Dynamic formation of internal sales teams or expert support teams

Abstract

A customer relationship management ("CRM") method implemented in a computer system includes a lead knowledge engine in communication with a plurality of remote agent stations. The lead knowledge engine includes a semantic graph database having a knowledge graph and a dynamic profile analysis module configured to identify a remote agent to query via a remote agent panel to receive inside sales information indicative of product / service interest and remote agent experience and expertise. The lead knowledge engine is further configured to query a sales analysis engine and receive outside sales information to identify product / service interest and generate a target lead profile. The lead knowledge engine automatically ranks the remote agents and creates an inside sales team or an expert support team to support a particular product or service, resolve a lead, and update the remote agent panel.

Description

BACKGROUND

[0001] Many products and services, including cloud-based or web-based products and services, computing systems and other software products, industrial goods and commodities, etc., are increasingly being sold over the phone by remote agents. Such sales are often directed to complex systems and very sophisticated customers. These remote agents are often able to modularize and customize products, thereby bringing increased efficiency and efficacy to their customers.

[0002] For example, cloud-based or web service-based products are highly customizable, and various products can be combined to provide the best solution to a customer, and can be further customized based on region or industry. Such cloud-based web services often include computing applications, database applications, migration applications, web and content delivery applications, business management tools, business analytics, artificial intelligence, mobile services, and more.

[0003] Customer relationship management (“CRM”) is a method of managing a company’s interactions with current and potential customers. CRM enables data analysis of a customer’s history with a company to improve business relationships with customers, specifically focusing on customer retention and sales growth. CRM systems compile data from a range of communication channels including phone, email, online chat, text messaging, marketing materials, websites, and social media. Through the CRM method and systems for facilitating the CRM method, businesses learn more about their target audience and how best to address their needs.

[0004] Enterprise CRM systems can be vast. Such systems can include data warehouse technology for aggregating transaction information, merging that information with information about CRM products and services, and providing key performance indicators. CRM systems help manage fluctuating growth and demand, and enable predictive models that integrate sales history with sales forecasts. CRM systems track and measure marketing activities across multiple networks, analyze customers through customer clicks and sales tracking. Some CRM software is available through cloud systems, software as a service (SaaS), delivered via the web and accessed via a browser, rather than installed on a local computer. Businesses using cloud-based CRM SaaS often subscribe to such CRM systems, paying a periodic subscription fee, rather than purchasing the system outright.

[0005] Despite the size of CRM systems, many CRM systems today lack the infrastructure to fully utilize the information to which they have access. As such, it is desirable to employ enterprise CRM systems to automatically make internal sales teams or expert support teams based on the data contained therein, thereby enhancing sales and support. BRIEF DESCRIPTION OF DRAWINGS

[0006] Many aspects of the present disclosure can be better understood with reference to the following drawings. The components in the drawings are not necessarily to scale, emphasis instead being placed upon clearly illustrating the principles of the present disclosure. Furthermore, in the drawings, like reference numerals designate corresponding parts throughout the several views.

[0007] Figure 1 is a functional block diagram of an example CRM system implementing automatic formation of an internal sales team or expert support team based on CRM and marketing data according to one or more embodiments of the present invention.

[0008] Figure 2 illustrates a call flow diagram illustrating additional aspects of automatic formation of an internal sales team or expert support team based on CRM and marketing data according to example embodiments of the present invention.

[0009] Figure 3 is a functional block diagram of an example CRM system for automatic formation of an internal sales team or expert support team based on CRM and marketing data according to embodiments of the present invention.

[0010] Figure 4 is a flow diagram illustrating an example CRM method for automatic formation of an internal sales team or expert support team based on CRM and marketing data according to embodiments of the present invention. DETAILED DESCRIPTION

[0011] The methods, systems, products, and other features described herein for automatic formation of an internal sales team or expert support team based on CRM and marketing data are described with reference to the drawings, beginning with FIG. 1. Figure 1 The methods, systems, products, and other features described herein for automatic formation of an internal sales team or expert support team based on CRM and marketing data are described with reference to the drawings, beginning with FIG. 1. Figure 1 illustrates a network diagram of a CRM system 99 for automatic team formation according to example embodiments of the present invention.

