DETAILED ACTION
1. The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
2. This action is in response to action filed on 6/25/2024, in which claims 1 – 20 was presented for examination.
3. Claims 1 – 20 are pending in the application.
Information Disclosure Statement
4. The information disclosure statement (IDS) submitted on 5/21/2025 has been reviewed and entered into the record. The submission is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is being considered by the examiner.
Claim Rejections - 35 USC § 103
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.
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.
5. Claims 1, 6 – 12, and 16 – 20 are rejected under 35 U.S.C. 103 as being unpatentable over Heo et al (US 2012/0101807 A1), in view of Walia et al (US 2017/0169101 A1)
As per claim 1, Heo et al (US 2012/0101807 A1) discloses,
A computer-readable non-transitory memory storing instructions that when executed by one or more computer processors cause the one or more computer processors to perform steps of a method for solving domain specific problems specified using natural language requests (para.[0002]; “domain identifying apparatus and method for classifying a user's question into a question appropriate for a question and answer and a query appropriate for information searching to identify the user's question”).
the steps comprising: receiving, by a chatbot, a natural language request for answering a question from one of a plurality of domains (para.[0004]; “user inputs required information in form of a question in a natural language” and para.[0009]; “provided a question type and domain identifying apparatus”).
the natural language request comprising a domain specific problem (para.[0009]; “provided a question type and domain identifying apparatus”).
determining whether any of a plurality of domain specific models are configured to answer the domain specific problem (para.[0042]; “determines a question and answer engine for processing the user's question among various domain-specialized and question and answer engines).
each of the plurality of domain specific models storing a knowledge base specific to a domain (NOTE: para.[0062]; “respective domain question and answer engines 300/1 to 300/n of the question and answer engine block 300 refer to question and answer engines specialized for respective domains”)
responsive to determining that at least one of the plurality of domain specific models is configured to answer the domain specific problem specified in the natural language request (para.[0052]; “domain distribution block 202 serves
to identify and distribute a domain for the user's question (i.e., determining a question and answer domain) on the basis of the law dictionary that is predefined for each domain with respect to the language analysis results over the user's question and stored in the law dictionary DB”).
selecting a domain specific model from a plurality of domain specific models for answering the domain specific problem (para.[0053]; “questions to be distributed
to a question and answer engine specialized as a 'sports' domain are highly likely to include names of sports events, so when a user's question includes the name of a sports event, it has a high possibility of being a question of the 'sports' domain”).
executing the domain specific model to answer the domain specific problem (para.[0064]; “contents search filtering engine 400 serves to identify a question subject and area through the analysis of the user's question, and restrict search target documents in the domain question and answer engine distributed on the basis of
the identified question subject information and area information”).
Heo does not specifically disclose responsive to determining that none of the plurality of domain specific models can answer the domain specific problem,
selecting a software tool from a plurality of software tools for answering the domain specific problem; sending a request to the software tool for answering the domain specific problem; and sending a result of execution of the software tool to a client device.
However, Walia et al (US 2017/0169101 A1) in an analogous art discloses,
receiving, by a chatbot, a natural language request (NOTE: para.[0093]; “dialog screen is caused on the webpage in response to customer input corresponding to the
chat widget on a webpage” and para.[0096]; “natural language query provided as an input by a customer in the dialog screen is received”).
each of the plurality of domain specific models storing a knowledge base specific to a domain (para.[0027]; “Each QA domain, i.e. a QA database, includes a plurality of questions typically asked by customers for a particular category along with corresponding answers”).
responsive to determining that none of the plurality of domain specific models can answer the domain specific problem (para.[0051]; “If the appropriate answer to the natural language query is not available in the QA domains, then the customer is offered options that can help lead to the appropriate answer” and para.[0096]; “determined whether an answer to the natural language query exists in at least one question-answer (QA) domain from among a plurality of QA domains”).
selecting a software tool from a plurality of software tools for answering the domain specific problem (para.[0051]; “If the appropriate answer to the natural language query is not available in the QA domains, then the customer is offered options that can help lead to the appropriate answer”).
sending a request to the software tool for answering the domain specific problem; and sending a result of execution of the software tool to a client device (para.[0051]; “the options include a link to a webpage (homepage, FAQ, etc.), an offer to provide an additional query or refine the query, an offer to chat with an agent, and
the like”).
