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 . In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
DETAILED ACTION
The following FINAL Office Action is in response to communication filed on 3/12/2026.
Priority
The Examiner has noted the Applicant claiming Priority from Provisional Application 63/594,688 filed 10/31/2023.
IDS
The information disclosure statement filed on 1/5/2026 complies with the provisions of 37 CFR 1.97, 1.98 and MPEP § 609 and is considered by the Examiner.
Status of Claims
Claims 1-20 are currently pending.
Claims 1, 2, 11, 13, 14, 15, 16, 20 are currently amended.
Claims 1-20 are currently under examination and have been rejected as follows.
-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
Response to Amendment
The previously pending Double Patenting rejection will be maintained.
The previously pending rejections under 35 USC 101 will be maintained. The 101 rejection is updated in view of the amendments.
The previously pending rejections under 35 USC 102 are withdrawn in view of the amendments.
New grounds for rejection under 35 USC 103 are applied as necessitated by the amendments.
-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
Response to Arguments
Regarding Applicant’s remarks pertaining to 35 USC 101:
Step 2A Prong 1:
Applicant argues on page 2 of remarks 3/12/2026:
“Importantly, the data processing pipeline steps recited in the amended claims… are NOT abstract ideas. These steps do not fall within the "Certain Methods of Organizing Human Activity" grouping because they are not commercial interactions, business relations, or methods of managing interactions between people-they are specific technical data processing operations performed by a computer system. Nor are these steps "Mathematical Concepts" because they do not recite mathematical relationships, formulas, equations, or calculations. Rather, these are specific technical data processing operations that require computer implementation and cannot be characterized as either of the abstract idea groupings alleged by the Examiner.”
Examiner respectfully disagrees. Requiring a computer or technical operations to be performed does not exempt claims from reciting abstract ideas. Analyzing customer experience, satisfaction, and value data to assign scores to customer feedback, thereby prescribing targeted customer engagement based on individual and group characteristics of the customers, despite being performed in a technical process by a computer, still falls within mitigating risk as it pertains to fundamental economic principles; marketing or sales activities or behaviors and business relations as they pertain to commercial or legal interactions; and managing relationships or interactions between people. Additionally, computing metrics as using methods such as feature vectors and weighted factors, despite also being performed by a computer, falls withing mathematical relationships and calculations.
Step 2A Prong 2:
Applicant argues on page 3 of remarks 3/12/2026:
“The specification identifies a specific technical problem in data processing systems… the inability of prior computer systems to identify correlations across disparate data sources that use inconsistent terminology.”
Continued on page 4: “The claims as amended recite a specific technical solution to this technical problem…. These disclosures [from specification paragraphs 108, 122] demonstrate that the claimed invention provides a technological improvement-enabling the computer system to identify correlations that would otherwise be impossible due to inconsistent terminology across disparate data sources.”
Examiner respectfully disagrees. Transforming customer feedback data from multiple types of data channels, such as text and voice, into a standardized formats are known in the field and also disclosed inter alia in primary reference Gupta (see Fig. 5 and related text) and newly presented reference Chopra et al. US 20230112369 A1, hereinafter Chopra (see Fig. 3; also see Step 2B response below). Considering this in tandem with known NPL processes for making correlations between terminology (e.g., Chopra ¶ [0066], Gupta ¶ [0056]-[0058], Applicant spec. ¶ [0108]-[0109]), it remains unclear to Examiner how the present invention’s identification of language correlation achieves the otherwise impossible with existing technology.
Applicant argues on page 4 of remarks 3/12/2026:
“In SME Example 47, Claim 3 (Anomaly Detection), the claim was found eligible because it recited specific technical steps that improved network security-specifically, detecting anomalies in network traffic, determining that a detected anomaly is associated with malicious network packets, detecting a source address, dropping the malicious packets in real time, and blocking future traffic from the source address…. Similarly, the
present claims recite specific technical steps that improve the computer system's ability to identify correlations across disparate data sources….”
Examiner respectfully disagrees. Similar to the above first Step 2A Prong Two argument, transforming customer feedback data from multiple types of data channels, such as text and voice, into a standardized formats are known in the field and also disclosed inter alia in primary reference Gupta (see Fig. 5 and related text) and newly presented reference Chopra (see Fig. 3; also see Step 2B response below). Considering this in tandem with known NPL processes for making correlations between terminology (e.g., Chopra ¶ [0066], Gupta ¶ [0056]-[0058], Applicant spec. ¶ [0108]-[0109]), it remains unclear to Examiner how existing technology is improved.
Applicant argues on page 5 of remarks 3/12/2026:
“Despite reciting this abstract idea, the claim [from SME Example 42] was found eligible at Step 2A Prong Two because "the additional elements recite a specific improvement over prior art systems by allowing remote users to share information in real time in a standardized format regardless of the format in which the information was input by the user." Like Example 42, the present claims recite converting data from multiple input channels (which may use different formats and terminology) into a standardized format in the semantic knowledge database, enabling a specific technical improvement-here, identification of correlations between feedback records that use different terminology to describe the same subject matter.”
Examiner respectfully disagrees. Though the claims of Example 42 may have demonstrated technological improvement in that field, similar to the above first Step 2A Prong Two argument, transforming customer feedback data from multiple types of data channels, such as text and voice, into a standardized formats are known in the field of customer feedback data processing and also disclosed inter alia in primary reference Gupta (see Fig. 5 and related text) and newly presented reference Chopra (see Fig. 3; also see Step 2B response below). Considering this in tandem with known NPL processes for making correlations between terminology (e.g., Chopra ¶ [0066], Gupta ¶ [0056]-[0058], Applicant spec. ¶ [0108]-[0109]), it remains unclear to Examiner how existing technology is improved.
Applicant argues on page 5 of remarks 3/12/2026:
“The amended claims are also analogous to SME Example 48 (Speech Separation), which was found eligible because the ordered combination of steps reflected a technical improvement to speech-to-text technology.”
Examiner respectfully disagrees. Though analogous, Examiner finds Example 48 to meet eligibility in a different way. The present invention appears to focus on improvements in aggregated customer sentiment data processing, including audio speech data, and incorporating existing speech-to-text technology, rather than focusing on improvement of specific speech-to-text technological algorithms (see Applicant spec. ¶ [0008].
Applicant argues on page 6 of remarks 3/12/2026:
“The amended claims are consistent with Federal Circuit precedent finding claims eligible when directed to specific technological improvements. In Enfish, LLC v. Microsoft Corp… claims to a self-referential table for a computer database were found directed to an improvement in computer capabilities and not directed to an abstract idea.”
Examiner respectfully disagrees. The Enfish claims attained eligibility because the the execution of the self-referential table demonstrated an improvement in the computer operation itself, not just the software. More specifically, Enfish demonstrated an improvement to the interactions between the computer processor and its memory.
Applicant argues on page 7 of remarks 3/12/2026:
“In McRO, Inc. v. Bandai Namco Games Am. Inc… claims to automatic lip synchronization and facial expression animation were found directed to an improvement in computer-related technology…. The present claims recite a particular ordered combination of steps that together enable the technical result of identifying correlations between feedback records that use different terminology to describe the same subject matter.”
Examiner respectfully disagrees. McRo improved/changed the operation of the computer system by defined a specific way, namely use of particular rules to set morph weights and transitions through phonemes, to solve the problem of producing accurate and realistic lip synchronization and facial expressions in animated characters, and thus were not directed to an abstract idea. In the present case, the claims define a new technological method for collecting, analyzing, and evaluating sentiment from customer feedback. The claims are not a technical improvement to the operation of a computer but the removal of human labor that is automating these tasks and not patent eligible (see In re Venner, 262 F.2d 91, 95, 120 USPQ 193, 194 (CCPA 1958)).
Applicant argues on page 7 of remarks 3/12/2026:
“Like the claims in Ex Parte Desjardins, the amended claims are directed to a specific technological solution rather than merely claiming the idea of a solution. The claims recite a particular ordered combination of steps-data conversion, aggregation, cleaning, ETL transformation into a standardized format, loading into a semantic knowledge database, NLP feature extraction, and clustering/segmentation-that together enable the technical result of identifying correlations between feedback records that use different terminology to describe the same subject matter.”
Examiner respectfully disagrees. Specifically, the Ex Parte Desjardins decision cited technological improvements in machine learning, including to “effectively learn new tasks in succession whilst protecting knowledge about previous tasks”, allowing AI systems to “us[e] less of their storage capacity”, and enabling “us[e] less of their storage capacity”. The Ex Parte Desjardins decision rested on both the specific technological solution and the improvement in the technology itself, the latter of which is not clear for the present invention for reasons explained above.
Step 2B:
Applicant argues on page 8 of remarks 3/12/2026:
“The specific ordered combination of steps recited in the amended claims-data conversion and aggregation, pre-processing and cleaning by removing PII and noise, ETL transformation into a standardized format for loading to a semantic knowledge database, NLP feature extraction to produce feature vectors, and clustering/segmentation on the feature vectors to identify clusters of feedback-is not well-understood, routine, or conventional activity…. Here, the specific combination of steps that enables identification of correlations between feedback records using different terminology is not conventional-it is the specific technical solution to the technical problem identified in the specification.”
Examiner respectfully disagrees. The specific steps listed above for the present case, which describe the recited claim limitations currently amended in the independent claims, are also disclosed in newly presented reference Chopra, at ¶s [0030], [0046], [0047], [0052], [0056], [0058], [0066], [0067], [0071] (see response to arguments 35 USC 103 section below). Each of the individual processes of data conversion/aggregation (Applicant spec. ¶ [0040]), cleaning (¶ [0107]), standardization (¶ [0070]), natural language processing with feature extraction (¶ [0109]), and clustering/segmentation ¶ [0103]) are known or conventional in the data processing field and demonstrated in combination inter alia by Chopra to evaluate customer sentiment.
-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
Regarding Applicant’s remarks pertaining to 35 USC 102/103:
Applicant argues on page 12 of remarks 3/12/2026:
“As discussed above in connection with the rejection under 35 U.S.C. § 102, Gupta fails to disclose the amended limitations of claim 1…. Applicant respectfully submits that Scholz does not cure the deficiencies of Gupta with respect to the amended claim limitations.”
Continued on page 13: “Furthermore, the combination of Gupta and Scholz fails to teach or suggest the specific three-tier metric architecture recited in claims 11 and 13 as amended.”
Continued on page 14: “… the combination of Gupta and Scholz fails to disclose the amended limitations of independent claims 1, 11, and 13. The addition of Matam does not cure these deficiencies.”
Examiner considers Applicant’s arguments but finds the arguments moot on new grounds. Examiner points to new reference Chopra et al. US 20230112369 A1, hereinafter Chopra, which teaches the claims as amended in combination with the previously presented references. Specifically, Chopra teaches the following amended claim limitations from claims 1, 11, and 13:
converting data from the multiple input channels to text data, and aggregating the text data in a data library (¶ [0030]);
pre-processing and cleaning the text data by removing personally identifiable information and removing noise from the text data to generate cleaned data (¶ [0042], [0046]-[0047]);
exporting the cleaned data into an export, transform and load (ETL) module to transform the cleaned data for loading to a semantic knowledge database as transformed data that is transformed into a standardized format; loading the transformed data into the semantic knowledge database (¶ [0052], [0056], [0058]);
wherein the transformed data in the standardized format enables identification of correlations between feedback records from the multiple input channels that use different terminology and phraseology to describe a same subject matter (¶ [0066]);
performing natural language processing on the transformed data of the semantic knowledge database using feature extraction to produce feature vectors (¶ [0052], [0067]);
performing data clustering and segmentation on the feature vectors to identify clusters of feedback related to products, services and departments (¶ [0068], [0071]);
[..] wherein the first metric is derived from the feature vectors (¶ [0067]);
Detailed citations and rationale are included in the 103 rejection section below.
Accordingly, new grounds for rejection under 35 USC 103 are applied as necessitated by the amendments.
-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
Double Patenting
The nonstatutory double patenting rejection is based on a judicially created doctrine grounded in public policy (a policy reflected in the statute) so as to prevent the unjustified or improper timewise extension of the “right to exclude” granted by a patent and to prevent possible harassment by multiple assignees. A nonstatutory double patenting rejection is appropriate where the conflicting claims are not identical, but at least one examined application claim is not patentably distinct from the reference claim(s) because the examined application claim is either anticipated by, or would have been obvious over, the reference claim(s). See, e.g., In re Berg, 140 F.3d 1428, 46 USPQ2d 1226 (Fed. Cir. 1998); In re Goodman, 11 F.3d 1046, 29 USPQ2d 2010 (Fed. Cir. 1993); In re Longi, 759 F.2d 887, 225 USPQ 645 (Fed. Cir. 1985); In re Van Ornum, 686 F.2d 937, 214 USPQ 761 (CCPA 1982); In re Vogel, 422 F.2d 438, 164 USPQ 619 (CCPA 1970); In re Thorington, 418 F.2d 528, 163 USPQ 644 (CCPA 1969).