[0012] Cloud-based applications, web service applications, computing systems, and other software products are increasingly being sold by remote agents over the telephone. These remote agents are often able to modularize and customize product offerings, bringing increased efficiency and efficacy to their customers. For example, cloud-based or web service-based products are highly customizable, and various products can be combined to provide the best solution to a customer, and can be further customized based on region or industry. Such cloud-based web services often include computing applications, database applications, migration applications, web and content delivery applications, business management tools, business analytics, artificial intelligence, mobile services, and more. Examples of providers of such software, cloud computing platforms, and web services include Amazon, Microsoft, Oracle, and the like.

[0013] The term remote agent 120 used in this specification is a person who handles incoming or outgoing customer calls for a business, such as, for example, a software, hardware or cloud-based web service sales. Such remote agents are typically subject matter experts on the products they sell and support, and typically work in a call center that handles sales, inquiries, customer complaint support issues and other related sales and support operations. The term remote agent used in this specification is meant to include, without limitation. Other example names for remote agents include call center agent, customer service representative, telemarketing or service representative, attendant, assistant, operator, business representative or team member.

[0014] The remote agents 120 are agents of the contact center 105 responsible for selling or supporting commercial products and services. The CRM contact center 105 is an organization of personnel and computer resources that provide CRM according to embodiments of the present application. In the example shown in FIG. 1, the contact center 105 is a call center. Figure 1 In the example shown, the area delineated by the dashed line indicates the extent of the contact center 105. The extent is logical rather than physical. For example, all of the resources and personnel that make up the contact center can have the same physical location, or the contact center can be highly virtualized with separate physical locations for remote agents, for client devices and for servers. Some or all of the remote agents can work together in a call center that provides the agents with desks, workstations, telephones, etc. All or some of the remote agents can work from home or on the go.

[0015] Time with any customer is valuable, and each organization should have the most knowledgeable and experienced remote agents available for a particular activity or market segment to maximize the efficiency and effectiveness of the organization. Therefore, Figure 1 A simplified block diagram of an example system for automatic formation of an inside sales team or expert support team based on CRM and marketing data according to embodiments of the present application is shown.

[0016] The term lead used in this specification represents a current or potential customer or client as structured data, typically including a lead ID, lead name, company, role of the lead, address of the lead or company, phone number of the lead and other related information that will occur to those skilled in the art. Such a lead can be implemented as a record, message, object or other data structure useful to an automated computer machine to automatically generate leads according to embodiments of the present application.

[0017] The CRM system 99 according to embodiments of the present application includes a lead knowledge engine 104, a sales analysis engine 108 and one or more remote agent stations 112 interconnected via a network 101. The lead knowledge engine 104, the sales analysis engine 108 and the remote agent stations 112 can be implemented as instances of an automated computer machine.

[0018] As used in this specification, "automatic computing machine" refers to a module, segment, or portion of local or remote hardware, software, firmware, code, or other automatic computing logic, as well as any combination thereof, local or remote. Automatic computing machines are typically implemented as executable instructions, physical units, or other computing logic for implementing specified logical functions.

[0019] like Figure 1 As shown, the lead knowledge engine 104 can be implemented using a computer server located within call center 105. However, as those skilled in the art will understand, other configurations can be employed. Similarly, the sales analysis engine 108 is shown as being implemented using a remote server or cloud service, but other suitable configurations can be used. Remote agent stations 112 are automated computing machines, each of which is configured as a CRM with CRM-related I / O via a display, graphical user interface, or voice-enabled interface that accepts and recognizes voice from a user and, optionally, provides voice prompts and responses to the user. Remote agent stations 112 may include desktop computers, tablets, smartphones, and laptops, any or all of which can act as workstations for remote agent 120 to perform CRM within, for example, contact center 105.

[0020] According to an embodiment of the present invention, Figure 1 The lead knowledge engine 104 is implemented to automatically generate internal sales or expert support teams based on CRM and marketing data. The lead knowledge engine 104 can query various available resources and provide relevant leads and marketing data related to products or services for which sales or support is targeting leads or sets of leads with similar characteristics. Available resources may include resources both within and outside the specific company operating the lead knowledge engine, as well as resources in various markets used to acquire leads. This lead knowledge engine 104 advantageously provides details about relevant products and services that may be of interest to leads or sets of similar leads.

[0021] exist Figure 1 In the example system, the lead knowledge engine 104 includes a dynamic profile module 164. The dynamic configuration module 164 is configured to query multiple internal remote agent panel applications 110 and, in response to the query, receive sales information identifying product sales made by remote agents 120 associated with the remote agent panel application 110. Figure 1Only one remote agent is described in the example. This is for ease of illustration and not for limitation. In typical embodiments, the dynamic profile module 164 will query many remote agent panel applications 110 and receive sales information from many remote agents 120.