Therefore, it would have been obvious to one of ordinary skill in the art before the invention was filed to incorporate alternate option to process the query when QA domain for the query is not available of the system of Walia into the process of identifying question type and domain for information searching of Heo to provide a contingency plans and processes which retain the customers long enough to answer their question while not incurring excessive cost for the enterprises.
As per claim 6, the rejection of claim 1 is incorporated and further Heo et al (US 2012/0101807 A1) discloses,
wherein at least a domain specific model comprises: a machine learning based model trained to make a prediction based on a particular input data, a knowledge model wherein the knowledge model is a rule-based model, wherein each rule makes a prediction based on one or more characteristics of input data, and an ensemble model configured to combine results of the knowledge model and the machine learning based model (para.[0042]; “determines a question and answer engine for processing the user's question among various domain-specialized question and answer engines) on the basis of a hybrid technique combining mechanic learning and laws, namely, on the basis of a law dictionary established by domain or a learning model established by using learning data”).
As per claim 7, the rejection of claim 6 is incorporated and further Heo et al (US 2012/0101807 A1) discloses,
wherein the ensemble model combines results of the knowledge model and the machine learning based model based on a measure of accuracy of the knowledge model and a measure or accuracy of the machine learning based model (para.[0043]; “the language analyzer 201 analyzes the language of the user's question and provides the analysis results to the law-based domain distribution block 202, and analyzes the language of the learning data established as representative questions of the respective domains and provides the analysis results to the leaning quality extraction block”).
As per claim 8, the rejection of claim 7 is incorporated and further Heo et al (US 2012/0101807 A1) discloses,
wherein the ensemble model is configured to select an output of the machine learning based model as a final output if the measure of accuracy of the machine learning based model is higher than the measure of accuracy of the knowledge model (para.[0038]; “classifies the user's question as a query when a weight value of a question and answer type does not exceed a preset threshold value, and classifies the user's question as a keyword array question when the weight value exceeds the preset threshold value”).
and select the output of the knowledge model as the final output if the measure of accuracy of the knowledge model is higher than the measure of accuracy of machine learning based model (para.[0040]; “compared to the difference between 0.9 and 0.85, only A and Bare selected as answer types, and in this case, the threshold value is 0.85”).
As per claim 9, the rejection of claim 6 is incorporated and further Heo et al (US 2012/0101807 A1) discloses,
wherein the ensemble model generates a final output that is a weighted aggregate of an output of the machine learning based model and an output of the knowledge model, wherein a weight of each output is determined based on a measure of accuracy of a corresponding model (para.[0039]; “weight values of the other remnant are determined by a structured support vector machine (SVM) learning model, and in this case, a numerical value”).
As per claim 10, the rejection of claim 1 is incorporated and further Heo et al (US 2012/0101807 A1) discloses,
wherein at least a software tool is a search engine, wherein the instructions cause the one or more computer processors to perform steps comprising: extracting one or more search keywords from the natural language request (para.[0037]; “question and answer type recognition unit 106 categorizes the user's question into a query form or keyword array form based on recognition results of predefined question and answer type”).
providing the one or more search keywords to the search engine (para.[0032]; “question type and domain identifying apparatus includes a question type identifier 100, a question domain distributor 200, a question-and-answer engine 300, a contents
search filtering engine”).
receiving a set of search results matching the one or more search keywords from the search engine (para.[0029]; “documents are restricted on the basis of a question subject identified in a question and area information in the question”).
Walia further discloses,
and extracting a response to the natural language request form a search result selected from the set of search results (para.[0054]; “search for appropriate question-answer pairs may then be performed within the domain best suited to (or matched to) the query. The search results may be ranked based on query matching metrics. Different threshold values can be used for the top-level natural language model and each sub-model”).
Therefore, it would have been obvious to one of ordinary skill in the art before the invention was filed to incorporate alternate option to process the query when QA domain for the query is not available of the system of Walia into the process of identifying question type and domain for information searching of the system of Heo to provide a contingency plans and processes which retain the customers long enough to answer their question while not incurring excessive cost for the enterprises.
