DETAILED ACTION
1. This action is responsive to Application no.18/827,106 filed 9/6/2024. All claims have been examined and are currently pending.
Claim 16 recites “a computer program product…, the computer program product comprising a computer readable storage medium”.
The specification states: “0074: computer-readable media; computer-readable media may comprise computer storage media and communication media;
0075: Computer storage media excludes signals per se.”
Notice of Pre-AIA or AIA Status
2. The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Information Disclosure Statement
3. The information disclosure statement (IDS) submitted is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is being considered by the examiner.
Specification
4. The title of the invention is not descriptive. A new title is required that is clearly indicative of the invention to which the claims are directed.
Claim Rejections - 35 USC § 102
5. 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 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.
6. 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.
7. Claims 1-3, 5-6, 8-11, 13-15 are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Gray et al (11,769,017).
Regarding claim 1 Gray et al (11,769,017) teaches A method for a content referencing system (figure 1; figure 2; col 6 l. 20-29: example environment; method; col 7 l. 6-15: device; system), the method comprising:
generating a user interface (UI) including a dialog window and an input field onto a display (figure 7A1 782; col 7 l. 54 – col 8 l 13: the client device 110 can include a user input engine 111 that is configured to detect user input provided by a user of the client device 110 using one or more user interface input devices.; col 27; 59-63: client device with a display, graphical interface, query);
receiving, via the UI, a text string inputted into the input field (figure 7A1 782; col 8 l. 7-9: the query can be a typed query that is typed via a physical or virtual keyboard; col 27; 59-63);
inputting the text string, and data points from a selected index associated with the text string, into a language model (fig 2; 7B1-7B3;
col 1 l.66 – col 2 l 8: Implementations disclosed herein are directed to at least selectively utilizing an LLM in generating an NL based summary to be rendered (e.g., audibly and/or graphically) in response to a query (e.g., a submitted query or an automatically generated query). In many of those implementations, in generating the NL based summary additional content is processed using the LLM. The additional content is in addition to query content of the query itself and, in generating the NL based summary, can be processed using the LLM and along with the query content
col 2 l. 59 – col 3 l 20 a given query is submitted
In response to submission of the given query, a search can performed for the given query to obtain query-responsive search result documents, a search can be performed for a related query to generate related-query-responsive search result documents, and recent-search-responsive search result documents that were responsive to a recent query can be obtained
can then be included in the additional content that is processed using the LLM in generating the NL based summary to provide responsive to submission of the query;
col 28 l. 60-63: interaction with the search result document);
outputting, via the language model, a summary response associated with the text string and the selected index data points (figure 7B3; col 1 l.66 – col 2 l 8: Implementations disclosed herein are directed to at least selectively utilizing an LLM in generating an NL based summary to be rendered (e.g., audibly and/or graphically) in response to a query (e.g., a submitted query or an automatically generated query). In many of those implementations, in generating the NL based summary additional content is processed using the LLM; col 28 l. 60-63: revised NL based summary); and
causing the UI to display the summary response in the dialog window (figure 7A1; 7B3: summary; col 28 l. 60-63: FIG. 7B3 depicts the example client device 710 rendering a graphical interface that includes an example revised NL based summary 784′, generated based on the interaction with the search result document 783 of FIG. 7B2.).
Regarding claim 2 Gray teaches The method of claim 1 wherein the summary response includes a reference to the selected index data points used by the language model to produce the summary response (figure 7A1; 7B1-7B3 : summary ; col 28 l. 60-63: FIG. 7B3 depicts the example client device 710 rendering a graphical interface that includes an example revised NL based summary 784′, generated based on the interaction with the search result document 783 of FIG. 7B2.).
Regarding claim 3 Gray teaches The method of claim 1, further comprising:
generating, via the UI, a drop down menu icon including a selectable list of searchable indexes (fig 7A1, 7A2 787, 7B1 786 view sources; col 28 l 35-45);
receiving, via the UI, an index selection from the searchable indexes included in the drop down menu icon (fig 7B2 791; col 28 l. 49-50 interacting with a search result document; l. 56 in response to a selection); and
applying the index selection as the selected index prior to inputting the selected index data points into the language model (fig 7B3; col 1 l.66 – col 2 l 8; col 28 l. 60- 65).
