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 .
This office action is in response to restriction/election response filed 05/28/26.
Claims 1-14, 19-20 are presented for examination.
Claims 1-15 are withdrawn from consideration as drawn towards non-elected group.
Restriction/Election
In response filed, applicant elected group 1 with claims 1-14, 19-20 for further examination, without traverse.
As such, claims 15-18 are withdrawn from consideration.
The restriction is made FINAL.
Information Disclosure Statement
The information disclosure statement (IDS) submitted on 06/30/2025 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 § 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)(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.
(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.
Claim(s) 8-14 is/are rejected under 35 U.S.C. 102(a)(1)/102(a)(2) as being anticipated by WANG et al. (US 2022/0027430 A1)
As per claim 8, WANG discloses a method for generative artificial intelligence of user interactions with a network site during a network session, the method being performed by one or more processors of a computer system (fig. 1) and comprising:
obtaining, from a capture agent on a user device, captured data for a set of captured user interactions with the network site during the network session, wherein the set of captured user interactions includes (1) movements between portions of the network site and (2) timestamps for one or more events during the network session (fig. 2 #s220-s240; [0024], [0029-0033], fig. 1);
generating, by a language model, a textual description of the network session using the captured data, the textual description summarizing the one or more events, the one or more events being linked to the timestamps corresponding to the one or more events (fig. 3 step #s260: generating session insights using any data analytics model);
providing a user interface for a client device to view a playback of a replay session of the network session (([0071], [0075-0076], fig. 6: item #650), the user interface displaying a first indicator corresponding to a first event (fig. 6: “insights pages such as login insights, search insights, checkout insights, etc.), and
responsive to a client interacting with the first indicator, providing, to the client device, the textual description corresponding to a timestamp that is associated with the first indicator and linked to the textual description (fig. 6: “Click on the pages with the highest opportunity score to discover the insights we found for you”. Note: session interaction data is time-ordered collection of a user’s interactions with multiple webpages of a website).
As per claim 9, WANG discloses the method of claim 8, wherein the set of captured user interactions further includes data provided in one or more fields on the network site ([0030-0033]).
As per claim 10, WANG discloses the method of claim 8, wherein the textual description includes an outcome indicating that a user intent with regard to the network session was not accomplished, and wherein the method further comprises:
identifying, by the language model, a most significant blocker that substantially contributed to the user intent not being accomplished ([0033-0037], fig. 6); and
providing, by the language model for the most significant blocker, information including an event name, an event value, and a blocker timestamp ([0033-0037], fig. 6: displays various metrics including rage clicks, multiple button interactions and its impact such as lost conversion and impact on goal).
As per claim 11, WANG discloses the method of claim 10, wherein the set of captured user interactions with the network site during the network session includes interactions between the network site and a plurality of user devices operated by a plurality of users, and the method further comprises, responsive to a client input via the user interface, providing, to the client device, information related to a set of user devices that encountered the most significant blocker among the plurality of user devices (fig. 6: various events and metrics are displayed including “Rage clicks”, “Multiple button Interactions”, etc. and their associated impacts, [0071]).
As per claim 12, WANG discloses the method of claim 11, wherein the information related to the set of user devices comprises information about a number of user devices included in the set of user devices (fig. 6, [0073]: stats, [0075]: impacted traffic counts, visits).
As per claim 13, WANG discloses the method of claim 12, wherein the information related to the set of user devices further comprises information about a change in the number of user devices over time ([0075]: traffic counts impacted, fig. 6).
