Escalation management and journey mining

The system addresses the challenge of analyzing customer journeys to identify root causes of KPIs by using graphical interfaces and machine learning for effective escalation management and journey mining, enhancing customer experience optimization.

JP7954145B2Active Publication Date: 2026-11-19POINTILLISTE
View PDF 4 Cites 0 Cited by

Patent Information

Application Number
JP2023537324
Authority / Receiving Office
JP · JP
Patent Type
Patents
Current Assignee / Owner
Priority Date
2020-12-22
Filing Date
2021-12-22
Publication Date
2026-11-19
Estimated Expiration
2041-12-22

AI Technical Summary

Technical Problem

Existing systems fail to effectively analyze customer journeys to identify root causes of key performance indicators (KPIs) and provide intuitive visualization for non-analytical users, making it difficult to understand and optimize customer experiences across multi-channel organizations.

Method used

A system and method for escalation management and journey mining that utilizes graphical user interfaces to analyze customer timelines, identify issues, determine their causes, and perform corrective actions, incorporating machine learning and natural language processing to provide actionable recommendations.

Benefits of technology

Enables efficient identification of customer journey deviations and root causes, leading to actionable insights for improving customer satisfaction and business performance by optimizing customer experiences.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 0007954145000001
    Figure 0007954145000001
  • Figure 0007954145000002
    Figure 0007954145000002
  • Figure 0007954145000003
    Figure 0007954145000003
Patent Text Reader

Abstract

Multiple customer journeys and / or timelines can be used in escalation management and / or journey mining. On the timelines, events of interest related to issues or incidents can be used in escalation management and / or journey mining. Escalation management is directed at addressing and resolving incidents, problems, and customer situations that may result in high levels of customer dissatisfaction or damage to the service provider's reputation with appropriate responses and / or resources. Journey mining is directed at using patterns across customers and their journeys to determine where things in the journey went differently than expected.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] (Cross-reference to Related Applications and Claim of Priority) This application claims priority to U.S. Patent Application No. 17 / 130,125, filed on December 22, 2020, entitled "Escalation Management and Journey Mining".

Background Art

[0002] In any customer-centric industry, business success is determined by the entire customer journey. Recently, data points representing events along the customer journey can be recorded in databases, and these data points can be aggregated to measure key performance indicators (KPIs) that are essential for evaluating enterprise performance, but the root causes driving these KPIs cannot be directly identified from the underlying data. This is because the root causes are contained within journeys (sets of disparate interrelated events that unfold over time), and simple aggregation of data points, and even machine learning on those data points, cannot break through the complexity of true journey analysis.

[0003] A journey can be defined not only by whether a customer saw an advertisement, when the customer visited a website, what the customer purchased, or who the customer is, but also by everything the customer has ever done, how those events relate to each other in time, and who or what was involved in those events. Analyzing a journey requires simultaneously analyzing all of a customer's interactions, including the gaps between events and the customer's state when those events were involved. Communicating and understanding journeys requires new ways to visualize and interact with data that convey this enormous complexity in an intuitive form to non-analytical users.

[0004] Traditional systems cannot provide such functionality. While marketing teams can monitor KPIs and track trends—that is, "slice and dice" results regarding current snapshots or aggregates of marketing data or other customer-related data—this only provides a limited (often outdated) view of a limited subset of available data. For example, a marketing team may know what the total sales per period are, dig into multiple dimensions, and identify who the most profitable customers are, or follow, for example, the Net Promoter Score (NPS). However, in a multi-channel and multi-process organization, determining the customer experience (interactions and other events that shape the customer's perception of the brand) that explains trends or fluctuations in these metrics is extremely difficult, if not impossible. In reality, each customer follows a unique path through the organization, and these paths lead to different outcomes. Understanding these paths and their impact on metrics requires a new ability to shape the customer journey and maximize business performance.

[0005] A new world of questions becomes possible by breaking down data silos within specific channels, processes, or organizations, and by maintaining the integrity of each customer journey. For example, in addition to knowing what a company's Net Promoter Score is, marketers may be able to effectively understand how customer interactions impact the NPS, identify where they should take action, and reshape the customer experience to improve the overall score.

[0006] Therefore, since the customer journey underlies all marketing metrics and business outcomes handled by the marketing team, the marketing team needs a solution specifically designed to uncover the story behind each metric, what drivers influence it, and how to shape the customer journey to maximize business value.

[0007] Escalation management is the process of addressing incidents, issues, and customer situations that could result in a high level of customer dissatisfaction or damage to the service provider's reputation. Escalation management concerns addressing and resolving these types of issues and challenges at the right level and with the right resources. Escalation management and opportunity assessment (e.g., NPS increase) depend on data (e.g., customer history, call transcripts, natural language processing, etc.) and data quality. Currently, escalation management and opportunity assessment (e.g., NPS increase) are difficult to achieve successfully and efficiently. Generating actionable recommendations and verifying the feasibility of those recommendations has traditionally been difficult.

[0008] Various aspects and embodiments of this disclosure are presented with respect to these and other considerations. [Overview of the Initiative]

[0009] Systems and methods for escalation management and journey mining are provided. Multiple customer journeys and / or timelines may be used in escalation management and / or journey mining. On the timeline, events of interest regarding issues or incidents may be used in escalation management and / or journey mining. Escalation management aims to address and resolve incidents, issues, and customer situations that could result in a high level of customer dissatisfaction or damage to the service provider's reputation, using appropriate responses and / or resources. Journey mining aims to determine where events within a journey have gone differently than expected, using patterns across customers and customer journeys.

[0010] In one implementation, the method includes identifying an issue in a customer's timeline, where the timeline includes multiple events; determining the cause of the issue; determining the impact of the issue on other customers; and performing escalation management based on the impact.

[0011] In one implementation, the method includes identifying issues in a customer's timeline, where the timeline includes multiple events; providing the timeline and issues to the user in a graphical user interface of a computing device; receiving notes from the user in the graphical user interface; annotating the timeline with notes; and performing escalation management based on the issues.

[0012] In one implementation, the method includes providing a first timeline to a computing device, wherein the first timeline includes a first set of events; providing a second timeline to a computing device, wherein the second timeline includes a second set of events; comparing the first timeline to the second timeline to determine a shared incident; determining the cause of the shared incident; determining corrective actions; and outputting the corrective actions.

[0013] In one implementation, the method includes retrieving data that includes at least one of the following: events from a customer timeline, information from a customer timeline, patterns from a customer timeline, events from patterns in a customer timeline, or issues related to patterns in a customer timeline; constructing a journey using the retrieved data; and outputting the journey.

[0014] In one implementation, the system comprises at least one processor and memory that, when executed by at least one processor, stores instructions causing at least one processor to perform the following actions: identify an issue in a customer's timeline, wherein the timeline includes multiple events; determine the cause of the issue; determine the impact of the issue on other customers; and perform escalation management based on the impact.

[0015] In one implementation, the system comprises at least one processor and memory that stores instructions causing at least one processor, when executed by at least one processor, to identify issues in a customer's timeline, wherein the timeline includes multiple events; to provide the timeline and issues to the user in a graphical user interface of the computing device; to receive notes from the user in the graphical user interface; to annotate the timeline with notes; and to perform escalation management based on the issues.

[0016] In one implementation, the system comprises at least one processor and a memory that stores instructions causing at least one processor to perform the following actions when executed by at least one processor: to provide a first timeline to a computing device, wherein the first timeline includes a first set of events; to provide a second timeline to a computing device, wherein the second timeline includes a second set of events; to compare the first timeline with the second timeline in order to determine a shared incident; to determine the cause of the shared incident; to determine corrective actions; and to output the corrective actions.

[0017] In one implementation, the system comprises at least one processor and memory that stores instructions, when executed by at least one processor, to retrieve data including at least one of events from a customer timeline, information from a customer timeline, patterns from a customer timeline, events from patterns in a customer timeline, or issues related to patterns in a customer timeline; to construct a journey using the retrieved data; and to output the journey.

[0018] In one implementation, the system comprises an issue identification engine configured to identify issues in a customer's timeline, the timeline comprising the issue identification engine, a timeline analysis engine configured to determine the cause of the issues, an impact determination engine configured to determine the impact of the issues on other customers, and an escalation management engine configured to perform escalation management based on the impact.

