System and method for measuring and optimizing organizational interaction dynamics

Abstract

A system and method are disclosed for measuring, analyzing, and optimizing organizational interaction dynamics as a proxy for inclusion and collaboration. Interactions between individuals are recorded and tagged with demographic attributes (e.g., gender, age, ethnicity, role, location, department) and categories of interest (e.g., innovation, sustainability, safety, production, wellness, mentoring, training, career development). The tagged data are stored in a structured repository and processed using analytics, artificial intelligence, and machine learning to generate inclusion scores, collaboration scores, and other indicators. Outputs include charts, heat maps, dashboards, and compliance reports aligned with standards such as ISO 30415. Embodiments provide real-time monitoring, trend analysis, team formation recommendations, predictive modeling, and automated feedback loops. The disclosed approach enables organizations to identify strengths and gaps, implement corrective actions, and track progress toward more inclusive and collaborative environments.

Description

Docket No. INC-25-01SYSTEM AND METHOD FOR MEASURING AND OPTIMIZING ORGANIZATIONAL INTERACTION DYNAMICSCROSS-REFERENCE TO RELATED APPLICATIONS

[0001] This application claims the benefit of priority to U.S. Provisional Patent Application No. 63 / 684,838, titled “Measurement of Inclusion within an Organization,” filed August 19, 2024, the entire contents of which are hereby incorporated by reference.FIELD OF THE DISCLOSURE

[0002] The present disclosure relates generally to the field of organizational analytics, interaction measurement, and performance optimization. More specifically, it relates to systems and methods for continuously measuring, analyzing, and improving organizational interaction dynamics including, but not limited to, inclusion and collaboration using multi-source data capture, automated tagging, artificial intelligence (Al), and machine learning (ML) to quantify, visualize, and optimize behaviors, connections, and participation patterns among individuals and teams.BACKGROUND

[0003] Drawbacks of Poor Inclusion - In many organizations, the absence of inclusion manifests not simply as an abstract cultural shortfall but as a measurable operational and financial liability. Alack of inclusion may result in certain individuals or groups being consistently excluded from critical meetings, decision-making processes, or informal networks where key opportunities are discussed. Such exclusion often occurs unintentionally through reliance on habitual collaboration patterns, geographic proximity bias, or preferential communication with familiar colleagues. The costs of exclusion are multifold:Docket No. INC-25-01• Reduced Innovation - Studies consistently show that heterogeneous groups generate more creative and higher-quality solutions than homogeneous ones; when certain perspectives are excluded, the organization forfeits potential innovations.• Lower Engagement and Morale - Employees who feel their input is disregarded are less motivated to contribute proactively, resulting in diminished discretionary effort.• Increased Turnover - Employees who perceive persistent exclusion are more likely to leave, taking institutional knowledge with them and increasing recruitment and onboarding costs. In competitive talent markets, this can lead to significant replacement expense and operational disruption.• Reputational Damage - External stakeholders increasingly evaluate organizations based on their inclusivity and diversity track records. Poor inclusion can harm brand equity, investor confidence, and customer loyalty.

[0004] Drawbacks of Poor Collaboration - Collaboration failures similarly create substantial measurable inefficiencies. In modem organizational contexts, work often spans multiple functions, geographies, and disciplines. A lack of effective collaboration leads to:• Duplicated Effort - Multiple teams unknowingly working on similar problems without knowledge-sharing waste time and resources.• Extended Project Timelines - Work handoffs slow down when communication is incomplete or delayed, often resulting in missed deadlines.• Poor Knowledge Transfer - Information silos prevent lessons learned from propagating, causing recurring mistakes and reinvention of solutions.• Reduced Problem-Solving Quality - Without collaboration, solutions lack the benefit of diverse perspectives, increasing the likelihood of suboptimal outcomes.• Employee Frustration - Individuals working in isolation or in competitive rather than cooperative environments report higher stress levels, lower job satisfaction, and are more prone to burnout.

[0005] The Inclusion-Collaboration Interdependency - While inclusion and collaboration are distinct constructs, they are mutually reinforcing. High inclusion ensures that diverse voices are present and empowered to contribute; high collaboration ensures those voices are integrated into collective action. An organization with strong collaboration but low inclusion risks amplifying only a narrow subset of voices. Conversely, an organization with strong inclusion but poorDocket No. INC-25-01 collaboration may generate ideas that never progress to impactful execution. The present invention recognizes and operationalizes this interdependency by measuring and optimizing both dimensions in parallel.

[0006] Organizational network analysis (ONA) systems and collaboration analytics platforms have long sought to measure relationships and communication flows within organizations. These systems often rely on metadata from emails, calendar events, or meeting records to quantify the volume or frequency of interactions. However, conventional ONA solutions typically focus on productivity, efficiency, or structural network health and do not address inclusion metrics. Similarly, diversity, equity, and inclusion (DEI) platforms often depend on surveys or periodic self-reported feedback, which can be biased, low-frequency, and disruptive to workflows.

[0007] Some tools attempt to infer engagement or collaboration from interactions, but these are generally limited to single-channel data sources, basic activity counts, or static organizational charts. They rarely integrate multi-modal interaction capture, demographic or role-based enrichment, advanced context tagging, privacy-preserving computation, and direct linkage to business key performance indicators (KPIs) in a single unified framework.

[0008] The present invention departs from prior art by using interactions as a proxy for inclusion and / or collaboration, operationalized through a multi-modal capture system that aggregates face-to-face, digital, sensor-based, and biometric interaction data. These raw interactions are enriched with demographic and organizational attributes, tagged using Al-driven classifiers and natural language processing (NLP) context extraction, and processed by machine learning models to compute both inclusion scores and collaboration scores. This dual-scoring approach allows identification of collaboration patterns, silos, and gaps, as well as inclusion or exclusion trends, all from the same underlying interaction dataset, without relying solely on surveys or manual reporting.

[0009] Furthermore, unlike prior art that treats inclusion and collaboration as separate analytical domains, the present invention integrates them into a single analytics pipeline with predictive and prescriptive capabilities. This includes automated team formation optimization, KPI alignment, longitudinal score tracking with temporal weighting, and multi-layer privacy safeguards (anonymization, pseudonymization, differential privacy). The invention thereby provides a scalable, continuous, and unbiased measurement framework that is both technically robust and operationally practical for real-time organizational insights.Docket No. INC-25-01

[0010] Importance of Quantification and Continuous Measurement - Historically, organizations have relied on annual or infrequent surveys to gauge inclusion or collaboration. These snapshots fail to capture dynamic changes in organizational behavior, particularly in times of restructuring, crisis, or rapid growth. Moreover, surveys are inherently subject to self-reporting bias and low participation rates. The absence of continuous, objective measurement allows inclusion and collaboration deficits to persist unnoticed until they manifest in costly outcomes such as employee attrition, failed projects, or reputational crises. Quantifying organizational interaction dynamics enables:• Trend Monitoring - Identifying early warning signals of declining inclusion or collaboration before they become systemic issues.• Targeted Intervention - Pinpointing specific teams, locations, or functions that require focused support.• Benchmarking - Comparing inclusion and collaboration performance across departments or industry peers.• Accountability and Reporting - Providing evidence-based metrics to boards, regulators, and environmental, social, and governance (ESG) reporting frameworks.

[0011] Economic and Innovation Costs of Deficiencies - Empirical research and internal organizational analyses indicate that turnover costs alone can exceed 150% of an employee’s annual salary, with the figure rising for specialized or senior roles. Poor collaboration has been linked to project delays of 20-40%, with direct financial consequences from missed market windows. In high-innovation environments, exclusion of diverse contributors has been shown to correlate with reduced patent filings, fewer product innovations, and lower overall research and development (R&D) return on investment. The combined effect of low inclusion and poor collaboration can erode an organization’s competitive position in as little as 12-18 months.

[0012] Critique of Prior Art - Surveys and Manual Audits - A large portion of prior art in inclusion and collaboration measurement relies heavily on survey-based instruments. These are inherently limited:• Low Temporal Resolution - Annual or semi-annual surveys cannot capture short-term fluctuations or the impact of specific events (e.g., leadership changes, mergers).• Response Bias - Individuals may tailor responses to align with perceived organizational expectations rather than their true experiences.Docket No. INC-25-01• Coverage Gaps - Surveys may fail to capture the experiences of individuals who choose not to respond, often those most affected by exclusion.

[0013] Critique of Prior Art - Metadata-Only Analytics - Some systems attempt to infer collaboration from communication metadata such as email counts or meeting volumes. While these approaches offer continuous data, they lack contextual richness:• No Sentiment or Tone Analysis - An increase in message volume may indicate conflict rather than productive collaboration.• Channel Narrowness - Focusing on a single platform (e.g., email) ignores substantial interaction occurring via chat, video, or in-person meetings.• No Role or Demographic Awareness - Without linking participants to organizational attributes, such systems cannot measure inclusion accurately.

[0014] Critique of Prior Art - Diversity Statistics Without Behavioral Data - Other prior systems measure diversity through demographic representation alone. This approach assumes that a demographically diverse organization is inherently inclusive and collaborative. In practice, without measuring behavioral interactions, organizations may have diversity “on paper” but operate in ways that marginalize certain groups.