As per claim 14, WANG discloses the method of claim 8, further comprising: overlaying the playback of the replay session with graphical representations corresponding to spans (WANG: fig. 6 item #650: Replays of 5 sessions which can be selected by the user is overlayed on top of original webpage. The sessions correspond to the date: April 29-May 5 2020 (7 days – All visitors)), wherein each of the spans corresponds to a logical grouping of events representing a topic during the network session (WANG: fig. 6: during the displayed span of Apr 29 – May 5 2020, metrics such as checkout: step 1, Home, Category, Product, etc. are displayed); and responsive to the client interacting with one of the graphical representations, displaying a textual description that describes the topic occurring in a time period for the span corresponding to the one of the graphical representations (WANG: fig. 6: “Click on the pages with the highest opportunity score to discover the insights”, [0071-0076]: page level score panel and insight overview panel. Pages can be selected to display further information corresponding to displayed metric)
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.
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.
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.
Claim(s) 1-7, 19-20 is/are rejected under 35 U.S.C. 103 as being unpatentable over WANG et al. (US 2022/0027430 A1) in view of Gardner et al. (US 12,008,332 B1).
As per claim 1, WANG discloses A method for generative artificial intelligence of user interactions with a network site during a network session, the method being performed by one or more processors of a computer system and comprising:
obtaining, from a capture agent on a user device (fig. 1, fig. 2, [0029-0030]: collecting user interaction data from the user devices), captured data for a set of captured user interactions with the network site during the network session, wherein the set of captured user interactions includes movements between portions of the network site (fig. 2 #s220-s240; [0024], [0029-0032]);
analyzing the captured data to identify a set of events (fig. 3 #s310, [0035]);
extracting event data corresponding to the set of events (fig. 3 #s330-s340; [0035]);
receiving a request for a textual description of the network session ([0072]);
receiving the textual description from the language model ([0036-0038]); and
providing the textual description to a computer associated with the network site ([0038], fig. 6, [0071]).
However, WANG does not teach generating a prompt for a language model, using the request and the event data and providing the prompt as an input to the language model.
Gardner, from the same field of endeavor (fig. 1), teaches generating a prompt for a language model, using the request and the event data (fig. 3 step 302-306, col. 8 L63 to col. 9 L9: automatically engineer a prompt for an LLM using content item and level of abstraction requested); providing the prompt as an input to the language model and receiving the textual description from the LLM (fig. 3 step 308-310, col. 12 L52 to col. 14 L30: provide the prompt to the LLM and receive a response from the LLM).
Therefore, it would have been obvious to a person of ordinary skilled in the art before the effective filing date of the claimed invention to modify WANG in view of Gardner in order to receive the textual description request, generate a prompt for LLM using the request and the event data, provide the prompt to the LLM and receive the textual description from the LLM to provide to the requesting computer.
One of ordinary skilled in the art would have been motivated in order to enable summarization of content using large language models in a controlled and configurable manner (Gardner: col. 1 L5-22).
As per claim 2, WANG-Gardner discloses the method of claim 1, wherein the set of captured user interactions further includes data provided in one or more fields on the network site (WANG: [0029-0032], fig. 2-3).
As per claim 3, WANG-Gardner discloses the method of claim 1, wherein the textual description includes an outcome indicating that a user intent with regard to the network session was not accomplished (WANG: [0040-0044], fig. 6: lost conversion metric), and wherein the method further comprises:
identifying, by the language model, a most significant blocker that substantially contributed to the user intent not being accomplished (WANG: [0033-0037], fig. 6); and
providing, by the language model for the most significant blocker, information including an event name, an event value, and a blocker timestamp (WANG: [0033-0037], fig. 6: displays various metrics including rage clicks, multiple button interactions and its impact such as lost conversion and impact on goal).
As per claim 4, WANG-Gardner discloses the method of claim 3, wherein the set of captured user interactions with the network site during the network session includes interactions between the network site and a plurality of user devices operated by a plurality of users (WANG: fig. 2, fig. 3, fig. 6]), and the method further comprises:
providing a user interface for a client device to view a playback of a replay session of the network session (WANG: [0071], [0075-0076], fig. 6: 650); and
responsive to a client input via the user interface, providing, to the client device, information related to a set of user devices that encountered the most significant blocker among the plurality of user devices (WANG: fig. 6: various events and metrics are displayed including “Rage clicks”, “Multiple button Interactions”, etc. and their associated impacts, [0071]).