[0019] In one implementation, the system comprises: an issue identification engine configured to identify issues in a customer's timeline, where the timeline includes multiple events; and to provide the timeline and issues to the user in a graphical user interface of a computing device; a note-taking engine configured to receive notes from the user in a graphical user interface; a timeline analysis engine configured to annotate the timeline with notes; and an escalation management engine configured to perform escalation management based on the issues.

[0020] In one implementation, the system comprises a computing device configured to receive a first timeline, the first timeline containing a first set of events, and to receive a second timeline, the second timeline containing a second set of events; a timeline analysis engine configured to compare the first timeline with the second timeline and determine the cause of a shared incident; and an escalation management engine configured to determine corrective actions and output corrective actions.

[0021] In one implementation, a system comprises a timeline analysis engine configured to retrieve data including at least one of an event from a customer timeline, information from a customer timeline, a pattern from a customer timeline, an event from a pattern of a customer timeline, or an issue associated with a pattern of a customer timeline, and a journey construction engine configured to construct a journey using the retrieved data and output the journey.

[0022] This summary is provided to introduce a selection of concepts in a simplified form that are further described below in the Detailed Description. This Summary is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to be used to limit the scope of the claimed subject matter. [Brief Description of the Drawings]

[0023] The foregoing summary, as well as the following detailed description of exemplary embodiments, is better understood when read in conjunction with the appended drawings. For the purpose of illustrating the embodiments, exemplary configurations of the embodiments are shown in the drawings. However, the embodiments are not limited to the specific methods and instrumentalities disclosed. The drawings are as follows. [Figure 1] Shows an exemplary visual representation of events within a journey in accordance with the present disclosure. [Figure 2] Shows an exemplary visual representation of an entire customer journey in accordance with the present disclosure. [Figure 3] Is a diagram of an exemplary environment for escalation management and journey mining. [Figure 4] Is an operational flow diagram that provides a general overview of exemplary operations executable by a system in accordance with the present disclosure. [Figure 5] Is an operational flow of an implementation of a method for escalation management. [Figure 6] Is an operational flow of another implementation of a method for escalation management. [Figure 7] This is an operation flow of an implementation of a method for journey mining. [Figure 8] This shows an exemplary graphical user interface according to the present disclosure. [Figure 9] This shows an exemplary graphical user interface according to the present disclosure. [Figure 10] This shows an exemplary graphical user interface according to the present disclosure. [Figure 11] This shows an exemplary graphical user interface according to the present disclosure. [Figure 12] This shows an exemplary graphical user interface according to the present disclosure. [Figure 13] This shows an exemplary graphical user interface according to the present disclosure. [Figure 14] This illustrates an exemplary computing environment in which exemplary embodiments and aspects may be implemented. [Detailed Description of the Invention]

[0024] The system will be described more fully hereinafter with reference to the included drawings, which are intended to be read in conjunction with this detailed description, the summary, and any preferred and / or specific embodiments specifically discussed or otherwise disclosed. However, this system may be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. Instead, these embodiments are provided by way of illustration only so that this disclosure will be thorough and complete, and will fully convey the full scope of the invention to those skilled in the art.

[0025] This description provides examples not intended to limit the scope of the attached claims. The figures generally illustrate the features of the embodiments, and it is understood and recognized that similar reference numerals are used to refer to similar elements. Any reference to “one embodiment,” “embodiment,” or “exemplary embodiment” herein means that the particular feature, structure, or characteristic described is included in at least one embodiment described herein, and not implies that the feature, structure, or characteristic is present in all embodiments described herein.

[0026] Components that may be used to carry out the disclosed systems and methods are further disclosed herein. When these and other components are disclosed herein, and when combinations, subsets, interactions, groups, etc., of these components are disclosed, specific references to each of the various individual combinations and collective combinations and permutations of these may not be expressly disclosed, but each will be understood to be specifically contemplated and described herein for all systems and methods. This applies to all aspects of this application, including but not limited to steps in the disclosed methods. Accordingly, where there are various additional steps that can be carried out, each of these additional steps will be understood to be carried out using any particular embodiment or combination of embodiments of the disclosed methods.

[0027] As will be understood by those skilled in the art, the systems and methods described herein may take the form of hardware embodiments, software embodiments, or embodiments combining software and hardware embodiments. Furthermore, the systems and methods may take the form of computer program products on a computer-readable storage medium having computer-readable program instructions (e.g., computer software) embodied on the storage medium (see also Figure 14 herein). In one embodiment, the systems and methods may take the form of hardware (e.g., a microcontroller) configured to perform specific steps. More specifically, the systems and methods may take the form of web-implemented computer software. Centralized servers, remotely located servers, or cloud services may implement embodiments of the systems and methods. Any suitable computer-readable storage medium, including hard disks, CD-ROMs, optical storage devices, or magnetic storage devices, may be used.

[0028] Embodiments of systems and methods are described herein with reference to block diagrams and flowcharts of methods, systems, apparatus, and computer program products. It will be understood that each block in the block diagrams and flowcharts, and combinations of blocks in the block diagrams and flowcharts, can be implemented by computer program instructions. These computer program instructions can be loaded onto general-purpose computers, computers and components found in cloud services, or other programmable data processing devices to create a machine, such that instructions executed on a computer or other programmable data processing device create means for implementing functions specified in one or more blocks of a flowchart. In one embodiment, computer program instructions may be loaded onto a dedicated computer or server to perform the functions and methods described below.

[0029] These computer program instructions can also be stored in computer-readable memory, which can instruct a computer or other programmable data processing device to function in a particular way so that the program instructions in the computer-readable medium produce a product containing computer-readable instructions for implementing the functions specified in the blocks of the flowchart. Computer program instructions can also be loaded onto a computer or other programmable data processing device to execute a series of operational steps on the computer or other programmable device to generate a computer implementation process, so that the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in the blocks of the flowchart.

[0030] Therefore, the blocks in block diagrams and flowcharts support combinations of means for performing a specified function, combinations of steps for performing a specified function, and program instruction means for performing a specified function. It will also be understood that each block in block diagrams and flowcharts, as well as combinations of blocks in block diagrams and flowcharts, can be implemented by a dedicated hardware-based computer system that performs a specified function or step, or by a combination of dedicated hardware and computer instructions.

[0031] The systems and methods discussed in further detail herein are described as comprising units. Those skilled in the art will understand that a unit is a functional description, and that software, hardware, or a combination of software and hardware may perform its respective function. In one exemplary embodiment, a unit may include a computer. This exemplary operating environment is merely an example of an operating environment and does not imply any limitation on the use or scope of functionality of the operating environment architecture. Furthermore, the operating environment should not be construed as having any dependence or requirements on any one or combination of components shown in the exemplary operating environment.

[0032] In one embodiment, the system and method may operate in a number of other general-purpose or dedicated computing system environments or configurations. Examples of well-known computing systems, environments, and / or configurations that may be suitable for use with the system and method include, but are not limited to, personal computers, server computers, laptop devices, cloud services, mobile devices (e.g., smartphones, tablets, etc.), and multiprocessor systems. Further examples include set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, enterprise servers, and distributed computing environments that include any of the systems or devices described above.

[0033] The processing of the disclosed systems and methods can be performed by software components. The disclosed systems and methods can be described in the general context of computer executable instructions, such as program modules, which are executed by one or more computers or other devices. Generally, program modules include computer code, routines, programs, objects, components, data structures, etc., that perform a specific task or implement a specific abstract data type. The disclosed methods can also be implemented in grid-based and distributed computing environments, where tasks are performed by remote processing devices linked over a communication network. In a distributed computing environment, program modules can reside on both local and remote computer storage media, including memory storage devices.

[0034] Where used herein and in the appended claims, the singular forms “a,” “an,” and “the” include multiple referents unless the context clearly indicates otherwise. Ranges may be expressed herein as “about” one particular value to and / or “about” another particular value. Where such ranges are expressed, another embodiment includes one particular value to and / or another particular value. Similarly, where values ​​are expressed as approximations by the use of the antecedent “about,” it will be understood that a particular value forms another embodiment. Furthermore, it will be understood that each endpoint of a range is important both with respect to the other endpoints and independently of the other endpoints.

[0035] "Optional" or "optional" means that the event or situation described thereafter may or may not occur, and that the description includes both the cases in which the event or situation occurs and the cases in which it does not occur.