[0015] Technical Gaps in Prior Art - Existing tools rarely integrate multi-source interaction data in real-time, apply AI / ML classification for nuanced tagging, implement bias mitigation algorithms, and link metrics directly to organizational KPIs. Furthermore, prior systems often lack feedback loops that deliver actionable recommendations, resulting in measurement without meaningful improvement.

[0016] Lead-In to the Invention - The present invention overcomes these limitations through a unified architecture capable of:• Continuous Multi-Source Data Capture across all major communication and collaboration platforms.• AI / ML-Based Event Tagging for contextual classification and sentiment detection.• Bias Mitigation to ensure equitable representation of all participants and interaction types.• KPI Mapping to directly link interaction metrics with business outcomes.• Predictive and Prescriptive Analytics to identify emerging risks and recommend targeted interventions.Docket No. INC-25-01

[0017] By delivering a continuously updated, objective, and context-aware measurement of inclusion and collaboration, using recorded interactions as a direct behavioral proxy, the system enables organizations to proactively address interaction gaps and sustain high-performance, equitable environments.SUMMARY

[0018] The present disclosure provides, in various embodiments, a system, method, and non- transitory computer-readable medium for measuring, analyzing, and optimizing organizational interaction dynamics, wherein recorded interactions between individuals within an organization are used as a proxy for inclusion and collaboration. This approach enables the quantification of social and professional exchanges that occur across various channels, both digital and physical, providing a robust, data-driven foundation for assessing and improving organizational culture.

[0019] In one embodiment, the invention comprises a computing environment that includes at least one processor, one or more memory modules, and network interfaces configured to capture and process interaction data. The interaction data may include, but is not limited to, electronic communications (e.g., emails, instant messages, videoconferences, social media platform messages and posts), in-person meeting attendance, project management activity, and social engagement indicators. These interactions may be recorded passively via integration with organizational systems or actively through user inputs, surveys, or tagging interfaces.

[0020] The captured interactions are enriched with contextual metadata, which may include, but is not limited to, participant identifiers, timestamps, duration, communication medium, subject matter tags, sentiment indicators, and associated projects or teams. In certain embodiments, the system also links demographic or role-based information for each participant, enabling the measurement of inclusion by analyzing interaction patterns across diverse groups, as well as the measurement of collaboration by evaluating frequency, reciprocity, and multi-party engagement.

[0021] The invention further includes an interaction tagging module that classifies interactions into relevant categories. The categories may include, but are not limited to, workstream -related collaboration, mentorship, cross-functional engagement, social inclusion, knowledge sharing, and innovation-focused exchanges. Tagging may be automated via Al and NLP techniques, manuallyDocket No. INC-25-01 performed by users, or derived from hybrid methods.

[0022] A data analytics and scoring module processes the tagged interaction data to generate quantitative measures such as an Inclusion Score and a Collaboration Score. These scores may be calculated using statistical, heuristic, and Al-based algorithms that consider both the volume and distribution of interactions, as well as qualitative factors such as sentiment, engagement depth, and network reach. In certain embodiments, the scoring algorithms are configurable to align with organizational priorities or industry-specific benchmarks.

[0023] The system may further comprise a reporting and visualization module that generates dashboards, charts, heat maps, and trend analyses. These visualizations may be filtered by time range, organizational unit, demographic segment, or interaction type. For example, a collaboration heat map may illustrate interdepartmental connectivity, while an inclusion trend chart may reveal changes in engagement patterns for underrepresented groups. Reports may be exported for compliance purposes, leadership reviews, or public disclosures, thereby supporting transparency and accountability.

[0024] In some embodiments, the invention integrates a recommendation engine that uses Al and machine learning to suggest targeted interventions for improving inclusion and collaboration. For example, the engine may recommend cross-team introductions, mentorship pairings, targeted training programs, or communication policy adjustments based on detected patterns or anomalies in interaction data.

[0025] The invention may be implemented in cloud-based, on-premises, or hybrid deployment models, and is compatible with common enterprise platforms. Application programming interfaces (APIs) may be provided for integration with third-party systems such as human resources information systems (HRIS), project management tools, communication platforms, and business intelligence (BI) suites.

[0026] In certain embodiments, the system also supports a scenario simulation capability, wherein users can model the potential impact of changes, such as reorganizations, new team formations, or policy implementations, on inclusion and collaboration scores. This feature allows decision-makers to assess possible outcomes before implementing changes in the real environment.

[0027] The invention supports longitudinal analysis, enabling organizations to track changes in inclusion and collaboration overtime. This may include the ability to correlate scores with KPIsDocket No. INC-25-01 such as employee retention rates, innovation outputs, customer satisfaction scores, and financial performance metrics.

[0028] In an exemplary embodiment, the invention comprises the following primary modules, which may be implemented in any combination and sequence depending on deployment needs:• Data Capture Module - Integrates with communication systems and logs interactions, including both structured and unstructured data.• Metadata Enrichment Module - Adds context to interactions using organizational data sources and optional Al inferences.• Interaction Tagging Module - Classifies interactions into relevant categories for scoring and analysis.• Analytics and Scoring Module - Calculates inclusion and collaboration scores using configurable algorithms.• Visualization and Reporting Module - Produces dashboards, reports, and visual summaries of metrics and trends.• Recommendation Engine - Generates targeted, actionable suggestions for improving scores.• Simulation and Modeling Module - Predicts outcomes of organizational changes before they are implemented.

[0029] Text-Described System Diagram: In one representative embodiment, the system architecture may include:• A data acquisition layer configured to connect to enterprise communication systems, physical meeting sensors, and external collaboration tools.• A data processing layer that includes extract-transform -load (ETL) pipelines, natural language processing engines, and Al classification models.• A data storage layer comprising relational databases for structured metadata and data lakes for unstructured interaction records.• An application logic layer that executes scoring algorithms, generates recommendations, and manages access control.• A presentation layer providing web-based and mobile user interfaces for analytics dashboards, reports, and alerts.• An integration layer with APIs for interoperability with HRIS, BI tools, and otherDocket No. INC-25-01 enterprise systems.

[0030] The disclosed invention is designed for scalability, security, and adaptability. In certain embodiments, security measures may include, but are not limited to, encryption of data in transit and at rest, role-based access control, audit logging, and compliance with relevant data privacy regulations such as general data protection regulation (GDPR) and California consumer privacy act (CCPA).

[0031] Advantages of the present invention over prior art include, but are not limited to, the ability to:• Quantify inclusion and collaboration using objective interaction data rather than subjective surveys alone.• Link interaction metrics directly to organizational KPIs.• Provide real-time or near-real-time feedback to decision-makers.• Support proactive interventions via Al-driven recommendations.• Adapt scoring models to fit diverse organizational contexts and goals.• Integrate seamlessly with existing enterprise systems without disrupting workflows.

[0032] The foregoing summary is intended to provide an overview of the invention and is not intended to be limiting. The various features described herein may be used alone or in combination, and not all features are required in all implementations. The steps of any described method may be performed in any order unless otherwise specified.BRIEF DESCRIPTION OF THE DRAWINGS

[0033] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments of the present disclosure and, together with the description, serve to explain the principles of the invention. It will be understood that the figures are presented for illustrative purposes only, and the invention is not limited to the specific embodiments shown. The components illustrated in the figures may be implemented in various ways, and their arrangement may vary without departing from the scope of the invention.Docket No. INC-25-01

[0034] FIGURE 1 is a schematic diagram illustrating an exemplary system architecture for measuring and optimizing organizational interaction dynamics, wherein interactions between individuals are captured, processed, tagged, analyzed, and output through analytic dashboards, the system including, but not limited to, data source connectors, ingestion and preprocessing engines, tagging and classification modules, central interaction databases, analytics and artificial intelligence (Al) engines, scoring and key performance indicator (KPI) mapping modules and visualization and reporting interfaces.

[0035] FIGURE 2 is a process flow diagram illustrating data tagging and category assignment, wherein each captured interaction is tagged with demographic attributes (including, but not limited to, gender, age, ethnicity, role, location, and department) and linked to organizational and employee categories of interest, enabling multifactor analysis and targeted interventions.

[0036] FIGURE 3 is an entity-relationship (ER) diagram illustrating exemplary database structures and relationships within the system for measuring and optimizing organizational interaction dynamics. The diagram depicts the Interaction Event table, including entities such as EventID, PersonlD Source, PersonlD Target, In teraction Type, and Timestamp, as well as associated tagging attributes. These entities proceed through tagging with a TagID to enable the interaction attributes to be tagged or classified by the tagging process described herein. After tagging, the Scoring Record is shown with fields including Confidence Score, InclusionScore, CollaborationScore, and CompositelnteractionScore. The KPI Linking Stage is also illustrated, mapping interaction-derived scores to organizational key performance indicators (KPIs) through fields such as KPI Link ID, KPI Name, KPI Value, and KPI Period. Relationships between these entities are represented through foreign key connections, enabling structured tracking from raw interactions through scoring and KPI alignment.

[0037] FIGURE 4 is a schematic dashboard output showing exemplary visualizations generated by the system, including, but not limited to, heat maps of interaction patterns, trend graphs of inclusion and collaboration scores, and interactive drill-down capabilities for reviewing tagged interactions and associated recommendations.