A timely filed terminal disclaimer in compliance with 37 CFR 1.321(c) or 1.321(d) may be used to overcome an actual or provisional rejection based on nonstatutory double patenting provided the reference application or patent either is shown to be commonly owned with the examined application, or claims an invention made as a result of activities undertaken within the scope of a joint research agreement. See MPEP § 717.02 for applications subject to examination under the first inventor to file provisions of the AIA as explained in MPEP § 2159. See MPEP § 2146 et seq. for applications not subject to examination under the first inventor to file provisions of the AIA . A terminal disclaimer must be signed in compliance with 37 CFR 1.321(b).
The filing of a terminal disclaimer by itself is not a complete reply to a nonstatutory double patenting (NSDP) rejection. A complete reply requires that the terminal disclaimer be accompanied by a reply requesting reconsideration of the prior Office action. Even where the NSDP rejection is provisional the reply must be complete. See MPEP § 804, subsection I.B.1. For a reply to a non-final Office action, see 37 CFR 1.111(a). For a reply to final Office action, see 37 CFR 1.113(c). A request for reconsideration while not provided for in 37 CFR 1.113(c) may be filed after final for consideration. See MPEP §§ 706.07(e) and 714.13.
The USPTO Internet website contains terminal disclaimer forms which may be used. Please visit www.uspto.gov/patent/patents-forms. The actual filing date of the application in which the form is filed determines what form (e.g., PTO/SB/25, PTO/SB/26, PTO/AIA /25, or PTO/AIA /26) should be used. A web-based eTerminal Disclaimer may be filled out completely online using web-screens. An eTerminal Disclaimer that meets all requirements is auto-processed and approved immediately upon submission. For more information about eTerminal Disclaimers, refer to www.uspto.gov/patents/apply/applying-online/eterminal-disclaimer.
Claims 1-20 are provisionally rejected on the ground of nonstatutory obviousness-type double patenting as being unpatentable over claims 1-9 of Application No. 19/335,956 (reference application). Although the conflicting claims are not identical, they are not patentably distinct from each other because claims in each application recite substantially similar limitations directed to a process for predicting a cause of the classified incident based on different information.
Although the conflicting claims are not identical, they are not patentably distinct from each other because claims 1-9 in the reference application and claims 11-18 in the instant application recite substantially similar limitations. Thus claims 11-18 in the instant application are obvious variants of claims 1-9 in the reference application.
This is a provisional nonstatutory double patenting rejection because the patentably indistinct claims have not in fact been patented.
-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
Claims 1-12 are directed to a system or machine which is a statutory category.
Claims 13-20 are directed to a method or process which is a statutory category.
Step 2A Prong One: The claims recite, describe, or set forth a judicial exception of an abstract idea (see MPEP 2106.04(a)). Specifically, the claims recite, describe or set forth mathematical relationships and calculations, mitigating risk, marketing or sales activities or behaviors, business relations, and managing relationships or interactions between people, including: “analyze data received from internal and external data sources via multiple input channels”, “converting data from the multiple input channels to text data, and aggregating the text data in a data library”, “removing personally identifiable information and removing noise from the text data to generate cleaned data”, “transform
the cleaned data… into a standardized format”, “the transformed data in the standardized format enables identification of correlations between feedback records from the multiple input channels that use different terminology and phraseology to describe a same subject matter”, “performing natural language processing on the transformed data of the semantic knowledge database using feature extraction to produce feature vectors”, “performing data clustering and segmentation on the feature vectors to identify clusters of feedback related to products, services and departments”, “computing a first metric from a plurality of first data sources, a second metric from a plurality of second data sources and a third metric from a plurality of third data sources, wherein the first metric is derived from the feature vectors”, “computing an assessment value using a calculation including the first, second and third metrics, and first, second and third weighting factors, each of the metrics being multiplied by its corresponding weighting factor in the calculation”, and “prescribing targeted interactions with a subject based on the assessment value”. Analyzing customer experience, satisfaction, and value data to assign scores to customer feedback, thereby prescribing targeted customer engagement based on individual and group characteristics of the customers falls within mitigating risk as it pertains to fundamental economic principles; marketing or sales activities or behaviors and business relations as they pertain to commercial or legal interactions; and managing relationships or interactions between people; each under the larger abstract grouping of Certain Methods of Organizing Human Activity (MPEP 2106.04(a)(2) II). Furthermore, computing metrics as using methods such as feature vectors and weighted factors falls withing mathematical relationships and calculations under the larger abstract grouping of Mathematical Concepts (MPEP 2106.04(a)(2) I).1 Accordingly, the claims recite an abstract idea.
Step 2A Prong Two: Independent claims 1, 3 recite the following additional elements: “semantic knowledge database”, “export, transform and load (ETL) module”, “computer”, “processors”, “memory”, “internal and external data sources”, various “input channels”, and “network connection”. The functions of these additional elements include examples such as analyzing data, connecting the computer to data sources, computing metrics with weighted sums, computing scores, prescribing client interactions based on scores, and updating weighting factors. The additional elements are recited at a high level of generality (i.e. as a generic computer performing functions of collecting and analyzing data, calculating metrics and scores, etc.) such that they amount to no more than mere instructions to apply the exception using generic computer components. Therefore, these functions can be viewed as not meaningfully different than a business method or mathematical algorithm being applied on a general-purpose computer as tested per MPEP 2106.05(f)(2)(i). The claims are directed to an abstract idea and the judicial exception does not integrate the abstract idea into a practical application.
Step 2B: According to MPEP 2106.05(f)(1), considering whether the claim recites only the idea of a solution or outcome i.e., the claims fail to recite the technological details of how the actual technological solution to the actual technological problem is accomplished. The recitation of claim limitations that attempt to cover an entrepreneurial and thus abstract solution to an entrepreneurial problem with no technological details on how the technological result is accomplished and no description of the mechanism for accomplishing the result do not provide significantly more than the judicial exception.
Dependent claims 10, 12, 20 recite the additional element “neural network”. The function of this additional element includes using supervised learning to identify weighting factor values minimizing the penalty function. The additional elements are also recited at a high level of generality (i.e. as a generic computer performing functions of optimizing mathematical functions, etc.) such that they amount to no more than mere instructions to apply the exception using generic computer components. Furthermore, the “neural network” and “supervised learning” language merely requires execution of an algorithm that can be performed by a generic computer component and provides no detail regarding the operation of that algorithm. As such, the claim requirement amounts to mere instructions to implement the abstract idea on a computer, and, therefore, is not sufficient to make the claim patent eligible. See Alice, 573 U.S. at 226 (determining that the claim limitations “data processing system,” “communications controller,” and “data storage unit” were generic computer components that amounted to mere instructions to implement the abstract idea on a computer); October 2019 Guidance Update at 11–12 (recitation of generic computer limitations for implementing the abstract idea “would not be sufficient to demonstrate integration of a judicial exception into a practical application”). Such a generic recitation of “machine learning model” alone is insufficient to show a practical application of the recited abstract idea.
Further, dependent claims 2-9, 11, 13-20 merely incorporate the additional elements recited in claims 1, 11, 13 along with further narrowing of the abstract idea of claims 1, 11, 13 and their execution of the abstract idea. Specifically, the dependent claims narrow the “semantic knowledge database”, “computer”, “internal and external data sources”, and various “input channels” to capabilities such as computing, summing, deriving, including, receiving, normalizing, maximizing, minimizing, and identifying various forms of data such as clients, feedback, sentiments, online chat, complaints, voices, KPIs, factors, ranges, correlations, parameters, scores, values etc. which, when evaluated per MPEP 2106.05(f)(2) represent mere invocation of computers to perform existing processes. Therefore, the additional elements recited in the claimed invention individually and in combination fail to integrate a judicial exception into a practical application (Step 2A prong two) and for the same reasons they also fail to provide significantly more (Step 2B). Thus, claims 1-20 are reasoned to be patent ineligible.
-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
REJECTIONS BASED ON PRIOR ART
Examiner Note: Some rejections will contain bracketed comments preceded by an “EN” that will denote an examiner note. This will be placed to further explain a rejection.
-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
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 of this title, 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.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claims 1-4, 6 are rejected under 35 U.S.C. 103 as being unpatentable over: Gupta et al. US 20220253777 A1, hereinafter Gupta, in view of
Chopra et al. US 20230112369 A1, hereinafter Chopra. As per,
Regarding claim 1: Gupta teaches:
A system for computing metrics from unstructured datatypes and data structures of a semantic knowledge database ontology with data clusters (Gupta ¶ [0024]: Embodiments disclosed herein relate to systems, devices, and methods for generating and dynamically updating an experience score for a client, where the experience score operates as a quantitative indicator describing a relationship between the client and an entity. Mid-¶ [0051]: the system is configured to recognize one or more predefined keywords that are known to be associated with particular sentiment of the client [EN: semantic knowledge] (i.e. where certain keywords indicate or contribute to a positive or negative sentiment score). ¶ [0052]: The data 300 can also be in the form of structured data 310 or unstructured data 315. ¶ [0107]: Act 1010 includes using natural language processing (NLP) to provide structure to the unstructured sentiment data. As a consequence, a second set of structured sentiment data (e.g., the set of structured sentiment data 415A [EN: semantic knowledge] from FIG. 4) is acquired), said system comprising:
a computer with one or more processors and memory, where the computer is configured to analyze data received from internal and external data sources via multiple input channels (Gupta ¶ [0046]: In some cases, the sources can be linked to an entity's platform [EN: internal data sources], such as a website that offers clients the opportunities to leave feedback. In other scenarios, the sources are independent relative to the entity [EN: external data sources], such as the case where the source is in the form of a social media platform or some other independent entity. In such scenarios, the interactions engine 140 can be configured to crawl 150 a public network (e.g., the Internet) to identify other sources (e.g., indirect sources or third-party sources) where a user may have expressed his/her viewpoints about a particular entity. For instance, FIG. 1 shows the interactions engine 140 crawling a network 155 to identify a source 160 that is entirely independent of the entity 130 and that can be a third-party source. From this source 160, the interactions engine 140 can acquire additional sentiment data. Accordingly, in this sense, the disclosed interactions engine 140 and ML engine 140A can be configured to perform big data mining 165 and analysis); and
a network connection operatively connecting the external data sources to the computer (Gupta mid-¶ [0046]: For instance, FIG. 1 shows the interactions engine 140 crawling a network 155 to identify a source 160 that is entirely independent [EN: external] of the entity 130 and that can be a third party source),
where the computer is configured to perform steps including:
[..]
computing a first metric from a plurality of first data sources, a second metric from a plurality of second data sources and a third metric from a plurality of third data sources, [..] (See Gupta Fig. 5 showing multiple metrics, or scores, generated from various data sources);
computing an assessment value using a calculation including the first, second and third metrics, and first, second and third weighting factors (Gupta ¶ [0079]: Returning to FIG. 4, the ML engine 405 aggregates the normalized and weighted scores to generate an aggregate score 440, which is then provided as output 445 in the form of an experience score),
each of the metrics being multiplied by its corresponding weighting factor in the calculation (See Gupta equation below ¶ [0079] multiplying corresponding metrics and weights. ¶ [0080]: In the above algorithm, M is the number of inputs for this particular customer, wi is the importance weight for the ith input, t; is the history weight for the ith input based on the time of feedback or interaction, and si is the normalized score [EN: metric] from that input. FIG. 5 shows an aggregated score 570, which is representative of the aggregate score 440); and
prescribing targeted interactions with a subject based on the assessment value (Gupta ¶ [0115]: Act 1035 then includes using the experience score to modify a subsequent interaction the client has with the entity. For instance, modify experience 175 from FIG. 1 and modify experience 700 from FIG. 7 are representative of example options for modifying the user's subsequent interactions with the entity…. Another way to dynamically influence interactions is by initiating [EN: prescribing] a new interaction, such as by prompting a client to refer another client. ¶ [0087]: FIG. 7 shows various examples of how the disclosed embodiments can modify a user's experience with an entity, as represented by modify experience 700. In one scenario, various campaigns 705 can be triggered. A campaign can include targeted promotions or advertisements that are directed to a client).