As per claim 11, the rejection of claim 10 is incorporated and further Walia et al (US 2017/0169101 A1) discloses,
wherein the instructions for extracting the response to the natural language request from the search result selected from the set of search results cause the one or more computer processors to perform steps (para.[0054]; “search for appropriate question-answer pairs may then be performed within the domain best suited to (or matched to) the query. The search results may be ranked based on query matching metrics. Different threshold values can be used for the top-level natural language model and each sub-model”).
comprising: generating a prompt comprising one or more search results and the natural language request and a request to determine whether the search result comprises information for answering the domain specific problem specified by the natural language request (para.[0081]; “if a question with the query matching metric of greater than the predefined threshold value is identified, then the answer of the corresponding question is provided to the customer as the response”).
providing the prompt as input to a large language model and selecting a result from the set of search results based on a response obtained by executing the large language model (para.[0098]; “When an appropriate answer to the query is found, the answer is presented to the customer. When an appropriate answer cannot be found, then the customer is offered options that can help lead to the appropriate answer”).
Therefore, it would have been obvious to one of ordinary skill in the art before the invention was filed to incorporate alternate option to process the query when QA domain for the query is not available of the system of Walia into the process of identifying question type and domain for information searching of the system of Heo to provide a contingency plans and processes which retain the customers long enough to answer their question while not incurring excessive cost for the enterprises.
Claims 12, 16, 17 – 18, and 19 are method claim corresponding to computer-readable non-transitory memory claims 1, 6, 8 – 9, and 10 -11 respectively, and rejected under the same reason set forth in connection to the rejection of claims 1, 6, 8 – 9, and 10 - 11 respectively above.
Claim 20 is a system claim corresponding to computer-readable non-transitory memory claim 1, and rejected under the same reason set forth in connection to the rejection of claim 1 above.
6. Claims 2 – 5 and 13 – 15 are rejected under 35 U.S.C. 103 as being unpatentable over Heo et al (US 2012/0101807 A1), in view of Walia et al (US 2017/0169101 A1), and further in view of Alexander et al (US 2023/0401387 A1).
As per claim 2, the rejection of claim 1 is incorporated, Heo et al (US 2012/0101807 A1) and Walia et al (US 2017/0169101 A1) does not specifically disclose wherein the instructions further cause the one or more computer processors to perform steps comprising: for each of the plurality of domain specific models, storing vector representation of description of the domain specific model in a vector database; determining a vector representation of the natural language request; and for each of the plurality of domain specific models, determining a vector distance between the vector representation the natural language request and the vector representation the description of the domain specific model.
However, Alexander et al (US 2023/0401387 A1) in an analogous art discloses,
wherein the instructions further cause the one or more computer processors to perform steps (para.[0050]; “memory 706 holds instructions and data used by the processor”).
comprising: for each of the plurality of domain specific models, storing vector representation of description of the domain specific model in a vector database (para.[0027]; “the training data store 215 stores feature vectors representing each natural language expression that is mapped to an intent”).
determining a vector representation of the natural language request (Fig.3 #320; “determine a feature vector representing the natural language expression”).
and for each of the plurality of domain specific models, determining a vector distance between the vector representation the natural language request and the vector representation the description of the domain specific model (para.[0035]; “measure of distance dl between the anchor data point and the positive data point”, para.[0039]; “the machine learning module 220 determines the domain specific ML
model as the product”, and para.[0042]; “identifies 340 a matching stored feature vector based on the comparison”).
Therefore, it would have been obvious to one of ordinary skill in the art before the invention was filed to incorporate vectorized storage of the system of Alexander into alternate option to process the query when QA domain for the query is not available of Walia to provide an effective matching of users’ request, thereby responding with action appropriate for the users' natural language expressions.
As per claim 3, the rejection of claim 2 is incorporated and further Heo et al (US 2012/0101807 A1) discloses,
wherein the instructions for determining whether any of a plurality of domain specific models are configured to answer the natural language request further cause the one or more computer processors to perform steps (para.[0002]; “domain identifying apparatus and method for classifying a user's question into a question appropriate for a question and answer and a query appropriate for information searching to identify the user's question”).
comprising: responsive to, for each of the plurality of domain specific models (para.[0042]; “determines a question and answer engine for processing the user's question among various domain-specialized and question and answer engines).
Heo does not specifically disclose determining that none of the domain specific model is capable of solving the domain specific problem specified in the natural language request.