[0038] FIGURE 5 is a schematic feedback loop diagram illustrating how system outputs, such as inclusion and collaboration scores, are used to trigger corrective actions, training, or policy changes, and how the outcomes of those interventions are fed back into the analytics engine for iterative improvement over time.Docket No. INC-25-01DEFINITIONS AND ACRONYMS

[0039] The following definitions are provided to promote clarity and consistency in the interpretation of the terms used herein. Unless otherwise specified, these definitions apply throughout the specification and claims. In the event of any inconsistency between these definitions and the common understanding of the terms, the definitions provided herein shall prevail for purposes of this disclosure. The terms defined herein are non-limiting, and other definitions may be adopted in other embodiments without departing from the scope of the invention.

[0040] Analytics Engine - A software component or set of components configured to process interaction data, demographic data, and organizational structure data to calculate metrics, scores, correlations, and trend analyses related to inclusion, collaboration, and other organizational interaction dynamics.

[0041] Collaboration - The extent to which individuals in an organization work together effectively to achieve shared goals, characterized by coordinated communication, knowledge sharing, and joint problem-solving across functional or hierarchical boundaries.

[0042] Collaboration Score - A computed metric representing the degree of collaboration within an organization or subgroup, calculated using one or more algorithms that process tagged interaction data, task interdependence data, and performance outcome data. The collaboration score may be expressed in a similar manner to the inclusion score.

[0043] Correlation Analysis - A statistical method for identifying and quantifying the relationship between two or more variables, such as inclusion score and employee turnover rate.

[0044] Demographic Data - Information describing participant attributes, including, but not limited to, age, gender, ethnicity, role, tenure, department, location, and educational background. Such data may be anonymized or pseudonymized in compliance with applicable privacy regulations.

[0045] Inclusion - The extent to which individuals in an organization feel valued, respected, and integrated into collaborative processes, decision-making, and information flows, regardless of demographic, experiential, or positional differences.Docket No. INC-25-01

[0046] Inclusion Score - A computed metric representing the degree of inclusion within an organization or subgroup, calculated using one or more algorithms that process tagged interaction data, participant demographic data, and organizational context data. The inclusion score may be expressed as an absolute value, a percentile, a trend index, or any other statistically relevant format.

[0047] Interaction - Any exchange of information, data, or communication between two or more participants within an organization, including, but not limited to, emails, instant messages, voice calls, video conferences, social media platform messages and posts, in-person meetings, project management updates, and shared document edits.

[0048] Interaction Data - Data derived from organizational communication and activity sources, which may include metadata (e.g., time, duration, participants), content (e.g., message text, document changes), and context (e.g., meeting purpose, project association).

[0049] Key Performance Indicator - A quantifiable measure used to evaluate the success of an organization in achieving specific objectives, such as innovation rate, employee retention, project completion time, and customer satisfaction.

[0050] Machine Learning Model - A computational model trained on historical interaction data to predict or classify interaction attributes, participant behaviors, or organizational outcomes

[0051] Non-Transitory Computer-Readable Medium - Any tangible storage medium capable of storing instructions that, when executed by one or more processors, cause the processors to perform methods disclosed herein. Examples include magnetic disks, optical disks, flash memory, and solid-state drives.

[0052] Organization - As used herein, "organization" refers to any structured group of individuals engaged in coordinated activities toward shared objectives, including, but not limited to, corporations, partnerships, government agencies, educational institutions, non-profit entities, teams, committees, and cross-functional working groups. An organization may be formal or informal, hierarchical or flat, and may operate physically, virtually, or in hybrid configurations.

[0053] Organizational Interaction Dynamics - The patterns, frequency, quality, and context of interactions between members of an organization, as measured and analyzed using the methods described herein. Such dynamics may include, but are not limited to, collaboration, inclusion, information exchange, mentorship, feedback, and decision-making interactions.Docket No. INC-25-01

[0054] Organizational Structure Data - Information describing the hierarchical or network relationships within an organization, including reporting lines, team membership, cross-functional linkages, and governance structures.

[0055] Tag Dictionary - As used herein, the term tag dictionary refers to a structured repository that defines and standardizes the set of permissible tags for categorizing interactions, participants, or related data elements within the system. The tag dictionary may include, for each tag, a name, a description, a category grouping, and any applicable constraints on use. In certain embodiments, the tag dictionary may also include synonyms, aliases, or mappings to ensure consistent tagging across multiple users, data sources, or automated processes. The tag dictionary functions as a controlled vocabulary, providing a common reference that enables accurate classification of interactions, integration with demographic attributes and organizational categories, and reliable generation of collaboration scores, inclusion scores, and other metrics.

[0056] Tagged Interaction - An interaction that has been analyzed and labeled with one or more categorical descriptors (tags) based on predefined or dynamically generated criteria, such as type, context, tone, participant roles, or subject matter.

[0057] Tagging Engine - A software component or set of components configured to apply tags to interactions using rule-based logic, Al, ML, or hybrid approaches, based on the interaction content, metadata, and context.

[0058] Visualization Dashboard - A user interface for presenting computed metrics and analysis results, including, but not limited to, charts, graphs, heat maps, and trend lines, which may support filtering, drill-down, and data export functionality.

[0059] For ease of reference, the table below lists certain acronyms used throughout this disclosure, along with their corresponding full terms. These acronyms are provided for convenience and clarity, and their inclusion should not be construed as limiting the scope of the invention.Docket No. INC-25-01Docket No. INC-25-01DETAILED DESCRIPTION

[0060] The present invention provides a comprehensive system and method for measuring, analyzing, and optimizing organizational interaction dynamics, wherein such dynamics are utilized as a proxy for assessing both inclusion and collaboration within an organization. This dual-focus approach allows the invention to quantify not only the diversity and equity dimensions associated with inclusion, but also the efficiency, innovation potential, and operational cohesion associated with collaboration. The invention further enables the capture, processing, and interpretation of structured and unstructured interaction data between members of an organization in order to generate metrics, visualizations, and recommendations that can improve organizational health and performance.

[0061] The system may include, but is not limited to, a plurality of hardware and software modules configured to:• Record and classify interaction events between individuals;• Enrich such records with demographic, role-based, and contextual metadata;• Process the enriched dataset through analytics and artificial intelligence (Al) pipelines;• Generate inclusion and collaboration scores; and• Deliver actionable recommendations and visual outputs via dashboards, reports, or integrated enterprise systems.

[0062] Interactions may include, but are not limited to, communications (e.g., email, chat, calls, video conferences, organization intranet and social media platform posts and reactions), coattendance in meetings, shared document editing, project management updates, and participation in enterprise social platforms. These interactions may be logged from multiple sources and normalized into a unified schema that supports downstream analytics.Docket No. INC-25-01

[0063] The system’s primary innovation lies in its use of interactions as a quantifiable, objective, and scalable proxy for both inclusion and collaboration. While inclusion reflects the extent to which all members feel welcomed, respected, and able to contribute, collaboration focuses on the efficiency, frequency, and value of cooperative engagements. By combining both measures into an integrated interaction framework, the invention enables organizations to diagnose issues, set targets, and monitor progress over time.

[0064] The invention is adaptable to organizations of any size, industry, or geographical scope. Configurable tagging and classification rules ensure that relevant interaction categories and KPIs can be tailored to reflect sector-specific norms or strategic objectives. For example, a healthcare organization may prioritize interdepartmental collaboration, whereas a technology startup may focus on cross-functional innovation sprints.

[0065] The system further supports secure, privacy-preserving operation by implementing role-based access controls, encryption-at-rest and in-transit, anonymization or pseudonymization of sensitive data, and configurable retention policies compliant with relevant regulations.

[0066] The data collection and analysis process may be continuous, periodic, or triggered by specific organizational events (e.g., mergers, restructurings, policy changes). The results can be incorporated into annual inclusion reports, ESG disclosures, innovation performance reviews, and leadership assessments.System Architecture Overview

[0067] FIGURE 1 is a schematic diagram illustrating an exemplary architecture for implementing the invention’s integrated system for measuring and optimizing organizational interaction dynamics, wherein organizational interactions are processed as a proxy for both inclusion and collaboration metrics. The architecture comprises multiple data source connectors (110), an ingestion and preprocessing engine (120), a tagging and classification module (130), a central interaction database (140), an analytics and Al engine (150), a scoring and KPI mapping module (160), and visualization and reporting interfaces (170). Each of these modules is designed to interoperate through secure communication protocols, including APIs, encrypted message queues, and data pipelines, thereby ensuring data integrity and scalability across enterprise environments.Docket No. INC-25-01

[0068] In certain embodiments, FIGURE 1 may further integrate with human resource information systems (HRIS), performance management tools, and enterprise communication platforms (e.g., email, instant messaging, meeting platforms, and project management systems). Such integrations expand the coverage of data sources and enrich the contextual basis for analysis. For example, HRIS integration may supply demographic or role-based attributes to augment interaction data, while performance management platforms may provide organizational priority indicators against which collaboration and inclusion can be assessed.

