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 . Claims 1-21 have been submitted for examination.
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 1-14 and 16-21 are rejected under 35 U.S.C. 103(a) as being unpatentable over Lewis et al (hereinafter Lewis) US Patent No 11477142 in view of Ozcan et al (hereinafter Ozcan) US Publication No 20220414741.
As per claim 1, Lewis teaches:
conversational recommender system implemented by one or more processors of a computer system, the conversational recommender system comprising:
a dialogue manager module having a trained large language model, the dialogue manager being configured to:
receive user input via a client device during an interactive conversation;
(Abstract and column 2, lines 5-37 and column 7, lines 20-26 and column 10, lines 3-38 and column 14, lines 34-67)
predict a dialogue state from the received user input according to the trained large language model;
(Abstract and column 2, lines 5-37 and column 7, lines 20-26 and column 10, lines 3-38 and column 14, lines 34-67)
and generate a response to the received user input based on the predicted dialogue state;
(Abstract and column 2, lines 5-37 and column 7, lines 20-26 and column 10, lines 3-38 and column 14, lines 34-67)
and a recommendation engine in operative communication with the dialogue manager, the recommendation engine being configured to:
receive a query from the dialogue manager according to the predicted dialogue state;
(Abstract and column 2, lines 5-37 and column 7, lines 20-26 and column 10, lines 3-38 and column 14, lines 34-67)
identify a set of relevant items from a candidate corpus;
(Abstract and column 2, lines 5-37 and column 7, lines 20-26 and column 10, lines 3-38 and column 14, lines 34-67)
and generate a recommendation slate comprising one or more of the relevant items from the set;
(Abstract and column 2, lines 5-37 and column 7, lines 20-26 and column 10, lines 3-38 and column 14, lines 34-67)
Lewis does not explicitly teach wherein the dialogue manager is further configured to present the recommendation slate and an explanation about the recommendation slate to a user of the client device along with the response to the received user input, however in an analogous content management, Ozcan teaches:
wherein the dialogue manager is further configured to present the recommendation slate and an explanation about the recommendation slate to a user of the client device along with the response to the received user input.
(Abstract and paragraphs [0156] and [0173])
Therefore, it would have been obvious to a person in the ordinary skill in the art at the time of the filling of the invention to combine Lewis and Ozcan by incorporating the teaching of Ozcan into the method of Lewis. One having ordinary skill in the art would have found it motivated to use the content management of Ozcan into the system of Lewis for the purpose of managing recommendation and providing to a user description why the recommendation was made.
As per claim 2, Lewis and Ozcan teach:
The conversational recommender system of claim 1, wherein the dialogue manager module is configured to predict the dialogue state based on the received user input and stored profile information associated with the user.
(Paragraphs [0009]-[0010], [0017], [0045] and [0137])(Ozcan)
As per claim 3, Lewis and Ozcan teach:
The conversational recommender system of claim 2, wherein the stored profile information is updatable by the conversational recommender system according to information provided by the user during the interactive conversation.
(Paragraphs [0137] and [0178] and [0189])(Ozcan)
As per claim 4, Lewis and Ozcan teach:
The conversational recommender system of claim 3, wherein the stored profile information is editable by the user.
(Paragraphs [0137] and [0178] and [0189])(Ozcan)
As per claim 5, Lewis and Ozcan teach:
The conversational recommender system of claim 1, wherein the dialogue manager module is configured to either predict the dialogue state or generate the response according to generation of a sequence of natural language outputs that encapsulate all context tracking and any intermediate reasoning during the interactive conversation.
(Column 1, lines 26-50 and column 21, lines 19-30)(Lewis)
As per claim 6, Lewis and Ozcan teach:
The conversational recommender system of claim 1, wherein the large language model is an encoder-based model configured to generate the response.
