes identifying one or more potential leads having a potential to get revived from a predetermined list of one or more failed leads, to a next stage in the one or more stages of the sales funnel, based on the one or more propensity models, using sentiment analysis and data pre-processing, thereby facilitating the lead behavior analysis for the sales management in step 360. In one embodiment, identifying the one or more potential leads may include identifying the one or more potential leads via the lead reviving module (70).
[0071] In one exemplary embodiment, the method (250) may also include categorizing the one or more failed leads under one or more stage-based lead categories, based on a generation of the one or more failed leads at the corresponding one or more stages of the sales funnel. In such embodiment, categorizing the one or more failed leads under the one or more stage-based lead categories may include categorizing the one or more failed leads under the one or more stage-based lead categories via a failed lead categorization module (205).
[0072] In one embodiment, the method (250) may also include generating a first suggestion for the one or more sales agents to contact the one or more leads for a first preferred count, based on the preferred lead category under which the corresponding one or more leads are classified. In such embodiment, generating the first suggestion for the one or more sales agents may include generating the first suggestion for the one or more sales agents via a suggestion module (180).
[0073] In one exemplary embodiment, the method (250) may further include generating a second suggestion for the one or more sales agents to contact the one or more potential leads for a second preferred count, based on the corresponding one or more stages of the sales funnel during which the one or more potential leads are identified. In such embodiment, generating the second suggestion for the one or more sales agents may include generating the second suggestion for the one or more sales agents via the suggestion module (180).
[0074] In a specific exemplary embodiment, the method (250) may include generating a feedback for the one or more sales agents in real-time, based on analysis of a conversion rate of the one or more leads to the one or more clients allocated to the corresponding one or more sales agents using artificial intelligence. In such embodiment, generating the feedback for the one or more sales agents may include generating the feedback for the one or more sales agents via an agent feedback module (200).
[0075] Further, from a technical effect point of view, the implementation time required to perform the method steps included in the present disclosure by the one or more processors of the system is very minimal, thereby the system maintains very minimal operational latency and requires very minimal processing requirements.
[0076] Various embodiments of the present disclosure enable maximizing sales efficiency in real estate and other businesses by using AI and ML models that can recognize high-intent customers, anticipate potential customers using smart rechurning, and boost sales with lead to an agent through intelligent allocation by AI. This leads to lower lead cost generation and lower cost pre-booking, thereby helping the businesses to maximize revenues.
[0077] Moreover, the system identifies the high-intent customers even before reaching out to the customers, thereby making the system more efficient. Further, the usage of AI has proved to be useful in improving the performance of the one or more sales agents by providing the one or more sales agents with regular feedbacks or tips to improve.
[0078] It is to be noted that although the system and method disclosed herein is best performed in real estate industries, it must not be limited to the said and may be applicable to various other suitable industries.
[0079] While specific language has been used to describe the disclosure, any limitations arising on account of the same are not intended. As would be apparent to a person skilled in the art, various working modifications may be made to the method in order to implement the inventive concept as taught herein.
[0080] The figures and the foregoing description give examples of embodiments. Those skilled in the art will appreciate that one or more of the described elements may well be combined into a single functional element. Alternatively, certain elements may be split into multiple functional elements. Elements from one embodiment may be added to another embodiment. For example, order of processes described herein may be changed and are not limited to the manner described herein. Moreover, the actions of any flow diagram need not be implemented in the order shown; nor do all of the acts need to be necessarily performed. Also, those acts that are not dependent on other acts may be performed in parallel with the other acts. The scope of embodiments is by no means limited by these specific examples. , C , Claims:1. A system (10) for facilitating Artificial Intelligence driven productivity enhancement for sales management, comprising:
a processing subsystem (20) hosted on a server (30), and configured to execute on a network to control bidirectional communications among a plurality of modules comprising:
a lead classification module (40) configured to:
identify one or more success characteristics that assisted one or more clients to complete a preferred purchase from a preferred seller, by analyzing one or more client behavioral characteristics corresponding to the corresponding one or more clients using artificial intelligence;
generate a prospect quality scoring model by superimposing the corresponding one or more success characteristics onto a plurality of lead details corresponding to one or more leads of the preferred seller, in real-time using machine learning;
generate a prospect quality score corresponding to a prediction of a probability of successfully converting the one or more leads to one or more future clients, using the prospect quality scoring model; and
classify the one or more leads under a preferred lead category based on the prospect quality score associated with the corresponding one or more leads;
an agent classification module (50) operatively coupled to the lead classification module (40), wherein the agent classification module (50) is configured to:
analyze one or more agent behavioral characteristics corresponding to one or more sales agents associated with the preferred seller using artificial intelligence, based on agent historic data corresponding to the corresponding one or more sales agents, upon classifying the one or more leads;
generate an agent score corresponding to a performance and a profile of the one or more sales agents, using an artificial intelligence-based model, based on the analysis of the one or more agent behavioral characteristics; and
classify the one or more sales agents under a preferred agent category based on the agent score associated with the corresponding one or more sales agents;
a lead allocation module (60) operatively coupled to the agent classification module (50), wherein the lead allocation module is configured to:
generate a lead allocation model in real-time, using machine learning based on at least one of lead historic data and the classification of the one or more sales agents; and