[0069] The architecture of FIGURE 1 also supports modular deployment, allowing organizations to adopt the system incrementally. For instance, some embodiments may deploy only the ingestion engine and tagging module to establish foundational data capture, whereas others may enable the full analytics, scoring, and reporting stack for advanced insights and compliance reporting. In still further embodiments, the system may be deployed in a cloud-native environment to enable elastic scaling and global accessibility.Core Components and Functional Mapping

[0070] The table below provides a non-limiting mapping between the system’s core components and their primary functions. This mapping is provided for illustrative purposes and should not be construed as limiting the scope of the claims.Docket No. INC-25-01

[0071] The architecture is modular to support scalability, fault tolerance, and deployment flexibility (e.g., on-premises, cloud-native, or hybrid models).

[0072] Data flow begins when connectors ingest interaction events from multiple systems. The ingestion engine applies preprocessing steps including deduplication, time zone normalization, and enrichment with metadata such as role, team, and location.

[0073] The tagging module applies deterministic and probabilistic classification to assign interaction types (e.g., mentoring, brainstorming, project coordination). The classification logic may include, but is not limited to, NLP, supervised learning, and rule-based keyword matching.

[0074] The analytics engine computes intermediate metrics (e.g., interaction diversity index, cross-team collaboration ratio) which are then fed into the scoring module. KPI mapping allows organizations to connect these scores to strategic goals, such as innovation rate, employee retention, or operational efficiency.

[0075] The visualization layer delivers outputs via web-based dashboards, periodic Portable Document Format (PDF) reports, and machine-readable exports for integration into corporate analytics environments.

[0076] The present invention may include, but is not limited to, a comprehensive data model designed to store, relate, and query interaction data for the purposes of calculating inclusion and collaboration scores. The schema supports both logical and physical representations to ensure portability across different database technologies.

[0077] In certain embodiments, the logical schema comprises primary entities including:• Person: representing individual members of the organization.• Team: representing functional or project-based groupings.• Interaction Event: representing a single measurable interaction between individuals.• Interaction Tag: representing one or more categories applied to an interaction event.Docket No. INC-25-01• Score Record: representing calculated inclusion and collaboration scores over a given time window.• KPI Link: representing the mapping between calculated scores and organization-specific key performance indicators.

[0078] The physical schema may be implemented in a relational database such as PostgreSQL or MySQL, or in a document-based database such as MongoDB for organizations requiring flexible document structures. The schema design ensures referential integrity while allowing for denormalization in high-performance analytics contexts.Tagging Taxonomy and Hierarchy

[0079] As illustrated in FIGURE 2, the system employs a structured process flow for data tagging and category assignment. In this exemplary embodiment, each captured interaction, whether originating from digital communication channels such as email, instant messaging, or project management tools, or from in-person attendance and scheduling systems, is ingested and enriched with metadata. This metadata includes demographic attributes associated with the participating individuals, such as, but not limited to, gender, age, ethnicity, job role, geographic location, and department. Concurrently, the system associates the interaction with one or more organizational and employee categories of interest, such as innovation, safety, sustainability, wellness, or mentoring. By assigning both demographic attributes and organizational categories in parallel, the system enables multifactor analysis of collaboration and inclusion patterns. The tagged interactions may then be stored in a relational database or equivalent data repository, allowing queries across multiple dimensions. For example, an administrator may identify whether a decline in safety-related discussions corresponds to specific demographics, or whether mentoring opportunities are equally distributed across regions and job levels. The structured tagging and assignment process illustrated in FIGURE 2 thus provides the foundation for targeted interventions, predictive analytics, and continuous monitoring of organizational interaction dynamics.

[0080] The tagging system may include, but is not limited to, a multi-level hierarchical taxonomy that enables both fine-grained classification and high-level aggregation of interaction types. At the top level, categories may include, but are not limited to:• Collaboration-Oriented Interactions (e.g., project planning, cross-team brainstorming)Docket No. INC-25-01• Inclusion-Oriented Interactions (e.g., mentoring, onboarding support, inclusion forums)• Operational Interactions (e.g., task assignments, performance reviews)• Innovation Interactions (e.g., hackathons, research collaboration)

[0081] Each top-level category may include multiple subcategories and tagging rules. For example, “Collaboration-Oriented Interactions” may include subcategories such as but bot limited to:• Cross-Functional Meeting• Joint Problem-Solving• Co-Authoring Deliverables

[0082] Tags may be applied through:• Rule-based deterministic tagging (e.g., if the meeting title contains “brainstorm” then tag as “Innovation: Brainstorming Session”)• Probabilistic Al tagging (e.g., NLP-based classifier assigning probability scores to categories)• Hybrid tagging (rule-based filtering followed by Al confidence scoring)

[0083] In certain embodiments, the system employs a tag dictionary, which serves as a structured reference of permissible tags for classifying interactions. The tag dictionary ensures consistent application of categories and attributes (e.g., organizational priorities, employee focus areas, demographics), enabling reliable tagging across diverse data sources and supporting accurate calculation of collaboration and inclusion metrics.

[0084] The tagging hierarchy and identification (ID) is stored in a Tag Dictionary table with attributes such as TagID, ParentTagID, TagName, Description, and TagType. This structure allows recursive queries to roll up interaction counts or scores to any level of the taxonomy.

[0085] Pseudocode for interaction tagging may be as follows: def tag interaction(interaction): tags = [] if 'patent' in interaction, content. lower(): tags.append('Innovation') if interaction. duration > 30 and interaction. channel == 'Meeting': tags.append('Collaboration lntensive') if interaction. parti cipant role == 'Manager' and 'training' in interaction.content.lowerQ:Docket No. INC-25-01 tags.append('Mentoring') return tagsThis pseudocode is illustrative and may be extended with NLP -based classification and ML-driven category prediction.Structured Query Language (SQL) Database Design

[0086] FIGURE 3 is a database entity-relationship (ER) diagram illustrating one embodiment of the invention’s relational schema. The schema defines relationships between Person, Interaction Type, Tag, Score Record, and KPI Link tables. Foreign keys (FKs) enforce referential integrity, while indexed timestamp fields enable efficient time-window queries.

[0087] In one embodiment, the Interaction Event table may include, but is not limited to, the following fields:• EventID_(PK (Primary Key))• PersonlD Source (FK to Person table)• PersonlD Target (FK to Person table)• Timestamp• Interact onType• ContextMetadata JavaScript Object Notation (JSON)• TagID (FK to Tag Dictionary)

[0088] The Score Record table may include, but is not limited to, the following fields:• Confidence Score (for Al-tagged events)• ScorelD (PK)• PersonlD (FK to Person)• TimePeriodStart• TimePeriodEnd• InclusionScore• Collaboration Score• CompositelnteractionScore (calculated metric)

[0089] The KPI Link table may store:• KPI Link ID (PK)• KPI_NameDocket No. INC-25-01• ScorelD (FK to Score Record)• KPI Value• KPI Period

[0090] Referring now to FIGURE 3, there is shown an exemplary entity-relationship (ER) diagram illustrating the structured database design for implementing the system of the present invention. In certain embodiments, an Interaction Event table is employed to capture the essential elements of organizational interactions, including but not limited to: a unique EventID (primary key), the PersonlD Source (foreign key referencing the person table), the PersonlD Target (foreign key referencing the Person table), the InteractionType (e.g., message, meeting, post, file share, or other event), and a Timestamp representing the temporal occurrence of the interaction. Each record is tagged with a TagID (foreign key referencing to a tag dictionary) to enable the interaction attributes to be tagged or classified by the tagging process described herein.

[0091] The Interaction Event records are linked to a Score Record table, wherein event-level scores are generated and stored. Non-limiting examples of these fields include a ConfidenceScore (indicating reliability of Al-based tagging), an InclusionScore, a CollaborationScore, and a CompositelnteractionScore which provides a unified measurement derived from multiple metrics.

[0092] The Score Record may then be associated with a KPI Link Stage, wherein the system maps derived scores to organizational key performance indicators (KPIs). As illustrated, the KPI Link Stage includes fields such as KPI Link ID (primary key), KPI Name (e.g., including, but not limited to, innovation score, safety metrics, employee retention, project delivery time, training completion), KPI Value, and KPI Period. This relational structure enables longitudinal analysis of how micro-level interactions affect macro-level business outcomes, thereby operationalizing the measurement of inclusion and collaboration within an enterprise context.

[0093] In one embodiment, real-time ingestion from streaming communication platforms (e.g., Microsoft Teams™, Slack™) is implemented using a message queue (e.g., Apache Kafka®) to ensure scalability and reliability. The queue holds serialized interaction payloads in JSON format. A consumer service deserializes each payload, applies initial metadata enrichment (timestamp normalization, participant ID mapping), and stores the enriched payload into the Raw interactions table. Sample pseudocode for the consumer service: for message in kafka_consumer: interaction = j son. loads(message. value)Docket No. INC-25-01 interaction['normalized_timestamp'] = normalize_time(interaction['timestamp']) interact on['participant_ids'] = map_participants(interaction['parti cipants']) save to db ('Raw Interact ons' , interact on)This approach decouples the ingestion layer from the analytics engine, allowing for fault -tolerant processing and flexible scaling.