Regarding claim 5 Gray teaches The method of claim 1, wherein the summary response includes a reference to documentation associated with the selected index (fig 7A1 784, 788; 7A2 787; col 27 l 63-col 28 l 1: linkified portions; source identifier; corresponding to search result document).
Regarding claim 6 Gray teaches The method of claim 5, wherein the reference includes a hyperlink to a section of the documentation associated with the summary response (figure 7A1 784, 788; 7A2 787; col 27 l 63-67 linkified portions; source identifier).
Regarding claim 8 Gray teaches The method of claim 1, wherein the language model is configured to generate a search query and summarize the selected index data points to produce the summary response (figure 7B3; col 1 l.66 – col 2 l 8: Implementations disclosed herein are directed to at least selectively utilizing an LLM in generating an NL based summary to be rendered (e.g., audibly and/or graphically) in response to a query (e.g., a submitted query or an automatically generated query). In many of those implementations, in generating the NL based summary additional content is processed using the LLM; col 28 l. 60-63: revised NL based summary).
Regarding claim 9 Gray teaches The method of claim 1, further comprising:
analyzing an intent associated with the text string (col 2 l. 59-65: In response to submission of the given query, a search can performed for the given query to obtain query-responsive search result documents, a search can be performed for a related query to generate related-query-responsive search result documents); and
determining the selected index based, at least in part, on the intent prior to inputting the selected index data points into the language model (7A1 788, 7A2 787; col 2 l. 59 – col 3 l 20: search result documents; col 11 l. 50-52: SRDs; col 12 l. 5-14).
Regarding claim 10 Gray teaches The method of claim 1, further comprising:
analyzing an intent associated with the text string (col 2 l. 59-65: In response to submission of the given query, a search can performed for the given query to obtain query-responsive search result documents, a search can be performed for a related query to generate related-query-responsive search result documents);
referencing a historical input associated with prior text string submissions within a period of time (col 2 l. 67: recent search responsive search result documents); and
determining the selected index based, at least in part, on the intent and the historical input prior to inputting the selected index data points into the language model (7A1 788, 7A2 787; col 2 l. 59 – col 3 l 20: search result documents; col 11 l. 50-52: SRDs; col 12 l. 5-14).
Regarding claim 11 Gray teaches A content referencing system (figure 1; figure 2; col 6 l. 20-29: example environment; method; col 7 l. 6-15: device; system), the system comprising:
a user interface (UI) configured with a display including a dialog window and an input field, wherein the input field is configured to receive a text string (figure 7A1 782; col 7 l. 54 – col 8 l 13: the client device 110 can include a user input engine 111 that is configured to detect user input provided by a user of the client device 110 using one or more user interface input devices.; the query can be a typed query that is typed via a physical or virtual keyboard; col 27; 59-63: client device with a display, graphical interface, query);
a language model (col 1 l 8-9 large language models LLM) configured to:
receive selected index data points and the text string (fig 2; 7B1-7B3;
col 1 l.66 – col 2 l 8: Implementations disclosed herein are directed to at least selectively utilizing an LLM in generating an NL based summary to be rendered (e.g., audibly and/or graphically) in response to a query (e.g., a submitted query or an automatically generated query). In many of those implementations, in generating the NL based summary additional content is processed using the LLM. The additional content is in addition to query content of the query itself and, in generating the NL based summary, can be processed using the LLM and along with the query content
col 2 l. 59 – col 3 l 20 a given query is submitted
In response to submission of the given query, a search can performed for the given query to obtain query-responsive search result documents, a search can be performed for a related query to generate related-query-responsive search result documents, and recent-search-responsive search result documents that were responsive to a recent query can be obtained
can then be included in the additional content that is processed using the LLM in generating the NL based summary to provide responsive to submission of the query);
and
output a summary response associated with at least the selected index data points and the text string (figure 7B3; col 1 l.66 – col 2 l 8: Implementations disclosed herein are directed to at least selectively utilizing an LLM in generating an NL based summary to be rendered (e.g., audibly and/or graphically) in response to a query (e.g., a submitted query or an automatically generated query). In many of those implementations, in generating the NL based summary additional content is processed using the LLM).