[0022] In a thin client architecture, the panel 110 can be displayed in a web browser running on the remote agent station 112 and can be generated using hypertext markup language (HTML) forms, cascading style sheets (CSS), and Java, PHP, Perl, or similar scripting languages as known to those skilled in the art. In a thin client architecture, the panel update module 168 is preferably a mass network server hosting one or more web server software applications for selectively and securely allowing access by one or more remote agent stations 112 over the Internet or other network 101 for the transmission of hypertext markup language (HTML) files and the like. Browser plug-ins or application programming interfaces (APIs) can also be used as appropriate. In a fat client architecture arrangement, the panel update module 168 can generate the panel display 110 directly on the remote agent station 112. Regardless, the panel display 110 desirably employs standard window-type display and control mechanisms, including windows, client windows, frames, flex frames, icons, buttons, check boxes, radio buttons, scroll bars, drop-down menus, pull-down menus, drill-down mechanisms, tabs, bar graphs, panes, panels, forms, sliders, selection boxes, dialog boxes, text boxes, list boxes, menu bars, bar graphs, widgets, wizards, and the like. The selection and layout of user interface components and their placement can vary widely within the scope of the present disclosure and can optionally be customized by each user. Desirably, the panel update module 168 employs responsive site design techniques so as to automatically adjust the layout and design to be readable and usable at any screen width. Further details are omitted as user interface programming and design are well known in the art.

[0023] The sales information collected from the remote agent 120 for a product can be actual sales made by the remote agent recorded during the sales process, interest shown in a product by a customer interacting with the remote agent, relevant notes recorded by the remote agent 120 regarding products sold by the remote agent, or any other relevant sales information as would occur to those skilled in the art. Collecting such sales information serves a dual purpose: to identify products or services that a given lead or set of leads can be interested in, and to identify particular remote agents that can have particular subject matter expertise or experience regarding a given product or service group.

[0024] The remote agent panel application 110 is an application used by the remote agents 120 to organize and support telephone sales. In Figure 1 In the example of a Voice over Internet Protocol ("VOIP") telephone communication, the panel application 110 provides a medium for the customer 122. The panel application 110 allows the remote agent to record notes 180 describing the sales call and providing lead details 182, which are collected by the lead intelligence engine 104.

[0025] Figure 1 The dynamic profile module 164 is also configured to query one or more external sales analytics engines 108 and, in response to the query, receive sales information identifying external sales of products of the plurality of companies. The sales analytics engines 108 are engines, typically implemented as servers, that provide external sales information about various companies. Such external sales analytics engines can be provided by third party vendors that collect sales information from various companies and publish the information to their customers. Querying the one or more external sales analytics engines can be performed by calling an application programming interface ("API") 132 exposed by the external sales analytics engine and receiving information identifying external sales of products of the plurality of companies. Such information identifying external sales can include the products being sold, the quantity of the products being sold, the companies purchasing the products, the industries of the companies purchasing the products, the size of the companies, the world regions in which the identified companies are located, and the like, as can be appreciated by those skilled in the art.

[0026] Figure 1 The dynamic profile module 164 is also configured to create product-specific target lead profiles based on the size of the identified companies, the industry of the identified companies, and the world region of the identified companies associated with a particular product or service. The target lead profiles identify companies in a particular industry and in a particular region of the world and the size and operations of those companies. These companies represent companies that purchase the specified product or service. Companies that meet the criteria of the target lead profiles are considered more likely to be candidates for customers of the specified product or service. The target lead profiles are also often implemented as structured data that often includes a profile ID, an industry, a company size, a region, and a product, a list of useful products, or a product type.

[0027] Figure 1The lead knowledge engine 104 has a semantic graph database 152 with a knowledge graph 154 stored therein having nodes populated at least with sales information identifying product sales by remote agents associated with the remote agent panel application and sales information identifying external sales of products of a plurality of companies. More preferably, the knowledge graph 154 can be comprised of an enterprise level graph database that includes all or most information describing, related to, or useful to the entire enterprise: financial records, business entities and structure, employee data, merger data, transactions, contracts, sales history, product descriptions, etc. Although Figure 1 The semantic graph database 152 is shown as being within the lead knowledge engine 104, but it equally can be located within another discrete resource, such as a dedicated networked database server.

[0028] A graph database is a database that uses graph structures for semantic queries with nodes, edges, and properties to represent and store data. The key concept of this database system is the graph (or edge or relationship) that is directly related to the data items in the data store. These relationships allow data in the store to be linked directly together and in many cases retrieved in one operation.