[0036] Throughout this description and claims, the word “comprise,” and variations thereof such as “comprising” and “comprises,” mean “including, but not limited to,” and are not intended to exclude, for example, other additives, ingredients, wholes, or steps. “Exemplary” means “example,” and is not intended to convey a preference or ideal embodiment. “Such as” is used for illustrative purposes, not in a restrictive sense.

[0037] In relation to embodiments of the present invention, “event” is an action that occurs at a specific point in time, such as an email being sent. “excluded event” is a period of time for other events that should not occur, such as an email that has not been opened for a certain period of time. “event type” defines the expected event category and attributes for an event. “label” is the type of category data field. “label name” is the name of the label. “value” defines a numeric field within an event. “value name” is the name of the value. “unit” defines the unit of the value, such as a percentage. “event data field” describes the label, value, and / or unit associated with the event. “event classification” describes organizing events hierarchically by category. “actor” is a person, place, or thing involved in an event. “actor state” is the mapping and transformation of event data fields to actors as a function of time. “actor role” defines the role of an actor for a given event. “actor type” defines actor categories and the expected actor states for an actor. "Trend" describes how an event, event data field, or actor state changes over time. "Dropout" is the difference between the number of actors that enter an event and the number of the same actors that enter any of the subsequent events. "Connection" is the link between two events, specifying their shared actors and temporal distance. "Event of Interest" is an event that has metrics that the user wants to analyze. "Story" is a pattern representing a set of events connected by common actors and their temporal relationships. "Journey" is a story for a single type of actor, such as a customer. "Driver" is an event that has a positive or negative impact on a particular customer journey. "Driver Strength" is the degree of positive or negative impact on a metric per occurrence, regardless of the number of occurrences. "Driver Impact" is defined as the driver strength multiplied by the number of occurrences. "Path" is a selection of a set of events in a story or journey.A "trigger" is a selection path monitored in real time at an individual level to detect comparable behavior and initiate action. A "metric" provides a measure that highlights the calculation of KPIs and therefore consists of data drawn from event data fields and actor states within a story. A "story query" is a request in a specialized language that specifies metrics and stories to collect from the platform dataset. A "result" is the metric value returned from a story query or story execution. "Filtering / grouping" defines grouping and filtering across all stories / journeys / paths at any event or actor level or group of events.

[0038] Figure 1 shows an exemplary visual representation of events within Journey 100 as provided in this disclosure. Customer 110 progresses along a series of events 120, 130, 140, 150, and 160 along Journey 100. Events such as event 140 may be events of interest to a user, such as an analyst or administrator. As further described herein, events in a journey may be used to create a timeline and / or may be included within a timeline. Furthermore, event 140 may be used in escalation management and / or journey mining.

[0039] Each customer can proceed through their own journey, which may include one or more events. Some or all of the events in each customer's journey may be the same as events in another customer's journey. As further described herein, multiple customer journeys and / or timelines may be used in escalation management and / or journey mining.

[0040] An event representation is a collection of multiple independent individual events tracked by each customer. The arrows in Figure 1 represent the customer linking two events and their temporal relationship. Interest events are anchors from which stories are built and to which they are built.

[0041] Journey 100 can take the form of a graph visualization where the nodes of the graph represent events (e.g., events 120, 130, 140, 150, 160), and the edges represent one or more customers at each event (e.g., customer 110) as well as the temporal relationships between the events (e.g., event 130 follows event 120 within 30 minutes). A journey can include events and customers that lay out a literal "human-readable" story that unfolds over time in real life. Stories can include branches that represent alternative journeys that converge or diverge from one another. An "event" is a discrete data point similar to a row in a database. In certain embodiments, all events are required to have a timestamp, a specified type (e.g., "login" or "purchase"), and at least one customer. Events can be used to represent recorded customer actions, but they can also be used to represent changes to static data, such as updating or creating address records, or assigning demographic or segmentation data. In certain embodiments, events do not need to be associated with customers. For example, changing a product price or placing a procurement order could also be an event. In certain embodiments, an event may not contain direct references to other events, but instead may share common actors that indirectly link them together. Customers are people, individuals, subjects, entities, etc., involved in an event. For example, with respect to an event of type "purchase," customers may include customers, stores, employees, and multiple product customers. Customers may be used by the system in a similar way to how foreign keys are used in relational databases. In certain embodiments, customers are used as a "key" in conjunction with timestamps to indicate relationships between events.

[0042] In certain embodiments, the nodes in the graph represent patterns for filtering events. That is, the nodes in the graph do not represent individual events (i.e., data points) themselves. The nodes and edges represent patterns that are used together to find matching occurrences within the dataset and enable the aggregation of similar patterns of events and customers.

[0043] In certain embodiments, each individual node in the graph specifies its own filter for events in the data pool. These filters include the event type and optionally include boundaries for timestamps and constraints for event parameters. For example, a node might represent a filter that finds purchase events paid by credit card in May 2014 for a value greater than $22.

[0044] Similarly, in certain embodiments, edges in the graph specify relationships between nodes, specifically shared customers, and temporal relationships between two event patterns (nodes). This is analogous to the "join-on" clause in an SQL statement, where two sets of data points are joined using a common foreign key.

[0045] There are various types of relationships that two events can have in time. For example, event A is before or after event B. Event A is within a specific time period before and / or after event B. Event A is either the most recent event before event B, or the closest event following event B, and event A is within n events of event B.

[0046] Further details disclosing the functions / operations of an exemplary system are provided below. Note that the description provides specific implementations of the system that can be modified by those skilled in the art to provide similar functions without departing from the spirit and scope of the system disclosed herein.

[0047] Figure 2 shows an exemplary visual representation of the entire customer journey 200 as provided in this disclosure. The customer journey 200 shown in Figure 2 is an example of a customer journey across an exemplary customer lifecycle. In a particular embodiment, the system creates classifications and hierarchies that categorize and group events, metrics, and KPIs. Each group represents a step in the customer lifecycle. An event may be part of multiple classifications and hierarchies. For example, the event "Add to Cart" may be in the following categories: "Conversion," "Web," "Purchase," and within different hierarchies such as "Lifecycle," "Channel," or "Sales Process." This approach enables visualization and analysis of the customer journey across different facets from the perspective of "Lifecycle," "Channel," or "Sales Process."

[0048] Figure 3 is a diagram of an exemplary environment 300 for escalation management and journey mining. Escalation management focuses on addressing and resolving incidents, issues, and customer situations that could result in a high level of customer dissatisfaction or damage to the service provider's reputation, using appropriate responses and / or resources. Journey mining focuses on using patterns across customers and their journeys (and / or microjourneys) to determine where events within a journey have gone differently than expected. Journey mining uses patterns in journeys and / or microjourneys to uncover, for example, root causes, opportunities for improving the customer experience, and deviations from nominal or expected paths, and facilitates sizing of opportunities and deviations, including their total impact on metrics or KPIs.

[0049] Journey mining can process thousands of touchpoints across a wide range of timeframes and multiple data sources (e.g., over 50). It can incorporate contextual data such as natural language processing (NLP), event attributes, free text, and call recordings. Journey mining reliably leads to actionable recommendations. It can identify key behaviors at the individual customer level (e.g., escalation management) and overall.

[0050] As shown in Figure 3, the system can be described in terms of several components and subsystems that enable the operations described herein to be performed. As shown, the exemplary system can generally acquire events, customers, timelines, and / or journeys and aggregate the data into a format usable by the system. The system can provide capabilities for escalation management and journey mining, as further described herein.

[0051] The system can be used in a variety of suitable environments. For example, it can be used in consumer marketing, particularly after the customer journey, including tracking customer interactions, engagement, retention, loss, and reactivation. However, the data structure and processing methods can be used in any industrial application where it is desirable to collect data and use it for modeling and optimization. Such applications include, but are not limited to, healthcare, manufacturing, human resources, education, hospitality, bioengineering, and social services industries.

[0052] In exemplary embodiments, timestamps associated with data or metrics such as events, customers, stories, and journeys may be collected and stored. In certain embodiments, all entries may be defined by a corresponding timestamp, enabling the data to be processed, analyzed, and visualized when other timestamps and associated data are temporally relevant. Since each entry in a data structure can be defined by a timestamp, and all data associated with a timestamp can be maintained in a timestamp format, this disclosure provides, in certain embodiments, a system for collecting data across all available data channels and preserving the integrity of all data associated with a customer.