Although Gupta teaches calculating multiple weighted client metrics and semantic assessment values based on client feedback and prescribing targeted interactions with clients based on the assessments, Gupta does not specifically teach converting non-text data to text data, cleaning data of noise and PII, standardizing the data in a semantic knowledge base, identifying correlations in client feedback phrased in different ways, and producing feature vectors to identify related products and services.
However, Chopra in analogous art of modeling consumer sentiment and behavior teaches or suggests:
converting data from the multiple input channels to text data, and aggregating the text data in a data library (Chopra ¶ [0030]: In some embodiments, the user activity database 102a [EN: library] stores transcripts or other memorializations of the interaction-for example, in the case of a text chat session or a virtual assistant chat session, the database 102a can store unstructured text corresponding to the messages exchanged between the CSR/VA and the end user. In the case of a voice call, the database 102a can store a digital audio recording of the voice call and/or a transcript of the voice call (e.g. as generated by a speech-to-text module that converts the digital audio recording
into unstructured text));
pre-processing and cleaning the text data by removing personally identifiable information and removing noise from the text data to generate cleaned data (Chopra ¶ [0042]: The embedding generation module 110 then performs a data pre-processing and cleaning routine (304) on the incoming interaction text data. During the data pre-processing and cleaning routine, the embedding generation module 110 performs one or more tasks on the unstructured text to ensure that the text is in a form that can be used to generate embeddings as will be described later in the document. Exemplary pre-processing and cleaning tasks performed by the module 110 can include: … ¶ [0046]: Replace end user-related masked information: the module 110 can determine end-user specific information that is sensitive or confidential (such as personally identifiable information (PII)) and mask this information in the transcript by, e.g., replacing the information with anonymizing overlay values… ¶ [0047]: Remove non-vocalized noise or unintelligible utterances: when converting a digital audio recording of a voice call, the module 110 may generate text that relates to non-vocalized noise and/or unintelligible words spoken by the participants. The module 110 can remove these words from the transcript by, e.g., determining whether they correspond to a recognized word in a predefined dictionary and if not, removing them from the text data);
exporting the cleaned data into an export, transform and load (ETL) module to transform the cleaned data for loading to a semantic knowledge database as transformed data that is transformed into a standardized format; loading the transformed data into the semantic knowledge database (Chopra ¶ [0052]: After the embedding generation module 110 has completed the pre-processing and cleaning the unstructured text data for the interactions, the module 110 converts the text data into interaction embeddings [EN: standardized data] for processing by the neural networks 108a, 108b. ¶ [0056]: Upon generation of the initial word embeddings for each of the intent model 108a and short summary model 108b, the embedding generation module 110 transmits the corresponding embeddings to the respective models 108a, 108b for training and/or execution. ¶ [0058]: Once the model 108b is trained, the server computing device 106 can subsequently execute (312b) the trained model 108b using as input interaction embeddings generated from new interactions to automatically generate a short summary for the interaction transcript and CSR notes to which new interactions correspond. Upon execution of the intent model 108a and/or the short summary model 108b against computer text segments from new interactions, the server computing device 106 stores the output (i.e., the intents and/or short summaries generated by the models 108a, 108b) in the output database 102b.);
wherein the transformed data in the standardized format enables identification of correlations between feedback records from the multiple input channels that use different terminology and phraseology to describe a same subject matter (Chopra ¶ [0066]: Next, the clustering module 112 performs the embedding creation step (606) to generate word/phrase embeddings based upon the cleaned intents and/or short summaries. Vectorization and embedding generation is important in this phase because two intents (as modified by CSRs) could have the same meaning but could be written differently);
performing natural language processing on the transformed data of the semantic knowledge database using feature extraction to produce feature vectors (Chopra mid-[0039]: the system 100 can convert the audio into unstructured text using, e.g., a speech-to-text conversion module that analyzes the waveforms in the audio file and converts them into natural language text. Mid-¶ [0052]: …each token corresponds to a word in the corpus of text and a token is a fundamental unit that a text processing system typically works with. By generating tokens from the unstructured text, the module 110 can apply sophisticated algorithms, e.g., to identify the part-of-speech of each token, form trigrams that are used for other processing function like clustering described in detail below, etc. ¶ [0067]: …As shown in FIG. 8, the cleaned and normalized intents 802 are converted into a multidimensional embedding (or vector) comprising feature values (e.g., 0.2, 0.65...) corresponding to the features of the intent detected by the clustering module 112);
performing data clustering and segmentation on the feature vectors to identify clusters of feedback related to products, services and departments (Chopra ¶ [0068]: As a result, the clustering module 112 performs a dimensionality reduction step (608) to convert the large dimension embedding [EN: feature vectorization, see paragraph 0067] into a form that is more efficient for the grouping [EN: segmenting] and clustering steps described herein. ¶ [0071]: After dimensionality reduction, the clustering module 112 performs entity detection (610) on the text of the intents and short summaries using a named entity recognition (NER) model that is trained to identify organization specific products, services, and other types of entities);
[..] wherein the first metric is derived from the feature vectors (Chopra ¶ [0067]: …As shown in FIG. 8, the cleaned and normalized intents 802 are converted into a multidimensional embedding (or vector) comprising feature values [EN: metrics] (e.g., 0.2, 0.65...) corresponding to the features of the intent detected by the clustering module 112)).
Chopra and Gupta are found as analogous art of modeling consumer sentiment and behavior. It would have been obvious to one skilled in the art, before the effective filing date of the invention, to have modified Gupta’s techniques for generating and dynamically updating client experience scores to have included Chopra’s teachings around converting non-text data to text data, cleaning data of noise and PII, standardizing the data in a semantic knowledge base, identifying correlations in client feedback phrased in different ways, and producing feature vectors to identify related products and services. The benefit of these additional features would have eased the efforts to identify customer intent behind interactions and planning for information and service needs, and reduced time for analysis and understanding of actionable information (Chopra ¶ [0004]). The predictability of such modifications and/or variations, would have been corroborated by the broad level of skill of one of ordinary skills in the art as articulated by Gupta in view of Chopra (see MPEP 2143 G).
Further, the claimed invention could have also been viewed as a mere combination of old elements in a similar field of modeling consumer sentiment and behavior. In such combination each element would have merely performed the same function as it did separately. Thus, one of ordinary skill in the art would have recognized that, given existing technical ability to combine the elements, as evidenced by Gupta in view of Chopra above, the to- be combined elements would have fit together like pieces of a puzzle in a logical, complementary, technologically feasible and/or economically desirable manner. Thus, it would have been reasoned that the results of the combination would have been predictable (see MPEP 2143 A).
Regarding claim 2: Gupta / Chopra teaches all the limitations of claim 1 above.
Gupta further teaches:
wherein the plurality of first data sources is client feedback data received from the external data sources via the multiple input channels (Gupta ¶ [0064]: FIG. 5 shows a set of input 500, which is representative of the input 410 from FIG. 4. The input 500 can include data from any number of sources and can include expressions made by a client), and
the first metric is computed as a weighted sum of client sentiments each derived from a different one of the input channels (Gupta ¶ [0064]: Returning to FIG. 4, the process flow 400 includes the ML engine 405 generating and applying weight(s) 435 to each respective input type [EN: input channel]. That is, the ML engine generates the weighting factors…. As a result of applying the weights, the ML engine 405 has generated a set of weighted scores 435A. FIG. 5 provides a useful illustration).
Regarding claim 3: Gupta / Chopra teaches all the limitations of claim 2 above.
Gupta further teaches:
wherein the client sentiments include a sentiment derived from each of a call center input channel, an online chat input channel, a client complaints input channel, a voice of the customer input channel, and two different mobile device application store input channels (Gupta mid-¶ [0064]: As some examples, the input 500 [EN: input channel] can be acquired from messages 505 [EN: mobile device application], a webchat 510, a survey 515 [EN: complaints], reviews 520 [EN: complaints], social media 525 [EN: mobile device application], texts 530 [EN: mobile device application], voicemail 535 [EN: call center, customer voice], email 540 [EN: mobile device application]. ¶ [0047]: In some scenarios, such as where a client has enabled microphone access associated with the entity or a separate application that is linked to the entity, the system is able to gather feedback data, through automatic speech [EN: voice] recognition, by identifying relevant speech signals recorded by a client's microphone (i.e. if the client is speaking about his or her interaction with the entity)).
Regarding claim 4: Gupta / Chopra teaches all the limitations of claim 1 above.
Gupta further teaches:
wherein the plurality of second data sources is client experience key performance indicators (KPIs) received from the internal data sources (Gupta ¶ [0046]: ¶ [0046]: In some cases, the sources can be linked to an entity's platform [EN: internal data sources], such as a website that offers clients the opportunities to leave feedback [EN: experience KPI]. Mid-¶ [0049]: For instance, one type of interaction can be a user's response to a survey [EN: experience KPI], and the [EN: internal data] "source" would be the survey… Another type of interaction can be a user providing feedback in a website, and the [EN: internal data] source would be the website), and
the second metric is computed as a weighted sum of the client experience KPIs (Gupta ¶ [0064]: Returning to FIG. 4, the process flow 400 includes the ML engine 405 generating and applying weight(s) 435 to each respective input type. That is, the ML engine generates the weighting factors…. As a result of applying the weights, the ML engine 405 has generated a set of weighted scores 435A. FIG. 5 provides a useful illustration).
Regarding claim 6: Gupta / Chopra teaches all the limitations of claim 1 above.
Gupta further teaches:
wherein the first, second and third metrics are normalized to a common range of values before computing the assessment value (Gupta ¶ [0063]: After providing structure to any unstructured data, the ML engine 405 then normalizes the data, all of which should now have the same or matching structure (e.g., perhaps the structure is a numerical indicator), as represented by normalized score(s) 430. As one example, all scores can optionally be normalized to fall within a range between O and 10. The process of normalizing the data results in all of the data having the same scale).
-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
Claims 5, 7-8, 11, 13-18 are rejected under 35 U.S.C. 103 as being unpatentable over:
Gupta / Chopra as applied above, in further view of
Scholz US 20170257285 A1, hereinafter Scholz. As per,
Regarding claim 5: Gupta teaches all the limitations of claim 1 above.
Although Gupta teaches calculating multiple weighted client metrics from internal data sources and multiple channels of external data sources, Gupta does not specifically teach an internal data source comprising client value KPIs used to calculate a third metric.
However, Scholz in analogous art of modeling consumer sentiment and behavior teaches or suggests:
wherein the plurality of third data sources is client value key performance indicators (KPIs) received from the internal data sources (Scholz mid-¶ [0053]: Other types of compound service metrics may be measured unambiguously based on data available to the service provider, such as the value or profitability of a particular customer to the service provider, the amount of physical/network resources of the service provider used a particular customer, etc.), and
the third metric is computed as a weighted sum of the client value KPIs (Scholz end-¶ [0053]: For instance, in each of these examples of compound service metrics, a set of service-specific data metrics may be identified, combined/grouped and/or weighted to serve as the compound service metric definition from which values may be calculated for individual customers or groups of customers).
Scholz, Chopra and Gupta are found as analogous art of modeling consumer sentiment and behavior. It would have been obvious to one skilled in the art, before the effective filing date of the invention, to have modified Gupta / Chopra’s techniques for generating and dynamically updating client experience scores to have included Scholz’s teachings around an internal data source comprising client value KPIs used to calculate a third metric. The benefit of these additional features would have provided additional insight into the relationship between customer experience metrics and customer behavior (Scholz abstract). The predictability of such modifications and/or variations, would have been corroborated by the broad level of skill of one of ordinary skills in the art as articulated by Gupta in view of Chopra and Scholz (see MPEP 2143 G).
Further, the claimed invention could have also been viewed as a mere combination of old elements in a similar field of modeling consumer sentiment and behavior. In such combination each element would have merely performed the same function as it did separately. Thus, one of ordinary skill in the art would have recognized that, given existing technical ability to combine the elements, as evidenced by Gupta in view of Chopra and Scholz above, the to-be combined elements would have fit together like pieces of a puzzle in a logical, complementary, technologically feasible and/or economically desirable manner. Thus, it would have been reasoned that the results of the combination would have been predictable (see MPEP 2143 A).
Regarding claim 7: Gupta / Chopra teaches all the limitations of claim 1 above.
Gupta further teaches:
wherein the assessment value is computed for each individual subject in a client base (Gupta ¶ [0079]: Returning to FIG. 4, the ML engine 405 aggregates the normalized and weighted scores to generate an aggregate score 440, which is then provided as output 445 in the form of an experience score), and
[..].
Although Gupta teaches calculating a client experience score from three metrics, Gupta does not specifically teach storing the client experience score in a score database.
