Jump to content

Patent Application 17967505 - CONTEXT-BASED NATURAL LANGUAGE PROCESSING - Rejection

From WikiPatents

Patent Application 17967505 - CONTEXT-BASED NATURAL LANGUAGE PROCESSING

Title: CONTEXT-BASED NATURAL LANGUAGE PROCESSING

Application Information

  • Invention Title: CONTEXT-BASED NATURAL LANGUAGE PROCESSING
  • Application Number: 17967505
  • Submission Date: 2025-05-14T00:00:00.000Z
  • Effective Filing Date: 2022-10-17T00:00:00.000Z
  • Filing Date: 2022-10-17T00:00:00.000Z
  • National Class: 704
  • National Sub-Class: 009000
  • Examiner Employee Number: 98511
  • Art Unit: 2654
  • Tech Center: 2600

Rejection Summary

  • 102 Rejections: 1
  • 103 Rejections: 0

Cited Patents

The following patents were cited in the rejection:

Office Action Text


    Notice of Pre-AIA  or AIA  Status
1.	The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .

Response to Arguments
2.	Applicant's arguments filed 04/03/2025 have been fully considered but they are not persuasive:
Applicant argues that D’Agostino “Associating a first conversational input with a particular uniform resource locator.” However, D’Agostino explicitly discusses the client device 202 transmitting the input (p[0054]) and the chat bot decision engine 212 selecting the appropriate bot instance for handling it (p[0056]). It is understood in the art that chat bot interactions are typically scoped within a particular service or endpoint (e.g., website or resource page). D’Agostino’s discussion of authentication, user identity (p[0051]) and intent resolution (p[0056]) necessarily includes association with a source context such as a URL, especially when routed through specific chat bot instances. Additionally, p[0085-0086] teach that the intent deciphering and decision engine modules determine “both intent of the conversational input 204” and “which bot to provide the received input for and answer.” Since different bots handle different domains, the underlying association between the input and scoped domain (e.g., via a URL) is inherently present and would be understood by a person of ordinary skill in the art.
Applicant further argues D’Agostino does not disclose “determining context based on the URL and the first input.”. However, D’Agostino discloses determining an intent based on the conversational input (p[0056) and routing that input to a specific bot library (p[0086]). A “context” in dialogue systems often correspond to which service or scope is active, which is what is resolved when D’Agostino determines which bot instance should respond. Therefore, even though D’Agostino does not use the word “context,” its teaching of determining intent and bout routing satisfies this limitation.
Applicant further argues D’Agostino does not disclose “Subsequent to receiving the first conversational input, receive a second conversational input.” However, D’Agostino discloses that many of the operations in these processes may take place simultaneously, concurrently, and/or in different orders (p[0085-0086]) which would be understood by a person of ordinary skill in the art as including multi-turn dialogues. The fact that D’Agostino routes inputs to different bots based on intent further implies a conversation context that evolves over multiple turns. Therefore, sequential inputs and updated intent processing are reasonably anticipated by D’Agostino.
Lastly, Applicant argues that D’Agostino does not disclose “Generate a second response to the second input based on updated intent and context.” However, D’Agostino teaches that the NLP engine deciphers the intent of input (p[056]), and the bot decision engine determines which bot responds (p[0086]). Repeated interactions with updated inputs would be necessary in the iterative operations of these components. A person of ordinary skill in the art would recognize that after handling the first input, the same architecture would apply to a subsequent input, which by definition uses the updated dialogue state (context, prior intent) through many established methods such as attention mechanisms, decision trees etc.
Therefore, the rejection of claims 1-20 are maintained.

Claim Rejections - 35 USC § 102
3.	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.  
4.	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)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.