However, Walia et al (US 2017/0169101 A1) in an analogous art discloses,
determining that none of the domain specific model is capable of solving the domain specific problem specified in the natural language request (para.[0051]; “If the appropriate answer to the natural language query is not available in the QA domains, then the customer is offered options that can help lead to the appropriate answer” and para.[0096]; “determined whether an answer to the natural language query exists in at least one question-answer (QA) domain from among a plurality of QA domains”).
Therefore, it would have been obvious to one of ordinary skill in the art before the invention was filed to incorporate alternate option to process the query when QA domain for the query is not available of the system of Walia into the process of identifying question type and domain for information searching of the system of Heo to provide a contingency plans and processes which retain the customers long enough to answer their question while not incurring excessive cost for the enterprises.
Neither Heo nor Walia specifically disclose determining that the vector distance between the vector representation the natural language request and the vector representation the description of the domain specific model exceeds a threshold value.
However, Alexander et al (US 2023/0401387 A1) in an analogous art further discloses,
determining that the vector distance between the vector representation the natural language request and the vector representation the description of the domain specific model exceeds a threshold value (para.[0047]; “compares 530 the
generated feature vector representing the input value against a set of stored feature vectors corresponding to values that were previously mapped to categories”).
Therefore, it would have been obvious to one of ordinary skill in the art before the invention was filed to incorporate vectorized storage of the system of Alexander into alternate option to process the query when QA domain for the query is not available of the system of Walia to provide an effective matching of users’ request, thereby responding with actions appropriate for the users' natural language expressions.
As per claim 4, the rejection of claim 1 is incorporated and further Heo et al (US 2012/0101807 A1) discloses,
wherein the instructions further cause the one or more computer processors to perform steps comprising: generating a prompt comprising: a description of each of the plurality of domain specific models, the natural language request, and a request to determine whether any of the plurality of domain specific models is capable of solving the domain specific problem specified in the natural language request (para.[0042]; “determines a question and answer engine for processing the user's question among various domain-specialized question and answer engines”).
sending the prompt to a large language model for execution (para.[0042]; “the question domain distributor 200 may include a language analyzer 201, a law-based domain distribution block 202, a law dictionary DB 203, a learning”).
receiving a response obtained by execution of the large language model and extracting from the response, an indication of whether any of the plurality of domain specific models is capable of solving the domain specific problem specified in the natural language request (para.[0043]; “the language analyzer 201 analyzes the language of the user's question and provides the analysis results to the law-based domain distribution block 202, and analyzes the language of the learning data established as representative questions of the respective domains and provides the analysis results to the leaning quality extraction block”).
As per claim 5, the rejection of claim 4 is incorporated and further Heo et al (US 2012/0101807 A1) discloses,
wherein the prompt further requests the large language model to select a domain specific model for solving the domain specific problem if any of the plurality of domain specific models is capable of solving the domain specific problem (para.[0052]; “law-based domain distribution block 202 serves to determine one of the respective domain question and answer engines of the question and answer engine block 300 in FIG. 1 as a question and answer domain”).
wherein the instructions further cause the one or more computer processors to perform steps comprising: extracting from the response, a domain specific model configured to solve the domain specific problem specified in the natural language request (para.[0053]; “when a user's question 'how many football referees?' is input, the user's question will be distributed to a sports domain question and answer engine based on the 'football' keyword”).
Claims 13 - 15 are method claim corresponding to computer-readable non-transitory memory claims 2 - 4 respectively, and rejected under the same reason set forth in connection to the rejection of claim 2 – 4 respectively above.
Conclusion
7. The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
TITLE: Chatbot system having multi domain and based operating the same,
K 2022-0126557 A author: Park Heung Soon (see pg.6 lines 29 – 33, pg.7 lines 11 – 14, pg.8 lines 25 – 41, pg.9 lines 28 – 49, and pg.10 lines 16 - 48).
TITLE: Method and system for providing domain-specific response to a user query, US 2019/0163785 A1 authors: Ramachandra Iyer (see para.[0082] – [00844]).
Any inquiry concerning this communication or earlier communications from the examiner should be directed to AUGUSTINE KUNLE OBISESAN whose telephone number is (571)272-2020. The examiner can normally be reached 9:00am - 5:00.
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, Ajay Bhatia can be reached at (571) 272-3906. 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.
/AUGUSTINE K. OBISESAN/
Primary Examiner
Art Unit 2156
8/30/2026
Prosecution Insights