DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Information Disclosure Statement
The information disclosure statements (IDS) submitted on 06/25/2025 and 04/23/2026 are in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statements are being considered by the examiner.
Drawings
The drawings were submitted on 03/28/2025. These drawings are reviewed and accepted by the examiner.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claim(s) 1-20 are rejected under 35 U.S.C. 103 as being unpatentable over Chishti (US 20160080573 A1) in view of Perez et al. (US 20170214799 A1).
Regarding claims 1, 8, and 15, Chishti teaches:
“A communication system for processing a call” (par. 0035; ‘The present disclosure generally relates to contact center systems, traditionally referred to as “Automated Call Distribution” (“ACD”) systems.’), the communication system comprising:
“control logic, the control logic comprising at least call flow logic to direct the call along a directed graph of one or more call processing nodes” (par. 0033; ‘A typical contact center algorithmically assigns contacts arriving at the contact center to agents available to handle those contacts. At times, the contact center may be in an “L1 state” and have agents available and waiting for assignment to inbound or outbound contacts (e.g., telephone calls, Internet chat sessions, email).’);
“at least one of the nodes comprising a call queue” (par. 0036; ‘The most common traditional assignment method within a queue is “First-In, First-Out” or “FIFO” assignment wherein the longest-waiting contact is assigned to the longest-waiting agent.’); and
“the at least one node comprising the call queue configured with a control to balance (a) contributions of first-in, first-out priority to the call queue, and (2) matching of the call to agent attributes, in determining a service priority of calls in the call queue” (par. 0036; ‘The most common traditional assignment method within a queue is “First-In, First-Out” or “FIFO” assignment wherein the longest-waiting contact is assigned to the longest-waiting agent.’ ‘FIFO may also order queues of contacts where higher priority contact types may be positioned in a queue ahead of lower priority contact types.’).
However, Chishti does not expressly teach:
“at least one machine learning model generating call classifiers from outputs of an audio signal processor and a natural language processor configured to operate on the call”;
“heuristic logic configured to transform the call classifiers into a plurality of weighted sub-metrics for the call”;
“aggregate normalized Gaussian logic to transform the weighted sub-metrics into a metric control”; and
“the metric control applied as feedback to adapt the control logic.”
Perez teaches:
“at least one machine learning model generating call classifiers from outputs of an audio signal processor and a natural language processor configured to operate on the call” (par. 0037; ‘The virtual agent(s) may include or have access to a natural language processor, such as a parser 58 employing a suitable natural language grammar, which processes the inbound speech from the customer.’);
“heuristic logic configured to transform the call classifiers into a plurality of weighted sub-metrics for the call” (par. 0041; ‘The classification component 62 uses a probabilistic call classification model 84, denoted M.sub.1, to predict the type (class) of the customer call, based on the extracted features of the initial utterance 82.’ ‘The classification component 62 assigns the call to a single one of the predefined classes, based on the output of the model M.sub.1, or computes a distribution over all classes.’);
“aggregate normalized Gaussian logic to transform the weighted sub-metrics into a metric control” (par. 0107; ‘Concerning the parameters for the bandit (1) the complexity estimation is drawn from Gaussian distributions. (2) the types are drawn using a confusion matrix produced from the performance of the classifier, (3) α is drawn from a Gaussian distribution and (4) the parameter λ.sub.humman=0.4 and λ.sub.virtual.=1.0.’ The complexity estimation is equivalent to the metric control.); and
“the metric control applied as feedback, during the call, to adapt the control logic” (par. 0087; ‘The action α.sub.i is thus linked to a cost so that when the model decides to choose a human or virtual agent, a cost is assigned. The bound maximizes the trade-off between the probability (expectation) of success of giving the particular type of call with the particular estimation of the complexity to a specific agent which attempts to maximize the probability of success while minimizing the cost.’ The cost to choose between human or virtual agent is equivalent to feedback.).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Chishti’s contact center system by incorporating Perez’s virtual agent and classification components in order to predict the type of customer call. The combination would minimize the probability of failure of virtual agent-handled calls by accurately assessing the nature and the complexity level of a given inbound call from the beginning of the customer dialogue while considering the cost of human handled calls. (Perez: par. 0007)
