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 amendment filed on 12/3/2025, in which claims 9 – 10 was canceled, claims 21 – 22 was added, and claims 1 – 8 and 11 - 22 was presented for examination.
3. Claims 1 – 8 and 11 - 22 are now pending in the application.
Response to Arguments
4. Applicant's arguments filed on 12/3/2025 have been fully considered but they are not persuasive.(see Remarks below).
Remarks
5.1 As per rejection of claim 1 – 8 and 11 – 20 under 35 USC 101, applicants’ argues in substance in pages 10 – 14 that the claims are statutory under 35 USC 101.
Examiner respectfully disagrees.
In response to applicant’s argument, Examiner respectfully responds that 35 USC 101 Abstract idea rejection follow the 2019 Revised Patent Subject Matter Eligibility Guidance (2019 PEG) and all features of the claimed limitation has been carefully considered.
With respect to applicant argument that the “Claims Are Directed to an Improved User Query Response System with a First Language Model that Outputs Metadata of UI Elements of Web Pages and a Second Language Model that
Augments Input Sequences with the Metadata of UI Elements”. This process can be achieved by human mind. A human can create a query to collect different information representations. Applying different models (i.e. mathematical algorithm) to improve the execution of the query does not provide an improvement. A human can state how different stages of execution at which specific mathematical algorithm can be added to a query in order to generate a response. Using the computer to automatically implement this step does not exclude the claim from the abstract idea.
With respect to applicant argument that the claims are directed to “an improvement in user navigation of a web application with a combination of language models that obtain metadata of UI elements for web pages of the web application and then use the metadata of UI element to augment user query responses”. This process is an abstract idea because it is not different from human identifying and annotating documents, adding the annotated information to query construction, and using the constructed query to selected similar or identical data.
Thus, the rejection is maintained.
5.2 As per applicant argument that Berk et al (US 2017/0109442 A1), Warren et al (US 2015/0278902 A1), and Deutsch et al (US 2025/0139057 A1), alone, in combination does not disclose “based on receiving a query from a user for content of the web application, augmenting a second input sequence to a second language model with a subset of the metadata of UI elements relevant to the query from the user, wherein the second input sequence comprises the subset of the metadata of UI elements and task instructions to the second language model to respond to the user”.
Examiner respectfully disagrees.
In response to applicant’s argument, Examiner respectfully responds that the combine teaching of Berk et al (US 2017/0109442 A1), Warren et al (US 2015/0278902 A1), and Deutsch et al (US 2025/0139057 A1) disclose each and every features of claim 1 including the features of “based on receiving a query from a user for content of the web application, augmenting a second input sequence to a second language model with a subset of the metadata of UI elements relevant to the query from the user, wherein the second input sequence comprises the subset of the metadata of UI elements and task instructions to the second language model to respond to the user”.
Berk discloses storing of tags or metadata that defines the content, layout, or style and features affinity that correlates the websites (see para.[0002] and para.[0042]). A data extraction module crawl the website and extract one or more features of the website and generate a data record that defines content, style, or layout of the website (see para.[0043]).
Warren discloses receiving a query from user interface, compare the query to the rule store in the knowledge database, and modify or rewrite the query with the matching rule (see para.[0008]). The product services intercept the query, extract the query phrase or term, search knowledge database for matching term, augment the query with the matching term, and execute the query against database to receive the relevant information (para.[0019]).
Deutsch discloses generation of metadata from content using one or more machine learning models such as a large language model (see para.[0004]). A user input prompt is received on the system, a metadata is generated by determining the main topic or key point of the input file. The input file being analyzed may include plain text, rich text, Hypertext Markup Language (HTML), markdown, XML etc.
Since Deutsch generate metadata from different documents structure, it can be inferred from this disclosure to integrate one or more language models of the system of Deutsch to crawl and extract websites metadata in the system of Berk and augment the query with generated metadata.
5.3 Thus, the rejection is maintained.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
6 Claims 1 – 8 and 11 - 22 are directed are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
As per claim 1,
Step 1: Claim 1 recites a method, which is one of the four statutory categories of eligible matter.