[0094] In one implementation, the Interactions table contains fields such as Interact on_ID (PK), Timestamp, Channel, Duration, Participants^, Tags[], and Score lD (FK). The Participants table includes Participant ID (PK), Name, Department, Role, and linked Demographics such as Age Group, Gender, Ethnicity, and Location. The Tags table maps each interaction to one or more categories (e.g., Innovation, Wellness, Safety), with each tag linked via a Tag_ID. The Scores table stores calculated metrics per interaction or aggregated per participant or department, including Inclusion Score, Collaboration Score, Category Specific Score, and Date Range. Sample SQL to retrieve average inclusion score for a given department over the last quarter:SELECT Department, AVG(Inclusion Score) AS Avg ScoreFROM ScoresJOIN Participants ON Scores.Participant ID = Participants. Participant IDWHERE Department = 'R&D'AND Date >= DATEADD(quarter, -1, GETDATEQ)GROUP BY Department;Implementation Notes

[0095] The schema supports partitioned tables for high-volume organizations, enabling performance optimization for queries on recent data while retaining historical records in archived partitions.

[0096] In some embodiments, the database layer may integrate with an online analytical processing (OLAP) cube for multidimensional analysis, allowing slice-and-dice queries across dimensions such as time, team, role, geography, and interaction type.

[0097] Data integrity may be preserved via periodic batch validation jobs, which may include, but are not limited to, orphan record detection, tag consistency checks, and KPI linkage verification.Docket No. INC-25-01

[0098] The Structured Query Language (SQL) schema is designed for extensibility, allowing future addition of new interaction categories, scoring algorithms, and KPI types without requiring disruptive migrations.AI / ML Processing Pipeline

[0099] In one embodiment, the Al / ML pipeline comprises the following stages:1. Data Ingestion Layer: Captures interaction event data from multiple sources, which may include, but are not limited to, email metadata, calendar invites, chat logs, meeting transcripts, project management system updates, and manual user entries.2. Pre-Processing Module: Performs data cleaning, timestamp normalization, entity resolution (e.g., matching multiple identifiers to a single PersonlD), and removal of duplicate or incomplete events.3. Feature Extraction Engine: Generates numerical and categorical features from the event metadata and any associated textual content. Features may include message length, response time, meeting participant diversity, cross-department frequency, sentiment polarity, and more.4. Tagging and Classification Module: Applies the tagging taxonomy rules and / or Al-based classifiers to categorize interactions. This module may be powered by NLP models such as BERT, RoBERTa, or domain-specific fine-tuned transformers.5. Scoring Engine: Computes inclusion and collaboration scores using the formulas and weightings defined by the organization’s policies or by default models provided by the system.6. Aggregation Layer: Summarizes scores across different time windows (e.g., weekly, monthly, quarterly) and organizational levels (e g., team, department, entire organization).Model Types and Training

[0100] Models used in the classification stage may include, but are not limited to:• Supervised classification models: Logistic regression, gradient boosted decision trees, random forests.• Deep learning models: Transformer-based NLP models for semantic tagging and contextual classification.Docket No. INC-25-01• Unsupervised clustering models: For discovering new interaction patterns and potential emergent collaboration or inclusion behaviors.

[0101] In certain embodiments, training data may be generated from a combination of historical labeled interaction records, synthetically generated examples, and anonymized industry benchmarks. Cross-validation and A / B testing may be performed to ensure robustness and fairness of predictions.

[0102] Bias mitigation techniques may be integrated into the training pipeline, which may include, but are not limited to, re-sampling, re-weighting, and adversarial debiasing methods to ensure equitable treatment of different demographic groups within the organization.Key Performance Indicator (KPI) Linking Models

[0103] The invention may include, but are not limited to, models that correlate inclusion and collaboration scores with organizational KPIs. KPIs may include, but are not limited to, employee retention rate, project delivery speed, innovation output, customer satisfaction scores, and diversity representation ratios.

[0104] The KPI linkage process may include:1. Selecting relevant KPIs for the organization’s strategic goals.2. Establishing statistical relationships between interaction scores and KPI outcomes using regression, time-series analysis, or causal inference methods.3. Presenting confidence intervals and effect sizes to decision-makers to indicate the reliability of these relationships.Analytics Engine Design

[0105] The analytics engine may be implemented as a distributed system, enabling near realtime computation of inclusion and collaboration scores across large organizations. The engine may expose APIs for integration with BI platforms such as Tableau, Power BI, or Looker.

[0106] The engine supports multiple aggregation dimensions, which may include, but are not limited to, time periods, team hierarchies, roles, and geographic regions.

[0107] To enhance interpretability, the analytics engine may provide explainability modules, displaying the top contributing factors to an individual’s or team’s score for a given period. ThisDocket No. INC-25-01 functionality may use SHAP (Shapley Additive Explanations) or LIME (Local Interpretable Model-Agnostic Explanations) techniques.

[0108] In some embodiments, predictive analytics features may forecast future inclusion or collaboration scores based on historical patterns and upcoming organizational events, enabling proactive interventions.

[0109] The analytics engine may also support “what-if’ simulations, allowing Human Resources (HR) or leadership teams to model the potential impact of specific interventions — for example, adding more cross-functional workshops - on projected collaboration and inclusion metrics.Demographic-Based Tagging and Category Mapping

[0110] In certain embodiments, the system applies demographic-based tagging to each recorded interaction to enable multi-dimensional analysis of organizational inclusion and collaboration. Demographics may include, but are not limited to, gender, age, sexual orientation, race, religion, geographic locationjob position, department, tenure, educational background, and employment status (e.g., full-time, part-time, contractor). These demographic attributes may be derived from human resources databases, employee self-reporting, or third-party data integrations, and are linked to the individuals participating in each interaction.

[0111] In addition to demographics, each interaction may be tagged with one or more categories of interest, which may include, but are not limited to, organizational objectives such as innovation, sustainability, safety, operational efficiency, and production performance, as well as employee-centric interests such as wellness, mentoring, training, career progression, social engagement, and team-building. Category tagging may be performed automatically using machine learning-based natural language processing models that parse meeting transcripts, chat logs, and email content, or manually through user-selected tags during interaction logging.

[0112] The mapping between demographic attributes and categories of interest allows for deep, multi-layered insights into how different groups within the organization engage with specific strategic and cultural objectives. For example, analysis may reveal that younger employees disproportionately engage in sustainability-related discussions but have lower participation in safety meetings, indicating a potential gap in knowledge transfer or interest alignment.Docket No. INC-25-01

[0113] These demographic and category mappings may be stored in a structured database schema (e.g., relational or graph-based) that enables flexible querying. This design allows stakeholders to perform “slice-and-dice” analytics, such as filtering interactions by department and cross-tabulating against collaboration scores in innovation-focused projects, or comparing inclusion levels between male and female employees in leadership training sessions.

[0114] In some embodiments, the demographic-based tagging module operates in near real time, updating organizational dashboards as new interaction data is ingested. This enables rapid identification of emerging trends or disparities in engagement patterns across inclusion and collaboration dimensions.

[0115] In one embodiment, the demographic tagging engine can be implemented using a structured pseudocode approach:FOR each interact on record IN interaction table: demographics = FETCH user_profile. demographics category _tags = FETCH category _lookup_table. tagsSTORE demographic tags, category tags INTO interaction metadata tableThis approach decouples the tagging logic from the downstream analytics, allowing easy updates to tagging criteria without impacting stored historical records.Generation of Analytical Outputs and Reporting

[0116] The system may generate analytical outputs in multiple formats, which may include, but are not limited to, tabular reports, interactive dashboards, network diagrams, heat maps, trend graphs, and scorecards. Outputs may be generated for internal decision-making or external compliance purposes, such as demonstrating adherence to diversity, equity, and inclusion commitments, or to collaboration performance benchmarks.

[0117] Reports may be configured to focus on specific demographic segments, categories of interest, or organizational units. For example, a leadership team may request a heat map showing collaboration intensity across departments, segmented by gender and project type. Similarly, a compliance officer may request a table summarizing inclusion scores for different demographic groups to assess ISO 30415 alignment.

[0118] Certain embodiments include export functionality to formats such as comma-separated values (CSV), Microsoft Excel Open XML Spreadsheet Format (XLSX), PDF, and JSON,Docket No. INC-25-01 allowing integration with BI tools and compliance management systems. In some configurations, reports may be auto-generated on a scheduled basis (e.g., monthly, quarterly) and delivered via secure email or API endpoints.

[0119] In some implementations, the reporting system supports role-based access control (RBAC) to ensure that sensitive demographic insights are visible only to authorized personnel, in compliance with privacy and employment regulations.

[0120] Heat map visualizations are generated by aggregating interaction counts or scores into a two-dimensional matrix keyed by source demographic (rows) and target demographic (columns). The aggregation function may compute total interaction count, average collaboration score, or weighted inclusion score. Sample SQL for a basic interaction count matrix:SELECT pl. Demographic Group AS Source Group, p2.Demographic_Group AS Target Group, COUNT(*) AS Interact on Count FROM Interactions iJOIN Participants pl ON i.Source Participant ID = pl. Parti cipant ID JOIN Participants p2 ON i.Target Participant ID = p2.Participant_ID GROUP BY pl .Demographic Group, p2.Demographic_Group;The resulting matrix is converted to a heat map image using a visualization library (e.g., Matplotlib, D3.js), with intensity scaled proportionally to the aggregated metric.