[0029] Graph databases contrast with traditional relational databases in which links between data are stored in the data and searches of the data in the store are queried and related data is collected using join concepts. By design, graph databases allow simple and fast retrieval of complex hierarchical structures that are difficult to model in relational systems.

[0030] The underlying storage mechanism of a graph database can vary. Some storage mechanisms rely on a relational engine and store graph data in tables. Other storage mechanisms use key-value stores or document-oriented databases to store, making them inherently NoSQL structures.

[0031] Retrieving data from a graph database often requires a query language other than SQL, which is designed for relational databases and does not accurately handle traversals of graphs. There are many systems, most closely tied to a product, and there are some multi-vendor query languages such as Gremlin, SPARQL, and Cypher. In addition to having a query language interface, some graph databases are accessed through an application programming interface (API).

[0032] Graph databases are based on graph theory and employ nodes, edges, and properties. Nodes represent entities such as people, businesses, accounts, or any other item to be tracked. They are roughly equivalent to records, relations, or rows in a relational database, or documents in a document database. Edges, also called graphs or relations, are the lines that connect nodes to other nodes; they represent the relationships between nodes. When the connections and interconnections of nodes, properties, and edges are examined, meaningful patterns emerge. Edges are a key concept in graph databases, representing abstract concepts that are not directly implemented in other systems. Properties are close relationship information related to a node. For example, if N3 is one of the nodes, it can be associated to properties such as web service support, cloud computing, or words beginning with the letter N, depending on which aspects of N3 have a close relationship to the given database.

[0033] Figure 1 The graph database of the Figure 1 Example enterprise knowledge graphs of the Figure 1 The enterprise knowledge graph of the

[0034] RDF makes the resource identifier relationships between data items the central property of its overall data model. Resource identifiers such as URIs are created with data and linked together using relationships that are also named with resource identifiers such as URIs.

[0035] Figure 1 The knowledge graph of the

[0036] Figure 1 The RDF-based knowledge graph of the Figure 2 In the RDF-based knowledge graph, each of the subject 158, predicate 160, and object 162 is represented as a URI. In a triple, the subject and object are vertices, while the predicate is an edge connecting the subject and object. The roles of the subject and object imply the direction of the edge, i.e., from the subject to the object. An RDF graph consists of a set of triples. A database containing an RDF graph is called a triple store.

[0037] The description of the graph database and the semantic graph database is for explanation and not for limitation. Indeed, alternative embodiments can include a SQL database, a relational database, a NoSQL or any other feasible database structure that would come to mind to the person skilled in the art.

[0038] In Figure 2 The dynamic profile module 164 identifies product interests of a plurality of companies of a particular size in a particular industry in a particular region of the world by traversing the knowledge graph 154 and identifying product interests from a plurality of nodes of the knowledge graph and relationships between the plurality of nodes of the knowledge graph. These nodes and their relationships are implemented as triples 156 of URIs 158, 160 and 162 in the example of Figure 2

[0039] To identify product interests, Figure 2 The dynamic profile module of employs a semantic reasoner. A semantic reasoner, often called a reasoning engine, a rules engine or simply a reasoner, is an automated computer machine for inferring logical consequences from a set of asserted facts or axioms. The concept of a semantic reasoner works by providing a richer set of mechanisms to generalize from an inference engine. The inference rules are usually specified with the aid of an ontology language (and often a description logic language). Many reasoners use first-order predicate logic to perform the reasoning; the inference is usually done by forward chaining and backward chaining.

[0040] There are also examples of probabilistic reasoners, including non-axiomatic reasoning systems and probabilistic logic networks. Some such reasoners can be derived from machine learning. Machine learning is closely related to (and often overlapping with) computational statistics, which also focuses on making predictions by using computers. Machine learning has strong ties to mathematical optimization, which passes methods, theory and application areas to the field. Machine learning is sometimes conflated or equated with data mining, where data mining is more focused on exploratory data mining and is sometimes referred to as unsupervised learning.

[0041] In the field of data analysis, machine learning is a method for designing sophisticated models and algorithms that are suitable for prediction; in business usage, this is referred to as predictive analytics. These analytical models allow researchers, data scientists, engineers and analysts to "produce reliable, repeatable decisions and outcomes" and discover "hidden insights" by learning from historical relationships and trends in the data.

