Method and system for matching entities in an auction

Patent No. US9456086 (titled "Method and system for matching entities in an auction") on Mar 8, 2010. The application was issued on Sep 27, 2016.

What is this patent about?

'086 is related to the field of intelligent communication routing and automated resource allocation within computer-telephony integrated (CTI) systems. It addresses the technical challenge of efficiently matching entities, such as callers and agents in a call center, by moving beyond simple rule-based or first-in-first-out (FIFO) logic. The background context involves managing high-volume real-time communications where the goal is to balance service quality with resource utilization, particularly in environments where agents possess varying skill levels and costs.

The underlying idea behind '086 is to treat the matching of entities as a multivariate optimization problem that accounts for both immediate economic gain and the long-term cost of resource unavailability. Instead of just looking for the best available agent for a specific caller, the system evaluates the opportunity cost of using a specific resource now versus saving it for a potentially more valuable future interaction. This engineering insight allows the system to maximize the total economic surplus across a series of matches rather than just optimizing a single transaction in isolation.

The claims of '086 focus on a method for matching subsets of entities by processing multivalued scalar data that represent inferential targeting and characteristic parameters. The independent claims specifically protect the use of an automated processor to perform an optimization that balances the economic surplus of a mutually exclusive match against the opportunity cost of making those entities unavailable for alternate pairings. This mechanism ensures that the resulting signal for call routing or resource allocation reflects a mathematically optimized selection across a plurality of potential matches.

In practice, the invention functions by maintaining a local database of agent skill vectors and caller requirement vectors within the low-level switching architecture. By integrating the optimization algorithm directly into the communication server rather than externalizing it to a high-level management system, the '086 patent reduces processing latency and communication overhead. The system can dynamically adjust to peak loads by shifting from complex training-focused optimizations to high-throughput efficiency modes, ensuring that the most critical matches are prioritized when resources are scarce.

This approach differs from prior solutions by incorporating game theory and economic modeling into the real-time switching logic. Traditional systems typically use static grouping or simple skill-based thresholds that ignore the relative value of an agent's time or the potential for skill growth. By quantifying abstract concepts like training value and future availability into a normalized cost function, the '086 patent allows for a more granular and globally efficient distribution of work that adapts to the shifting state of the entire call center ecosystem.

How does this patent fit in bigger picture?

Technical Landscape

In the early 2000s when ’086 was filed, computer-telephony integration (CTI) was typically implemented using a rigid architectural split where low-level voice switching was performed by dedicated hardware or Private Branch Exchanges (PBXs), while high-level routing logic was externalized to separate general-purpose servers. At a time when systems commonly relied on static, rule-based Least Cost Routing (LCR) or simple first-in-first-out (FIFO) queues, the integration of complex, non-deterministic algorithms directly into the call-control path was rare. Hardware and software constraints of the era made the real-time execution of sophisticated optimization models non-trivial, as non-deterministic operating systems often introduced latencies that could impair the performance of time-critical voice processing functions.

Prosecution Position

The disclosed invention represents a meaningful technical advancement through the structural integration of an intelligent switching architecture directly within the low-level communications management layer. By partitioning control such that the main processor of a telephony server evaluates complex algorithms—including probabilistic models, Bayesian logic, and collaborative filtering—simultaneously with voice channel management, the system overcomes the latency constraints inherent in externalized management architectures. This architectural shift enables a capability for inferential target resolution, where a communication is routed based on a real-time algorithmic optimization of agent skill metrics, training costs, and predicted outcomes rather than a static address. The technical effect achieved is a reduction in the required bandwidth for external synchronization and a decrease in the transactional load on high-level management systems, allowing for more granular, context-aware routing without sacrificing real-time performance.

Claims

The patent contains a total of 20 claims, with claims 1, 11, and 20 serving as the independent claims. These independent claims generally focus on a method for matching subsets of entities by storing multivalued scalar data representing targeting and characteristic parameters and using an automated processor to perform an economic optimization that maximizes surplus while accounting for the opportunity cost of entity unavailability. The dependent claims further refine this process by specifying applications in real-time communication routing, call center agent skill weighting, the inclusion of extrinsic perturbations, and the use of message queues within an operating system to control the matching signal.

Key Claim Terms New

Definitions of key terms used in the patent claims.

Term (Source)Support for SpecificationInterpretation
Economic surplus
(Claim 1, Claim 11, Claim 20)
Business goals, such as customer satisfaction, must be converted and normalized into economic terms prior to use in an optimization. The expected outcome resulting from a particular agent may be added as a factor in the cost function. The optimization may be influenced by economic and non-economic factors, and the optimization may include objective and subjective factors normalized into a common metric.A normalized metric representing the net value or benefit derived from a specific match between entities, calculated by considering factors such as transaction value, agent productivity, and customer satisfaction converted into economic terms.
Inferential targeting parameters
(Claim 1, Claim 11, Claim 20)
The present invention allows replacement or supplementation of telephone numbers, IP addresses, and the like, with high-level definitions which are contextually interpreted at the time of communications routing. The target of a communication is defined by an algorithm, rather than a predetermined address or simple rule, and the algorithm is evaluated in real time for resolution of the target. This integration allows communications to be established based on an inferential description of a target, rather than a concrete description.Multivalued scalar data used to define the requirements or characteristics of an entity (such as a caller or a task) through inference rather than a fixed address, used by an algorithm to resolve a match in real-time.
Multivalued scalar data
(Claim 1, Claim 11, Claim 20)
A set of skills are defined, which are generally independent skills. Each agent is assigned a metric with respect to each skill. The optimization is denoted by a formula maximizing the sum, for each of the required skills, of the product of weighting for that skill and the score for the agent.A set of multiple independent numerical values (such as a vector) where each value represents a specific skill metric, characteristic, or weighting factor used in the optimization calculation.
Mutually exclusive match
(Claim 1, Claim 11, Claim 20)
The system selects an optimal pairing of respective multiple agents with multiple matters. In the case of competing requests for allocation, one might compare all of the cost functions for the matters in the queue with respect to each permissible pairing of agent and matter. The software system handles virtual or real circuit switching and management to resolve the destination.A specific pairing between a member of a first group (e.g., a caller) and a member of a second group (e.g., an agent) that prevents those specific members from being paired with others during the duration of the communication.
Opportunity cost
(Claim 1, Claim 11, Claim 20)
Another factor to consider in making a selection of an agent in a multi-skill call center is the availability of agents for other calls, predicted or actual. While a selection of an agent for one matter may be optimal in a narrow context, the selected agent might be more valuable for another matter. This is represented as a term which indicates the opportunity cost for allocating an agent to the particular call.A calculated value representing the potential loss of value or benefit incurred by making a specific match, specifically accounting for the fact that an entity (like a highly skilled agent) becomes unavailable for other potential matches.

Litigation Cases New

US Latest litigation cases involving this patent.

Case NumberFiling DateTitle
1:25-cv-00026Jan 8, 2025Patent Armory Inc. V. Corkcicle, Llc

Patent Family

Patent Family

File Wrapper

The dossier documents provide a comprehensive record of the patent's prosecution history - including filings, correspondence, and decisions made by patent offices - and are crucial for understanding the patent's legal journey and any challenges it may have faced during examination.

  • Get instant alerts for new documents

US9456086

Application Number
US12719827A
Filing Date
Mar 8, 2010
Publication Date
Sep 27, 2016
External Links
Slate, USPTO , Google Patents