Step 2A Prong 1: The claim recites the limitation of
crawling first uniform resource locators (URLs) for one or more web pages of a web application to retrieve at least one of display data and content data for the one or more web pages (Mental Process performed in human mind using a pen and paper (i.e. observation and data gathering)).
prompting a first language model with a first input sequence to obtain metadata of user interface (UI) elements for the one or more web pages as output (Mental Process performed in human mind using a pen and paper (i.e. data gathering)).
wherein the first input sequence indicates at least one of the display data and the content data (Mental Process performed in human mind using a pen and paper (i.e. observation)).
storing the metadata of UI elements indexed by metadata parameters indicated in the metadata of UI elements (Mental Process performed in human mind using a pen and paper (i.e. judgmental)).
and based on receiving a query from a user for content of the web application, augmenting a second input sequence to a second language model with a subset of the metadata of UI elements relevant to the query from the user ((Mental Process performed in human mind using a pen and paper (i.e. evaluation)).
wherein the second input sequence comprises the subset of the metadata of UI elements and task instructions to the second language model to respond to the user (Mental Process performed in human mind using a pen and paper (i.e. evaluation)).
Step 2A Prong 2: The judicial exceptions are not integrated into a practical application. The claim recites the additional elements of
crawling first uniform resource locators (URLs) for one or more web pages of a web application to retrieve at least one of display data and content data for the one or more web pages (the step is directed to obtaining information, which is understood to be significant extra-solution activity, see MPEP 2106.05(g))
storing the metadata of UI elements indexed by metadata parameters indicated in the metadata of UI elements (the step is directed to evaluating information, which is understood to be significant extra-solution activity, and is well understood, routine, and conventional activity of keeping data for presentation (MPEP 2106.05(d)(II)(i))))).
Although the additional element limits the identified judicial exceptions. The limitation merely confines the use of the abstract idea to a particular technological environment and thus fails to add an inventive concept to the claims. See MPEP 2106.05(h).
Even when viewed in combination, these additional elements do not integrate the recited judicial exception into a practical application and the claim is directed to the judicial exception.
Step 2B: The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception.
Additional element
crawling first uniform resource locators (URLs) for one or more web pages of a web application to retrieve at least one of display data and content data for the one or more web pages (the step is directed to gathering information, which is understood to be significant extra-solution activity, see MPEP 2106.05(g)).
storing the metadata of UI elements indexed by metadata parameters indicated in the metadata of UI elements (this step is directed to organizing information, which is understood to be significant extra-solution activity and is well understood, routine, and conventional activity of keeping data for presentation (MPEP 2106.05(d)(II)(i))))).
As explained above, the additional element are recited at a high level of generality. These elements amount to collecting, evaluating, and presenting information are well-understood, routine, conventional activity. See MPEP 2106.05(d), subsection II. The recitation of a computer to perform these limitations amounts to no more than mere instructions to apply the exception using a generic computer. Even when considered in combination, these additional elements represent mere instructions to implement an abstract idea or other exception on a computer and insignificant extra-solution activity, which do not provide an inventive concept.
Thus, the claim is ineligible.
As per claim 2, the rejection of claim 1 is incorporated.
Step 1: The claim recite a method, which is one of the four statutory categories of eligible matter.
Step 2A Prong 1: The judicial exceptions of claim 1 are incorporated, the limitation wherein the task instructions to the second language model comprise task instructions to identify second URLs that navigate to information responsive to the query from the user (Mental Process performed in human mind using a pen and a paper (i.e. evaluation)).
Step 2A Prong 2: the judicial exceptions are not integrated into a practical application. The claim recites additional elements of
wherein the task instructions to the second language model comprise task instructions to identify second URLs that navigate to information responsive to the query from the user (the step is directed to evaluating information, which is understood to be significant extra-solution activity, see MPEP 2106.05(g)).
The limitation recited at high level of generality and thus are insignificant extra-solution activity. Even when viewed in combination, these additional elements do not integrate the recited judicial exception into a practical application.
Step 2B: The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exceptions. Mere instructions to implement an abstract idea or other exception on a computer and insignificant extra-solution activity, which do not provide an inventive concept.
The claim is not patent eligible.
As per claim 3, the rejection of claim 1 is incorporated.
Step 1: The claim recite a method, which is one of the four statutory categories of eligible matter.