[0042] To further illustrate, Figure 2 A call flow diagram illustrating additional aspects of the automatic formation of an internal sales team or an expert support team based on CRM and marketing data according to an example embodiment of the present invention is shown. In Figure 2 ​In the example, within a specific industry and a specific region of the world, the Lead Knowledge Engine 104 identifies specific products or services that may be associated with a company of a certain size. Regarding the identified products or services, the Lead Knowledge Engine 104 sends an external sales information request 210 to the Sales Analytics Engine 108. Figure 2 The sales analytics engine 108 receives request 210 and, in response 212, sends the external sales information collected by the sales analytics engine 108 from company 272 to the lead knowledge engine 104. Figure 2 In the example, the lead knowledge engine repeatedly sends requests 210 and receives responses 212 until the lead knowledge engine 104 has sufficient external sales information to automatically form an internal sales team or expert support team based on CRM and marketing data according to embodiments of the present invention, as will be apparent to those skilled in the art.

[0043] exist Figure 2 In the example, regarding the identified product or service, the Lead Knowledge Engine 104 also sends an internal sales information request 202 to one or more remote agent panel applications 110. Figure 3 The Leads Knowledge Engine responded to request 202 and received internal sales information from the remote agent panel application 110 in response 204. Figure 3 Internal sales information responses typically include information describing sales or potential sales made by a remote agent in the form of products, sales, companies, customers, or regions of the world where sales are being made, additional notes made by the remote agent, or any other internal sales information that a person skilled in the art would think of. Figure 3 In the example, the lead knowledge engine repeatedly sends requests 202 and receives responses 204 until the lead knowledge engine 104 has sufficient internal sales information to automatically form an internal sales team or expert support team based on CRM and marketing data according to embodiments of the present invention, as will be apparent to those skilled in the art.

[0044] In parallel with the lead knowledge engine 104 sending requests 202 and receiving responses 204 for internal sales information, the sales analysis engine 108 sends market information requests 206 to companies 272 and receives market information responses from those companies, the market information responses containing information about external sales made by companies 272 for the identified products or services. Figure 3 External sales information responses typically include information describing sales or potential sales made by an external company, usually including the product, sales, company ID, customer, the world region where the sales are made, or any other external sales information that a person skilled in the art would think of. Figure 3In the example, the sales analytics engine 272 repeatedly sends requests and receives responses until the sales analytics has sufficient external sales information to provide to the lead knowledge engine 104 for use in automatically forming an internal sales team or expert support team based on CRM and marketing data according to embodiments of the present invention, as will be apparent to those skilled in the art.

[0045] To further illustrate, Figure 3 This is a functional block diagram of an exemplary CRM system 99 for automatically generated internal sales teams or expert support teams based on CRM and marketing data, according to an embodiment of the present invention. Figure 3 The CRM system 99 includes a lead knowledge engine 104, which is coupled for data communication via network 101 with multiple remote resources, including a sales analytics engine 108. This example presents... Figure 3 The remote resource 108 is for illustrative purposes and not for limitation. In practice, the automated formation of an internal sales team or expert support team based on CRM and marketing data according to embodiments of the present invention may include additional remote resources that those skilled in the art would conceive of.

[0046] exist Figure 1 In the example, the remote agent is able to view clue details 182 on panel 110 displayed on the user interface of remote agent station 112. Figure 3 In the example, remote agent station 112 is coupled for data communication with the clue knowledge engine 104 via network 101. In various embodiments of the invention, as will be apparent to those skilled in the art, the computer station used by the remote agent may be implemented as either local or remote relative to the clue knowledge engine 104.

[0047] exist Figure 4 In the example, the clue knowledge engine 104 is described as software implemented on server 290. This description is for explanation and not for limitation. As will be appreciated by those skilled in the art as described above, a dynamic scripting engine can be implemented in any number of permutations of automated computing machines. Figure 4 Example server 290 ideally includes volatile and / or non-volatile memory 270 connected to data bus 278, processor 276, communication adapter 274, and I / O module 282. Clue knowledge engine 104 is shown as stored in memory 270. Memory 270 may include cache, random access memory (“RAM”), disk storage, and most other computer memory, whether expanded or yet to be developed.

[0048] Figure 1The lead knowledge engine 104 of the present application can include a dynamic profile module 164, a semantic graph database 152, a panel update module 168, and a plurality of leads, details of which can be displayed on the panel application 110 of the remote agent 230, stored in the memory 270. As discussed above, the dynamic profile module 164 includes an automated computer machine configured to query a plurality of internal remote agent panel applications 110 and, in response to the query, receive sales information identifying product sales made by the remote agents 120 associated with the remote agent panel applications 110 and query one or more external sales analytics engines 108 and, in response to the query, receive sales information identifying external sales of products of a plurality of companies.