5.	Claims 1-20 are rejected under 35 U.S.C. 102(a)(1) as being anticipated by D’Agostino (US 2020/0099633).

Regarding Claim 1:
	D’Agostino a discloses system, comprising: a memory; and at least one computing device in communication with the memory (D’Agostino: p[0004-0006]), wherein the at least one computing device is configured to: 
receive a first conversational input of a plurality of sequential conversational inputs via at least one user input device, wherein the first conversational input is associated with a particular uniform resource locator (URL) address (D’Agostino: p[0024] and p[0051] The conversational manager receives inputs from client devices through a conversational interface. p[0054] and p[0078] describes inputs linked to contextual sources such as a chat bot interface or systems, which extends to URL-based contexts);
process the first conversational input via at least one natural language processing (NLP) algorithm to: determine a context based on the particular URL address and the first conversational input (D’Agostino: p[0054-0056] discloses that the NLP system analyzes inputs for context determination);
and determine at least one intent based on the context and the first conversational input (D’Agostino: p[0054-0056] discloses that the NLP system analyzes inputs for intent determination); 
generate a response to the first conversational input based on the context and the at least one intent (D’Agostino: p[0054-0056] discloses that the NLP system analyzes inputs for context determination);
subsequent to receiving the first conversational input, receive a second conversational input of the plurality of sequential conversational inputs (D’Agostino: p[0024], p[0059], p[0085] discloses the conversational managers ability to manage multi-turn interactions, including receiving subsequent inputs);
process the second conversational input via the NLP algorithm to generate at least one updated intent based on the first conversational input, the second conversational input, and the particular URL address (D’Agostino: p[0059] and p[0085-0086] disclose iterative context determination and intent refinement for handling sequential conversational inputs); 
and generate a second response to the second conversational input based on the at least one updated intent and the context (D’Agostino: p[0059] and p[0085-0086] disclose iterative context determination and intent refinement for handling sequential conversational inputs).

Regarding Claim 2:
	D’Agostino further discloses the system of claim 1, wherein the context is a first context and the at least one computing is further configured to: 
identify a contextual change in a subset of the plurality of sequential conversational inputs (D’Agostino: p[0056-0058] discloses analyzing sequential inputs to detect changes in conversational context, with mechanisms to track ongoing conversations and detect when context shifts);
and initiate a change from the first context to a second context based on the contextual change (D’Agostino: p[0069-0072] and p[0056] discloses that the conversational manager routes subsequent inputs to different chat bots or contexts when a change in intent or subject matter is identified seamlessly transitioning between contexts).

Regarding Claim 3:
D’Agostino further discloses the system of claim 2, wherein the at least one computing is further configured to iteratively process a plurality of second sequential conversational inputs, via natural language processing (NLP) algorithm and based on the second context, to generate a plurality of second responses individually corresponding to a respective one of the plurality of second sequential conversational inputs (D’Agostino: p[0071-0072] discloses tracking conversation history and iteratively refining context for subsequent inputs to generate contextually relevant responses).

Regarding Claim 4:
	D’Agostino further discloses the system of claim 3, wherein the at least one computing is further configured to iteratively process the plurality of sequential conversational inputs based on the second context prior to generating the plurality of second responses (D’Agnostino: p[0070-0072] refines inputs iteratively within the new context before generating responses ensuring continuity, it can also switch to a different device/conversational manager).

Regarding Claim 5:
	D’Agostino further discloses the system of claim 1, wherein: the at least one computing is configured to receive the first conversational input via the at least one computing device by a first container (D’Agostino: p[0068-0069] discloses routing input to context-specific chat bots (containers) for their respective topics i.e., “routes to chat bot 3 because chat bot 3’s expertise is in social media”);
the context is a first context of the first container (D’Agostino: p[0041] any of the contexts can be containers i.e., Chat bot 1, ‘bob’, Chat bot financial etc., no particular order is necessary);
the at least one computing device is further configured to: prior to generating the at least one updated intent, determine to change to a second container based on at least one of: 
the second conversational input, a profile associated with a particular user account, and the first context of the first container (D’Agostino: p[0058] user conversational and account data can be used to seamlessly switch to a new chat bot);
and relay the second conversational input to a second container (D’Agostino: p[0058] discloses switching chat bots container).

