Method and system for matching entities in an auction

Patent No. US10237420 (titled "Method and system for matching entities in an auction") on Dec 28, 2017. The application was issued on Mar 19, 2019.

What is this patent about?

’420 is related to the field of computer-integrated telecommunications and automated resource allocation. Specifically, it addresses the technical challenges of managing real-time communication environments, such as call centers, where incoming requests must be efficiently matched with available human agents or automated resources. The background context involves moving beyond simple first-in-first-out (FIFO) queues or static rule-based routing toward systems that can handle complex, multi-dimensional variables in high-latency environments.

The underlying idea behind ’420 is to integrate high-level intelligent decision-making directly into the low-level switching architecture to perform real-time multivariate optimization. Rather than relying on rigid scripts or external databases that introduce delay, the system treats every potential match as a dynamic economic problem. By modeling the interaction using advanced statistical tools, the invention seeks to maximize the 'economic surplus' of a match while simultaneously accounting for the opportunity cost of making a specific resource unavailable for other potential requests.

The claims of ’420 focus on a method and system for pairing requests with partners by evaluating a plurality of potential matches through a probabilistic predictive evaluator. The independent claims specifically protect the use of automated processors to run complex algorithms—such as Bayesian logic, hierarchical Markov models, or neural networks—that analyze content-specific or requestor-specific characteristics against partner-specific traits. This evaluation results in a control signal that dictates the optimal allocation of resources based on these predictive rankings.

In practice, the invention functions by assigning characteristic vectors to both the incoming request (e.g., caller intent, language, or emotional state) and the available partners (e.g., agent proficiency, cost, or training needs). The system performs a combinatorial analysis to determine the best possible pairing across the entire pool of active requests and available agents. This allows the system to deviate from standard routing if a specific pairing is predicted to yield a higher long-term value, such as using a call as a targeted training opportunity for a trainee while a mentor shadows the session.

This approach differs from prior solutions by shifting the intelligence from external, high-level Customer Relationship Management (CRM) systems down to the telephony server level. Traditional systems often suffer from communication latencies between the switch and the decision-making logic; ’420 eliminates this bottleneck by embedding the optimization within the consolidated platform. Furthermore, unlike static skill-based routing, this invention adaptively updates agent profiles in real-time and considers non-economic factors that change over time, ensuring the system remains efficient even as call volumes and agent capabilities fluctuate.

How does this patent fit in bigger picture?

Technical Landscape

In the early 2000s when ’420 was filed, computer-integrated telephony was typically implemented using a rigid architectural split where low-level voice processing hardware handled real-time switching while high-level policy management was externalized to separate general-purpose servers. At a time when systems commonly relied on static rule-based routing or manual database lookups to direct calls, the integration of complex decision-making logic directly into the switching layer was non-trivial due to the processing latencies of non-deterministic operating systems. Consequently, standard engineering constraints necessitated that intelligent functions, such as workforce management and skill-based optimizations, remain decoupled from the underlying circuit-switching infrastructure to avoid impairing real-time communication performance.

Prosecution Position

The invention addresses the technical problem of communication and processing latencies inherent in distributed computer-telephony integration by consolidating intelligent routing algorithms directly within the low-level switching architecture. This architectural shift moves the evaluation of complex, multi-variable cost functions—incorporating agent skill metrics, training objectives, and economic outcomes—from external management systems to the primary telephony server. The technical effect achieved is a reduction in required communication bandwidth and the elimination of non-deterministic delays during call resolution. By integrating real-time inferential targeting and adaptive skill-based routing into the switching process, the system enables a more responsive and globally optimized allocation of resources that accounts for both immediate operational efficiency and long-term agent development.

Claims

This patent includes a total of 20 claims, with claims 1, 19, and 20 serving as the independent claims. These independent claims focus on methods and systems for pairing requests with available partners or resources by estimating requestor characteristics and using automated processors to evaluate potential pairings through probabilistic functions, Markov models, or neural networks to generate a control signal. The dependent claims serve to further define the evaluation process by incorporating economic functions, auction mechanisms, specific clustering algorithms, and various statistical models, while also specifying applications such as voice call routing and transaction optimization.

Key Claim Terms New

Definitions of key terms used in the patent claims.

Term (Source)Support for SpecificationInterpretation
Content-specific or requestor-specific characteristic
(Claim 1, Claim 20)
As a call is received, sufficient information is gathered to define the caller, either by identity or characteristics. This definition may then trigger an initial database lookup, for example to recall a user transaction file or a user profile. Such information may include preferred language, a voice stress analysis, word cadence, accent, sex, the nature of the call, personality type, etc.Data points extracted from a communication or its source used to define the nature of the task or the profile of the caller, such as language, technical issues, personality type, or historical transaction data.
Control signal
(Claim 1, Claim 19, Claim 20)
The voice channel processor handles connections and switching, but does not implement control. The control information is provided by the main processor over, for example, a PCI bus. The software system which handles virtual or real circuit switching and management resolves the destination using an algorithm.An electronic instruction generated by the processor to execute the physical routing or allocation of a communication channel to a selected target resource.
Evaluator for valuing pairings
(Claim 1)
Intelligent functions include, for example, but are not limited to, optimizations, artificial neural network implementation, probabilistic and stochastic process calculations, fuzzy logic, Bayesian logic and hierarchical Markov models (HMMs). The system according to the present invention may process advanced and complex algorithms for implementing intelligent control. The optimization of agent selection may also be influenced by other factors, such as training opportunities.An intelligent control algorithm—specifically utilizing probabilistic functions, Markov models, Bayesian logic, or neural networks—that calculates the suitability or cost-benefit of matching a specific request to a specific agent.
Partner characteristic
(Claim 1, Claim 19)
Each agent is assigned a metric with respect to each skill. As the agent is presented with tasks, the proficiency of the agent is analyzed, and the results used to define skill-specific metrics. The skill determining process may employ both manual assessment and collaborative filtering to infer agent skill levels where specific data is unavailable.A metric or profile representing the specific skills, proficiency levels, or attributes of an agent, which can be manually assigned or automatically derived from past performance analysis.
Probabilistic predictive multivariate evaluator
(Claim 20)
The skill sets are assigned using a multivariate analysis technique, based on analysis of a plurality of transactions, predicting the best set of skills consistent with the results achieved. In this analysis, each skill metric may be associated with reliability indicia. The system selects an optimal pairing of respective multiple agents with multiple matters based on a consolidated cost function.A computational model that analyzes multiple skill and characteristic variables simultaneously to predict the outcome or cost of an allocation based on statistical likelihoods.

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

US10237420

Application Number
US15856729A
Filing Date
Dec 28, 2017
Publication Date
Mar 19, 2019
External Links
Slate, USPTO , Google Patents