[0049] Internal and external sales information and other information such as remote agent ID, product, lead details, company, world region, surge, sales history, market history, and other information is stored in the semantic graph database 152. As will be appreciated by those skilled in the art, this information can be stored as part of the enterprise knowledge graph 154 using RDF triples. Figure 3 ).

[0050] Figure 2 The dynamic profile module 164 of the present application is further configured to identify product interests of a plurality of companies of a particular size in a particular industry in a particular region of the world from the knowledge graph in the semantic graph database 152 and create a company profile according to the size of the identified companies associated with the interest, the industry of the identified companies, and the region of the world of the identified companies.

[0051] To further explain, Figure 4 is a flowchart illustrating an exemplary method for automatic formation of an internal sales team or expert support team based on CRM and marketing data according to an embodiment of the present application. Figure 4 The method of the present application includes an initial step 502 of querying a plurality of internal remote agent panel applications 110 by the dynamic profile module 164. In step 504, in response to the query 202, internal sales information 204 identifying sales and support of products or services made by the remote agents 120 ( Figure 1 and Figure 3 ) via the remote agent panel applications 110 is provided to the dynamic profile module 164. As discussed with respect to Figure 1 , steps 502 and 504 are desirably repeated by the dynamic profile module 164 for all remote agents 120 and for all products or services of interest.

[0052] As described above, the remote agent panel application 110 is an application used by a remote agent to organize and support telephone sales. Sales information for products conducted by the remote agent 120 may include actual sales made by the remote agent during the sales process, interest in products shown by customers interacting with the remote agent, relevant notes recorded by the remote agent 120 regarding products sold by the remote agent, or any other relevant sales information that a person skilled in the art would consider.

[0053] In addition to providing valuable data for identifying which products and services might be of interest to specific leads, internal sales information 204 may also include data relating to determining which remote agents 120 should ideally be assigned to the internal sales team or expert support team for a specific product or service. This information may include expertise developed from actual sales or support for a specific product or service, relationships developed with specific clients, formal training or certification for a specific product or service, and the availability (i.e., bandwidth) of a specific remote agent.

[0054] In step 506, the dynamic profile module 164 queries sales information from one or more external sales analysis engines 108. In step 508, in response to query 210, the sales analysis engines (one or more) provide the dynamic profile module 164 with external sales information 212 identifying external sales of products and services from multiple companies. In step 510, the dynamic profile module 164 identifies specific product or service interests from multiple companies of a specific size in a specific industry within a specific region of the world from both the external sales information 212 and the internal sales information 204, and creates product-specific target lead profiles 428 from them. Figure 1 In the example, the product-specific target lead profile 428 is implemented as an instance of a data structure that includes profile ID 430, industry type 432, company size 434, world region 436, and one or more products or services 438.

[0055] according to Figure 4 Identifying the product or service interests of multiple companies of a specific size in a specific industry within a specific region of the world can be performed by traversing a semantic graph database.152 Figure 1 and Figure 1 Knowledge Graph 154 in ) Figure 1 Furthermore, it identifies specific product or service interests from multiple nodes in the knowledge graph and the relationships between those nodes. In some embodiments, the semantic reasoner can be used to identify product interests, as will be apparent to those skilled in the art.

[0056] In step 512, the dynamic profile module 164 uses internal sales information 204 to create a profile with the call center 305 ( Figure 1) supported by the particular product or service 111. The remote agent ranking 468 can be derived based on specialized skills developed from actual sales or support of the particular product and service 111, relationships developed with particular customers, formal training or certification in the particular product or service 111, and availability (i.e., bandwidth) of individual remote agents. More experienced and successful remote agents are more likely to be assigned to particular inside sales or expert support teams, but the dynamic profile module 164 can optionally weight the ranking to promote fairness in remote agent assignment. Further, the dynamic profile module 164 can pair less knowledgeable remote agents with more experienced remote agents in particular teams to promote education and advancement of the overall sales force.

[0057] In Figure 4 In the example, the remote agent ranking 468 is implemented as an instance of a data structure that includes a ranking ID 470, a target lead profile ID 470 corresponding to a particular target lead profile 428, and a remote agent ranking matrix 474 identifying remote agent members for automatic ranking according to a plurality of criteria, including product expertise, current assignment, availability, formal training, etc.