[0121] As illustrated in FIGURE 4, a dashboard interface may be provided to present system outputs in a user-friendly and actionable format. The dashboard may include a plurality of visualization components configured to display different perspectives on the processed interaction data. For example, heat maps may be generated to illustrate interaction density and collaboration intensity across teams, departments, or demographic groups, thereby enabling the identification of areas of strong connectivity as well as regions of potential isolation. Trend graphs may be displayed to show temporal changes in calculated inclusion scores and collaboration scores, allowing management to track organizational progress over defined periods such as weeks, quarters, or years. The dashboard may further include interactive drill-down capabilities enabling a user to select a region of interest, demographic category, or time period to review the underlying tagged interactions. In some embodiments, associated system-generated recommendations, such as targeted interventions, training suggestions, or alerts for potential exclusionary behavior, mayDocket No. INC-25-01 also be presented alongside the visualizations. The dashboard may be accessible through secure web and mobile interfaces, thereby allowing stakeholders such as executives, human resources personnel, and team leaders to continuously monitor and act upon collaboration and inclusion dynamics within the organization.

[0122] As shown in FIGURE 5, the system implements a schematic feedback loop that enables closed-cycle monitoring and continuous improvement of organizational interaction dynamics. In this exemplary embodiment, the analytics engine generates system outputs such as inclusion scores, collaboration scores, trend analyses, and heat maps. These outputs may be configured to trigger corrective actions when defined thresholds or anomalies are detected. Such actions may include targeted training programs, updates to organizational policies, or interventions at the team or departmental level. For example, a drop in collaboration scores within a particular demographic group may automatically generate a recommendation for additional mentoring opportunities or leadership engagement. The outcomes of these corrective measures are subsequently captured through the same interaction-tracking process, and the resulting data is fed back into the analytics engine. This iterative cycle allows the system to evaluate the effectiveness of interventions, refine predictive models, and provide increasingly accurate recommendations over time. By incorporating human resource, compliance, and operational feedback into the analytics engine, the feedback loop illustrated in FIGURE 5 ensures that organizations are not only measuring interaction dynamics but also continuously optimizing them in alignment with strategic objectives and employee well-being.ISO Standard 30415 Inclusion Standard Compliance and Reporting

[0123] Where applicable, the system can be configured to align analytical outputs to generate evidence packages aligned with ISO 30415 (Human Resource Management - Diversity and Inclusion) standards. ISO 30415 compliance may require reporting on specific diversity metrics, demonstrating inclusive practices, and documenting continuous improvement efforts. Optimized analytical outputs may include inclusion reports and scores as well as the documented methodologies for data collection and processing for inclusion assessments. Such packages may include reproducible SQL queries, pseudocode implementations, and audit trails that verify compliance claims.Docket No. INC-25-01

[0124] In some embodiments, the system includes an ISO Compliance Mode, which filters and structures data outputs in a format directly mappable to ISO 30415 clauses. For example, the system may produce compliance-ready summaries that demonstrate equitable participation in decision-making processes or evidence of systematic bias reduction in collaborative activities.

[0125] By integrating ISO 30415 alignment into its reporting pipeline, the invention not only serves as a measurement and improvement tool but also as a compliance facilitation system, reducing the burden on organizations seeking certification or external validation of their inclusion and collaboration efforts.

[0126] The ISO integration may also extend to automated alerts that notify administrators when measured inclusion or collaboration scores fall below ISO-recommended thresholds, prompting corrective actions.Privacy, Anonymization, and Ethical Considerations

[0127] Given the sensitive nature of demographic and interaction data, the system incorporates privacy-by-design principles. Personally identifiable information (PII) may be anonymized or pseudonymized where possible, while still enabling aggregate analytics.

[0128] Ethical safeguards may include user consent protocols, transparency reports detailing how interaction data is processed, and opt-out mechanisms for employees who do not wish to have certain attributes tracked.

[0129] In some embodiments, privacy safeguards are dynamically adjustable based on jurisdiction-specific legal requirements, such as GDPR in the European Union or CCPA in California, ensuring the system can be deployed globally without violating local privacy laws.

[0130] In further embodiments, the present system and method may be configured to operate as an end-to-end organizational interaction quantification platform, capable of measuring both inclusion and collaboration metrics from the same underlying interaction dataset. This dualpurpose architecture allows organizations to leverage a unified data collection and analytics framework while producing separate, targeted outputs for inclusion-related compliance, such as ISO 30415, and col lab oration -related performance, such as innovation velocity or cross-team problem resolution rates.

[0131] In one exemplary combined process flow, interactions are recorded from multiple organizational data sources (e.g., email, instant messaging, meeting platforms, projectDocket No. INC-25-01 management tools, in-person attendance systems) and are automatically tagged with metadata including demographic attributes and categories of interest. The tagged interaction data is subsequently processed by an analytics engine configured to calculate various Key Performance Indicators (KPIs) and to generate both inclusion scores and collaboration scores. The resulting outputs may be displayed in dashboards, summarized in reports, or exported for use in compliance audits.Implementation Examples

[0132] Example 1 - Large Enterprise Innovation and Safety Integration. In a multinational energy company employing over 50,000 staff across 20 countries, the system is deployed across corporate email, Microsoft Teams, Zoom meetings, and site-access control systems. Interaction records are tagged with demographic data (gender, age, location, department, position level) and linked to organizational categories of interest such as innovation, safety, sustainability, and production. The analytics engine calculates, for example:• Inclusion Score: Measures the diversity of participation in innovation-related meetings by demographic group, highlighting underrepresented voices.• Collaboration Score: Quantifies cross-department collaboration in safety incident resolution. Outputs include heat maps showing sites with low cross-functional safety collaboration and time-series trend lines tracking improvement after interventions.The enterprise uses these outputs to demonstrate compliance with ISO 30415 inclusion standards and to document collaborative improvements during quarterly board reviews.

[0133] Example 2 - Academic Institution Faculty-Student Mentoring. At a mid-sized university, the system is integrated with the campus scheduling platform, virtual learning environment, and faculty mentoring logs. Interactions are tagged by faculty rank, student year, academic department, and mentoring category (e g., career development, wellness, research supervision).• The Inclusion Score identifies whether mentoring opportunities are equitably distributed among students from different socioeconomic or ethnic backgrounds.• The Collaboration Score measures co-supervision patterns across departments. Reports generated for accreditation bodies show demonstrable progress in both inclusivity and interdisciplinary collaboration.Docket No. INC-25-01

[0134] Example 3 - Global Manufacturing Firm Cross-Site Collaboration. In a company operating multiple production sites, the platform collects data from project management tools (e.g., Jira, Trello), video conferences, and shared document editing platforms. Categories of interest include production optimization, supply chain resilience, and employee training. Demographic tags include site locationjob role, tenure, and shift pattern.• The Collaboration Score is calculated for cross-site problem-solving tasks, revealing bottlenecks between engineering and procurement teams.• The Inclusion Score identifies whether training sessions are reaching all shifts and locations equally.• Outputs are fed into operational dashboards to guide targeted interventions.

[0135] Example 4 - Email Collaboration for Innovation. A design engineer in the R&D department sends an email thread to a cross-functional team discussing a new sustainability feature for a product. The system captures the interaction via the integrated email connector, logs participants (tagged by department, role, location), and applies NLP analysis to detect keywords such as “prototype,” “testing,” and “innovation.” The interaction is tagged under “Innovation” and “Sustainability” categories. The demographic overlay shows inclusion across gender and location diversity. The analytics module computes a collaboration score of 0.87 (on a 0-1 scale) for this interaction and rolls it into weekly department averages. The KPI linkage model then correlates high innovation collaboration scores with product launch timelines.

[0136] Example 5 - Mentoring Session Tracking. A senior manager conducts a scheduled mentoring call with a junior engineer. The system captures the interaction from the organization’s calendar integration, verifies participation via call log APIs, and associates the mentor’s and mentee’s demographic profiles. The tagging engine applies “Mentoring” and “Career Development” labels. Sentiment analysis on meeting transcripts indicates a positive engagement tone. The inclusion score for the mentee’s demographic group increases in that reporting period. The KPI model links this improvement to a decrease in employee turnover for that group over the last two quarters.

[0137] Example 6 - Safety Interactions and Incident Reduction. Employees from multiple sites, particularly within a demographic group of field technicians under age 35, regularly exchange safety moments and safety observations on the company’s intranet social platform over the course of a year. Each post and comment is automatically captured by the system’s socialDocket No. INC-25-01 media connector, tagged under the “Safety” category, and linked to participant demographic profdes. Historical analysis shows a 25% increase in tagged safety interactions for this demographic compared to the previous year. The analytics module cross-references this data with the organization’s safety incident and near-miss records, revealing a correlated 15% decrease in incidents for this group. The system automatically generates visual graphs and summary reports for the Safety Director and executive management, including heat maps highlighting other demographic groups where safety incidents have increased and safety-related interactions have decreased. This enables targeted managerial follow-up and rapid intervention to address underlying issues, representing a significant improvement in responsiveness compared to presystem safety tracking practices.