However, Scholz in analogous art of modeling consumer sentiment and behavior teaches or suggests:
the assessment values for all of the subjects are stored in a score database (Scholz mid-¶ [0018]: The received data metrics may be stored in a compound service metric data store 115 which may operate independently or may be implemented within / integrated into the compound service metric generator 110. ¶ [0055]: In step 504, the compound service metric generator 110 may store and deploy the updated compound service data metric(s) defined in step 503).
Scholz, Chopra and Gupta are found as analogous art of modeling consumer sentiment and behavior. It would have been obvious to one skilled in the art, before the effective filing date of the invention, to have modified Gupta / Chopra’s techniques for generating and dynamically updating client experience scores to have included Scholz’s teachings around storing the client experience score in a score database. The benefit of these additional features would have provided additional insight into the relationship between customer experience metrics and customer behavior (Scholz abstract). The predictability of such modifications and/or variations, would have been corroborated by the broad level of skill of one of ordinary skills in the art as articulated by Gupta in view of Chopra and Scholz (see MPEP 2143 G).
Further, the claimed invention could have also been viewed as a mere combination of old elements in a similar field of modeling consumer sentiment and behavior. In such combination each element would have merely performed the same function as it did separately. Thus, one of ordinary skill in the art would have recognized that, given existing technical ability to combine the elements, as evidenced by Gupta in view of Chopra and Scholz above, the to- be combined elements would have fit together like pieces of a puzzle in a logical, complementary, technologically feasible and/or economically desirable manner. Thus, it would have been reasoned that the results of the combination would have been predictable (see MPEP 2143 A).
Regarding claim 8: Gupta / Chopra / Scholz teaches all the limitations of claim 7 above.
Gupta further teaches:
further comprising periodically updating the weighting factors [..] (Gupta ¶ [0066]: Optionally, the ML engine can continuously or periodically update the weighting factors over time based on newly learned data, such as newly acquired sentiment data. The weights can also be set manually or perhaps refined. As a result of applying the weights, the ML engine 405 has generated a set of weighted scores 435A), wherein,
after updating the weighting factors, the assessment value is recomputed for all of the subjects (Gupta ¶ [0116]: Beneficially, an interactions engine can be configured to at least periodically monitor for new sentiment data. As a further benefit, the client's experience score can be updated based on the new sentiment data that is acquired).
Although Gupta teaches calculating multiple weighted client metrics from internal data sources and multiple channels of external data sources, Gupta does not specifically teach maximizing correlation between client experience scores and client behavior.
However, Scholz in analogous art of modeling consumer sentiment and behavior teaches or suggests:
[..] using an optimization process which maximizes a correlation between the assessment value for each of the subjects and a behavioral parameter of a group of the subjects (Scholz ¶ [0048]: In step 502, the compound service metric generator 110 may use analytics processes to identify correlations between the customer action [EN: behavior] data received in step 501, and one or more corresponding data metrics [EN: client experience score]. For example, the generator 110 may perform various computational analyses on the service-specific data metrics received from various services 120 in step 301, and the subsequent customer action data received in step 501, in order to identify particular data metrics that are positively or negatively correlated with particular customer actions. Mid-¶ [0052]: Updating compound service metric definitions in step 503 may include…updating the assigned weights for data metrics and for different groupings/intermediate layers of data metrics. Mid-¶ [0054]: In such cases, the analytics performed in step 502 and the updated data metrics, relationships, weights, etc., determined in step 503 may be used to tune and/or optimize the previously defined compound service metrics).
Scholz, Chopra and Gupta are found as analogous art of modeling consumer sentiment and behavior. It would have been obvious to one skilled in the art, before the effective filing date of the invention, to have modified Gupta / Chopra’s techniques for generating and dynamically updating client experience scores to have included Scholz’s teachings around maximizing correlation between client experience scores and client behavior. The benefit of these additional features would have provided additional insight into the relationship between customer experience metrics and customer behavior (Scholz abstract). The predictability of such modifications and/or variations, would have been corroborated by the broad level of skill of one of ordinary skills in the art as articulated by Gupta in view of Chopra and Scholz (see MPEP 2143 G).
Further, the claimed invention could have also been viewed as a mere combination of old elements in a similar field of modeling consumer sentiment and behavior. In such combination each element would have merely performed the same function as it did separately. Thus, one of ordinary skill in the art would have recognized that, given existing technical ability to combine the elements, as evidenced by Gupta in view of Chopra and Scholz above, the to-be combined elements would have fit together like pieces of a puzzle in a logical, complementary, technologically feasible and/or economically desirable manner. Thus, it would have been reasoned that the results of the combination would have been predictable (see MPEP 2143 A).
Regarding claim 11: Gupta teaches:
A system for computing a client experience score from structured and unstructured datatypes of a semantic knowledge database (Gupta ¶ [0024]: Embodiments disclosed herein relate to systems, devices, and methods for generating and dynamically updating an experience score for a client, where the experience score operates as a quantitative indicator describing a relationship between the client and an entity. Mid-¶ [0051]: the system is configured to recognize one or more predefined keywords that are known to be associated with particular sentiment of the client [EN: semantic knowledge] (i.e. where certain keywords indicate or contribute to a positive or negative sentiment score). ¶ [0052]: The data 300 can also be in the form of structured data 310 or unstructured data 315. ¶ [0107]: Act 1010 includes using natural language processing (NLP) to provide structure to the unstructured sentiment data. As a consequence, a second set of structured sentiment data (e.g., the set of structured sentiment data 415A [EN: semantic knowledge] from FIG. 4) is acquired), said system comprising:
a computer with one or more processors and memory, where the computer is configured to analyze data received from internal and external data sources via multiple input channels (Gupta ¶ [0046]: In some cases, the sources can be linked to an entity's platform [EN: internal data sources], such as a website that offers clients the opportunities to leave feedback. In other scenarios, the sources are independent relative to the entity [EN: external data sources], such as the case where the source is in the form of a social media platform or some other independent entity. In such scenarios, the interactions engine 140 can be configured to crawl 150 a public network (e.g., the Internet) to identify other sources (e.g., indirect sources or third-party sources) where a user may have expressed his/her viewpoints about a particular entity. For instance, FIG. 1 shows the interactions engine 140 crawling a network 155 to identify a source 160 that is entirely independent of the entity 130 and that can be a third-party source. From this source 160, the interactions engine 140 can acquire additional sentiment data. Accordingly, in this sense, the disclosed interactions engine 140 and ML engine 140A can be configured to perform big data mining 165 and analysis); and
a network connection operatively connecting the external data sources to the computer (Gupta mid-¶ [0046]: For instance, FIG. 1 shows the interactions engine 140 crawling a network 155 to identify a source 160 that is entirely independent [EN: external] of the entity 130 and that can be a third party source),
where the computer is configured to perform steps including:
[..]
computing, for each client in a client base, a first metric from a plurality of first data sources [..] (See Gupta Fig. 5 showing multiple metrics, or scores, generated from various data sources) where
the plurality of first data sources includes client feedback data received from the external data sources via the multiple input channels (Gupta ¶ [0064]: FIG. 5 shows a set of input 500, which is representative of the input 410 from FIG. 4. The input 500 can include data from any number of sources and can include expressions made by a client), and
the first metric is computed as a weighted [..] client sentiments each derived from a different one of the input channels (Gupta ¶ [0064]: Returning to FIG. 4, the process flow 400 includes the ML engine 405 generating and applying weight(s) 435 to each respective input type [EN: input channel]. That is, the ML engine generates the weighting factors…. As a result of applying the weights, the ML engine 405 has generated a set of weighted scores 435A. FIG. 5 provides a useful illustration), and where
the client sentiments include a sentiment derived from each of a call center input channel, an online chat input channel, a client complaints input channel, a voice of the customer input channel, and two different mobile device application store input channels (Gupta mid-¶ [0064]: As some examples, the input 500 [EN: input channel] can be acquired from messages 505 [EN: mobile device application], a webchat 510, a survey 515 [EN: complaints], reviews 520 [EN: complaints], social media 525 [EN: mobile device application], texts 530 [EN: mobile device application], voicemail 535 [EN: call center, customer voice], email 540 [EN: mobile device application]. ¶ [0047]: In some scenarios, such as where a client has enabled microphone access associated with the entity or a separate application that is linked to the entity, the system is able to gather feedback data, through automatic speech [EN: voice] recognition, by identifying relevant speech signals recorded by a client's microphone (i.e. if the client is speaking about his or her interaction with the entity));
computing a second metric from a plurality of second data sources (See Gupta Fig. 5 showing multiple metrics, or scores, generated from various data sources), where
the plurality of second data sources is client experience key performance indicators (KPIs) received from the internal data sources (Gupta ¶ [0046]: ¶ [0046]: In some cases, the sources can be linked to an entity's platform [EN: internal data sources], such as a website that offers clients the opportunities to leave feedback [EN: experience KPI]. Mid-¶ [0049]: For instance, one type of interaction can be a user's response to a survey [EN: experience KPI], and the [EN: internal data] "source" would be the survey… Another type of interaction can be a user providing feedback in a website, and the [EN: internal data] source would be the website), and
the second metric is computed as [..] weighted [..] client experience KPIs (Gupta ¶ [0064]: Returning to FIG. 4, the process flow 400 includes the ML engine 405 generating and applying weight(s) 435 to each respective input type. That is, the ML engine generates the weighting factors…. As a result of applying the weights, the ML engine 405 has generated a set of weighted scores 435A. FIG. 5 provides a useful illustration);
computing a third metric from a plurality of third data sources (See Gupta Fig. 5 showing multiple metrics, or scores, generated from various data sources), where
[..];
computing the client experience score using a calculation including the first, second and third metrics and first, second and third weighting factors (Gupta ¶ [0079]: Returning to FIG. 4, the ML engine 405 aggregates the normalized and weighted scores to generate an aggregate score 440, which is then provided as output 445 in the form of an experience score),
each of the metrics being multiplied by its corresponding weighting factor in the calculation (See Gupta equation below ¶ [0079] multiplying corresponding metrics and weights. ¶ [0080]: In the above algorithm, M is the number of inputs for this particular customer, wi is the importance weight for the ith input, t; is the history weight for the ith input based on the time of feedback or interaction, and si is the normalized score [EN: metric] from that input. FIG. 5 shows an aggregated score 570, which is representative of the aggregate score 440);
prescribing targeted interactions with clients based on the client experience score (Gupta ¶ [0115]: Act 1035 then includes using the experience score to modify a subsequent interaction the client has with the entity. For instance, modify experience 175 from FIG. 1 and modify experience 700 from FIG. 7 are representative of example options for modifying the user's subsequent interactions with the entity…. Another way to dynamically influence interactions is by initiating [EN: prescribing] a new interaction, such as by prompting a client to refer another client. ¶ [0087]: FIG. 7 shows various examples of how the disclosed embodiments can modify a user's experience with an entity, as represented by modify experience 700. In one scenario, various campaigns 705 can be triggered. A campaign can include targeted promotions or advertisements that are directed to a client); and
periodically updating the weighting factors [..] (Gupta ¶ [0066]: Optionally, the ML engine can continuously or periodically update the weighting factors over time based on newly learned data, such as newly acquired sentiment data. The weights can also be set manually or perhaps refined. As a result of applying the weights, the ML engine 405 has generated a set of weighted scores 435A), wherein,
after updating the weighting factors, an assessment value is recomputed for all of the clients (Gupta ¶ [0116]: Beneficially, an interactions engine can be configured to at least periodically monitor for new sentiment data. As a further benefit, the client's experience score can be updated based on the new sentiment data that is acquired).
Although Gupta teaches calculating multiple weighted client metrics and semantic assessment values based on client feedback and prescribing targeted interactions with clients based on the assessments, Gupta does not specifically teach converting non-text data to text data, cleaning data of noise and PII, standardizing the data in a semantic knowledge base, identifying correlations in client feedback phrased in different ways, and producing feature vectors to identify related products and services, an internal data source comprising client value KPIs used to calculate a third metric, maximizing correlation between client experience scores and client behavior, nor the weighting calculations for the metrics involving a sum.