Step 2A Prong 1: The judicial exceptions of claim 1 are incorporated, the limitation wherein the task instructions to the second language model further comprise task instructions to add and populate filters to one or more of the first URLs to obtain the second URLs, wherein the task instructions for populating filters comprise task instructions for populating the filters with values in the query from the user. (Mental Process performed in human mind using a pen and a paper (i.e. evaluation)).
Step 2A Prong 2: the judicial exceptions are not integrated into a practical application. The claim recites additional elements of
wherein the task instructions to the second language model further comprise task instructions to add and populate filters to one or more of the first URLs to obtain the second URLs, wherein the task instructions for populating filters comprise task instructions for populating the filters with values in the query from the user. (the step is directed to evaluating information, which is understood to be significant extra-solution activity, see MPEP 2106.05(g)).
The limitation recited at high level of generality and thus are insignificant extra-solution activity. Even when viewed in combination, these additional elements do not integrate the recited judicial exception into a practical application.
Step 2B: The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exceptions. Mere instructions to implement an abstract idea or other exception on a computer and insignificant extra-solution activity, which do not provide an inventive concept.
The claim is not patent eligible.
As per claim 4, the rejection of claim 1 is incorporated.
Step 1: The claim recite a method, which is one of the four statutory categories of eligible matter.
Step 2A Prong 1: The judicial exceptions of claim 1 are incorporated, the limitation identifying the subset of the metadata of UI elements relevant to the query from the user, wherein identifying the subset of the metadata of UI elements (Mental Process performed in human mind using a pen and a paper (i.e. evaluation)).
comprises, identifying first metadata from the stored metadata of UI elements based on matching metadata parameters indexed in storage with parameters indicated in the query from the user (Mental Process performed in human mind using a pen and a paper (i.e. evaluation)).
and identifying the subset of the metadata of UI elements based on semantic similarity between the first metadata and the query from the user (Mental Process performed in human mind using a pen and a paper (i.e. evaluation)).
Step 2A Prong 2: the judicial exceptions are not integrated into a practical application. The claim recites additional elements of
identifying the subset of the metadata of UI elements relevant to the query from the user, wherein identifying the subset of the metadata of UI elements (the step is directed to evaluating information, which is understood to be significant extra-solution activity, see MPEP 2106.05(g)).
comprises, identifying first metadata from the stored metadata of UI elements based on matching metadata parameters indexed in storage with parameters indicated in the query from the user (the step is directed to evaluating information, which is understood to be significant extra-solution activity, see MPEP 2106.05(g)).
and identifying the subset of the metadata of UI elements based on semantic similarity between the first metadata and the query from the user (the step is directed to evaluating information, which is understood to be significant extra-solution activity, see MPEP 2106.05(g)).
The limitation recited at high level of generality and thus are insignificant extra-solution activity. Even when viewed in combination, these additional elements do not integrate the recited judicial exception into a practical application.
Step 2B: The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exceptions. Mere instructions to implement an abstract idea or other exception on a computer and insignificant extra-solution activity, which do not provide an inventive concept.
The claim is not patent eligible.
As per claim 5, the rejection of claim 1 is incorporated.
Step 1: The claim recite a method, which is one of the four statutory categories of eligible matter.
Step 2A Prong 1: The judicial exceptions of claim 1 are incorporated, the limitation wherein identifying the subset of the metadata of UI elements similar to the query from the user is further based on similarity of characteristics of the user and characteristics of behavior of the user for the web application and the stored metadata of UI elements (Mental Process performed in human mind using a pen and a paper (i.e. evaluation)).
Step 2A Prong 2: the judicial exceptions are not integrated into a practical application. The claim recites additional elements of
wherein identifying the subset of the metadata of UI elements similar to the query from the user is further based on similarity of characteristics of the user and characteristics of behavior of the user for the web application and the stored metadata of UI elements (the step is directed to evaluating information, which is understood to be significant extra-solution activity, see MPEP 2106.05(g)).
The limitation recited at high level of generality and thus are insignificant extra-solution activity. Even when viewed in combination, these additional elements do not integrate the recited judicial exception into a practical application.
Step 2B: The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exceptions. Mere instructions to implement an abstract idea or other exception on a computer and insignificant extra-solution activity, which do not provide an inventive concept.
The claim is not patent eligible.
As per claim 6, the rejection of claim 1 is incorporated.