[0053] In another implementation of the exemplary system, different (and related) data sources may be automatically collected through batch or streaming inputs to a database associated with the system. The system and database may be stored on a local server or in a remote configuration, realizing a “cloud”-based system, or any preferred combination thereof. In other words, some embodiments are not limited to a specific storage solution or environment.

[0054] Exceptional sources of raw or pre-processed information that the system may receive include email data, social media data (e.g., feeds from Facebook, LinkedIn, Twitter, etc.), promotional materials (e.g., electronic coupons), call center data, customer relationship management (CRM) data, mobile marketing data, operational data (e.g., revenue, sales reports, etc.), and point-of-sale data (e.g., payment format, customer identity, etc.). However, in certain embodiments, the system is not intended to be limited to specific types of data. Instead, the system may acquire data used and tracked by enterprises in heterogeneous and / or related systems and aggregate and / or store this data in a format that allows for efficient retrieval, analysis, and representation by the system. As further described herein, data may be associated through events, connections, customers, and stories. For example, the system may associate data by creating a timestamp and type for each event and associate it with one or more customers.

[0055] As referenced above, an event is an action or observation that occurs at a point in time related to at least one customer, and an event data point may consist of at least a timestamp, an event type, and at least one customer. An event data point may include other attributes such as categorical data, numerical data, geographical data, and unstructured data. Events may share customers. A connection relates two events to each other by specifying the shared customers and their relative locations in time. A story is a pattern that represents two or more events related through a shared connection. The system may visually present a story by means of a graph in which the nodes generally represent events and the edges generally represent connections. A journey containing one or more stories related to a particular type of customer can be graphically presented by the system in a form that allows for an intuitive understanding of which events, event attributes, and event sequences have the greatest impact on customer outcomes, so that future interactions can be optimized. The system can also graphically represent future actions to optimize performance.

[0056] Customer 302 performs events along a journey (for example, events 120, 130, 140, 150, and 160 along journey 100). Journey events can be stored in storage 304. In addition, one or more timelines, such as one or more customer timelines 306, can be stored in storage 304.

[0057] A user 352 (who may be, for example, a company analyst, representative, employee, or colleague) may use a user computing device 355 to access storage 304 (including customer timelines 306) via network 308. In some embodiments, user 352 may be a virtual analyst rather than a human analyst.

[0058] The computing device 310 can communicate with the user computing device 355 and the storage 304 to provide various functions, operations, capabilities, and / or data to the user computing device 355 (and therefore the user 352). In some implementations, the computing device 310 can be implemented in or embodied in a desktop analytics product. Depending on the implementation, the output device 398 can communicate with the computing device 310 via either a wired or wireless connection.

[0059] In some implementations, a subject matter expert (SME) 392 (which may be human or virtual) may use an SME computing device 395 to communicate with user computing devices 355 and computing devices 310, for example, via a network 358.

[0060] Networks 308 and 358 can each be various network types, including a public switched telephone network (PSTN), a cellular telephone network, and a packet-switched network (e.g., the Internet). Networks 308 and 358 may be the same network or different networks, depending on the implementation. Although only one user computing device 355, one computing device 310, one SME computing device 395, one storage 304, and one output device 398 are shown in Figure 3, there is no limit to the number of computing devices 310, 355, 395, storage 304, and output device 398 that may be supported.

[0061] The user computing device 355, SME computing device 395, computing device 310, and output device 398 can each be implemented using various computing devices such as smartphones, desktop computers, laptop computers, tablets, set-top boxes, vehicle navigation systems, and video game consoles. Other types of computing devices may be supported. A suitable computing device is shown in Figure 14 as computing device 1400.

[0062] In some implementations, the computing device 310 comprises a problem identification engine 315, a note-taking engine 320, a timeline analysis engine 325, a journey construction engine 330, an impact determination engine 335, and an escalation management engine 340. As further described herein, the computing device 310 and its various engines 315, 320, 325, 330, 335, and 340 help the user 352 provide better services and information to the customer 302 through escalation management and journey mining.

[0063] The issue identification engine 315 is configured to analyze one or more timelines of one or more customers and identify one or more issues within them. An issue can be any type of event, as defined by the implementation. Examples of issues may include a customer contacting a help center, a customer canceling a purchase, a customer emptying their shopping cart, a customer pausing the journey for a predetermined amount of time, a customer logging off, or leaving an online experience or journey.

[0064] In some implementations, human users (as opposed to automated systems) can identify issues based on their own business context applied to the timeline they are observing.

[0065] In some implementations, human users can be augmented with artificial intelligence (AI). For example, based on previous human input, a machine learning system can learn the statistical characteristics of incidents previously identified as issues and use this knowledge of characteristics to identify issues that may be relevant to the current investigation. The issue identification engine 315 can be fully automated or can provide supplementary information to a human user to accelerate its own issue identification process. To enhance accurate identification and mitigate future inaccuracies, human interaction with the output of the issue identification engine 315 can be further incorporated into the machine learning model. Statistical characteristics may depend on features of time-series data such as: the occurrence, attributes, timestamps, or other metadata of events that may be typical problems; other characteristics of benign events; or the temporal relationships between two or more events. Note that any of the above can generally be subject to issues, even in the context of a human analyst. Issues are not limited to the simple occurrence of specific event types. The model can further incorporate customer attributes such as demographics.

[0066] In some implementations, the issue identification engine 315 is configured to retrieve the event history about the customer, render it in a timeline visual representation for the user, and also provide access to the underlying metadata of individual events through user interaction.

[0067] The issue identification engine 315 may also be configured to provide filtering of events shown in the timeline. The filtering can be inclusive or exclusive and may be specific event types and / or specific sets of metadata about those events (e.g., displaying only events from the website, or not displaying events related to internal processes).

[0068] The note-taking engine 320 is configured, as further described herein, to enable a user 352 to input notes about a timeline, or issues and / or events therein, into an interface displayed on the user computing device 355. In some implementations, all notes are pinned to a timeline visual representation of either an event on the timeline or a point on the timeline between events. Notes may be used, for example, to flag observations such as failure or success, to indicate root causes and incidents, or for collaboration by addressing or assigning tasks or questions to other users.

[0069] The timeline analysis engine 325 is configured to analyze timelines by comparing timelines, analyzing timelines for patterns related to events in one or more journeys, and identifying these patterns or events and / or issues, including root causes related to the identified patterns, as further described herein. In some implementations, a human user (as opposed to an automated system) may identify one or more root causes based on their own business context that applies to the timelines they are observing. In the case of multiple timelines, the timeline analysis engine 325 may determine commonalities across timelines to help narrow the search space for the human user when looking for potential root causes.

[0070] The timeline analysis engine 325 can be fully automated or can provide supplementary information to human users to accelerate their own root cause identification processes.

[0071] The journey building engine 330 is configured, as further described herein, to enable user 352 to create (build) a new journey using events and / or information from one or more customer timelines and / or patterns, or events and / or issues associated with an identified pattern. More specifically, using the journey building engine 330, user 352 has the ability to arrange events in sequence, specify "connection" properties between events (such as sharing specific event properties within a specific time period with each other), and filter events by their attributes / metadata. Furthermore, multiple journeys can be created as affordances to, for example, highlight multiple journey patterns in a displayed timeline, import timelines from different but related journeys, or import timelines of customers involved in multiple journeys.

[0072] The journey building engine 330 can be used to fetch additional timelines of customers involved in a journey and add them to the user interface for manual or automated analysis. The journey building engine 330 can highlight the occurrence of each journey on the timeline.

[0073] In addition to using events in the visible timeline during the journey, users can manually add other events that are known to the system but are not necessarily present in the currently viewed timeline.

[0074] The impact determination engine 335 is configured to determine the impact that identified patterns have (or may have) on other customers' journeys or timelines. This allows entities associated with the journey or timeline being analyzed to determine the scale of the issue within their customer base.

[0075] In some implementations, the impact determination engine 335 can obtain and provide the total number of customers involved in the journey or the total number of times the journey occurred. The impact determination engine 335 can provide “funnel” type statistics at each node in the journey, providing the number and percentage of customers who advanced or completed the journey, as well as the number of customers who dropped out at each event along the way.