(Column 1, lines 26-50 and column 21, lines 19-30)(Lewis)
As per claim 7, Lewis and Ozcan teach:
The conversational recommender system of claim 6, wherein the encoder-based model includes a first encoder configured to process a target response for the interactive conversation and a second encoder configured to process a dialogue context for the interactive conversation.
(Column 17, lines 13-32 and column 19, lines 38-52 and column 20, lines 56-63)(Lewis)
As per claim 8, Lewis and Ozcan teach:
The conversational recommender system of claim 7, wherein the encoder-based model is further configured to process at least one of intent or sentiment in order to generate the response.
(Abstract and column 2, lines 5-37 and column 7, lines 20-26 and column 10, lines 3-38 and column 14, lines 34-67)(Lewis)
As per claim 9, Lewis and Ozcan teach:
The conversational recommender system of claim 1, wherein based on the predicted dialogue state, the generated response includes a clarifying question that is not presented with the recommendation slate.
(Abstract and column 21, lines 31-42)(Lewis)
As per claim 10, Lewis and Ozcan teach:
The conversational recommender system of claim 1, wherein based on the predicted dialogue state, the generated response is selected to steer the interactive conversation back to a prior topic.
(Paragraph [0176])(Ozcan)
As per claim 11, Lewis and Ozcan teach:
The conversational recommender system of claim 10, wherein the dialogue manager module includes a policy guardrail defining a maximum number of turns permitted during the interactive conversation before steering the interactive conversation back to the prior topic.
(Paragraphs [0015], [0041], [0067], [0153]-[0154])(Ozcan)
As per claim 12, Lewis and Ozcan teach:
The conversational recommender system of claim 1, further comprising a summary model configured to generate the explanation about the recommendation and to provide the explanation to the dialogue manager module.
(Abstract and paragraphs [0003], [0017], [0120], [0133], [0156] and [0173])
As per claim 13, Lewis and Ozcan teach:
The conversational recommender system of claim 1, wherein the recommendation engine includes a ranking module configured to generate the explanation according to item metadata associated with items of the candidate corpus.
(Abstract and paragraphs [0156] and [0173])(Ozcan)
As per claim 14, Lewis and Ozcan teach:
The conversational recommender system of claim 1, wherein the dialogue manager module is configured to predict the dialogue state by evaluation of a user utterance according to stored user information.
(Column 4, lines 62-67and column 5, lines 1-12)(Lewis)
Claims 16-21 are method claims respectively corresponding to system claims 1-2, 5, 7, 9 and 14 and they are rejected under the same rational as claims 1-2, 5, 7, 9 and 14
Claim 15 is rejected under 35 U.S.C. 103(a) as being unpatentable over Lewis and Ozcan in view of Earle et al (hereinafter Earle) US Publication No 20240111960.
As per claim 15, Lewis and Ozcan do explicitly teach evaluation of the user utterance is done according to the large language model based on in-context few-shot learning, however in an analogous art of data processing, Earle teaches:
evaluation of the user utterance is done according to the large language model based on in-context few-shot learning.
(Paragraphs [0041], [0065]-[0069] and [0111])
Therefore, it would have been obvious to a person in the ordinary skill in the art at the time of the filling of the invention to combine Lewis and Ozcan and Earle by incorporating the teaching of Earle into the method of Lewis and Ozcan. One having ordinary skill in the art would have found it motivated to use the content management of Earle into the system of Lewis and Ozcan for the purpose of managing data processing and improving accuracy/performance of the data generation.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Tarek Chbouki whose telephone number is 571-2703154. The examiner can normally be reached on Mon-Fri 9:00 am to 6:00 pm EST. If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Aleksandr Kerzhner can be reached at 571-2701760. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of an application may be obtained from the Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from either Private PAIR or Public PAIR. Status information for unpublished applications is available through Private PAIR only. For more information about the PAIR system, see http://pair-direct.uspto.gov. Should you have questions on access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative or access to the automated information system, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/TAREK CHBOUKI/ Primary Examiner, Art Unit 2165 7/8/2026
Prosecution Insights