However, Chopra in analogous art of modeling consumer sentiment and behavior teaches or suggests:
converting data from the multiple input channels to text data, and aggregating the text data in a data library (Chopra ¶ [0030]: In some embodiments, the user activity database 102a [EN: library] stores transcripts or other memorializations of the interaction-for example, in the case of a text chat session or a virtual assistant chat session, the database 102a can store unstructured text corresponding to the messages exchanged between the CSR/VA and the end user. In the case of a voice call, the database 102a can store a digital audio recording of the voice call and/or a transcript of the voice call (e.g. as generated by a speech-to-text module that converts the digital audio recording
into unstructured text));
pre-processing and cleaning the text data by removing personally identifiable information and removing noise from the text data to generate cleaned data (Chopra ¶ [0042]: The embedding generation module 110 then performs a data pre-processing and cleaning routine (304) on the incoming interaction text data. During the data pre-processing and cleaning routine, the embedding generation module 110 performs one or more tasks on the unstructured text to ensure that the text is in a form that can be used to generate embeddings as will be described later in the document. Exemplary pre-processing and cleaning tasks performed by the module 110 can include: … ¶ [0046]: Replace end user-related masked information: the module 110 can determine end-user specific information that is sensitive or confidential (such as personally identifiable information (PII)) and mask this information in the transcript by, e.g., replacing the information with anonymizing overlay values… ¶ [0047]: Remove non-vocalized noise or unintelligible utterances: when converting a digital audio recording of a voice call, the module 110 may generate text that relates to non-vocalized noise and/or unintelligible words spoken by the participants. The module 110 can remove these words from the transcript by, e.g., determining whether they correspond to a recognized word in a predefined dictionary and if not, removing them from the text data);
exporting the cleaned data into an export, transform and load (ETL) module to transform the cleaned data for loading to a semantic knowledge database as transformed data that is transformed into a standardized format; loading the transformed data into the semantic knowledge database (Chopra ¶ [0052]: After the embedding generation module 110 has completed the pre-processing and cleaning the unstructured text data for the interactions, the module 110 converts the text data into interaction embeddings [EN: standardized data] for processing by the neural networks 108a, 108b. ¶ [0056]: Upon generation of the initial word embeddings for each of the intent model 108a and short summary model 108b, the embedding generation module 110 transmits the corresponding embeddings to the respective models 108a, 108b for training and/or execution. ¶ [0058]: Once the model 108b is trained, the server computing device 106 can subsequently execute (312b) the trained model 108b using as input interaction embeddings generated from new interactions to automatically generate a short summary for the interaction transcript and CSR notes to which new interactions correspond. Upon execution of the intent model 108a and/or the short summary model 108b against computer text segments from new interactions, the server computing device 106 stores the output (i.e., the intents and/or short summaries generated by the models 108a, 108b) in the output database 102b.);
wherein the transformed data in the standardized format enables identification of correlations between feedback records from the multiple input channels that use different terminology and phraseology to describe a same subject matter (Chopra ¶ [0066]: Next, the clustering module 112 performs the embedding creation step (606) to generate word/phrase embeddings based upon the cleaned intents and/or short summaries. Vectorization and embedding generation is important in this phase because two intents (as modified by CSRs) could have the same meaning but could be written differently);
performing natural language processing on the transformed data of the semantic knowledge database using feature extraction to produce feature vectors (Chopra mid-[0039]: the system 100 can convert the audio into unstructured text using, e.g., a speech-to-text conversion module that analyzes the waveforms in the audio file and converts them into natural language text. Mid-¶ [0052]: …each token corresponds to a word in the corpus of text and a token is a fundamental unit that a text processing system typically works with. By generating tokens from the unstructured text, the module 110 can apply sophisticated algorithms, e.g., to identify the part-of-speech of each token, form trigrams that are used for other processing function like clustering described in detail below, etc. ¶ [0067]: …As shown in FIG. 8, the cleaned and normalized intents 802 are converted into a multidimensional embedding (or vector) comprising feature values (e.g., 0.2, 0.65...) corresponding to the features of the intent detected by the clustering module 112);
performing data clustering and segmentation on the feature vectors to identify clusters of feedback related to products, services and departments (Chopra ¶ [0068]: As a result, the clustering module 112 performs a dimensionality reduction step (608) to convert the large dimension embedding [EN: feature vectorization, see paragraph 0067] into a form that is more efficient for the grouping [EN: segmenting] and clustering steps described herein. ¶ [0071]: After dimensionality reduction, the clustering module 112 performs entity detection (610) on the text of the intents and short summaries using a named entity recognition (NER) model that is trained to identify organization specific products, services, and other types of entities);
[..] wherein the first metric is derived from the feature vectors (Chopra ¶ [0067]: …As shown in FIG. 8, the cleaned and normalized intents 802 are converted into a multidimensional embedding (or vector) comprising feature values [EN: metrics] (e.g., 0.2, 0.65...) corresponding to the features of the intent detected by the clustering module 112)).
Chopra and Gupta are found as analogous art of modeling consumer sentiment and behavior. It would have been obvious to one skilled in the art, before the effective filing date of the invention, to have modified Gupta’s techniques for generating and dynamically updating client experience scores to have included Chopra’s teachings around converting non-text data to text data, cleaning data of noise and PII, standardizing the data in a semantic knowledge base, identifying correlations in client feedback phrased in different ways, and producing feature vectors to identify related products and services. The benefit of these additional features would have eased the efforts to identify customer intent behind interactions and planning for information and service needs, and reduced time for analysis and understanding of actionable information (Chopra ¶ [0004]). The predictability of such modifications and/or variations, would have been corroborated by the broad level of skill of one of ordinary skills in the art as articulated by Gupta in view of Chopra (see MPEP 2143 G).
Further, the claimed invention could have also been viewed as a mere combination of old elements in a similar field of modeling consumer sentiment and behavior. In such combination each element would have merely performed the same function as it did separately. Thus, one of ordinary skill in the art would have recognized that, given existing technical ability to combine the elements, as evidenced by Gupta in view of Chopra above, the to- be combined elements would have fit together like pieces of a puzzle in a logical, complementary, technologically feasible and/or economically desirable manner. Thus, it would have been reasoned that the results of the combination would have been predictable (see MPEP 2143 A).
Furthermore, Scholz in analogous art of modeling consumer sentiment and behavior teaches or suggests:
the plurality of third data sources is client value key performance indicators received from the internal data sources (Scholz mid-¶ [0053]: Other types of compound service metrics may be measured unambiguously based on data available to the service provider, such as the value or profitability of a particular customer to the service provider, the amount of physical/network resources of the service provider used a particular customer, etc.), and
the third metric is computed as [..] weighted [..] client value KPIs (Scholz end-¶ [0053]: For instance, in each of these examples of compound service metrics, a set of service-specific data metrics may be identified, combined/grouped and/or weighted to serve as the compound service metric definition from which values may be calculated for individual customers or groups of customers);
[..] using an optimization process which maximizes a correlation between the client experience score for each of the clients and a behavioral parameter of a group of the clients (Scholz ¶ [0048]: In step 502, the compound service metric generator 110 may use analytics processes to identify correlations between the customer action [EN: behavior] data received in step 501, and one or more corresponding data metrics [EN: client experience score]. For example, the generator 110 may perform various computational analyses on the service-specific data metrics received from various services 120 in step 301, and the subsequent customer action data received in step 501, in order to identify particular data metrics that are positively or negatively correlated with particular customer actions. Mid-¶ [0052]: Updating compound service metric definitions in step 503 may include…updating the assigned weights for data metrics and for different groupings/intermediate layers of data metrics. Mid-¶ [0054]: In such cases, the analytics performed in step 502 and the updated data metrics, relationships, weights, etc., determined in step 503 may be used to tune and/or optimize the previously defined compound service metrics);
[first/second/third metric is computed as a weighted] sum [of client [sentiments/KPIs] (Scholz mid-¶ [0060]: The generator 110 may sum the weighted data metrics 401-403 to calculate a customer sentiment signaling data metric 406 for the voice service 120a.The generator 110 may sum the weighted data metrics 401-403 to calculate a customer sentiment signaling data metric 406 for the voice service 120a. Using similar processes… the generator 110 may sum the weighted data metrics 404 and 405 to calculate a customer sentiment media quality data metric 407 for the voice service 120a. The generator 110 then may… sum these category data metrics 406 and 407….).
Scholz, Chopra and Gupta are found as analogous art of modeling consumer sentiment and behavior. It would have been obvious to one skilled in the art, before the effective filing date of the invention, to have modified Gupta / Chopra’s techniques for generating and dynamically updating client experience scores to have included Scholz’s teachings around an internal data source comprising client value KPIs used to calculate a third metric, maximizing correlation between client experience scores and client behavior, and the weighting calculations for the metrics involving a sum. The benefit of these additional features would have provided additional insight into the relationship between customer experience metrics and customer behavior (Scholz abstract). The predictability of such modifications and/or variations, would have been corroborated by the broad level of skill of one of ordinary skills in the art as articulated by Gupta in view of Chopra and Scholz (see MPEP 2143 G).
Further, the claimed invention could have also been viewed as a mere combination of old elements in a similar field of modeling consumer sentiment and behavior. In such combination each element would have merely performed the same function as it did separately. Thus, one of ordinary skill in the art would have recognized that, given existing technical ability to combine the elements, as evidenced by Gupta in view of Chopra and Scholz above, the to-be combined elements would have fit together like pieces of a puzzle in a logical, complementary, technologically feasible and/or economically desirable manner. Thus, it would have been reasoned that the results of the combination would have been predictable (see MPEP 2143 A).
Regarding claim 13: Gupta teaches:
A computer-implemented method for computing a client experience score from structured and unstructured datatypes of a semantic knowledge database (Gupta ¶ [0024]: Embodiments disclosed herein relate to systems, devices, and methods for generating and dynamically updating an experience score for a client, where the experience score operates as a quantitative indicator describing a relationship between the client and an entity. Mid-¶ [0051]: the system is configured to recognize one or more predefined keywords that are known to be associated with particular sentiment of the client [EN: semantic knowledge] (i.e. where certain keywords indicate or contribute to a positive or negative sentiment score). ¶ [0052]: The data 300 can also be in the form of structured data 310 or unstructured data 315. ¶ [0107]: Act 1010 includes using natural language processing (NLP) to provide structure to the unstructured sentiment data. As a consequence, a second set of structured sentiment data (e.g., the set of structured sentiment data 415A [EN: semantic knowledge] from FIG. 4) is acquired), said method comprising:
[..]
computing, for each client in a client base, a first metric from a plurality of first data sources, a second metric from a plurality of second data sources and a third metric from a plurality of third data sources [..] (See Gupta Fig. 5 showing multiple metrics, or scores, generated from various data sources);
computing the client experience score using a calculation including the first, second and third metrics, and first, second and third weighting factors (Gupta ¶ [0079]: Returning to FIG. 4, the ML engine 405 aggregates the normalized and weighted scores to generate an aggregate score 440, which is then provided as output 445 in the form of an experience score),
each of the metrics being multiplied by its corresponding weighting factor in the calculation (See Gupta equation below ¶ [0079] multiplying corresponding metrics and weights. ¶ [0080]: In the above algorithm, M is the number of inputs for this particular customer, wi is the importance weight for the ith input, t; is the history weight for the ith input based on the time of feedback or interaction, and si is the normalized score [EN: metric] from that input. FIG. 5 shows an aggregated score 570, which is representative of the aggregate score 440);
[..]; and
prescribing targeted interactions with individual clients based on the client experience score (Gupta ¶ [0115]: Act 1035 then includes using the experience score to modify a subsequent interaction the client has with the entity. For instance, modify experience 175 from FIG. 1 and modify experience 700 from FIG. 7 are representative of example options for modifying the user's subsequent interactions with the entity…. Another way to dynamically influence interactions is by initiating [EN: prescribing] a new interaction, such as by prompting a client to refer another client. ¶ [0087]: FIG. 7 shows various examples of how the disclosed embodiments can modify a user's experience with an entity, as represented by modify experience 700. In one scenario, various campaigns 705 can be triggered. A campaign can include targeted promotions or advertisements that are directed to a client).
Although Gupta teaches calculating a client experience score from three metrics, Gupta does not specifically teach converting non-text data to text data, cleaning data of noise and PII, standardizing the data in a semantic knowledge base, identifying correlations in client feedback phrased in different ways, and producing feature vectors to identify related products and services, nor storing the client experience score in a score database.