Step 1: The claim recite a method, which is one of the four statutory categories of eligible matter.
Step 2A Prong 1: The judicial exceptions of claim 1 are incorporated, the limitation prompting the second language model with the second input sequence to obtain a response as output; and presenting the response to the user (Mental Process performed in human mind using a pen and a paper (i.e. data gathering and presentation)).
Step 2A Prong 2: the judicial exceptions are not integrated into a practical application. The claim recites additional elements of
prompting the second language model with the second input sequence to obtain a response as output; and presenting the response to the user (this step is directed to organizing information, which is understood to be significant extra-solution activity and is well understood, routine, and conventional activity of preparing data for presentation (MPEP 2106.05(d)(II)(i))))).
The limitation recited at high level of generality and thus are insignificant extra-solution activity. Even when viewed in combination, these additional elements do not integrate the recited judicial exception into a practical application.
Step 2B: The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exceptions. Mere instructions to implement an abstract idea or other exception on a computer and insignificant extra-solution activity, which do not provide an inventive concept.
The claim is not patent eligible.
As per claim 7, the rejection of claim 1 is incorporated.
Step 1: The claim recite a method, which is one of the four statutory categories of eligible matter.
Step 2A Prong 1: The judicial exceptions of claim 1 are incorporated, the limitation wherein the metadata of UI elements comprise at least one of web page names, web page titles, web page types, URLs, web page navigation task instructions, web page filters, and at least one of UI element descriptions and UI element content. (Mental Process performed in human mind using a pen and a paper (i.e. observation)).
Step 2A Prong 2: the judicial exceptions are not integrated into a practical application. The claim recites additional elements of
wherein the metadata of UI elements comprise at least one of web page names, web page titles, web page types, URLs, web page navigation task instructions, web page filters, and at least one of UI element descriptions and UI element content (this step is directed to observing information, which is understood to be significant extra-solution activity and is well understood, routine, and conventional activity of preparing data for processing (MPEP 2106.05(d)(II)(i))))).
The limitation recited at high level of generality and thus are insignificant extra-solution activity. Even when viewed in combination, these additional elements do not integrate the recited judicial exception into a practical application.
Step 2B: The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exceptions. Mere instructions to implement an abstract idea or other exception on a computer and insignificant extra-solution activity, which do not provide an inventive concept.
The claim is not patent eligible.
As per claim 8, the rejection of claim 1 is incorporated.
Step 1: The claim recite a method, which is one of the four statutory categories of eligible matter.
Step 2A Prong 1: The judicial exceptions of claim 1 are incorporated, the limitation wherein the content data comprises Hypertext Markup Language (HTML) documents for the one or more web pages, and wherein the display data comprises screenshots of web browser renderings for the one or more web pages (Mental Process performed in human mind using a pen and a paper (i.e. judgmental)).
Step 2A Prong 2: the judicial exceptions are not integrated into a practical application. The claim recites additional elements of
wherein the content data comprises Hypertext Markup Language (HTML) documents for the one or more web pages, and wherein the display data comprises screenshots of web browser renderings for the one or more web pages (this step is directed to observing information, which is understood to be significant extra-solution activity and is well understood, routine, and conventional activity of preparing data for presentation (MPEP 2106.05(d)(II)(i))))).
The limitation recited at high level of generality and thus are insignificant extra-solution activity. Even when viewed in combination, these additional elements do not integrate the recited judicial exception into a practical application.
Step 2B: The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exceptions. Mere instructions to implement an abstract idea or other exception on a computer and insignificant extra-solution activity, which do not provide an inventive concept.
The claim is not patent eligible.
Claims 11 – 14 and 15 recite a non-transitory machine-readable medium, which is one of the four statutory categories of eligible matter. As per other analysis, claims 11 – 14 and 15 are non-transitory machine-readable medium claim correspond to method claims 1 — 4 and 6 respectively, thus the rationale discussed above regarding claims 1 — 4 and 6 are applied to claims 11 – 14 and 15 respectively.
Claims 16 – 19 and 20 recites an apparatus, which is one of the four statutory categories of eligible matter. As per other analysis, claims 16 – 19 and 20 are apparatus claim correspond to method claims 1 – 4 and 6 respectively, thus, the rationale discussed above regarding claims 1 – 4 and 6 is applied to claims 16 – 19 and 20 respectively.