[0138] Example 7 - R&D Collaboration and Invention Disclosure Trends. An R&D division maintains a dedicated group site for idea sharing and technical discussions. Over a 12-month period, the system captures posts, comments, and file shares, tagging them under “Innovation” and “Collaboration” categories. Demographic overlays reveal that one specific demographic group (e.g., mid-career engineers in the Asia Pacific region) increased their tagged collaboration interactions by 40% compared to the prior year. The KPI linkage model correlates this increase with a 35% rise in invention disclosures filed by this demographic. Conversely, another demographic group (e.g., early-career engineers in a different region) shows a 20% decline in collaboration interactions and a corresponding drop in invention disclosures. Management uses this insight to investigate root causes, discovering exclusionary practices in meeting participation. Corrective measures are implemented, and the system monitors post-intervention trends, enabling faster and more precise resolution than would have been possible without automated interaction tracking and demographic correlation.

[0139] Example 8 - Wellness Category Tracking in Employee Resource Groups (ERGs). In an enterprise with a large and diverse workforce, employees participate in multiple ERGs, workplace social clubs, and sports teams. Over a two-year period, the platform captures and processes interaction data originating from the company’s internal social media platform, intranet event pages, and attendance logs for in-person and virtual activities. The interaction tagging module applies category logic to assign these data points to the “Wellness” category, using both content-based analysis (e.g., post metadata, keywords, image recognition of event photos) and context-based analysis (e.g., group affiliation, event type). Simultaneously, the demographicDocket No. INC-25-01 tagging engine enriches each record with demographic attributes sourced from participant profiles, such as age bracket, gender, job role, location, and tenure. The system aggregates these wellness- related interactions and correlates them with periodic employee happiness ratings gathered from HR surveys and pulse checks. Over time, the analytics engine generates visual outputs including:• Time-series graphs showing correlation between wellness-related interactions and average happiness ratings by demographic segment.• Heat maps illustrating relative levels of wellness engagement across different offices, departments, and demographic groupings.• Inclusion Score trends specific to wellness-related activities.The platform’s automated alerting mechanism detects a sustained decline in wellness-related interactions for a specific demographic cohort. Upon reaching a configurable threshold, the system issues a real-time notification to the Chief Human Resources Officer (CHRO) and the HR analytics team. Subsequent investigation identifies underlying causes, including subtle patterns of exclusion and non-inclusive behavior, which had previously gone unnoticed. By enabling early detection and targeted intervention, the system mitigates the risk of further disengagement, enhances inclusivity, and delivers measurable organizational benefits - outcomes that would have been difficult, if not impossible, to achieve without continuous tracking of interactions and demographic linkages.Alternative Embodiments

[0140] In some embodiments, the system is deployed in a lightweight, mobile-first configuration for smaller organizations or distributed field teams. In this configuration, interaction capture may rely primarily on mobile messaging logs, voice call metadata, and location-based attendance check-ins.

[0141] In other embodiments, the system integrates with third-party analytics or human resources (HR) platforms via secure APIs. This allows the inclusion and collaboration metrics to be embedded directly into existing HR dashboards or enterprise data warehouses without requiring users to switch interfaces.

[0142] In privacy-sensitive environments, the platform may use privacy-preserving computation techniques, such as anonymization, pseudonymization, or secure multi-partyDocket No. INC-25-01 computation, to ensure that in dividual -level demographic data is never exposed while still enabling aggregated analysis.

[0143] While the above examples demonstrate specific contexts - large enterprise, academic institution, and manufacturing firm - the system is adaptable to a wide variety of organizational types, including non-profits, healthcare providers, and government agencies. Each implementation may tailor its demographic tags, categories of interest, and KPIs to suit its operational goals while still using the same underlying architecture.

[0144] The invention is not limited to any single deployment model, industry, or scoring formula. The described embodiments, figures, and examples are intended to be illustrative rather than limiting, and variations that achieve the same measurement, analytics, and reporting outcomes fall within the scope of the claims.

Claims

Docket No. INC-25-01CLAIMSWhat is claimed is:

1. A method comprising the measurement of interactions as a proxy for inclusion and / or collaboration within an organization, the method comprising:(a) capturing interaction data between individuals within an organization, wherein interaction capture comprises face-to-face interactions, digital communications, shared tasks, wearable devices, sensor-based systems, or biometric authentication logs;(b) tagging said interactions with one or more category labels based on interaction type, context, or purpose, wherein said categories comprise mentoring, onboarding, brainstorming, consulting, safety, sustainability, innovation, social, wellness, decision-making, or project management, and wherein said tagging is performed using automated classifiers trained on labeled organizational interaction datasets;(c) associating the tagged interaction data with demographic, role-based, or identitybased information retrieved from human resources systems, professional profiles, or personnel databases, wherein said information comprises job title, department, tenure, location, or other relevant organizational attributes;(d) analyzing the interaction and demographic data using a trained machine learning model to calculate an inclusion score and / or collaboration score for individuals, teams, or departments, wherein said score comprises numeric, categorical, graphical, textual, or probabilistic representations of inclusion or collaboration levels;(e) identifying inclusion and / or collaboration gaps, silos, or exclusion patterns based on deviations from historical baselines or organization-defined norms, wherein such identification comprises statistical thresholds, anomaly detection, or comparative benchmarking; andDocket No. INC-25-01(f) generating one or more outputs based at least in part on said analysis, wherein said outputs comprise visualizations, alerts, recommendations, or team formation suggestions, wherein team formation comprises optimizing for skill diversity, workload balance, geographic proximity, or alignment with organizational objectives; wherein the steps of the method may be performed in any order, and not all steps are required in all implementations.

2. A method for joint measurement of inclusion and collaboration within an organization, comprising:(a) capturing multi-modal interaction data between individuals within the organization;(b) tagging the interaction data with one or more category labels indicative of interaction type, context, or purpose;(c) associating the tagged interaction data with demographic, role-based, or identitybased attributes;(d) analyzing the associated data using one or more machine learning models to concurrently compute an inclusion score and a collaboration score from the same interaction dataset;(e) identifying deviations in the inclusion score, the collaboration score, or both, from historical baselines or predefined thresholds; and(f) generating outputs comprising at least one visualization, alert, or recommendation configured to address identified deviations; wherein computing both scores from a unified dataset enables correlation analysis, cross-comparison, and integrated intervention planning in a manner not achievable by computing such scores independently.

3. The method of claim 1, wherein the organization may include, but is not limited to a workplace, business, non-profit entity, governmental agency, academic institution, educational organization, social group, sports team, virtual or non-virtual team, or online community, where applicable.

4. The method of claim 2, wherein the organization may include, but is not limited to a workplace, business, non-profit entity, governmental agency, academic institution,Docket No. INC-25-01 educational organization, social group, sports team, virtual or non-virtual team, or online community, where applicable.

5. The method of claim 1, further comprising linking the calculated inclusion score and / or collaboration score to one or more key performance indicators (KPIs) of the organization, wherein said KPIs comprise productivity, retention rate, employee satisfaction, project delivery time, revenue growth, innovation metrics, quality, safety incidents, or customer satisfaction, where applicable.

6. The method of claim 2, further comprising linking the calculated inclusion score and / or collaboration score to one or more key performance indicators (KPIs) of the organization, wherein said KPIs comprise productivity, retention rate, employee satisfaction, project delivery time, revenue growth, innovation metrics, quality, safety incidents, or customer satisfaction, where applicable.

7. The method of claim 1, wherein the interaction capture may include integration with external collaboration platforms, enterprise resource planning (ERP) systems, customer relationship management (CRM) systems, project management software, or other digital tools, where applicable.

8. The method of claim 2, wherein the interaction capture may include integration with external collaboration platforms, enterprise resource planning (ERP) systems, customer relationship management (CRM) systems, project management software, or other digital tools, where applicable.

9. The method of claim 1, wherein tagging further comprises applying natural language processing (NLP) to conversation transcripts, chat logs, and meeting notes to determine context, sentiment, or topic, where applicable.

10. The method of claim 2, wherein tagging further comprises applying natural language processing (NLP) to conversation transcripts, chat logs, and meeting notes to determine context, sentiment, or topic, where applicable.

11. The method of claim 1, wherein the machine learning model may include, but is not limited to decision trees, neural networks, support vector machines, ensemble methods, probabilistic graphical models, or rule-based systems, and is trainable on historical performance data, annotated interaction datasets, or simulated collaboration scenarios, where applicable.Docket No. INC-25-0112. The method of claim 2, wherein the machine learning model may include, but is not limited to decision trees, neural networks, support vector machines, ensemble methods, probabilistic graphical models, or rule-based systems, and is trainable on historical performance data, annotated interaction datasets, or simulated collaboration scenarios, where applicable.

13. The method of claim 1, wherein the calculated score may comprise temporal weighting, seasonal adjustment, normalization, or decay factors to emphasize recent interactions over older ones, where applicable.

14. The method of claim 2, wherein the calculated score may comprise temporal weighting, seasonal adjustment, normalization, or decay factors to emphasize recent interactions over older ones, where applicable.

15. The method of claim 1, wherein the calculated score is normalized across departments, teams, or demographic groups to allow cross-comparison, where applicable.

16. The method of claim 2, wherein the calculated score is normalized across departments, teams, or demographic groups to allow cross-comparison, where applicable.