[0058] In one or more embodiments, the lead knowledge engine 104( Figure 1 ) also stores the structured and content target lead profiles 428 and the remote agent ranking 468 as semantic triples in the enterprise knowledge graph 154( Figure 1 ) : parses the structured and content into parsed triples; the lead knowledge engine 104 analyzes the parsed triples to create inferred triples. The parsed and inferred triples are then stored in the enterprise knowledge graph 154( Figures 1 to 4 ). The parsed triples, inferred triples, and enterprise knowledge graph 154( ​ ) are described in greater detail in co-pending U.S. Application Serial No. 16 / 154,718, filed October 9, 2018, entitled “Semantic Call Notes,” and U.S. Application Serial No. 16 / 911,717, filed June 25, 2020, entitled “Semantic Artificial Intelligence Agent,” and U.S. Application Serial No. 16 / 916,615, filed June 30, 2020, entitled “Improved Enterprise Level Sales Management System and Method Including Real-Time Incentive Compensation,” which are incorporated by reference in their entirety.

[0059] At step 514, the products and / or services 428 (some of which can originate from outside sales) are mapped by the dynamic profile module 164 to the products and / or services 111 supported by the call center 305 ​ ). The dynamic profile module 164 then automatically assigns a team of remote agents, such as an inside sales team or an expert support team, responsible for supporting the particular target lead profile 428 based on the aforementioned factors such as experience or expertise, market size, number of remote agents, and availability of particular remote agents. In particular, the dynamic profile module 164 can employ simulation and optimization algorithms to maximize profitability. As noted above, probabilistic reasoners including non-monotonic reasoning systems and probabilistic logic networks, computational statistics focused on making predictions through the use of computers, and machine learning techniques with strong ties to mathematical optimization can be used to design sophisticated models and algorithms suitable for predicting and optimizing for remote agent personnel. Additionally, the dynamic profile module 164 can designate team leaders, backups, and the like. ​ The method of FIG. 4 can be repeated periodically over time, utilizing additional remote agent feedback collected through the panel 110 to optimize team assignments. For example, tracking of missed calls, long hold times with customers, over- or under-utilized remote agents, and the like can be used to improve team assignments.

[0060] The lead knowledge engine 104 ​ also includes a remote agent panel update module 168. The remote agent panel update module 168 is implemented as an automated computer machine configured to resolve the lead 102 associated with the particular target lead profile 428 for one or more remote agents automatically identified with the associated team assignment matrix 474. At step 516, the remote agent panel update module 168 transmits the resolved lead to the associated one or more remote agent panel applications 110. Resolving the lead for the remote agents provides each selected remote agent with a lead related to sales, support, and unique aspects of the products associated with the particular remote agent and the activities they are engaged in. Resolving the lead for the one or more remote agents can be performed automatically by the lead knowledge engine 104 by selecting the lead for the particular team of remote agents based on factors such as those sold by the remote agents, experience of the remote agents, world region in which the remote agents serve, industry in which the remote agents serve, and many other factors that will occur to those skilled in the art. As shown in FIG. 5, the lead details 182 are displayed to the remote agents on the panel application 110 presented on the remote agent's computer station 112. ​

[0061] ​ ​Architectures, functionalities, and operations of possible implementations of systems, methods, and products in accordance with various embodiments of the present application are shown. In this regard, each block in the flowchart or block diagrams can represent a module, segment, or portion of code which comprises one or more executable instructions or logical blocks for implementing the specified logical function(s). It should also be noted that in some alternative implementations, the functions noted in the blocks can occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently or the blocks can sometimes be executed in the reverse order, depending on the functionality involved. It will also be noted that each block of the block diagrams and / or flowchart illustrations, and combinations thereof, can be implemented by a dedicated hardware-based system that performs the specified functions or combinations of special-purpose hardware and computer instructions.

[0062] The abstract of the present disclosure is provided only for the purpose of summarizing the full disclosure of the present technology and presenting the essential features of the present disclosure in a concise form, and the abstract of the present disclosure is only representative of one or more embodiments.

[0063] The above-described embodiments of the present disclosure are merely possible examples of implementations and are set forth for a clear understanding of the principles of the present disclosure. The above-described embodiments of the present disclosure can be changed and modified without departing from the spirit and principles of the present disclosure. All such modifications and changes are intended to be included within the scope of the present disclosure and the appended claims.