As per claim 21, the rejection of claim 1 is incorporated.
Step 1: The claim recite a method, which is one of the four statutory categories of eligible matter.
Step 2A Prong 1: The judicial exceptions of claim 1 are incorporated, the limitation of wherein the subset of the metadata of UI elements relevant to the query of the user comprise metadata of UI elements relevant to a first user persona of a plurality of user personas that corresponds to the user(Mental Process performed in human mind using a pen and a paper (i.e. data gathering)).
wherein prompting the first language model with the first input sequence comprises, for each second user persona of the plurality of user personas (Mental Process performed in human mind using a pen and a paper (i.e. observation)).
prompting the first language model with the first input sequence and task instructions to extract metadata of UI elements from the one or more web pages that are relevant to the second user persona (Mental Process performed in human mind using a pen and a paper (i.e. data gathering)).
Step 2A Prong 2: the judicial exceptions are not integrated into a practical application. The claim recites additional elements of
metadata of UI elements relevant to a first user persona of a plurality of user personas that corresponds to the user (the step is directed to observing information, which is understood to be significant extra-solution activity, see MPEP 2106.05(g))
wherein prompting the first language model with the first input sequence comprises, for each second user persona of the plurality of user personas (the step is directed to evaluating information, which is understood to be significant extra-solution activity, see MPEP 2106.05(g))
prompting the first language model with the first input sequence and task instructions to extract metadata of UI elements from the one or more web pages that are relevant to the second user persona (the step is directed to obtaining information, which is understood to be significant extra-solution activity, see MPEP 2106.05(g)).
The limitation recited at high level of generality and thus are insignificant extra-solution activity. Even when viewed in combination, these additional elements do not integrate the recited judicial exception into a practical application.
Step 2B: The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exceptions. Mere instructions to implement an abstract idea or other exception on a computer and insignificant extra-solution activity, which do not provide an inventive concept.
The claim is not patent eligible.
As per claim 22, the rejection of claim 1 is incorporated.
Step 1: The claim recite a method, which is one of the four statutory categories of eligible matter.
Step 2A Prong 1: The judicial exceptions of claim 1 are incorporated, the limitation wherein the second input sequence further comprises behavioral data of the user (Mental Process performed in human mind using a pen and a paper (i.e. observation)).
Step 2A Prong 2: the judicial exceptions are not integrated into a practical application. The claim recites additional elements of
wherein the second input sequence further comprises behavioral data of the user (this step is directed to observing information, which is understood to be significant extra-solution activity see MPEP 2106.05(g)).
The limitation recited at high level of generality and thus are insignificant extra-solution activity. Even when viewed in combination, these additional elements do not integrate the recited judicial exception into a practical application.
Step 2B: The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exceptions. Mere instructions to implement an abstract idea or other exception on a computer and insignificant extra-solution activity, which do not provide an inventive concept.
The claim is not patent eligible.
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.
7. Claims 1 – 8 and 11 - 22 are rejected under 35 U.S.C. 103 as being unpatentable over Berk et al (US 2017/0109442 A1), in view of Warren et al (US 2015/0278902 A1), and further in view of Deutsch et al (US 2025/0139057 A1).
As per claim 1, Berk et al (US 2017/0109442 A1) discloses,
A method comprising: crawling first uniform resource locators (URLs) for one or more web pages of a web application to retrieve at least one of display data and content data for the one or more web pages (para.[0043]; “One or more data extraction software modules 215 may extract website feature data from one or more crawled websites. This data extraction software 215 may perform an internet crawl, and for each crawled website, the data extraction software 215 may identify the industry associated with the website and extract the website feature data defining the website's content, layout and style”).
prompting a first language model with a first input sequence to obtain metadata of user interface (UI) elements for the one or more web pages as output (para.[0043]; “generate individual data records from the extracted content, each data record defining, within a meta data and/or tag stored within one or more data fields, various characteristics of the content, layout or style of the crawled website”).
wherein the first input sequence indicates at least one of the display data and the content data (para.[0043]; “a meta data and/or tag stored within one or more data fields, various characteristics of the content, layout or style of the crawled website”).
storing the metadata of UI elements indexed by metadata parameters indicated in the metadata of UI elements (para.[0043]; “data records may then each be stored in the website features repository”).