Regarding claim 13 Gray teaches The system of claim 11, wherein an intent analyzer includes pointers corresponding to the text string and the pointers provide indication of what searchable indexes to search for data points to provide to the language model (col 2 l. 59-65: In response to submission of the given query, a search can performed for the given query to obtain query-responsive search result documents, a search can be performed for a related query to generate related-query-responsive search result documents;
7A1 788, 7A2 787; col 2 l. 59 – col 3 l 20: search result documents; col 11 l. 50-52: SRDs; col 12 l. 5-14).
Regarding claim 14 Gray teaches The system of claim 11 wherein the language model is configured to determine an intent associated with the text string and determine an index corresponding to the intent prior to inputting the index data points into the language model (figure 7B3; col 1 l.66 – col 2 l 8: Implementations disclosed herein are directed to at least selectively utilizing an LLM in generating an NL based summary to be rendered (e.g., audibly and/or graphically) in response to a query (e.g., a submitted query or an automatically generated query). In many of those implementations, in generating the NL based summary additional content is processed using the LLM; col 28 l. 60-63: revised NL based summary;
col 2 l. 59-65: In response to submission of the given query, a search can performed for the given query to obtain query-responsive search result documents, a search can be performed for a related query to generate related-query-responsive search result documents).
Regarding claim 15 Gray teaches The system of claim 11, wherein the language model suppresses the summary response when the text string is not associated with the index data points (7A1 – presenting summary without the use of index data points of the selected index).
Claim Rejections - 35 USC § 103
8. 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.
9. Claims 4, 16-17, 19-20 are rejected under 35 U.S.C. 103 as being unpatentable over Gray in view of Hadley et al (8,856,134).
Regarding claim 4 Gray teaches The method of claim 1, further comprising:
generating, via the UI, a drop down menu icon including a selectable list {of searchable aircraft} (fig 7A1, 7A2 787);
receiving, via the UI, {an aircraft model} selection from the searchable {aircraft included in the} drop down menu icon (7B2); and
inputting the {aircraft model} selection with the selected index to further filter the selected index data points and the text string into the language model (7B2, 7B3).
Recites the limitations of and is Rejected for similar rationale and reasoning as claim 3
Claim 4 further recites aircraft, Where Gray does not specifically teach the aircraft references (presenting a list of aircraft for selection and used for search).
Hadley et al (8,856,134), in a similar field of endeavor, also teaches data retrieval and, more particularly, to maintenance data retrieval (col 1 l. 114-15).
Hadley teaches provide portable access to large information data sets necessary to operate and maintain machinery, such as a commercial airplane (Col 4 l. 19-21);
And
Col 6 l. 38-45: the user 102 inputs service request data and information to the user device 120 (block 210). The user 102 inputs the service request to the user device 120 via keypad/keyboard input, voice recognition or a graphical interface. In various examples, the user 102 may input at least one of an ATA number, a part number, a task number, an LRU name, a wire bundle number (e.g., using aerospace acronyms including RefDes), location information, EICAS message;
5F/G & col 8 l. 42-53: the interactively presented data and information provides procedural steps, reference support material and/or engineering data for maintenance, service and repair of machinery, such as an airplane. In one example, as shown in FIG. 5D, the search application 132 of the user device 120 allows the user 102 to search and select sub-topics, such as specific maintenance and inspection practices and procedures for selected topics, from the data and information received from the server device 170 via the network 150. As shown in FIGS. 5E-5F, portions of the data and information received from the server device 170 may be printed or viewed by the user 102
It would have been obvious to one of ordinary skill in the art before the effective filing date to incorporate Hadley for an improved and more customized system, allowing for search and retrieval of information relating to aircraft maintenance. Gray already teaches retrieving information and summaries for user queries, and one could look to Hadley to allow the content to further include aircraft documentation that allows the user to quickly identify and research the particular part directly (Hadley col 6 l. 5-6) and
provide portable access to large information data sets necessary to operate and maintain machinery, such as a commercial airplane (Col 4 l. 19-21).