17. The method of claim 1, wherein the identified gaps or silos may trigger automated interventions that may include, but are not limited to targeted training, policy updates, nudge communications, or facilitated introductions between individuals or groups, where applicable.

18. The method of claim 2, wherein the identified gaps or silos may trigger automated interventions that may include, but are not limited to targeted training, policy updates, nudge communications, or facilitated introductions between individuals or groups, where applicable.

19. The method of claim 1, wherein team formation suggestions may be optimized using combinatorial optimization, genetic algorithms, constraint solvers, or reinforcement learning, where applicable.

20. The method of claim 2, wherein team formation suggestions may be optimized using combinatorial optimization, genetic algorithms, constraint solvers, or reinforcement learning, where applicable.

21. The method of claim 1, wherein the calculated score is displayed through interactive dashboards, heat maps, network graphs, or time-series visualizations, where applicable.Docket No. INC-25-0122. The method of claim 2, wherein the calculated score is displayed through interactive dashboards, heat maps, network graphs, or time-series visualizations, where applicable.

23. The method of claim 21, wherein the interactive dashboards, heat maps, or network graphs may further display interaction counts and inclusion and / or collaboration scores segmented by demographic attribute and category, and wherein the one or more category labels may further comprise training, consulting, collaborating, or other organizational activities not otherwise enumerated, where applicable.

24. The method of claim 22, wherein the interactive dashboards, heat maps, or network graphs may further display interaction counts and inclusion and / or collaboration scores segmented by demographic attribute and category, and wherein the one or more category labels may further comprise training, consulting, collaborating, or other organizational activities not otherwise enumerated, where applicable.

25. The method of claim 1, wherein alerts generated by the system may include, but are not limited to threshold breaches, sudden drops in inclusion or collaboration levels, predicted risks of collaboration breakdown, or emerging high-performing clusters, where applicable.

26. The method of claim 2, wherein alerts generated by the system may include, but are not limited to threshold breaches, sudden drops in inclusion or collaboration levels, predicted risks of collaboration breakdown, or emerging high-performing clusters, where applicable.

27. The method of claim 1, wherein recommendations may include, but are not limited to mentorship pairings, cross-departmental projects, rotation programs, or diversity and inclusion initiatives, where applicable.

28. The method of claim 2, wherein recommendations may include, but are not limited to mentorship pairings, cross-departmental projects, rotation programs, or diversity and inclusion initiatives, where applicable.

29. The method of claim 1, wherein interaction capture may include, but is not limited to passive data collection, active user input, or hybrid methods, and wherein wearable, sensor, and / or biometric data may be used to infer proximity or co-presence to distinguish in-person interactions from virtual interactions, where applicable.Docket No. INC-25-0130. The method of claim 2, wherein interaction capture may include, but is not limited to passive data collection, active user input, or hybrid methods, and wherein wearable, sensor, and / or biometric data may be used to infer proximity or co-presence to distinguish in-person interactions from virtual interactions, where applicable.

31. The method of claim 1, wherein the demographic or identity -based information may comprise one or more of: gender, age, ethnicity, sexual orientation, marital status, parental status, physical abilities, mental health status, neurodiversity, military status, location, education level, job title, or tenure, and further comprising generating and storing a personnel profde for each individual, wherein the profile may comprise demographic attributes, education history, work experience, skills, and other relevant characteristics, with configurable visibility and linkage to recorded interactions for inclusion and / or collaboration measurement, and wherein the personnel profile may be imported from an external source including, but not limited to, a human resources database, social or professional networking profile, or other organizational record, where applicable.

32. The method of claim 2, wherein the demographic or identity-based information may comprise one or more of: gender, age, ethnicity, sexual orientation, marital status, parental status, physical abilities, mental health status, neurodiversity, military status, location, education level, job title, or tenure, and further comprising generating and storing a personnel profile for each individual, wherein the profile may comprise demographic attributes, education history, work experience, skills, and other relevant characteristics, with configurable visibility and linkage to recorded interactions for inclusion and / or collaboration measurement, and wherein the personnel profile may be imported from an external source including, but not limited to, a human resources database, social or professional networking profile, or other organizational record, where applicable.

33. The method of claim 1, wherein the inclusion score and / or collaboration score may be computed based on interaction frequency, diversity, category, and quality, the quality being determined from contextual or sentiment analysis, peer feedback, or outcomebased performance metrics, and wherein interaction data may be monitored in real-timeDocket No. INC-25-01 or near-real-time with dynamic updating of scores and automated triggering of alerts and recommendations when deviations from baselines are detected, where applicable.

34. The method of claim 2, wherein the inclusion score and / or collaboration score may be computed based on interaction frequency, diversity, category, and quality, the quality being determined from contextual or sentiment analysis, peer feedback, or outcomebased performance metrics, and wherein interaction data may be monitored in real-time or near-real-time with dynamic updating of scores and automated triggering of alerts and recommendations when deviations from baselines are detected, where applicable.

35. The method of claim 1, wherein only inclusion is measured.

36. The method of claim 1, wherein only collaboration is measured.

37. The method of claim 2, wherein only inclusion is measured.

38. The method of claim 2, wherein only collaboration is measured.

39. A system for measuring interactions as a proxy for inclusion and / or collaboration within an organization, the system comprising:(a) one or more processors;(b) one or more memory devices storing instructions that, when executed by the processors, cause the system to: i. capture interaction data between individuals within the organization; ii. tag the interaction data with one or more category labels based on interaction type, context, or purpose; iii. associate the tagged interaction data with demographic, role-based, or identity-based information; iv. analyze the interaction and demographic data using one or more machine learning models to calculate an inclusion score and / or collaboration score; and v. generate one or more outputs comprising visualizations, alerts, recommendations, or team formation suggestions; wherein the steps of the system may be performed in any order, and not all components are required in all implementations.Docket No. INC-25-0140. The system of claim 39, wherein the processors and memory devices are further configured to generate personnel profiles for individuals and update said profiles in real-time or near-real-time with interaction and score data.

41. The system of claim 39, wherein the machine learning models comprise decision trees, random forests, support vector machines, neural networks, logistic regression, ensemble methods, probabilistic models, probabilistic graphical models, or rule-based systems, where applicable.

42. The system of claim 39, wherein the outputs comprise one or more interactive dashboards, heat maps, or network graphs configured to display interaction counts and inclusion or collaboration scores segmented by demographic attributes and category labels.

43. The system of claim 39, wherein alerts comprise threshold breaches, sudden drops in inclusion or collaboration levels, predicted risks of collaboration breakdown, or identification of emerging high-performing clusters.

44. The system of claim 39, wherein recommendations comprise mentorship pairings, cross-departmental projects, rotation programs, diversity initiatives, or collaboration incentives.

45. The system of claim 39, wherein the machine learning models may be improved via active learning, semi-supervised learning, feedback capture, or human-in-the-loop review to refine tagging and scoring, where applicable.

46. A non-transitory computer-readable medium storing instructions that, when executed by one or more processors, cause the processors to perform a method for measuring inclusion and / or collaboration within an organization, the method comprising:(a) capturing interaction data between individuals within the organization;(b) tagging said interactions with one or more category labels based on interaction type, context, or purpose;(c) associating the tagged interaction data with demographic, role-based, or identity-based information;(d) analyzing the data using one or more machine learning models to calculate an inclusion score and / or collaboration score; andDocket No. INC-25-01(e) generating one or more outputs comprising visualizations, alerts, recommendations, or team formation suggestions.

47. The non-transitory computer-readable medium of claim 46, wherein the instructions cause the processors to generate personnel profdes and update said profiles with realtime interaction and score data.

48. The non-transitory computer-readable medium of claim 46, wherein the machine learning models comprise decision trees, neural networks, support vector machines, ensemble methods, probabilistic models, probabilistic graphical models, rule-based systems, scoring logic implementing temporal weighting, seasonal adjustment, normalization, or decay factors, where applicable.

49. The non-transitory computer-readable medium of claim 46, wherein the outputs comprise interactive dashboards, heat maps, or network graphs configured to display interaction counts and scores segmented by demographic attributes and category labels.

50. The non-transitory computer-readable medium of claim 46, wherein alerts comprise threshold breaches, sudden drops in inclusion or collaboration levels, predicted risks of collaboration breakdown, or identification of emerging high-performing clusters.

51. The non-transitory computer-readable medium of claim 46, wherein recommendations comprise mentorship pairings, cross-departmental projects, rotation programs, diversity initiatives, or collaboration incentives.

52. The non-transitory computer-readable medium of claim 46, wherein the tagging step further comprises applying natural language processing to conversation transcripts, chat logs, messages, posts or meeting notes.

53. The non-transitory computer-readable medium of claim 46, wherein the calculated scores comprise temporal weighting, seasonal adjustment, normalization, or decay factors to emphasize recent interactions.

54. The non-transitory computer-readable medium of claim 46, wherein the calculated scores are normalized across departments, teams, or demographic groups to allow cross-comparison.

55. The non-transitory computer-readable medium of claim 46, wherein the outputs further comprise targeted interventions including training, nudge communications, or policy adjustments.Docket No. INC-25-0156. The non-transitory computer-readable medium of claim 46, wherein two or more features recited in dependent claims 47-55 are implemented in combination.

Images