Claims

1. A customer relationship management system comprising: a lead knowledge engine implemented as a first instance of software running on a server, the lead knowledge engine including a dynamic profile module and a panel update module also implemented as software running on the server; and a plurality of remote agent stations each configured to execute a remote agent panel application thereon, the remote agent stations operably coupled to the lead knowledge engine via a computer network; wherein the dynamic profile module is configured to: query, over the computer network, the remote agent panel applications executing on the plurality of remote agent stations located remotely relative to the server, and in response, receive, over the computer network, inside sales information including identification of sales of products or services by a plurality of remote agents associated with the remote agent panel applications; query, over an application programming interface (API), one or more outside sales analytics engines, and in response, receive outside sales information including identification of outside sales of products or services by a plurality of companies; create a target lead profile from the outside sales information and the inside sales information, wherein the target lead profile is stored as one or more semantic triples in an enterprise knowledge graph including a plurality of nodes populated with the inside sales information and the outside sales information; generate a remote agent ranking ranking remote agents according to a plurality of criteria from the inside sales information, wherein the remote agent ranking is stored as one or more semantic triples in the enterprise knowledge graph; and identify a remote agent team from the target lead profile and the remote agent ranking, wherein the dynamic profile module is configured to identify the remote agent team by traversing the enterprise knowledge graph.

2. The system of claim 1, wherein, the panel update module is configured to parse a lead and send the parsed lead to one or more of the remote agent panel applications according to the remote agent team.

3. The system of claim 1, wherein, the lead knowledge engine further includes a semantic graph database storing the enterprise knowledge graph.

4. The system of claim 1, wherein, each of the plurality of nodes includes three resource identifiers.

5. The system of claim 3, wherein, the lead knowledge engine is designed and arranged to iteratively traverse the semantic graph database and apply semantic reasoning at each of the plurality of nodes.

6. The system of claim 1, wherein, the dynamic profile module is configured to establish the outside sales information and the inside sales information as object-oriented modules of an automated computer machine as a structure of computer memory of the first instance of the automated computer machine.

7. The system of claim 1, wherein, the dynamic profile module is configured to establish the target lead profile and the remote agent ranking as object-oriented modules of an automated computer machine as a structure of computer memory of the first instance of the automated computer machine.

8. The system of claim 1, wherein, the target lead profile includes a profile identification, an industry name, a size name, a region name, and a product / service name.

9. A computer-implemented method of customer relationship management comprising: by a dynamic profile module implemented as a first instance of software running on a server, querying a plurality of remote agent panel applications on a plurality of remote agent stations located at remote locations relative to the server over a computer network and, in response, receiving internal sales information comprising identification of sales of products or services by a plurality of remote agents associated with the remote agent panel applications; by the dynamic profile module, querying one or more external sales analytics engines over an application programming interface (API) and, in response, receiving external sales information comprising identification of external sales of products or services by a plurality of companies; by the dynamic profile module, creating a target lead profile from the external sales information and the internal sales information, wherein the target lead profile is stored as one or more semantic triples in an enterprise knowledge graph comprising a plurality of nodes populated with the internal sales information and the external sales information; by the dynamic profile module, generating a remote agent ranking ranking remote agents according to a plurality of criteria from the internal sales information, wherein the remote agent ranking is stored as one or more semantic triples in the enterprise knowledge graph; and by the dynamic profile module, identifying a remote agent team from the target lead profile and the remote agent ranking, wherein the dynamic profile module is configured to identify the remote agent team by traversing the enterprise knowledge graph.

10. The method of claim 9, further comprising: by a panel update module implemented as a second instance of an automated computer machine, resolving a lead; and by the panel update module, sending the resolved lead to one or more of the remote agent panel applications according to the remote agent team.

11. The method of claim 9, further comprising: storing the enterprise knowledge graph as a semantic graph database.

12. The method of claim 11, wherein, each of the plurality of nodes comprises three resource identifiers.

13. The method of claim 11, further comprising: iteratively traversing the semantic graph database; and applying semantic reasoning at each of the plurality of nodes.

14. The method of claim 9, further comprising: by the dynamic profile module, establishing the external sales information and the internal sales information as object-oriented modules of an automated computer machine as a structure of computer memory.

15. The method of claim 9, further comprising: by the dynamic profile module, establishing the target lead profile and the remote agent ranking as object-oriented modules of an automated computer machine as a structure of computer memory.

16. The method of claim 9, wherein, the target lead profile comprises a profile identification, an industry name, a size name, a region name, and a product / service name.

Images