However, Chopra in analogous art of modeling consumer sentiment and behavior teaches or suggests:
converting data from the multiple input channels to text data, and aggregating the text data in a data library (Chopra ¶ [0030]: In some embodiments, the user activity database 102a [EN: library] stores transcripts or other memorializations of the interaction-for example, in the case of a text chat session or a virtual assistant chat session, the database 102a can store unstructured text corresponding to the messages exchanged between the CSR/VA and the end user. In the case of a voice call, the database 102a can store a digital audio recording of the voice call and/or a transcript of the voice call (e.g. as generated by a speech-to-text module that converts the digital audio recording
into unstructured text));
pre-processing and cleaning the text data by removing personally identifiable information and removing noise from the text data to generate cleaned data (Chopra ¶ [0042]: The embedding generation module 110 then performs a data pre-processing and cleaning routine (304) on the incoming interaction text data. During the data pre-processing and cleaning routine, the embedding generation module 110 performs one or more tasks on the unstructured text to ensure that the text is in a form that can be used to generate embeddings as will be described later in the document. Exemplary pre-processing and cleaning tasks performed by the module 110 can include: … ¶ [0046]: Replace end user-related masked information: the module 110 can determine end-user specific information that is sensitive or confidential (such as personally identifiable information (PII)) and mask this information in the transcript by, e.g., replacing the information with anonymizing overlay values… ¶ [0047]: Remove non-vocalized noise or unintelligible utterances: when converting a digital audio recording of a voice call, the module 110 may generate text that relates to non-vocalized noise and/or unintelligible words spoken by the participants. The module 110 can remove these words from the transcript by, e.g., determining whether they correspond to a recognized word in a predefined dictionary and if not, removing them from the text data);
exporting the cleaned data into an export, transform and load (ETL) module to transform the cleaned data for loading to a semantic knowledge database as transformed data that is transformed into a standardized format; loading the transformed data into the semantic knowledge database (Chopra ¶ [0052]: After the embedding generation module 110 has completed the pre-processing and cleaning the unstructured text data for the interactions, the module 110 converts the text data into interaction embeddings [EN: standardized data] for processing by the neural networks 108a, 108b. ¶ [0056]: Upon generation of the initial word embeddings for each of the intent model 108a and short summary model 108b, the embedding generation module 110 transmits the corresponding embeddings to the respective models 108a, 108b for training and/or execution. ¶ [0058]: Once the model 108b is trained, the server computing device 106 can subsequently execute (312b) the trained model 108b using as input interaction embeddings generated from new interactions to automatically generate a short summary for the interaction transcript and CSR notes to which new interactions correspond. Upon execution of the intent model 108a and/or the short summary model 108b against computer text segments from new interactions, the server computing device 106 stores the output (i.e., the intents and/or short summaries generated by the models 108a, 108b) in the output database 102b.);
wherein the transformed data in the standardized format enables identification of correlations between feedback records from the multiple input channels that use different terminology and phraseology to describe a same subject matter (Chopra ¶ [0066]: Next, the clustering module 112 performs the embedding creation step (606) to generate word/phrase embeddings based upon the cleaned intents and/or short summaries. Vectorization and embedding generation is important in this phase because two intents (as modified by CSRs) could have the same meaning but could be written differently);
performing natural language processing on the transformed data of the semantic knowledge database using feature extraction to produce feature vectors (Chopra mid-[0039]: the system 100 can convert the audio into unstructured text using, e.g., a speech-to-text conversion module that analyzes the waveforms in the audio file and converts them into natural language text. Mid-¶ [0052]: …each token corresponds to a word in the corpus of text and a token is a fundamental unit that a text processing system typically works with. By generating tokens from the unstructured text, the module 110 can apply sophisticated algorithms, e.g., to identify the part-of-speech of each token, form trigrams that are used for other processing function like clustering described in detail below, etc. ¶ [0067]: …As shown in FIG. 8, the cleaned and normalized intents 802 are converted into a multidimensional embedding (or vector) comprising feature values (e.g., 0.2, 0.65...) corresponding to the features of the intent detected by the clustering module 112);
performing data clustering and segmentation on the feature vectors to identify clusters of feedback related to products, services and departments (Chopra ¶ [0068]: As a result, the clustering module 112 performs a dimensionality reduction step (608) to convert the large dimension embedding [EN: feature vectorization, see paragraph 0067] into a form that is more efficient for the grouping [EN: segmenting] and clustering steps described herein. ¶ [0071]: After dimensionality reduction, the clustering module 112 performs entity detection (610) on the text of the intents and short summaries using a named entity recognition (NER) model that is trained to identify organization specific products, services, and other types of entities);
[..] wherein the first metric is derived from the feature vectors (Chopra ¶ [0067]: …As shown in FIG. 8, the cleaned and normalized intents 802 are converted into a multidimensional embedding (or vector) comprising feature values [EN: metrics] (e.g., 0.2, 0.65...) corresponding to the features of the intent detected by the clustering module 112)).
Chopra and Gupta are found as analogous art of modeling consumer sentiment and behavior. It would have been obvious to one skilled in the art, before the effective filing date of the invention, to have modified Gupta’s techniques for generating and dynamically updating client experience scores to have included Chopra’s teachings around converting non-text data to text data, cleaning data of noise and PII, standardizing the data in a semantic knowledge base, identifying correlations in client feedback phrased in different ways, and producing feature vectors to identify related products and services. The benefit of these additional features would have eased the efforts to identify customer intent behind interactions and planning for information and service needs, and reduced time for analysis and understanding of actionable information (Chopra ¶ [0004]). The predictability of such modifications and/or variations, would have been corroborated by the broad level of skill of one of ordinary skills in the art as articulated by Gupta in view of Chopra (see MPEP 2143 G).
Further, the claimed invention could have also been viewed as a mere combination of old elements in a similar field of modeling consumer sentiment and behavior. In such combination each element would have merely performed the same function as it did separately. Thus, one of ordinary skill in the art would have recognized that, given existing technical ability to combine the elements, as evidenced by Gupta in view of Chopra above, the to- be combined elements would have fit together like pieces of a puzzle in a logical, complementary, technologically feasible and/or economically desirable manner. Thus, it would have been reasoned that the results of the combination would have been predictable (see MPEP 2143 A).
Furthermore, Scholz in analogous art of modeling consumer sentiment and behavior teaches or suggests:
storing the client experience score in a score database (Scholz mid-¶ [0018]: The received data metrics may be stored in a compound service metric data store 115 which may operate independently or may be implemented within / integrated into the compound service metric generator 110. ¶ [0055]: In step 504, the compound service metric generator 110 may store and deploy the updated compound service data metric(s) defined in step 503).
Scholz, Chopra and Gupta are found as analogous art of modeling consumer sentiment and behavior. It would have been obvious to one skilled in the art, before the effective filing date of the invention, to have modified Gupta / Chopra’s techniques for generating and dynamically updating client experience scores to have included Scholz’s teachings around storing the client experience score in a score database. The benefit of these additional features would have provided additional insight into the relationship between customer experience metrics and customer behavior (Scholz abstract). The predictability of such modifications and/or variations, would have been corroborated by the broad level of skill of one of ordinary skills in the art as articulated by Gupta in view of Chopra and Scholz (see MPEP 2143 G).
Further, the claimed invention could have also been viewed as a mere combination of old elements in a similar field of modeling consumer sentiment and behavior. In such combination each element would have merely performed the same function as it did separately. Thus, one of ordinary skill in the art would have recognized that, given existing technical ability to combine the elements, as evidenced by Gupta in view of Chopra and Scholz above, the to- be combined elements would have fit together like pieces of a puzzle in a logical, complementary, technologically feasible and/or economically desirable manner. Thus, it would have been reasoned that the results of the combination would have been predictable (see MPEP 2143 A).
Regarding claim 14: Gupta / Chopra / Scholz teaches all the limitations of claim 13 above.
Gupta further teaches:
wherein the plurality of first data sources includes client feedback data received from external data sources via the multiple input channels (Gupta ¶ [0064]: FIG. 5 shows a set of input 500, which is representative of the input 410 from FIG. 4. The input 500 can include data from any number of sources and can include expressions made by a client), and
the first metric is computed as a weighted sum of client sentiments each derived from a different one of the input channels (Gupta ¶ [0064]: Returning to FIG. 4, the process flow 400 includes the ML engine 405 generating and applying weight(s) 435 to each respective input type [EN: input channel]. That is, the ML engine generates the weighting factors…. As a result of applying the weights, the ML engine 405 has generated a set of weighted scores 435A. FIG. 5 provides a useful illustration), and where
the client sentiments include a sentiment derived from each of a call center input channel, an online chat input channel, a client complaints input channel, a voice of the customer input channel, and two different mobile device application store input channels (Gupta mid-¶ [0064]: As some examples, the input 500 [EN: input channel] can be acquired from messages 505 [EN: mobile device application], a webchat 510, a survey 515 [EN: complaints], reviews 520 [EN: complaints], social media 525 [EN: mobile device application], texts 530 [EN: mobile device application], voicemail 535 [EN: call center, customer voice], email 540 [EN: mobile device application]. ¶ [0047]: In some scenarios, such as where a client has enabled microphone access associated with the entity or a separate application that is linked to the entity, the system is able to gather feedback data, through automatic speech [EN: voice] recognition, by identifying relevant speech signals recorded by a client's microphone (i.e. if the client is speaking about his or her interaction with the entity)).
Regarding claim 15: Gupta / Chopra / Scholz teaches all the limitations of claim 13 above.
Gupta further teaches:
wherein the plurality of second data sources is client experience key performance indicators (KPIs) received from internal data sources (Gupta ¶ [0046]: ¶ [0046]: In some cases, the sources can be linked to an entity's platform [EN: internal data sources], such as a website that offers clients the opportunities to leave feedback [EN: experience KPI]. Mid-¶ [0049]: For instance, one type of interaction can be a user's response to a survey [EN: experience KPI], and the [EN: internal data] "source" would be the survey… Another type of interaction can be a user providing feedback in a website, and the [EN: internal data] source would be the website), and
the second metric is computed as a weighted sum of the client experience KPIs (Gupta ¶ [0064]: Returning to FIG. 4, the process flow 400 includes the ML engine 405 generating and applying weight(s) 435 to each respective input type. That is, the ML engine generates the weighting factors…. As a result of applying the weights, the ML engine 405 has generated a set of weighted scores 435A. FIG. 5 provides a useful illustration).
Regarding claim 16: Gupta / Chopra / Scholz teaches all the limitations of claim 13 above.
Although Gupta teaches calculating multiple weighted client metrics from internal data sources and multiple channels of external data sources, Gupta does not specifically teach an internal data source comprising client value KPIs used to calculate a third metric.
However, Scholz in analogous art of modeling consumer sentiment and behavior teaches or suggests:
wherein the plurality of third data sources is client value key performance indicators (KPIs) received from internal data sources (Scholz mid-¶ [0053]: Other types of compound service metrics may be measured unambiguously based on data available to the service provider, such as the value or profitability of a particular customer to the service provider, the amount of physical/network resources of the service provider used a particular customer, etc.), and
the third metric is computed as a weighted sum of the client value KPIs (Scholz end-¶ [0053]: For instance, in each of these examples of compound service metrics, a set of service-specific data metrics may be identified, combined/grouped and/or weighted to serve as the compound service metric definition from which values may be calculated for individual customers or groups of customers).
Rationales to have modified / combined Gupta / Chopra / Scholz are in claim 13 above and reincorporated.
Regarding claim 17: Gupta / Chopra / Scholz teaches all the limitations of claim 13 above.
Gupta further teaches:
wherein the first, second and third metrics are normalized to a common range of values before computing the client experience score (Gupta ¶ [0063]: After providing structure to any unstructured data, the ML engine 405 then normalizes the data, all of which should now have the same or matching structure (e.g., perhaps the structure is a numerical indicator), as represented by normalized score(s) 430. As one example, all scores can optionally be normalized to fall within a range between O and 10. The process of normalizing the data results in all of the data having the same scale).
Regarding claim 18: Gupta / Chopra / Scholz teaches all the limitations of claim 13 above.
Gupta further teaches:
further comprising periodically updating the weighting factors [..] (Gupta ¶ [0066]: Optionally, the ML engine can continuously or periodically update the weighting factors over time based on newly learned data, such as newly acquired sentiment data. The weights can also be set manually or perhaps refined. As a result of applying the weights, the ML engine 405 has generated a set of weighted scores 435A), wherein,
after updating the weighting factors, the client experience score is recomputed for all of the clients (Gupta ¶ [0116]: Beneficially, an interactions engine can be configured to at least periodically monitor for new sentiment data. As a further benefit, the client's experience score can be updated based on the new sentiment data that is acquired).
Although Gupta teaches calculating multiple weighted client metrics from internal data sources and multiple channels of external data sources, Gupta does not specifically teach maximizing correlation between client experience scores and client behavior.