Regarding Claim 6:
D’Agostino further discloses the system of claim 5, wherein the system comprises: a first application that, when executed by the at least one computing device (D’Agostino p[0024-0025] discloses the first application operates as an initial processing agent, handling the receipt and preliminary processing of conversational inputs, also see Fig. 2 204 through 210), causes the first application to: 
receive the first conversational input the at least one user input device (D’Agostino p[0051-0052] the first application takes input from a user via devices like keyboards microphones or touchscreens);
process the first conversational input via the at least one natural language processing (NLP) algorithm to: 
determine the first context of the first container based on the particular URL address and the first conversational input (D’Agostino: p[0051-0052] and p[0069] identifies the context by associating the input with a link/route and categorizing it in the appropriate ‘container’. It is noted this is done over a network as seen in Fig. 1 and therefore must include some form of URL or internet/intranet directory system); 
and determine the at least one intent based on the first context of the first container and the first conversational input (D’Agostino: p[0071-0077] the intent is derived from analyzing the input within the context established by the container);
and generate the response to the first conversational input based on the context and the at least one intent (D’Agostino: p[0059] );
receive, by the first container, the second conversational input (D’Agostino: p[0082] continues tracking user interaction and processes additional input with received second sets of input);
prior to generating the at least one updated intent, determine whether to change to the second container based on at least one of the second conversational input, the profile associated with the particular user account, and the first context of the first container (D’Agostino: p[0069] system decides whether to switch to a new container based on updated information); 
and relay the second conversational input to the second container (D’Agostino: p[0084] when a context change is detected the input is forwarded to the relevant container);
and a second application that, when executed by the at least one computing device, causes the second application to:
receive, by the second container, the second conversational input relayed from the first container (D’Agostino: p[0084] the inputs are relayed to the second chatbot, the second container begins processing the relayed input);
determine a second context of the second container based on the second conversational input (D’Agostino: p[0084] when a context change is detected the input is forwarded to the relevant container);
process the second conversational input via the NLP algorithm to generate at least one updated intent based on the first conversational input, the second conversational input, and the particular URL address (D’Agostino: p[0084] the system leverages historical and current inputs to update its understanding);
and process at least one second conversational input, based on the at least one updated intent and the second context in the second container, to generate at least one second response (D’Agostino: p[0059] second container generates a response tailored to the updated intent and context).

Regarding Claim 7:
D’Agostino further discloses the system of claim 6, wherein the first application is executed by a first computing device of the at least one computing device and the second application is executed by a second computing device of the at least one computing device (D’Agostino: p[0029] and p[0058] discloses a distributed architecture where applications/chat bots can run on separate computing devices).

Regarding Claim 8:
	Claim 8 has been analyzed with regard to claims 1 (see rejection above) and
is rejected for the same reasons of anticipation as used above.

Regarding Claim 9:
D’Agostino further discloses the method of claim 8, wherein processing the first conversational input via the at least one NLP algorithm comprises scanning through a plurality of tiers of knowledge bases to determine the context and the at least one intent (D’Agostino: p[0051-0058] contextual repository and domain intelligence analyze inputs for context and intent).

Regarding Claim 10:
D’Agostino further discloses the method of claim 9, wherein processing the second conversational input via the at least one NLP algorithm comprises scanning through the plurality of tiers of knowledge bases to determine the at least one updated intent (D’Agostino: p[0059] and p[0085-0086] disclose iterative context determination and intent refinement for handling sequential conversational inputs).

Regarding Claim 11:
	D’Agostino further discloses the method of claim 10, wherein the plurality of tiers of knowledge bases (D’Agostino: p[0069] the conversational manager organizes requests into conversational contexts and routes them to specific chat bots that act as containers for their respective topics) are assigned to a hierarchy based on an as-signed information scope (D’Agostino: p[0071] the intent deciphering module determines intent by analyzing contextual data, which can include hierarchical relationships between topics or contexts).

Regarding Claim 12:
D’Agostino further discloses the method of claim 8, wherein generating the response to the first conversational input comprises processing a response tree algorithm based on the context and the at least one intent (D’Agostino: p[0068] discloses the system applies structured decision-making algorithms to select the most appropriate response and p[0093] discloses that the system accesses structured repositories of information to refine responses based on contextual importance and priority).

Regarding Claim 13:
	D’Agostino further discloses the method of claim 12, wherein generating the second response comprises processing the response tree algorithm based on the context and the at least one updated intent (D’Agostino: p[0059] responses are generated based on the context and intent identified through natural language processing of first and second communications).