[0076] The Impact Determination Engine 335 enables the creation of custom calculations and charts that have the ability to perform aggregation and arithmetic operations on any of the attributes in events within the journey. The Impact Determination Engine 335 also enables the creation of charts that analyze the attributes of customers involved in the journey (e.g., the number of participants by age range, the average customer NPS score), and how the mixture of those attributes changes as the customer progresses through the journey.

[0077] The function described above provides the ability to quantify the impact of a journey on costs, revenue, customer satisfaction, or any other metric. Its effect is to take patterns identified from multiple timelines, obtain the total number of customers who exhibited that same behavioral pattern, and quantify how the occurrence of that pattern corresponds to changes in any given metric. This functionality can also be used to quantify potential "silent detractors," or customers who may have had problematic behavior / event patterns but did not have a final consequence incident that allowed them to be flagged / counted.

[0078] The escalation management engine 340 is configured to correct, plan for, and / or prevent issues relating to some or all of the customer base of one or more individual customers and / or entities. The escalation management engine 340 has the capability to automatically create reports and / or deliverables from work products generated by other engines, particularly the note-taking engine 320. Thus, within the platform, reports can be delivered to the intended audience. Consumers of the reports can also "dive into" the reports to see the underlying customer timeline and analysis.

[0079] In some implementations, the impact determination engine 335 and / or the escalation management engine 340 identify opportunities that can be used to guide or modify the interaction toward a better outcome for the mutual benefit of both the customer 302 (i.e., end customer) and the user 352 entity (e.g., organization).

[0080] Various templates can be used for escalation management deliverables. Templates can be created to address the specific needs of different use cases and scenarios. Different aspects of analysis can be included in the deliverables, such as notes, measurements, journeys, charts, customer lists, and data in free-form summary fields.

[0081] The analysis and / or deliverables (e.g., timelines or data output from computing device 310) may be output to or displayed on one or more users or user computing devices, such as analyst computing device 355 and / or output device 398. Through a graphical interface, user 352 may clarify questions or request additional analysis. User 352 may click on deliverables to view detailed underlying data stories within the analysis.

[0082] The SME computing device 395 may be used by the SME 392 to communicate with the user 352 (via the user computing device 355) in various implementations as further described herein.

[0083] The system is intended to be delivered as a software as a service (SaaS) model through a cloud-based database structure. However, other embodiments may include localized whole or partial data storage. In addition, the exact location of the processors and computers implementing the system may vary depending on the embodiment. In some embodiments, the entire system may reside remotely from the end user (e.g., user 352 or other users or administrators associated with the entity), except for client (user) service devices, e.g., mobile phones, computers, etc., from which a graphical interface is provided; in other embodiments, the entire system may reside locally from the end user. Therefore, the exact location of the system components may not necessarily be important for understanding the applications of the functionality of the system of the disclosed invention.

[0084] In some embodiments, the system 300 may receive data from one or more sources and store the data in storage 304 or other storage associated with one or more of the computing devices 310, 355, and 395. This may be done through batch transfers of past events or in real time as provided herein. A data manager may acquire data that may be in various different formats and prepare the data for use by the system described herein. For example, the data may be formatted to correlate details such as the time of the event, the type of the event, the subject of the event, and / or the customer performing the event. In at least one embodiment, the data is formatted to correlate with other data through at least a timestamp and identification of the event to which the data relates. The data may then be stored in storage 304 or other data memory for efficient retrieval by one or more components of the system 300.

[0085] Once the data is formatted or converted into a usable format (or stored according to system requirements), the data can then be used by the system to provide it to a user, such as user 352, via user computing device 355. To do so, a client application may be provided on a third-party client device (e.g., user computing device 355), such as a personal computer or mobile device (e.g., a telephone or tablet). The client device may further provide a graphical interface from which the user can interact with the system. In some embodiments, this interaction may involve the user selecting a specific preset query provided by the system or constructing additional queries based on options provided by the system. For example, through a client application on user computing device 355 (and / or SME computing device 395), a user (such as user 352 or SME 392) may request to view, for example, a set of events within a specific period that affect the sale of a product or service over the same period. The client application can then request the system to execute the requested query and deliver the requested information, which can be provided in an intuitive graphical interface such as those provided herein. This can be done by sending the query directly to computing device 310. Next, the computing device 310 can construct and execute queries (perform a set of logical operations on the available data) and return the available results to the client application. In addition, the client application can also request and retrieve information directly from storage 304 and / or other data memory, and this information can also be provided to the user via a graphical interface.

[0086] Therefore, the system can provide an easy-to-understand graphical interpretation of the data to relate events, customers, and stories to each other, thereby providing a means of feedback to the system's users.

[0087] Figure 4 is an operation flow diagram showing a rough overview of an exemplary operation 400 that can be performed by a system (e.g., system 300) according to this disclosure.

[0088] In 410, a system such as the one described with respect to Figure 3 and / or Figure 14 receives a journey selection. Depending on the implementation, a user (e.g., an analyst) may select a previously generated journey from storage such as storage 304, or may instruct the system to build a journey (e.g., using a journey building engine) as described herein.

[0089] In 420, the analysis of the journey selected in 410 is initiated (e.g., selected), and in 430, the analysis is executed. In some implementations, a user (e.g., an analyst) may start the analysis in 420 by clicking a start button on the graphical user interface. In 430, the analysis is performed using customer data (e.g., journey data from the customer's journey) alone or in combination with third-party data. Such data may be stored and / or retrieved from storage associated with the system (e.g., a data repository such as storage 304) as described with respect to Figure 3 and / or Figure 14, depending on the implementation. This operation may be performed by the issue identification engine 315 and / or the timeline analysis engine 325, depending on the implementation.

[0090] Features that can be analyzed include occurrence (whether an event occurred at least once), frequency (how many times an event occurred), time interval (the amount of time between the current event and the milestone event), root time interval (the amount of time between the milestone event and the target event), and time cycle (periodicity with a specified period). The journey can be analyzed to identify, or otherwise determine, events that are, or may be, or could be, issues. In some implementations, individual customer journeys and / or timelines (history) are analyzed for escalation management and opportunity investigation. Depending on the implementation, this analysis may include measuring and / or calculating various metrics, comparing actions, metrics, and / or results, and annotating one or more of the customer timelines.

[0091] In some implementations, the analysis in 430 examines customer history and their patterns and behaviors, as well as conversation flow and conversation analysis, which led to specific issues, events, or problems.

[0092] In 440, output based on the analysis is generated and provided to a user (e.g., an analyst). The system provides the output to the user (analyst), for example, via a user interface or an output device such as another display or output device 398. Depending on the implementation, the output may be events, timelines, issues, journeys, etc. Risks or opportunities relating to an entity (e.g., a business in which a customer is involved) may be determined by constructing a journey directly from the timeline and provided as output in 440. A list of customers with similar issues, events, or situations may be generated and output in 440 for subsequent use by a user such as an analyst or an entity. The output may be provided in a user interface, such as a graphical interface, with which the user can interact (e.g., by reviewing, annotating, etc.).

[0093] In 450, an analyst or other user may use the results of the analysis to update and / or adjust the output and / or procedures (e.g., escalation procedures, risks, opportunities, etc.) (e.g., by annotating the output). Depending on the implementation, this operation may be performed by the note-taking engine 320 and / or the escalation management engine 340.

[0094] In 460, changes (i.e., updates and / or adjustments) may be monitored (e.g., by users such as analysts or entities) to determine their effectiveness, etc. Case management workflows may be used to create and assign cases, track their progress, and generate actionable deliverables.

[0095] Figure 5 shows an operational flow of an implementation of Method 500 for escalation management. Method 500 may be implemented by a system according to this disclosure (e.g., System 300).

[0096] In 510, a customer timeline (for example, of an entity) is generated or retrieved from storage. The timeline has a series of events. In some implementations, the customer timeline may be one of the actor timelines 306 maintained in storage 304.

[0097] In 520, the timeline is analyzed to identify one or more issues (e.g., events indicating deviations from expectations, default events, etc.). Depending on the implementation, this operation may be performed by the issue identification engine 315 and / or the timeline analysis engine 325.

[0098] In step 530, the cause of the problem is determined. In some implementations, one or more opportunities and / or risks related to the problem may be determined. This operation may be performed by the problem identification engine 315 and / or the timeline analysis engine 325, depending on the implementation.

[0099] In step 540, the potential impact of the issue on other customers (for example, of an entity) is determined. This operation may be performed by the impact determination engine 335 in some implementations.