However, Scholz in analogous art of modeling consumer sentiment and behavior teaches or suggests:
[..] using an optimization process which maximizes a correlation between the score for each of the clients and a behavioral parameter of a group of the clients (Scholz ¶ [0048]: In step 502, the compound service metric generator 110 may use analytics processes to identify correlations between the customer action [EN: behavior] data received in step 501, and one or more corresponding data metrics [EN: client experience score]. For example, the generator 110 may perform various computational analyses on the service-specific data metrics received from various services 120 in step 301, and the subsequent customer action data received in step 501, in order to identify particular data metrics that are positively or negatively correlated with particular customer actions. Mid-¶ [0052]: Updating compound service metric definitions in step 503 may include…updating the assigned weights for data metrics and for different groupings/intermediate layers of data metrics. Mid-¶ [0054]: In such cases, the analytics performed in step 502 and the updated data metrics, relationships, weights, etc., determined in step 503 may be used to tune and/or optimize the previously defined compound service metrics).
Scholz, Chopra and Gupta are found as analogous art of modeling consumer sentiment and behavior. It would have been obvious to one skilled in the art, before the effective filing date of the invention, to have modified Gupta / Chopra’s techniques for generating and dynamically updating client experience scores to have included Scholz’s teachings around maximizing correlation between client experience scores and client behavior. The benefit of these additional features would have provided additional insight into the relationship between customer experience metrics and customer behavior (Scholz abstract). The predictability of such modifications and/or variations, would have been corroborated by the broad level of skill of one of ordinary skills in the art as articulated by Gupta in view of Chopra and Scholz (see MPEP 2143 G).
Further, the claimed invention could have also been viewed as a mere combination of old elements in a similar field of modeling consumer sentiment and behavior. In such combination each element would have merely performed the same function as it did separately. Thus, one of ordinary skill in the art would have recognized that, given existing technical ability to combine the elements, as evidenced by Gupta in view of Chopra and Scholz above, the to-be combined elements would have fit together like pieces of a puzzle in a logical, complementary, technologically feasible and/or economically desirable manner. Thus, it would have been reasoned that the results of the combination would have been predictable (see MPEP 2143 A).
------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
Claims 9, 10, 12, 19-20 are rejected under 35 U.S.C. 103 as being unpatentable over:
Gupta / Chopra / Scholz as applied above, in further view of
Matam et al. US 20180268318 A1, hereinafter Matam. As per,
Regarding claim 9: Gupta / Chopra / Scholz teaches all the limitations of claim 8 above.
Gupta further teaches:
wherein updating the weighting factors includes performing a logistic regression calculation on the assessment value for each of the subjects to produce a regression value [..] (Gupta ¶ [0048]: As used herein, any type of ML engine, algorithm, model, or neural network may be used to perform the disclosed operations. As used herein, reference to "machine learning" or to a ML model or to a "neural network" may Include… logistic regression model(s). ¶ [0081]: In some embodiments, the ML engine 405 can also perform a regression analysis 450. The regression analysis 450 generally refers to a technique for identifying trends in data, such as possible dependencies between variables. As will be discussed in more detail shortly, the ML engine 405 can perform the regression analysis 450 in an effort to identify which specific interaction types or which specific events contributed most heavily to a user's particular experience score).
Although Gupta teaches applying a logistic regression function to the client experience scores to produce a regression value, Gupta does not specifically teach producing a regression value in a range of zero to one; optimizing correlation between the regression value of the experience scores and the client behavior, and adjusting the weighting factors to optimize the function for the clients in the group; nor the optimization function being a penalty minimization function.
However, Scholz in analogous art of modeling consumer sentiment and behavior teaches or suggests:
defining a [..] function which [optimizes] correlation between the regression value and the behavioral parameter for the group of the subjects, and performing the optimization process to adjust the weighting factors in order to [optimize] a total value of the [..] function for the group of the subjects (Scholz mid-¶ [[0051]: Such processes may… form correlations between the various inputs and outputs in order to train the neural network to predict customer actions [EN: behaviors] and/or to perform other predictive analyses based on future data metrics. Mid-¶ [0052]: Updating compound service metric [EN: function] definitions in step 503 may include…updating the assigned weights for data metrics and for different groupings/intermediate layers of data metrics. End-¶ [0053]: …a set of service-specific data metrics may be identified, combined/grouped and/or weighted to serve as the compound service metric definition from which values may be calculated for individual customers or groups of customers. Mid-¶ [0054]: In such cases, the analytics performed in step 502 and the updated data metrics, relationships, weights, etc., determined in step 503 may be used to tune and/or optimize the previously defined compound service metrics).
Scholz, Chopra and Gupta are found as analogous art of modeling consumer sentiment and behavior. It would have been obvious to one skilled in the art, before the effective filing date of the invention, to have modified Gupta Chopra’s techniques for generating and dynamically updating client experience scores to have included Scholz’s teachings around optimizing correlation between the regression value of the experience scores and the client behavior and adjusting the weighting factors to optimize the function for the clients in the group. The benefit of these additional features would have provided additional insight into the relationship between customer experience metrics and customer behavior (Scholz abstract). The predictability of such modifications and/or variations, would have been corroborated by the broad level of skill of one of ordinary skills in the art as articulated by Gupta in view of Chopra and Scholz (see MPEP 2143 G).
Further, the claimed invention could have also been viewed as a mere combination of old elements in a similar field of modeling consumer sentiment and behavior. In such combination each element would have merely performed the same function as it did separately. Thus, one of ordinary skill in the art would have recognized that, given existing technical ability to combine the elements, as evidenced by Gupta in view of Chopra and Scholz above, the to-be combined elements would have fit together like pieces of a puzzle in a logical, complementary, technologically feasible and/or economically desirable manner. Thus, it would have been reasoned that the results of the combination would have been predictable (see MPEP 2143 A).
Furthermore, Matam in analogous art of modeling consumer sentiment and behavior teaches or suggests:
[produce a regression value in a] range of zero to one (Matam ¶ [0068]: In the example depicted in FIG. 4, a trained regression model (or other predictive model) is generated for predicting the probability [EN: regression value in range of zero to one] of an end-user's behavior (e.g., a consumer reaction to a sales call);
[the optimization function being a] penalty minimizing function (Matam ¶ [0081]: In the AIC and BIC, the 2log (L) term rewards the latent space model 422 for the goodness of the fit on the training non-conversational data 218… each of the AIC and BIC also includes penalty terms (e.g., the 2q term for the AIC and the q log(n) term for the BIC). Each penalty term is a function whose value increases if the number of estimated parameters in the latent space model 422 increases. The penalty term penalizes over-fitting in the model. In this manner, the 2log(L) term and the penalty term in the AIC and the BIC create a trade-off between fitting the model to the selected training data and reducing [EN: minimizing] the complexity of the model).
Matam, Scholz, Chopra and Gupta are found as analogous art of modeling consumer sentiment and behavior. It would have been obvious to one skilled in the art, before the effective filing date of the invention, to have modified Gupta / Chopra / Scholz’s techniques for generating and dynamically updating client experience scores to have included Matam’s teachings around producing a regression value in a range of zero to one and the optimization function being a penalty function. The benefit of these additional features would have improved accuracy of predicting consumer intentions, dispositions, and behavior (Matam ¶ [0004]). The predictability of such modifications and/or variations, would have been corroborated by the broad level of skill of one of ordinary skills in the art as articulated by Gupta in view of Chopra, Scholz and Matam (see MPEP 2143 G).
Further, the claimed invention could have also been viewed as a mere combination of old elements in a similar field of modeling consumer sentiment and behavior. In such combination each element would have merely performed the same function as it did separately. Thus, one of ordinary skill in the art would have recognized that, given existing technical ability to combine the elements, as evidenced by Gupta in view of Chopra, Scholz and Matam above, the to-be combined elements would have fit together like pieces of a puzzle in a logical, complementary, technologically feasible and/or economically desirable manner. Thus, it would have been reasoned that the results of the combination would have been predictable (see MPEP 2143 A).
Regarding claim 10: Gupta / Chopra / Scholz / Matam teaches all the limitations of claim 9 above.
Although Gupta teaches applying a logistic regression function to the client experience scores to produce a regression value, Gupta does not specifically teach optimizing correlation between the regression value of the experience scores and the client behavior using a neural network trained via supervised learning; adjusting the weighting factors to optimize the function for the clients in the group; nor the optimization function being a penalty minimization function.
However, Scholz in analogous art of modeling consumer sentiment and behavior teaches or suggests:
wherein the optimization process uses a gradient descent iterative computation to identify values of the weighting factors which [optimize] the total value of the [..] function, or the optimization process uses a neural network trained via supervised learning to identify values of the weighting factors which minimize the total value of the [..] function (Scholz [0051]: The data analytics processes performed in step 502 may include, in various embodiments, machine learning activities, classification activities using large volumes of raw data, a Bayesian Belief Network (BBN) engine [EN: used in supervised learning]…. In some cases a neural network may be generated and trained, using input data (e.g., service-specific data metrics) and output data (e.g., customer-initiated actions) during the training [EN: optimization] process. Such processes may involve pattern recognition and adaptive machine learning, to form correlations between the various inputs and outputs in order to train the neural network to predict customer actions and/or to perform other predictive analyses based on future data metrics. Mid-¶ [0052]: Updating compound service metric definitions in step 503 may include…updating the assigned weights for data metrics and for different groupings/intermediate layers of data metrics. Mid-¶ [0054]: In such cases, the analytics performed in step 502 and the updated data metrics, relationships, weights, etc., determined in step 503 may be used to tune and/or optimize the previously defined compound service metrics).
Scholz, Chopra and Gupta are found as analogous art of modeling consumer sentiment and behavior. It would have been obvious to one skilled in the art, before the effective filing date of the invention, to have modified Gupta / Chopra’s techniques for generating and dynamically updating client experience scores to have included Scholz’s teachings around optimizing correlation between the regression value of the experience scores and the client behavior using a neural network trained via supervised learning and adjusting the weighting factors to optimize the function for the clients in the group. The benefit of these additional features would have provided additional insight into the relationship between customer experience metrics and customer behavior (Scholz abstract). The predictability of such modifications and/or variations, would have been corroborated by the broad level of skill of one of ordinary skills in the art as articulated by Gupta in view of Chopra and Scholz (see MPEP 2143 G).
Further, the claimed invention could have also been viewed as a mere combination of old elements in a similar field of modeling consumer sentiment and behavior. In such combination each element would have merely performed the same function as it did separately. Thus, one of ordinary skill in the art would have recognized that, given existing technical ability to combine the elements, as evidenced by Gupta in view of Chopra and Scholz above, the to-be combined elements would have fit together like pieces of a puzzle in a logical, complementary, technologically feasible and/or economically desirable manner. Thus, it would have been reasoned that the results of the combination would have been predictable (see MPEP 2143 A).
Furthermore, Matam in analogous art of modeling consumer sentiment and behavior teaches or suggests:
[the optimization function being a] penalty minimizing function (Matam ¶ [0081]: In the AIC and BIC, the 2log (L) term rewards the latent space model 422 for the goodness of the fit on the training non-conversational data 218… each of the AIC and BIC also includes penalty terms (e.g., the 2q term for the AIC and the q log(n) term for the BIC). Each penalty term is a function whose value increases if the number of estimated parameters in the latent space model 422 increases. The penalty term penalizes over-fitting in the model. In this manner, the 2log(L) term and the penalty term in the AIC and the BIC create a trade-off between fitting the model to the selected training data and reducing [EN: minimizing] the complexity of the model).
Rationales to have modified / combined Gupta / Chopra / Scholz / Matam are above in claim 9 and reincorporated.
Regarding claim 12: Gupta / Chopra / Scholz teaches all the limitations of claim 11 above.
Gupta further teaches:
The system according to Claim 11 where updating the weighting factors includes performing a logistic regression calculation on the client experience score for each of the clients to produce a regression value [..] (Gupta ¶ [0048]: As used herein, any type of ML engine, algorithm, model, or neural network may be used to perform the disclosed operations. As used herein, reference to "machine learning" or to a ML model or to a "neural network" may Include… logistic regression model(s). ¶ [0081]: In some embodiments, the ML engine 405 can also perform a regression analysis 450. The regression analysis 450 generally refers to a technique for identifying trends in data, such as possible dependencies between variables. As will be discussed in more detail shortly, the ML engine 405 can perform the regression analysis 450 in an effort to identify which specific interaction types or which specific events contributed most heavily to a user's particular experience score).
Although Gupta teaches applying a logistic regression function to the client experience scores to produce a regression value, Gupta does not specifically teach producing a regression value in a range of zero to one; optimizing correlation between the regression value of the experience scores and the client behavior, and adjusting the weighting factors to optimize the function for the clients in the group; nor the optimization function being a penalty minimization function.