allocate a predefined count of the one or more sales agents for dealing with the one or more leads using the lead allocation model, based on the prospect quality score corresponding to the corresponding one or more leads and the agent score corresponding to the corresponding one or more sales agents; and
a lead reviving module (70) operatively coupled to the lead allocation module (60), wherein the lead reviving module (70) is configured to:
generate one or more propensity models in real-time, based on analysis of at least one of one or more structured parameters, one or more unstructured parameters, and one or more features using artificial intelligence, when a specific count of the one or more leads fail to reach a final stage of one or more stages of sales funnel; and
identify one or more potential leads having a potential to get revived from a predetermined list of one or more failed leads, to a next stage in the one or more stages of the sales funnel, based on the one or more propensity models, using sentiment analysis and data pre-processing, thereby facilitating the lead behavior analysis for the sales management.
2. The system (10) as claimed in claim 1, wherein the processing subsystem (20) comprises a data collection module (130) operatively coupled to the lead classification module (40), wherein the data collection module (130) is configured to extract and record the plurality of lead details corresponding to the one or more leads of the preferred seller, upon generation of the one or more leads via a plurality of sources.
3. The system (10) as claimed in claim 2, wherein the data collection module (130) is configured to extract the agent historic data corresponding to the one or more sales agents responsible for working on converting the one or more leads to the one or more clients for the preferred seller.
4. The system (10) as claimed in claim 1, wherein the processing subsystem (20) comprises a suggestion module (180) operatively coupled to the lead reviving module (70), wherein the suggestion module (180) is configured to generate a first suggestion for the one or more sales agents to contact the one or more leads for a first preferred count, based on the preferred lead category under which the corresponding one or more leads are classified.
5. The system (10) as claimed in claim 4, wherein the suggestion module (180) is configured to generate a second suggestion for the one or more sales agents to contact the one or more potential leads for a second preferred count, based on the corresponding one or more stages of the sales funnel during which the one or more potential leads are identified.
6. The system (10) as claimed in claim 1, wherein the processing subsystem (20) comprises an agent feedback module (200) operatively coupled to the lead reviving module (70), wherein the agent feedback module (200) is configured to generate a feedback for the one or more sales agents in real-time, based on analysis of a conversion rate of the one or more leads to the one or more clients allocated to the corresponding one or more sales agents using artificial intelligence.
7. The system (10) as claimed in claim 6, wherein the feedback comprises a rewarda plan for improving the performance and the profile of the one or more sales agents.
8. The system (10) as claimed in claim 1, wherein the processing subsystem (20) comprises a failed lead categorization module (205) operatively coupled to the lead reviving module (70), wherein the failed lead categorization module (205) is configured to categorize the one or more failed leads under one or more stage-based lead categories, based on a generation of the one or more failed leads at the corresponding one or more stages of the sales funnel.
9. A method (250) for facilitating lead behavior analysis for sales management, comprising:
identifying, via a lead classification module (40), one or more success characteristics that assisted one or more clients to complete a preferred purchase from a preferred seller, by analyzing one or more client behavioral characteristics corresponding to the corresponding one or more clients using artificial intelligence; (260)
generating, via the lead classification module (40), a prospect quality scoring model by superimposing the corresponding one or more success characteristics onto a plurality of lead details corresponding to one or more leads of the preferred seller, in real-time using machine learning; (270)
generating, via the lead classification module (40), a prospect quality score corresponding to a prediction of a probability of successfully converting the one or more leads to one or more future clients, using the prospect quality scoring model; (280)
classifying, via the lead classification module (40), the one or more leads under a preferred lead category based on the prospect quality score associated with the corresponding one or more leads; (290)
analyzing, via an agent classification module (50), one or more agent behavioral characteristics corresponding to one or more sales agents associated with the preferred seller using artificial intelligence, based on agent historic data corresponding to the corresponding one or more sales agents, upon classifying the one or more leads; (300)
generating, via the agent classification module (50), an agent score corresponding to a performance and a profile of the one or more sales agents, using an artificial intelligence-based model, based on the analysis of the one or more agent behavioral characteristics; (310)
classifying, via the agent classification module (50), the one or more sales agents under a preferred agent category based on the agent score associated with the corresponding one or more sales agents; (320)
generating, via a lead allocation module (60), a lead allocation model in real-time, using machine learning based on at least one of lead historic data and the classification of the one or more sales agents; (330)
allocating, via the lead allocation module (60), a predefined count of the one or more sales agents for dealing with the one or more leads using the lead allocation model, based on the prospect quality score corresponding to the corresponding one or more leads and the agent score corresponding to the corresponding one or more sales agents; (340)
generating, via a lead reviving module (70), one or more propensity models in real-time, based on analysis of at least one of one or more structured parameters, one or more unstructured parameters, and one or more features using artificial intelligence, when a specific count of the one or more leads fail to reach a final stage of one or more stages of sales funnel; and (350)
identifying, via the lead reviving module (70), one or more potential leads having a potential to get revived from a predetermined list of one or more failed leads, to a next stage in the one or more stages of the sales funnel, based on the one or more propensity models, using sentiment analysis and data pre-processing, thereby facilitating the lead behavior analysis for the sales management (360).
10. The method (250) as claimed in claim 9, comprises categorizing, via a failed lead categorization module (205), the one or more failed leads under one or more stage-based lead categories, based on a generation of the one or more failed leads at the corresponding one or more stages of the sales funnel.

Dated this 02nd day of September 2022

Signature

Jinsu Abraham
Patent Agent (IN/PA-3267)
Agent for the Applicant