As per claim 5, WANG-Gardner discloses the method of claim 4, wherein the information related to the set of user devices comprises information about a number of user devices included in the set of user devices (WANG: fig. 6, [0073]: stats, [0075]: impacted traffic counts, visits).
As per claim 6, WANG-Gardner discloses the method of claim 5, wherein the information related to the set of user devices further comprises information about a change in the number of user devices over time (WANG: [0075]: traffic counts impacted, fig. 6).
As per claim 7, WANG-Gardner discloses the method of claim 1, further comprising: storing the event data at a storage location accessible by the language model (WANG: [0027], [0033]).
As per claim 19, WANG discloses A method for generative artificial intelligence of user interactions with a network site during a set of network sessions, the method being performed by one or more processors of a computer system and comprising:
for each network session of the set of network sessions (fig. 6: 650: Session interaction data is collected for each of the displayed session):
obtaining, from a capture agent on a user device, captured data for a set of captured user interactions with the network site during the network session, wherein the set of captured user interactions includes movements between portions of the network site (fig. 2 #s220-s240; [0024], [0029-0032]), and
generating, by a language model, a session-specific textual description of the network session using the captured data, thereby generating a set of session-specific textual descriptions (fig. 3 step #s260: generating session insights using any data analytics model);
receiving a request for a combined textual description of the set of network sessions (fig. 6: item #650: Selecting all the sessions to replay and display generated insights);
receiving the combined textual description from the language model (([0036-0038], fig. 6); and
providing the combined textual description to a computer associated with the network site ([0038], fig. 6, [0071]).
However, WANG does not teach generating a prompt for a language model using the request, and providing the prompt and the session specific textual descriptions as inputs to the language model.
Gardner, from the same field of endeavor (fig. 1), teaches generating a prompt for a language model, using the request (fig. 3 step 302-306, col. 8 L63 to col. 9 L9: automatically engineer a prompt for an LLM using content item and level of abstraction requested); providing the prompt AND content items or data as an input to the language model and receiving the textual description from the LLM (fig. 3 step 308-310, col. 12 L52 to col. 14 L30: provide the prompt to the LLM and receive a response from the LLM, col. 3 L44-67, col. 6 L440-62).
Therefore, it would have been obvious to a person of ordinary skilled in the art before the effective filing date of the claimed invention to modify WANG in view of Gardner in order to receive a request for a combined textual description, generate a prompt for LLM using the request, provide the prompt and the session specific textual descriptions to the LLM and receive the combined textual description from the LLM to provide to the requesting computer.
One of ordinary skilled in the art would have been motivated in order to enable summarization of content using large language models in a controlled and configurable manner (Gardner: col. 1 L5-22).
As per claim 20, WANG-Gardner discloses the method of claim 19, wherein the language model is a transformer (Gardner: fig. 1: LLM 111, col. 6 L13 to col. 7 L6, col. 14 L31-44).
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Mishra et al., US 2016/0292170 A1: Determining content sessions using content-consumption events.
Crossley et al., US 2018/0063265: Machine Learning Techniques for Processing Tag-based representation of sequential interactions events
Ardham et al., US 2025/0138992 A1: Error Reproduction in Web-based applications.
Hoffman, US 12,124,324 B1: Identifying resource access faults based on webpage assessment.
Saleh et al., US 11,714,997 B2: Analyzing sequences of interactions using a neural network with attention mechanism
Any inquiry concerning this communication or earlier communications from the examiner should be directed to KAMAL B DIVECHA whose telephone number is (571)272-5863. The examiner can normally be reached IFP Normal Hours M-F: 8am-4.30pm EST.
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, COLLEEN FAUZ can be reached at 5712721667. 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.
KAMAL B. DIVECHA
Primary Patent Examiner
Art Unit 2453
/KAMAL B DIVECHA/Supervisory Patent Examiner, Art Unit 2453
Prosecution Insights