[0100] In 550, one or more artifacts for escalation management are generated and output to, for example, an analyst computing device or another output device. This operation may be performed by the escalation management engine 340 in some implementations.

[0101] Figure 6 shows an operational flow of another implementation of Method 600 for escalation management. Method 600 may be implemented by the system according to this disclosure (e.g., System 300).

[0102] In 610, issues related to events in the customer timeline are identified, for example, by the issue identification engine 315. A "case" is generated for the issue and sent to an analyst, such as a user 352. In some implementations, the case may be submitted to a queue and then subsequently sent to the user at a predetermined time, for example.

[0103] In 620, the case is accepted by the user, for example, via the user computing device 355. In 630, the user reviews the case, which includes a timeline (i.e., a history represented by data) containing events that indicate the issue. The user reviews the case in a graphical user interface displayed on the user computing device 355 and can annotate notes on the case via the graphical user interface. The note-taking engine 320 can facilitate note-taking and annotation of the case.

[0104] In 640, the user may use inline collaboration to discuss observations with one or more SMEs (human subject matter experts), such as SME 392, via SME computing device 395. The case notes may be further annotated by user 352 via a graphical user interface provided on user computing device 355.

[0105] In 650, the user may identify the root cause of the issue and determine the risks and / or opportunities of escalation management to improve customer satisfaction. The user may provide this information in a case note or output this information otherwise.

[0106] In 660, for example, the impact determination engine 335 can be used to determine the total impact of the issue. In one implementation, an integrated journey builder can be used to determine the scale of the total impact of the issue and to determine or estimate whether the issue is a major issue affecting many customers.

[0107] In 670, for example, the escalation management engine 340 generates and distributes deliverables for escalation management, or otherwise performs such actions.

[0108] Figure 7 shows the operational flow of an implementation of Method 700 for journey mining. Method 700 may be executable by the system according to this disclosure (e.g., System 300).

[0109] In 710, the timeline of the first customer is received or retrieved, for example, from one or more customer timelines 306 in storage 304 (i.e., the first timeline). In 720, the timeline of the second customer is received or retrieved, for example, from one or more customer timelines 306 in storage 304 (i.e., the second timeline).

[0110] In 730, the first timeline and the second timeline may be displayed together to the user, for example, by being displayed on a graphical user interface provided on the user computing device 355 (e.g., by being pinned together).

[0111] In 740, the first and second timelines may be compared with each other to determine shared incidents (e.g., similar events on each timeline). The first and second customers may both call the call center at the same time, after the same event, or for some other common point. Depending on the implementation, the shared incidents may occur at approximately the same time or at different times and / or on different days. This comparison may be performed in some implementations by the timeline analysis engine 325 and / or using the user 352 and / or user computing device 355.

[0112] In step 750, it is determined which patterns in the two timelines (e.g., common events, common parts, etc.) led to the shared incident. In this way, it can be determined whether there are any patterns that led to similar behavior in the two customers (e.g., both customers calling the call center, or having some shared incident). This determination may be performed in some implementations by the timeline analysis engine 325 and / or using the user 352 and / or the user computing device 355.

[0113] In 760, corrective actions targeting incident response and / or prevention may be determined and output. In some implementations, the determination and output of corrective actions may be performed by the escalation management engine 340 and / or by the user 352 and / or the user computing device 355.

[0114] In 770, in some implementations, one or more timelines of one or more additional customers may be selected, added, displayed on a graphical user interface (e.g., on a user computing device 355), and / or analyzed. In this way, these one or more timelines may also be pinned together with the first and second timelines for further analysis of the shared incident. This analysis may be performed in some implementations by the timeline analysis engine 325, and / or using user 352 and / or user computing device 355.

[0115] In 780, additional or alternative corrective actions (compared to those in 760) targeting incident response and / or prevention may be determined and output using the additional analysis in 770. The determination and output of corrective actions may, in some implementations, be performed by the escalation management engine 340 and / or by the user 352 and / or the user computing device 355.

[0116] Figure 8 shows an exemplary graphical user interface 800 according to the present disclosure. Depending on the implementation, the graphical user interface 800 may be displayed on a computing device such as a user computing device 355, an SME computing device 395, a computing device 310, and / or an output device, or otherwise provided.

[0117] In the illustrative graphical user interface 800, the first timeline 810 for a first customer 805 is shown together with the second timeline 820 for a second customer 815. Each timeline represents a specific customer with a particular event.

[0118] These two timelines can be considered pinned together here. Various events are shown in each timeline, such as the mobile welcome event 812 in the first timeline 810 and the mobile app information event in the second timeline 820. Shared incidents 850 corresponding to calls are shown in each of the first timeline 810 and the second timeline 820. Patterns and / or events in the first timeline 810 and / or the second timeline 820 can be determined and / or analyzed to identify which actions may have led to shared incidents and what corrective actions (e.g., escalation management) can be taken to address current and / or future shared incidents.

[0119] Users can pin timelines to each other at any point in time they choose, such as in a shared incident, but this is not intended to be limiting. In some implementations, timelines are scaled so that the order of events and the relative time positions of events across timelines (between multiple timelines) are equivalent. So, for example, if event 2 in timeline B is to the right of event 1 in timeline A, this means that, with respect to the pinning point on each timeline, customer B had event 2 after customer A had event 1.

[0120] The graphical user interface 800 may provide an area 802 where timelines and / or journeys can be created, displayed, and / or analyzed in near real-time from heterogeneous data sources. Information collected by the system can be evaluated and analyzed through this graphical user interface 800. The occurrence rate of events based on selected modeling may be provided by the system in the timeline area (part of area 802) of the graphical user interface 800. For example, the timeline may show the distribution of stories over time. The user can focus on a specific period by selecting specific start and end dates, and area 802 can be automatically refreshed by the system based on this new period.

[0121] Figure 9 shows an exemplary graphical user interface 900 according to the present disclosure. The interface 900 provides various tabs 905 that show basic data around a customer account (e.g., phone type, phone display URL size, etc.). A notes section 925 corresponding to an associated event is provided. Each event may have an associated notes section where the user can record, for example, a timeline and / or thoughts, notes, and / or observations associated with the event. Buttons allow the user to skip through the user's notes in order. The user looks at what is of interest in the customer history and takes notes on what is of interest (e.g., what may be the root cause) that led to a shared event (i.e., a shared incident). A note-taking engine 320 may be used to receive and maintain event notes and timeline notes in this manner.

[0122] Figure 10 shows an exemplary graphical user interface 1000 according to the present disclosure. An area 1020 (i.e., a journey canvas) is provided that allows the user to create or otherwise construct a timeline (or journey) using events (i.e., selected nodes). The user may select “Add Event” 1030 and then add an event to the timeline or journey being created. The new journey is then created when the user makes the “Apply” selection (not shown). The user may add an event from a displayed timeline (e.g., a first timeline or a second timeline) by selecting “From Timeline” 1032, or may manually select an event (e.g., from a library in storage or from another timeline not displayed on the graphical user interface 1000) by selecting “Manual Selection” 1035. A journey construction engine 330 may be used to create a timeline or journey in this manner.

[0123] By creating a new journey using events selected from one or more journeys, users such as analysts may be able to determine how many people (e.g., customers) have experienced similar incidents or issues, check the demographics of those people (e.g., customers), perform other types of analysis, and thus determine solutions to incidents or issues that many people (e.g., customers) have encountered or may encounter.

[0124] Figure 11 shows an exemplary graphical user interface 1100 as provided in this disclosure. Area 1110, provided to allow the user to use events to create or otherwise construct a timeline (or journey), displays a journey 1115 that is being constructed. Journey 1115 includes events such as event 1120. These events may be based on events in the customer timeline, such as one or more events from timeline 1130.

[0125] Figure 12 shows an exemplary graphical user interface 1200 as provided in this disclosure. Area 1210, provided to enable the user to use events to create or otherwise construct a timeline (or journey), displays a journey 1215 that is being constructed. The journey 1215 includes events, such as event 1230, and time information between events (such as time information 1220). The events and time information may be based, for example, on events in one or more customer timelines.

[0126] Figure 13 shows an exemplary graphical user interface 1300 as provided in this disclosure. Area 1310, provided to allow the user to use events to create or otherwise construct a timeline (or journey), displays a journey 1315 that is being constructed. The journey 1315 includes events such as event 1340 and displays various selectable actions 1342 regarding data surrounding event 1340. These actions 1342 may provide data generated from various customer timelines 1320 and 1330.

