DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Claim Rejections - 35 USC § 102
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention.
Claims 1, 2, 5 – 12, 15 – 20 are rejected under 35 U.S.C. 102(a)(2) as being anticipated by Faulkner et al. (US PAP 2022/0383867).
As per claims 1, 11, Faulkner et al. teach a system/method used in a computing environment in which unstructured computer text is analyzed for generation of a structured conversation flow for a conversation service application, the system comprising a server computing device having a memory for storing computer-executable instructions and a processor that executes the computer-executable instructions to:
extract a sequence of questions from each of a plurality of historical voice call transcripts by executing, using the processor, a combined rule-based and natural language processing machine learning model on the plurality of historical voice call transcripts (“automatically generating fine-grained call reasons from customer service call transcripts by detecting themes in publicly-available corpus of personal finance questions”; paragraphs 91 -93);
convert each of the extracted questions into a multidimensional embedding using a sentence transformer machine learning model (“One example technique evaluated several embedding- and transformer-based models in combination with different clustering and distance metrics on newswire and scientific texts and reported that a simple skip-gram model, operating over character n-grams, along with agglomerative clustering, provides the highest-quality result, where cluster quality was measured using Adjusted Mutual Information.”; paragraphs 93 – 97);
cluster the multidimensional embeddings into one or more question clusters using a similarity measure algorithm, each of the question clusters assigned a cluster identification label (“The event embeddings can enable the cluster generation system 602 to identify clusters of situationally similar events independent of lexical overlap. The cluster generation system 602 can then utilize the embeddings representation generation model 610 to generate a problem-statement semantics vector 616 indicative of the event embeddings (e.g., the semantics of the problem statement represented as a dense n-dimensional vector).”; paragraphs 67, 92 – 97);
generate, for each historical voice call transcript, a sequence of cluster identification labels corresponding to the sequence of questions extracted from the call transcript (“the cluster generation system 208 can label each cluster of events using a graph-based sentence compression algorithm that generalizes lexical variations in the events of each cluster of events.”; paragraphs 76 – 78, 92 – 95, 125 - 128); and
create a conversation flow graph for each historical voice call transcript based upon the associated sequence of cluster identification labels (“provide a label for each cluster that generalizes the lexical variation found in the cluster into a human-readable string. These labels can then be leveraged as an analytics solution to provide insight into the occurrence of fine-grained call reasons relative to particular time periods or can be used to create call metadata to aid in search…After clustering all events across the corpus, the cluster generation system 602 can perform cluster labeling 630 to provide a label to each cluster using a graph-based sentence compression algorithm that generalizes the lexical variation found in that cluster's events.”; paragraphs 32, 68, 76 – 78).
As per claims 2, 12, Faulkner et al. further disclose the server computing device modifies a conversation flow of the conversation service application using the conversation flow graph (paragraphs 53 - 56,128, 129).
As per claims 5, 15, Faulkner et al. further disclose the server computing device preprocesses the plurality of historical voice call transcripts before executing the combined rule-based and natural language processing machine learning model on the plurality of historical voice call transcripts (“The business value of theme detection for call center data has motivated its inclusion in natural language processing (NLP) tool benches for call center transcript analyses. The DCRS tool for theme detection employs a pipeline approach to this task. In the first step, a small number of customer utterances likely to contain mentions of the customer's reason for calling, as determined by simple heuristics, are pulled from the transcript.”; paragraphs 5, 95).
As per claims 6, 16, Faulkner et al. further disclose preprocessing the plurality of historical voice call transcripts comprises: replacing one or more regular expressions in the historical voice call transcripts with default values; detecting boundaries between sentences in the historical voice call transcripts; and inserting punctuation at each sentence boundary in the historical voice call transcripts (“the speaker turn preprocessing system 402 can be configured to clean, autopunctuate, and resolve co-references in the text strings of speaker turns extracted by a transcript processing and classification system (e.g., the extracted speaker turns 316 generated by the transcript processing and classification system 302 shown in FIG. 3)… The speaker turn preprocessing system 402 can utilize an autopunctuation model 410 to perform vectorization 412 and assign punctuation using a bidirectional LSTM 414 to generate autopunctuated speaker turns”; paragraphs 49 – 60).