However, Scholz in analogous art of modeling consumer sentiment and behavior teaches or suggests:
defining a [..] function which [optimizes] correlation between the regression value and the behavioral parameter for the group of the clients, and performing the optimization process to adjust the weighting factors in order to [..] [optimize] a total value of the [..] function for all of the clients in the group (Scholz mid-¶ [[0051]: Such processes may… form correlations between the various inputs and outputs in order to train the neural network to predict customer actions [EN: behaviors] and/or to perform other predictive analyses based on future data metrics. Mid-¶ [0052]: Updating compound service metric [EN: function] definitions in step 503 may include…updating the assigned weights for data metrics and for different groupings/intermediate layers of data metrics. End-¶ [0053]: …a set of service-specific data metrics may be identified, combined/grouped and/or weighted to serve as the compound service metric definition from which values may be calculated for individual customers or groups of customers. Mid-¶ [0054]: In such cases, the analytics performed in step 502 and the updated data metrics, relationships, weights, etc., determined in step 503 may be used to tune and/or optimize the previously defined compound service metrics), and
where the optimization process uses a gradient descent iterative computation to identify values of the weighting factors which [optimize] the total value of the [..] function, or the optimization process uses a neural network trained via supervised learning to identify values of the weighting factors which [optimize] the total value of the [..] function (Scholz [0051]: The data analytics processes performed in step 502 may include, in various embodiments, machine learning activities, classification activities using large volumes of raw data, a Bayesian Belief Network (BBN) engine [EN: used in supervised learning]…. In some cases a neural network may be generated and trained, using input data (e.g., service-specific data metrics) and output data (e.g., customer-initiated actions) during the training [EN: optimization] process. Such processes may involve pattern recognition and adaptive machine learning, to form correlations between the various inputs and outputs in order to train the neural network to predict customer actions and/or to perform other predictive analyses based on future data metrics. Mid-¶ [0052]: Updating compound service metric definitions in step 503 may include…updating the assigned weights for data metrics and for different groupings/intermediate layers of data metrics. Mid-¶ [0054]: In such cases, the analytics performed in step 502 and the updated data metrics, relationships, weights, etc., determined in step 503 may be used to tune and/or optimize the previously defined compound service metrics).
Rationales to have modified / combined Gupta / Scholz are above in claim 10 and reincorporated.
Furthermore, Matam in analogous art of modeling consumer sentiment and behavior teaches or suggests:
[produce a regression value in a] range of zero to one (Matam ¶ [0068]: In the example depicted in FIG. 4, a trained regression model (or other predictive model) is generated for predicting the probability [EN: regression value in range of zero to one] of an end-user's behavior (e.g., a consumer reaction to a sales call);
[the optimization function being a] penalty minimizing function (Matam ¶ [0081]: In the AIC and BIC, the 2log (L) term rewards the latent space model 422 for the goodness of the fit on the training non-conversational data 218… each of the AIC and BIC also includes penalty terms (e.g., the 2q term for the AIC and the q log(n) term for the BIC). Each penalty term is a function whose value increases if the number of estimated parameters in the latent space model 422 increases. The penalty term penalizes over-fitting in the model. In this manner, the 2log(L) term and the penalty term in the AIC and the BIC create a trade-off between fitting the model to the selected training data and reducing [EN: minimizing] the complexity of the model).
Rationales to have modified / combined Gupta / Chopra / Scholz / Matam are above in claim 9 and reincorporated.
Regarding claim 19: Gupta / Chopra / Scholz teaches all the limitations of claim 8 above.
Gupta further teaches:
wherein updating the weighting factors includes performing a logistic regression calculation on the assessment value for each of the subjects to produce a regression value [..] (Gupta ¶ [0048]: As used herein, any type of ML engine, algorithm, model, or neural network may be used to perform the disclosed operations. As used herein, reference to "machine learning" or to a ML model or to a "neural network" may Include… logistic regression model(s). ¶ [0081]: In some embodiments, the ML engine 405 can also perform a regression analysis 450. The regression analysis 450 generally refers to a technique for identifying trends in data, such as possible dependencies between variables. As will be discussed in more detail shortly, the ML engine 405 can perform the regression analysis 450 in an effort to identify which specific interaction types or which specific events contributed most heavily to a user's particular experience score).
Although Gupta teaches applying a logistic regression function to the client experience scores to produce a regression value, Gupta does not specifically teach producing a regression value in a range of zero to one; optimizing correlation between the regression value of the experience scores and the client behavior, and adjusting the weighting factors to optimize the function for the clients in the group; nor the optimization function being a penalty minimization function.
However, Scholz in analogous art of modeling consumer sentiment and behavior teaches or suggests:
defining a [..] function which [optimizes] correlation between the regression value and the behavioral parameter for the group of the subjects, and performing the optimization process to adjust the weighting factors in order to [optimize] a total value of the [..] function for the group of the subjects (Scholz mid-¶ [[0051]: Such processes may… form correlations between the various inputs and outputs in order to train the neural network to predict customer actions [EN: behaviors] and/or to perform other predictive analyses based on future data metrics. Mid-¶ [0052]: Updating compound service metric [EN: function] definitions in step 503 may include…updating the assigned weights for data metrics and for different groupings/intermediate layers of data metrics. End-¶ [0053]: …a set of service-specific data metrics may be identified, combined/grouped and/or weighted to serve as the compound service metric definition from which values may be calculated for individual customers or groups of customers. Mid-¶ [0054]: In such cases, the analytics performed in step 502 and the updated data metrics, relationships, weights, etc., determined in step 503 may be used to tune and/or optimize the previously defined compound service metrics).
Scholz, Chopra and Gupta are found as analogous art of modeling consumer sentiment and behavior. It would have been obvious to one skilled in the art, before the effective filing date of the invention, to have modified Gupta / Chopra’s techniques for generating and dynamically updating client experience scores to have included Scholz’s teachings around optimizing correlation between the regression value of the experience scores and the client behavior and adjusting the weighting factors to optimize the function for the clients in the group. The benefit of these additional features would have provided additional insight into the relationship between customer experience metrics and customer behavior (Scholz abstract). The predictability of such modifications and/or variations, would have been corroborated by the broad level of skill of one of ordinary skills in the art as articulated by Gupta in view of Chopra and Scholz (see MPEP 2143 G).
Further, the claimed invention could have also been viewed as a mere combination of old elements in a similar field of modeling consumer sentiment and behavior. In such combination each element would have merely performed the same function as it did separately. Thus, one of ordinary skill in the art would have recognized that, given existing technical ability to combine the elements, as evidenced by Gupta in view of Chopra and Scholz above, the to- be combined elements would have fit together like pieces of a puzzle in a logical, complementary, technologically feasible and/or economically desirable manner. Thus, it would have been reasoned that the results of the combination would have been predictable (see MPEP 2143 A).
Furthermore, Matam in analogous art of modeling consumer sentiment and behavior teaches or suggests:
[produce a regression value in a] range of zero to one (Matam ¶ [0068]: In the example depicted in FIG. 4, a trained regression model (or other predictive model) is generated for predicting the probability [EN: regression value in range of zero to one] of an end-user's behavior (e.g., a consumer reaction to a sales call);
[the optimization function being a] penalty minimizing function (Matam ¶ [0081]: In the AIC and BIC, the 2log (L) term rewards the latent space model 422 for the goodness of the fit on the training non-conversational data 218… each of the AIC and BIC also includes penalty terms (e.g., the 2q term for the AIC and the q log(n) term for the BIC). Each penalty term is a function whose value increases if the number of estimated parameters in the latent space model 422 increases. The penalty term penalizes over-fitting in the model. In this manner, the 2log(L) term and the penalty term in the AIC and the BIC create a trade-off between fitting the model to the selected training data and reducing [EN: minimizing] the complexity of the model).
Rationales to have modified / combined Gupta / Chopra / Scholz / Matam are above in claim 9 and reincorporated.
Regarding claim 20: Gupta / Scholz teaches all the limitations of claim 13 above.
Although Gupta teaches applying a logistic regression function to the client experience scores to produce a regression value, Gupta does not specifically teach optimizing correlation between the regression value of the experience scores and the client behavior, and adjusting the weighting factors to optimize the function for the clients in the group; nor the optimization function being a penalty minimization function.
However, Scholz in analogous art of modeling consumer sentiment and behavior teaches or suggests:
wherein the optimization process uses a gradient descent iterative computation to identify values of the weighting factors which [optimize] a total value of a [..] function, or the optimization process uses a neural network trained via supervised learning to identify values of the weighting factors which [optimize] the total value of the [..] function (Scholz [0051]: The data analytics processes performed in step 502 may include, in various embodiments, machine learning activities, classification activities using large volumes of raw data, a Bayesian Belief Network (BBN) engine [EN: used in supervised learning]…. In some cases a neural network may be generated and trained, using input data (e.g., service-specific data metrics) and output data (e.g., customer-initiated actions) during the training [EN: optimization] process. Such processes may involve pattern recognition and adaptive machine learning, to form correlations between the various inputs and outputs in order to train the neural network to predict customer actions and/or to perform other predictive analyses based on future data metrics. Mid-¶ [0052]: Updating compound service metric definitions in step 503 may include…updating the assigned weights for data metrics and for different groupings/intermediate layers of data metrics. Mid-¶ [0054]: In such cases, the analytics performed in step 502 and the updated data metrics, relationships, weights, etc., determined in step 503 may be used to tune and/or optimize the previously defined compound service metrics).
Furthermore, Matam in analogous art of modeling consumer sentiment and behavior teaches or suggests:
[the optimization function being a] penalty minimizing function (Matam ¶ [0068]: In the example depicted in FIG. 4, a trained regression model (or other predictive model) is generated for predicting the probability [EN: regression value in range of zero to one] of an end-user's behavior (e.g., a consumer reaction to a sales call). ¶ [0081]: In the AIC and BIC, the 2log (L) term rewards the latent space model 422 for the goodness of the fit on the training non-conversational data 218… each of the AIC and BIC also includes penalty terms (e.g., the 2q term for the AIC and the q log(n) term for the BIC). Each penalty term is a function whose value increases if the number of estimated parameters in the latent space model 422 increases. The penalty term penalizes over-fitting in the model. In this manner, the 2log(L) term and the penalty term in the AIC and the BIC create a trade-off between fitting the model to the selected training data and reducing [EN: minimizing] the complexity of the model).
Rationales to have modified / combined Gupta / Chopra / Scholz / Matam are above in claim 9 and reincorporated.
------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
The following art is made of record and considered pertinent to Applicant’s disclosure:
Purohit; Nitin et al. US 20210201335 A1, Customer experience rating system and method.
Null; Bradley William et al. US 20230281678 A1, Impact-based strength and weakness determination.
Griebeler; Jeffrey et al. US 20150051957 A1, Measuring customer experience value.
SEKAR; ARCHANA et al. US 20210201359 A1, Systems and methods relating to automation for personalizing the customer experience.
Bjelajac; Cris et al. US 20160034918 A1, System and method for managing customer feedback.
BHATNAGAR; Saumya et al. US 20230351421 A1, Customer-intelligence predictive model.
Perepa; Vijay Rao et al. US 20150206157 A1, Methods and systems for estimating customer experience.
Kumar; Shailesh et al. US 20070094067 A1, Method and apparatus for recommendation engine using pair-wise co-occurrence consistency.
Cattaneo; Laura et al. US 20230206160 A1, Systems and methods for rapport determination.
Briancon; Alain Charles et al. US 20200356900 A1, Predictive, machine-learning, locale-aware computer models suitable for location- and trajectory-aware training sets.
Johnsen; Mads et al. US 20190043063 A1, Model-based assessment and improvement of relationships.
Muthusamy; Ganesh et al. US 11853938 B1, System and method of reinforced machine-learning retail allocation.
Clodore; Glen et al. WO 2021173611 A1, Intent analysis for call center response generation.
Fu, Teng, et al. "Modeling Customer Experience in a Contact Center through Process Log Mining." ACM Transactions on Intelligent Systems and Technology (TIST) 12.4 (2021): 1-21.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to REED M. BOND whose telephone number is (571) 270-0585. The examiner can normally be reached Monday - Friday 8:00 am - 5:00 pm.
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, Patricia Munson can be reached at (571) 270-5396. 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.
/REED M. BOND/Examiner, Art Unit 3624
April 27, 2026
/HAMZEH OBAID/Primary Examiner, Art Unit 3624 April 27, 2026
1 MPEP 2106.04(a): “examiners should identify at least one abstract idea grouping, but preferably identify all groupings to the extent possible”.
Prosecution Insights