[0127] Figure 14 shows an exemplary computing environment 1400 in which exemplary embodiments and aspects may be implemented. While specific embodiments have been described herein, it should be understood that this disclosure can be applied to a wide range of contexts and technical fields beyond those explicitly addressed.

[0128] Furthermore, if the logical operations described herein are implemented in software, the processes can run on any type of computing architecture or platform. For example, referring to Figure 14, an exemplary computing device on which embodiments of the present invention may be implemented is shown. In particular, the system may operate using one or more computing devices, such as computing device 1400 shown in Figure 14. Figure 14 shows an exemplary computing environment on which exemplary embodiments and aspects may be implemented. The computing device environment is merely an example of a preferred computing environment and does not imply any limitation on the scope of use or functionality.

[0129] Numerous other general-purpose or dedicated computing device environments or configurations may be used. Examples of well-known computing devices, environments, and / or configurations that may be suitable for use include, but are not limited to, personal computers, server computers, handheld or laptop devices, multiprocessor systems, microprocessor-based systems, network personal computers (PCs), minicomputers, mainframe computers, embedded systems, and distributed computing environments that include any of the above systems or devices.

[0130] Computer-executable instructions, such as program modules executed by a computer, may be used. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform a specific task or implement a specific abstract data type. Distributed computing environments may be used, in which tasks are performed by remote processing devices linked via a communication network or other data transmission medium. In a distributed computing environment, program modules and other data may reside in both local and remote computer storage media, including memory storage devices.

[0131] Referring to Figure 14, an exemplary system for implementing the embodiments described herein includes a computing device such as computing device 1400. In its most basic configuration, computing device 1400 typically includes at least one processing unit 1402 and memory 1404. Depending on the exact configuration and type of computing device, memory 1404 may be volatile (e.g., random access memory (RAM)), non-volatile (e.g., read-only memory (ROM), flash memory), or any combination of the two. This most basic configuration is shown by the dashed line 1406 in Figure 14.

[0132] The computing device 1400 may have additional features / functions. For example, the computing device 1400 may include, but not limited to, additional storage (removable and / or non-removable) including, magnetic or optical disks or tapes. Such additional storage is shown in Figure 14 by removable storage 1408 and non-removable storage 1410.

[0133] The computing device 1400 typically includes various computer-readable media. These computer-readable media can be any available media accessible by the device 1400, and include both volatile and non-volatile media, and removable and non-removable media.

[0134] Computer storage media include volatile and non-volatile, removable and non-removable media, implemented in any method or technique for storing information such as computer-readable instructions, data structures, program modules, or other data. Memory 1404, removable storage 1408, and non-removable storage 1410 are all examples of computer storage media. Computer storage media include, but are not limited to, RAM, ROM, electrically erasable program read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile disk (DVD) or other optical storage devices, magnetic cassettes, magnetic tapes, magnetic disk storage devices or other magnetic storage devices, or any other media that can be used to store desired information and can be accessed by computing device 1400. Any such computer storage media may be part of computing device 1400.

[0135] The computing device 1400 may include a communication connection 1412 that enables the device to communicate with other devices. The computing device 1400 may also have input devices 1414 such as a keyboard, mouse, pen, voice input device, or touch input device. Output devices 1416 such as a display, speaker, or printer may also be included. All of these devices are well known in the art and do not need to be discussed in detail here.

[0136] In one implementation, the method includes identifying an issue in a customer's timeline, where the timeline includes multiple events; determining the cause of the issue; determining the impact of the issue on other customers; and performing escalation management based on the impact.

[0137] The implementation includes some or all of the following features: The method further includes retrieving timelines from storage before identifying issues. The method further includes generating timelines before identifying issues. The method further includes determining opportunities or risks associated with issues. Performing escalation management based on impact includes generating and outputting deliverables for escalation management. The timelines are based on the customer journey. The method further includes analyzing timelines to identify issues and determine the causes of issues. The method further includes outputting the results of the analysis to a graphical user interface. The method further includes monitoring procedural changes provided by escalation management.

[0138] In one implementation, the method includes identifying issues in a customer's timeline, where the timeline includes multiple events; providing the timeline and issues to the user in a graphical user interface of a computing device; receiving notes from the user in the graphical user interface; annotating the timeline with notes; and performing escalation management based on the issues.

[0139] The implementation includes some or all of the following features: The method further includes providing inline collaboration between users and subject matter experts (SMEs) via computing devices and SME computing devices. The method further includes determining the root cause of an issue. The method further includes determining the impact of an issue on other customers. Determining the impact includes using journey construction. The method further includes retrieving timelines from storage before identifying an issue. The method further includes generating timelines before identifying an issue. The method further includes determining opportunities or risks associated with an issue. Performing escalation management includes generating and outputting deliverables for escalation management. The timelines are based on the customer's journey.

[0140] In one implementation, the method includes providing a first timeline to a computing device, wherein the first timeline includes a first set of events; providing a second timeline to a computing device, wherein the second timeline includes a second set of events; comparing the first timeline to the second timeline to determine a shared incident; determining the cause of the shared incident; determining corrective actions; and outputting the corrective actions.

[0141] The implementation includes some or all of the following characteristics: The first timeline is the timeline of a first customer, and the second timeline is the timeline of a second customer distinct from the first customer. The method further includes receiving the first and second timelines from storage. Providing the first and second timelines includes displaying the first and second timelines on the graphical user interface of a computing device. Determining the cause of a shared incident includes determining one or more patterns in the first and second timelines that led to the shared incident. The method further includes analyzing the shared incident with respect to at least one additional timeline. The at least one additional timeline is the timeline of an additional customer distinct from the first and second customers.

[0142] In one implementation, the method includes retrieving data that includes at least one of the following: events from a customer timeline, information from a customer timeline, patterns from a customer timeline, events from patterns in a customer timeline, or issues related to patterns in a customer timeline; constructing a journey using the retrieved data; and outputting the journey.

[0143] The implementation includes some or all of the following features: The method further includes determining risks or opportunities based on the journey. The method further includes outputting risks or opportunities. The method further includes determining the impact of the journey on other customers. The method further includes performing escalation management based on the journey. The method further includes receiving data from storage. Building the journey is performed by the user via a graphical user interface. The method further includes the user adding events to the journey.

[0144] In one implementation, the system comprises at least one processor and memory that, when executed by at least one processor, stores instructions causing at least one processor to perform the following actions: identify an issue in a customer's timeline, wherein the timeline includes multiple events; determine the cause of the issue; determine the impact of the issue on other customers; and perform escalation management based on the impact.

[0145] The implementation may include some or all of the following features: The instruction may further include, when executed by at least one processor, an instruction that causes at least one processor to retrieve a timeline from storage before identifying an issue. The instruction may further include, when executed by at least one processor, an instruction that causes at least one processor to generate a timeline before identifying an issue. The instruction may further include, when executed by at least one processor, an instruction that causes at least one processor to determine the opportunities or risks associated with an issue. Performing escalation management based on impact includes generating and outputting artifacts for escalation management. The timeline is based on the customer journey. The instruction may further include, when executed by at least one processor, an instruction that causes at least one processor to analyze the timeline to identify an issue and determine the cause of the issue. The instruction may further include, when executed by at least one processor, an instruction that causes at least one processor to output the results of the analysis to a graphical user interface. The instruction may further include instructions that, when executed by at least one processor, cause at least one processor to monitor the procedural changes provided by escalation management.

[0146] In one implementation, the system comprises at least one processor and memory that stores instructions causing at least one processor, when executed by at least one processor, to identify issues in a customer's timeline, wherein the timeline includes multiple events; to provide the timeline and issues to the user in a graphical user interface of the computing device; to receive notes from the user in the graphical user interface; to annotate the timeline with notes; and to perform escalation management based on the issues.