As per claims 7, 17, Faulkner et al. further disclose the server computing device executes a natural language processing model to replace the regular expressions and the server computing device executes a large language model to detect the boundaries and insert the punctuation(“the speaker turn preprocessing system 402 can be configured to clean, autopunctuate, and resolve co-references in the text strings of speaker turns extracted by a transcript processing and classification system (e.g., the extracted speaker turns 316 generated by the transcript processing and classification system 302 shown in FIG. 3)… The speaker turn preprocessing system 402 can utilize an autopunctuation model 410 to perform vectorization 412 and assign punctuation using a bidirectional LSTM 414 to generate autopunctuated speaker turns”; paragraphs 49 – 60).
As per claims 8, 18, Faulkner et al. further disclose the similarity measure algorithm comprises a k-means clustering algorithm or an hdbscan algorithm (“The DCRS used HDBSCAN to accomplish this by first organizing embeddings into a distance weighted graph and then found a corresponding minimum spanning tree to obtain a hierarchy of connected components comprising a cluster.”; paragraphs 70, 110).
As per claims 9, 19, Faulkner et al. further disclose the conversation flow graph comprises a data structure with a plurality of nodes connected via edges and arranged according to the sequence of cluster identification labels (“The DCRS used HDBSCAN to accomplish this by first organizing embeddings into a distance weighted graph and then found a corresponding minimum spanning tree to obtain a hierarchy of connected components comprising a cluster.”; paragraphs 93, 110).
As per claims 10, 20, Faulkner et al. further disclose the server computing device merges at least two of the conversation flow graphs to generate an aggregate conversation flow graph (“The DCRS used HDBSCAN to accomplish this by first organizing embeddings into a distance weighted graph and then found a corresponding minimum spanning tree to obtain a hierarchy of connected components comprising a cluster.”; paragraphs 93, 110).
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claims 3, 4, 13, and 14 are rejected under 35 U.S.C. 103 as being unpatentable over Faulkner et al. (US PAP 2022/0383867) in view of Pathak et al. (US PAP 2025/0131501).
As per claims 3, 13, Faulkner et al. do not specifically teach modifying a conversation flow of the conversation service application comprises rearranging a sequence of prompts in a conversation flow of the conversation service application, adding one or more prompts to a conversation flow of the conversation service application, removing one or more prompts from a conversation flow of the conversation service application, or changing content of one or more prompts in a conversation flow of the conversation service application.
Pathak et al. teach that an embodiment may employ a prompt-based training strategy for question generation from earnings report. In prompt-based training, a tuning-free prompting strategy is selected. Tuning-free prompting directly generates the text without changing the parameters of the pre-trained LMs based only on a prompt. Question generation is a task that involve generating questions, usually conditioned on some contextual information. Prompting methods can be easily applied to this task by using prefix prompts together with autoregressive pre-trained LMs (paragraph 81).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective date of the claimed invention to modify a conversation flow of the conversation service application as taught by Pathak et al. in Faulkner et al., because that would help improve communications between parties based on analysis of past behavior of one of the parties (paragraph 24).
As per claims 4, 14, Faulkner et al. in view of Pathak et al. further disclose the conversation service application comprises a chatbot application, an interactive voice response (IVR) application, a virtual assistant application, or a guided service application (“comprise or consist of a virtual machine (VM), that VM may constitute a virtualization of any combination of the physical components”; Pathak et al., paragraph 119).
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure. Attwater et al. teach System And Method For Automatic Summarization In Interlocutor Turn-Based Electronic Conversational Flow. Orkin et al. teach Event-based Semantic Search And Retrieval.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to LEONARD SAINT-CYR whose telephone number is (571)272-4247. The examiner can normally be reached Monday- Friday.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Richemond Dorvil can be reached at (571)272-7602. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/LEONARD SAINT-CYR/ Primary Examiner, Art Unit 2658
Prosecution Insights