Berk does not specifically disclose based on receiving a query from a user for content of the web application, augmenting a second input sequence to a second language model with a subset of the metadata of UI elements relevant to the query from the user, wherein the second input sequence comprises the subset of the metadata of UI elements and task instructions to the second language model to respond to the user.
However, Warren et al (US 2015/0278902 A1) in an analogous art discloses,
and based on receiving a query from a user for content of the web application (para.[0008]; “receive the query from the user over a communications network, the query including a query term”).
augmenting a second input sequence to a second language model with a subset of the metadata of UI elements relevant to the query from the user (para.[0008]; “set of stored rules based on at least one of content or format of the product information
contained in a product index associated with a search engine, augment the query term using the matching rule to generate an augmented query containing an augmented query term based on the query term”).
wherein the second input sequence comprises the subset of the metadata of UI elements and task instructions to the second language model to respond to the user (para.[0008]; “send the augmented query to the search engine for searching against the product index, receive a query result from the search engine containing the product information in response to the augmented query”).
Therefore, it would have been obvious to one of ordinary skill in the art before the invention was filed to incorporate augmented query process of the system of Warren into website crawler process of the system of Berk to improve the quality of information retrieved from the system.
Neither Berk nor Warren specifically disclose “first language model …….. second language model”.
However, Deutsch et al (US 2025/0139057 A1) in an analogous art discloses,
first language model …….. second language model (para.[0004]; “generating, using the large language model, metadata from at least the first file, the metadata reflecting a context associated with the content” and para.[0030]; “machine learning models, such as large language models, image generation models, or multimodal models, may be used to understand a context of content, such as textual content”).
Therefore, it would have been obvious to one of ordinary skill in the art before the invention was filed to incorporate machine learning process of the system of Deutsch into augmented query process of the system of Warren to generate metadata from content or website, thereby enabling the user to access similar information.
As per claim 2, the rejection of claim 1 is incorporated and further Warren et al (US 2015/0278902 A1) discloses,
wherein the task instructions to the second language model comprise task instructions to identify second URLs that navigate to information responsive to the query from the user (para.[0054]; “the response query 20. For example, available Navigation as an array of objects (com.gbi.gsa.model.Navigation) representing refinements that can be made by the product service 14 using rules 25,26 to further drill-down on the current set of returned records”).
Therefore, it would have been obvious to one of ordinary skill in the art before the invention was filed to incorporate augmented query process of the system of Warren into website crawler process of the system of Berk to improve the quality of information retrieved from the system.
As per claim 3, the rejection of claim 2 is incorporated and further Warren et al (US 2015/0278902 A1) discloses,
wherein the task instructions to the second language model further comprise task instructions to add and populate filters to one or more of the first URLs to obtain the second URLs, wherein the task instructions for populating filters comprise task instructions for populating the filters with values in the query from the user (para.[0054]; “submit navigation queries 18 based on the content received in the response query 20. For example, available Navigation as an array of objects (com.gbi.gsa.model.Navigation) representing refinements that can be made by the product service 14 using rules 25,26 to further drill-down on the current set of returned records”).
Therefore, it would have been obvious to one of ordinary skill in the art before the invention was filed to incorporate augmented query process of the system of Warren into website crawler process of the system of Berk to improve the quality of information retrieved from the system.
As per claim 4, the rejection of claim 1 is incorporated and further Berk et al (US 2017/0109442 A1) discloses,
further comprising identifying the subset of the metadata of UI elements relevant to the query from the user (para.[0049]; “query the website features repository 200 for all data records associated with the user's identified industry” and para.[0092]; “query the database to retrieve all data records associated with the user's identified industry and the layout”).
wherein identifying the subset of the metadata of UI elements comprises, identifying first metadata from the stored metadata of UI elements based on matching metadata parameters indexed in storage with parameters indicated in the query from the user (para.[0049]; “query the website features repository 200 for all data records associated with the user's identified industry ……. identify, within each of these data records, the category associated with the data records (e.g., a content, layout or style website feature), analyze the metadata/tags defining the content, layout or style feature, and determine the most frequently occurring website features, based on these tags”).
and identifying the subset of the metadata of UI elements based on semantic similarity between the first metadata and the query from the user (para.[0049]; “identify, within each of these data records, the category associated with the data records (e.g., a content, layout or style website feature), analyze the metadata/tags defining the content, layout or style feature, and determine the most frequently occurring website features, based on these tags”).