[0147] The implementation may include some or all of the following features: The instructions may further include, when executed by at least one processor, instructions that cause at least one processor to provide inline collaboration between users and subject matter experts (SMEs) via computing devices and subject matter expert (SME) computing devices. The instructions may further include, when executed by at least one processor, instructions that cause at least one processor to determine the cause of an issue. The instructions may further include, when executed by at least one processor, instructions that cause at least one processor to determine the impact of an issue on other customers. Determining the impact may include using journey construction. The instructions may further include, when executed by at least one processor, instructions that cause at least one processor to retrieve a timeline from storage before identifying an issue. The instructions may further include, when executed by at least one processor, instructions that cause at least one processor to generate a timeline before identifying an issue. The instructions may further include, when executed by at least one processor, instructions that cause at least one processor to determine the opportunities or risks associated with an issue. Implementing escalation management involves generating and outputting deliverables for escalation management. The timeline is based on the customer's journey.

[0148] In one implementation, the system comprises at least one processor and a memory that stores instructions causing at least one processor to perform the following actions when executed by at least one processor: to provide a first timeline to a computing device, wherein the first timeline includes a first set of events; to provide a second timeline to a computing device, wherein the second timeline includes a second set of events; to compare the first timeline with the second timeline in order to determine a shared incident; to determine the cause of the shared incident; to determine corrective actions; and to output the corrective actions.

[0149] The implementation may include some or all of the following features: The first timeline is the timeline of a first customer, and the second timeline is the timeline of a second customer distinct from the first customer. The instruction may further include, when executed by at least one processor, instructions to cause at least one processor to receive the first and second timelines from storage. Providing the first and second timelines includes displaying the first and second timelines on the graphical user interface of the computing device. Determining the cause of a shared incident includes determining one or more patterns in the first and second timelines that led to the shared incident. The instruction may further include, when executed by at least one processor, instructions to cause at least one processor to analyze the shared incident with respect to at least one additional timeline. The at least one additional timeline is the timeline of an additional customer distinct from the first and second customers.

[0150] In one implementation, the system comprises at least one processor and memory that stores instructions, when executed by at least one processor, to retrieve data including at least one of events from a customer timeline, information from a customer timeline, patterns from a customer timeline, events from patterns in a customer timeline, or issues related to patterns in a customer timeline; to construct a journey using the retrieved data; and to output the journey.

[0151] The implementation may include some or all of the following features: The instructions may further include instructions that cause at least one processor to determine risks or opportunities based on the journey when executed by at least one processor. The instructions may further include instructions that cause at least one processor to output risks or opportunities when executed by at least one processor. The instructions may further include instructions that cause at least one processor to determine the impact of the journey on other customers when executed by at least one processor. The instructions may further include instructions that cause at least one processor to perform escalation management based on the journey when executed by at least one processor. The instructions may further include instructions that cause at least one processor to receive data from storage when executed by at least one processor. Building the journey is performed by the user via a graphical user interface. The instructions may further include instructions that cause at least one processor to add events to the journey when executed by at least one processor.

[0152] In one implementation, the system comprises an issue identification engine configured to identify issues in a customer's timeline, the timeline including multiple events, an issue recognition engine configured to determine the cause of the issue, an impact determination engine configured to determine the impact of the issue on other customers, and an escalation management engine configured to perform escalation management based on the impact.

[0153] In one implementation, the system comprises: an issue identification engine configured to identify issues in a customer's timeline, where the timeline includes multiple events; and to provide the timeline and issues to the user in a graphical user interface of a computing device; a note-taking engine configured to receive notes from the user in a graphical user interface; a timeline analysis engine configured to annotate the timeline with notes; and an escalation management engine configured to perform escalation management based on the issues.

[0154] In one implementation, the system comprises a computing device configured to receive a first timeline, the first timeline containing a first set of events, and to receive a second timeline, the second timeline containing a second set of events; a timeline analysis engine configured to compare the first timeline with the second timeline and determine the cause of a shared incident; and an escalation management engine configured to determine corrective actions and output corrective actions.

[0155] In one implementation, the system comprises a timeline analysis engine configured to extract data that includes at least one of the following: events from a customer timeline, information from a customer timeline, patterns from a customer timeline, events from patterns in a customer timeline, or issues related to patterns in a customer timeline; and a journey construction engine configured to use the extracted data to construct a journey and to output the journey.

[0156] As used herein, the terms “can,” “may,” “optionally,” “can optionally,” and “may optionally” are interchangeable and mean both cases in which a condition occurs and cases in which a condition does not occur.

[0157] It should be understood that the various techniques described herein may be implemented in relation to hardware components, software components, or, where appropriate, a combination of both. Exemplary types of hardware components that may be used include field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), system-on-a-chip systems (SOCs), and complex programmable logic devices (CPLDs). The methods and apparatus of the subject matter of this disclosure, or particular aspects or parts thereof, may take the form of program code (i.e., instructions) embodied on tangible media such as floppy diskettes, CD-ROMs, hard drives, or any other machine-readable storage media, and when the program code is loaded into and executed by a machine such as a computer, the machine becomes an apparatus for carrying out the subject matter of this disclosure.

[0158] Exemplary implementations may refer to utilizing aspects of the subject matter of this disclosure in the context of one or more standalone computer systems, but the subject matter is not limited thereto and can rather be implemented in connection with any computing environment, such as a network or distributed computing environment. Furthermore, aspects of the subject matter disclosed herein may be implemented in or across multiple processing chips or devices, and similarly, storage may be performed across multiple devices. Such devices may include, for example, personal computers, network servers, and handheld devices. While the subject matter has been described in language specific to its structural features and / or methodological behavior, it should be understood that the subject matter as defined in the attached claims is not necessarily limited to the specific features or behaviors described above. Rather, the specific features and behaviors described above are disclosed as exemplary forms of implementing the claims.

Claims

1. A method for formulating corrective actions, wherein the method is for identifying corrective actions for a shared timeline event within a contact center environment between one or more customers, The computing device obtains a first customer timeline, which includes data of multiple events that occurred chronologically with respect to a first customer, stored in a database, wherein each event includes a timestamp, a specified type, and at least one customer associated with that event. The computing device obtains a second customer timeline, which includes data of multiple events that occurred chronologically with respect to a second customer different from the first customer, stored in the database, wherein each event includes a timestamp, a specified type, and at least one customer associated with the event. The computing device displays the first customer timeline together with the second customer timeline on a graphical user interface. The computing device compares the first customer timeline with the second customer timeline and determines a given event common to both customer timelines as a shared incident. The computing device associates the shared incident common to the first customer timeline and the second customer timeline by specifying the shared customer and relative time position on each timeline via the timestamp associated with the event, The computing device determines one or more patterns that exist in both the first and second customer timelines, which are patterns comprised of one or more events related to the shared incident, selected from a plurality of events included in each of the first and second customer timelines, wherein determining the one or more patterns includes analyzing the shared incident to determine whether the patterns in the first and second customer timelines led to the shared incident, examining each customer's history and transcript, and applying natural language processing to the transcript to identify contextual data. The escalation management engine of the computing device identifies the shared incident as a problematic shared incident as a function of a machine learning model of a machine learning system, using one or more determined patterns, wherein the machine learning model continuously learns the statistical features of events and event patterns that have been identified as problematic. The escalation management engine of the computing device identifies and outputs corrective actions configured to address the root cause of the corrective issues associated with the problematic shared incident, The escalation management engine of the computing device applies the corrective action configured to address the root cause of the corrective issue associated with the problematic shared incident, and the application of the corrective action includes identifying opportunities to improve the interaction by creating deliverables related to the problematic shared incident. The computing device improves the accuracy of the machine learning model by incorporating interactions provided to the machine learning model via the graphical user interface into the machine learning model's output, wherein the interactions include determining the impact of the problematic shared incident, the impact representing the number of customers who experienced the problematic shared incident and the effect of the problematic shared incident on one or more key performance indicators, thereby enhancing the machine learning model's accurate identification of problematic events and mitigating future inaccuracies by the machine learning model. A method that includes this.

2. The method according to claim 1, further comprising determining the shared incident with respect to at least one additional customer timeline.

3. The method according to claim 2, wherein the at least one additional customer timeline is selected from a third customer, and the third customer is different from both the first and second customers.

4. The method according to claim 1, wherein whether the shared incident is common to both customer timelines is determined based on the attributes of the event that is common to both customer timelines.

Citation Information

Patent Citations

  • Extraction device, extraction method, and extraction program

    JP2016038822A

  • Dialogue monitoring and communications system using artificial intelligence based analytics

    JP2020144857A

  • System and method for event data visualization

    US20180129390A1

  • Dialogue monitoring and communications system using artificial intelligence (AI) based analytics

    US20200265483A1