Regarding Claim 14:
D’Agostino further discloses the method of claim 12, wherein generating the response to the first conversational input comprises: determining a dynamic content variable associated with the response (D’Agostino: p[0043] includes domain intelligence for the conversation analysis system, and it stores various objects/data including dynamic information, variables parameters, algorithms instructions rules constraints etc. associated with the purposes of the conversation system);
and formatting the response based on a channel type corresponding to a current user session and the dynamic content variable (D’Agostino: p[0043] the domain intelligence may include contextual repositories, the chat bot library and the user profile, all of which is used to determine the type of session/chat bot that should be utilized).

Regarding Claim 15:
	D’Agostino further discloses the method of claim 14, wherein the step of processing the first conversational input via the at least one natural language processing (NLP) algorithm to determine the at least one intent is further based on a plurality of past conversational inputs corresponding to the current user session (D’Agostino: p[0058] the conversational system tracks and stores historical inputs within an ongoing session to refine the determination of context and intent, it is also used to provide continuity and refine response generation across multi-step interactions).
Regarding Claim 16:
D’Agostino further discloses the method of claim 8, wherein the response is a top-ranked entry of a main response track and the method further comprises:
determining that the top-ranked entry of the main response track is unavailable (D’Agostino: p[0058] discloses generating and prioritizing responses based on content and ranking mechanisms);
determining that a top-ranked entry of a fallback response track satisfies the at least one intent (D’Agostino: p[0058] discloses the conditions where specific chatbots may not be able to handle a request, prompting fallback mechanisms by transitioning to another chat bot between response tracks);
and identifying the top-ranked entry of the fallback response track as the response (D’Agostino: p[0049] and p[0058] explicitly describes finalizing the response by selecting the most appropriate fallback option when the primary is unavailable and producing the response).

Regarding Claim 17:
	Claim 17 has been analyzed with regard to claims 1 (see rejection above) and
is rejected for the same reasons of anticipation as used above.

Regarding Claim 18:
Claim 18 has been analyzed with regard to claims 9 (see rejection above) and
is rejected for the same reasons of anticipation as used above.



Regarding Claim 19:
D’Agostino further discloses the non-transitory, computer-readable medium of claim 18, wherein the program, when executed by the at least one computing device, further causes the at least one computing device to: 
receive first criteria associated with a client (D’Agostino: p[0055] and p[0065] discloses the chat bot decision engine receiving user-specific conversational inputs and credentials to determine authentication and guide subsequent actions. These inputs act as the “first criteria” associated with a client); 
obtain a plurality of knowledge volumes based on the first criteria (D’Agostino: p[0064] discloses accessing a domain intelligence repository containing contextual information and intent data associated with the multiple chatbots these knowledge volumes are retrieved based on user-specific criteria, such as a conversational context or authentication data), wherein each of the plurality of knowledge volumes comprises a respective plurality of contexts and a respective plurality of intents (D’Agostino: p[0064] discloses accessing a domain intelligence repository containing contextual information (user provides, transaction types) and intent information (financial inquiries and social media tasks));
and generate a plurality of knowledge tiers based on the plurality of knowledge volumes (D’Agostino: p[0065] discloses that chat bot engine organizing retrieved knowledge into actionable tiers or hierarchies).

Regarding Claim 20:
Claim 20 has been analyzed with regard to claims 11 (see rejection above) and
is rejected for the same reasons of anticipation as used above.

Conclusion
THIS ACTION IS MADE FINAL. 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.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to IAN SCOTT MCLEAN whose telephone number is (703)756-4599. The examiner can normally be reached "Monday - Friday 8:00-5:00 EST, off Every 2nd 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, Hai Phan can be reached at (571) 272-6338. 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.





/IAN SCOTT MCLEAN/Examiner, Art Unit 2654                                                                                                                                                                                                        
/HAI PHAN/Supervisory Patent Examiner, Art Unit 2654


Retrieved from "https://wikipatents.org/index.php?title=Patent_Application_17967505_-_CONTEXT-BASED_NATURAL_LANGUAGE_PROCESSING_-_Rejection&oldid=594949"
Cookies help us deliver our services. By using our services, you agree to our use of cookies.