Regarding claims 2 (dep. on claim 1), 9 (dep. on claim 8), and 16 (dep. on claim 15), the combination of Chishti in view of Perez further teaches:
“a communication interface configured to receive the call from a telephony carrier network” (Chishti: par. 0074; ‘The central switch 710 may receive incoming contacts (e.g., callers) or support outbound connections to contacts via a dialer, a telecommunications network, or other modules (not shown).’); and
“logic to configure a call flow between the communication interface and one or more of an outlet node and a call hangup node” (Chishti: par. 0033; ‘At times, the contact center may be in an “L1 state” and have agents available and waiting for assignment to inbound or outbound contacts (e.g., telephone calls, Internet chat sessions, email).’),
“the call flow comprising: an inlet node binding a communication address to the call flow” (Chishti: par. 0033; ‘At times, the contact center may be in an “L1 state” and have agents available and waiting for assignment to inbound or outbound contacts (e.g., telephone calls, Internet chat sessions, email).’);
“one or more queue nodes” (Chishti: par. 0034; ‘“L2 state” and have contacts waiting in one or more queues for an agent to become available for assignment. Such L2 queues could be inbound, outbound, or virtual queues.’); and
“at least one of the queue nodes coupled to one of the outlet node and the call hangup node” (Chishti: par. 0034; ‘“L2 state” and have contacts waiting in one or more queues for an agent to become available for assignment. Such L2 queues could be inbound, outbound, or virtual queues.’).
Regarding claims 3 (dep. on claim 2), 10 (dep. on claim 9), and 17 (dep. on claim 16), the combination of Chishti in view of Perez further teaches:
“the call flow further comprising: at least one bot node, the control logic adapting the at least one bot node responsive to the feedback metric control” (Chishti: par. 0033; ‘At times, the contact center may be in an “L1 state” and have agents available and waiting for assignment to inbound or outbound contacts (e.g., telephone calls, Internet chat sessions, email).’).
Regarding claims 4 (dep. on claim 3), 11 (dep. on claim 10), and 18 (dep. on claim 17), the combination of Chishti in view of Perez further teaches:
“wherein the at least one bot node is configured as an automated voice attendant” (Perez: par. 0026; ‘Then, a sequential decision process is used in order to dispatch calls to human or automated agents based on the inferred class of the call, its inherent complexity, a feedback loop of the success of the calls and a cost associated with each agent type.’).
Regarding claims 5 (dep. on claim 1) and 12 (dep. on claim 8), the combination of Chishti in view of Perez further teaches:
“at least one template, the control logic adapting the template responsive to the feedback metric control” (Perez: par. 0045; ‘The feedback component 70 derives feedback 94 on the success of the dialogue, e.g., after the dialogue is complete, and provides the feedback to the update component 72’).
Regarding claims 6 (dep. on claim 1), 13 (dep. on claim 8), and 19 (dep. on claim 15), the combination of Chishti in view of Perez further teaches:
“wherein the control logic comprises a machine learning model” (Perez: par. 0043; ‘The model M.sub.3 may be learned by the training component 74, using success labels assigned to the dialogues in the corpus 86. As will be appreciated, separate training components may be employed for learning each of the models M.sub.1, M.sub.2, and M.sub.3.’).
Regarding claims 7 (dep. on claim 6), 14 (dep. on claim 13), and 20 (dep. on claim 19), the combination of Chishti in view of Perez further teaches:
“further comprising a learning function for the machine learning model of the control logic utilizing a call history and one or more of the weighted sub-metrics and the metric control” (Perez: par. 0020; ‘The method includes learning a dialogue class model for predicting a class of a dialogue to be conducted based on an utterance of a call, the learning being based on prior dialogues conducted between a respective customer and an agent that are annotated by class.’).
Conclusion
Other pertinent prior art are cited in the PTO-892 for the applicant's consideration.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to MARK VILLENA whose telephone number is (571)270-3191. The examiner can normally be reached 10 am - 6pm EST Monday through Friday.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Richemond Dorvil can be reached at (571) 272-7602. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
MARK . VILLENA
Examiner
Art Unit 2658
/MARK VILLENA/Examiner, Art Unit 2658