As per claim 5, the rejection of claim 4 is incorporated and further Berk et al (US 2017/0109442 A1) discloses,
wherein identifying the subset of the metadata of UI elements similar to the query from the user is further based on similarity of characteristics of the user and characteristics of behavior of the user for the web application and the stored metadata of UI elements (para.[0049]; “identify, within each of these data records, the category associated with the data records (e.g., a content, layout or style website feature), analyze the metadata/tags defining the content, layout or style feature, and determine the most frequently occurring website features, based on these tags” and para.[0050]; “user profile elements from the user profile repository ( e.g., similarities to the content, layout and style of other websites operated by the user)”).
As per claim 6, the rejection of claim 1 is incorporated and further Warren et al (US 2015/0278902 A1) discloses,
further comprising, prompting the second language model with the second input sequence to obtain a response as output and presenting the response to the user (para.[0080]; “searching of the product information 22 in the product index rather than to the external content unrelated to the product index ……. and sending 420 the product information 22 over the communications network 16 to the user for subsequent presentation on the user interface of the user”).
Therefore, it would have been obvious to one of ordinary skill in the art before the invention was filed to incorporate augmented query process of the system of Warren into website crawler process of the system of Berk to improve the quality of information retrieved from the system.
As per claim 7, the rejection of claim 1 is incorporated and further Berk et al (US 2017/0109442 A1) discloses,
wherein the metadata of UI elements comprise at least one of web page names, web page titles, web page types, URLs, web page navigation task instructions, web page filters, and at least one of UI element descriptions and UI element content (para.[0020]; “content, such as images, descriptive text, web page titles and internal organizational links between web pages, and element layout choices”, para.[0042]; “one or more metadata elements or tags defining or describing the website feature”, and para.[0049]; “metadata/tags defining the content, layout or style feature”).
As per claim 8, the rejection of claim 1 is incorporated and further Berk et al (US 2017/0109442 A1) discloses,
wherein the content data comprises HyperText Markup Language (HTML) documents for the one or more web pages, and wherein the display data comprises screenshots of web browser renderings for the one or more web pages (para.[0018]; “HTML uses text indicators called tags to provide interpretation instructions to the browser. The tags specify the composition of design elements such as text, images, shapes, hyperlinks to other web pages”).
Claims 11 – 14 and 15 are non-transitory machine-readable medium claim corresponding to method claims 1 – 4 and 6 respectively, and rejected under the same reason set forth in connection to the rejection of claims 1 – 4 and 6 respectively above.
Claims 16 – 19 and 20 are apparatus claim corresponding to method claims 1 – 4 and 6 respectively, and rejected under the same reason set forth in connection to the rejection of claims 1 – 4 and 6 respectively above.
As per claim 21, the rejection of claim 1 is incorporated and further Berk et al (US 2017/0109442 A1) discloses,
wherein the subset of the metadata of UI elements relevant to the query of the user comprise metadata of UI elements relevant to a first user persona of a plurality of user personas that corresponds to the user (para.[0049]; “query the website features repository 200 for all data records associated with the user's identified industry (Step 330). The website generation software may identify, within each of these data records, the category associated with the data records (e.g., a content, layout or style website feature)”).
wherein prompting the first language model with the first input sequence comprises, for each second user persona of the plurality of user personas (para.0052]; “one or more metadata elements or tags defining or describing the website feature; and a feature affinity data correlating each website feature”).
prompting the first language model with the first input sequence and task instructions to extract metadata of UI elements from the one or more web pages that are relevant to the second user persona (para.[0083]; “user's specific identification of the industry associated with the user's website, and/or may be extrapolated from user profile data”).
As per claim 22, the rejection of claim 1 is incorporated and further Berk et al (US 2017/0109442 A1) discloses,
wherein the second input sequence further comprises behavioral data of the user (para.[0083]; “user's specific identification of the industry associated with the user's website, and/or may be extrapolated from user profile data”).
.
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 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
3/27/2026