The incorporation thus allowing:
generating, via the UI, a drop down menu icon including a selectable list of searchable aircraft;
receiving, via the UI, an aircraft model selection from the searchable aircraft included in the drop down menu icon; and
inputting the aircraft model selection with the selected index to further filter the selected index data points and the text string into the language model.
Regarding claim 16 Gray teaches A computer program product for a content referencing system, the computer program product comprising a computer readable storage medium having computer readable instructions stored therein, wherein the computer readable instructions, when executed on a computing device (fig 1; 7A1; 8), causes the computing device to:
receive an input of index data points and a text string {associated with an aircraft} via a user interface (UI) (fig 2; 7B1-7B3;
col 1 l.66 – col 2 l 8: Implementations disclosed herein are directed to at least selectively utilizing an LLM in generating an NL based summary to be rendered (e.g., audibly and/or graphically) in response to a query (e.g., a submitted query or an automatically generated query). In many of those implementations, in generating the NL based summary additional content is processed using the LLM. The additional content is in addition to query content of the query itself and, in generating the NL based summary, can be processed using the LLM and along with the query content
col 2 l. 59 – col 3 l 20 a given query is submitted
In response to submission of the given query, a search can performed for the given query to obtain query-responsive search result documents, a search can be performed for a related query to generate related-query-responsive search result documents, and recent-search-responsive search result documents that were responsive to a recent query can be obtained
can then be included in the additional content that is processed using the LLM in generating the NL based summary to provide responsive to submission of the query); and
output, to the UI, a summary response produced by a language model using the text string and the index data points as input (figure 7B3; col 1 l.66 – col 2 l 8: Implementations disclosed herein are directed to at least selectively utilizing an LLM in generating an NL based summary to be rendered (e.g., audibly and/or graphically) in response to a query (e.g., a submitted query or an automatically generated query). In many of those implementations, in generating the NL based summary additional content is processed using the LLM);
but does not specifically teach where Hadley teaches receive an input of index data points and a text string associated with an aircraft via a user interface (UI)
(Col 6 l. 38-45: the user 102 inputs service request data and information to the user device 120 (block 210). The user 102 inputs the service request to the user device 120 via keypad/keyboard input, voice recognition or a graphical interface. In various examples, the user 102 may input at least one of an ATA number, a part number, a task number, an LRU name, a wire bundle number (e.g., using aerospace acronyms including RefDes), location information, EICAS message;
5F/G & col 8 l. 42-53: the interactively presented data and information provides procedural steps, reference support material and/or engineering data for maintenance, service and repair of machinery, such as an airplane. In one example, as shown in FIG. 5D, the search application 132 of the user device 120 allows the user 102 to search and select sub-topics, such as specific maintenance and inspection practices and procedures for selected topics, from the data and information received from the server device 170 via the network 150. As shown in FIGS. 5E-5F, portions of the data and information received from the server device 170 may be printed or viewed by the user 102).
It would have been obvious to one of ordinary skill in the art before the effective filing date to incorporate Hadley for an improved and customized system, allowing for search and retrieval of information relating to aircraft maintenance. Gray already teaches retrieving information and summaries for user queries, and one could look to Hadley to allow the content to further include aircraft documentation that allows the user to quickly identify and research the particular part directly (Hadley col 6 l. 5-6) and
provide portable access to large information data sets necessary to operate and maintain machinery, such as a commercial airplane (Col 4 l. 19-21).
Regarding claim 17 Gray teaches The computer program product of claim 16, further comprising:
generate an intent associated with the text string (col 2 l. 59-65: In response to submission of the given query, a search can performed for the given query to obtain query-responsive search result documents, a search can be performed for a related query to generate related-query-responsive search result documents); and
determine the index based, at least in part, on the intent prior to inputting the index data points into the language model (7A1 788, 7A2 787; col 2 l. 59 – col 3 l 20: search result documents; col 11 l. 50-52: SRDs; col 12 l. 5-14).
Regarding claim 19 Gray teaches The computer program product of claim 16 comprising an intent analyzer configured to determine the intent and provide indication to the language model of portions of the index associated with the text string (7A1 788, 7A2 787; col 2 l. 59-65: In response to submission of the given query, a search can performed for the given query to obtain query-responsive search result documents, a search can be performed for a related query to generate related-query-responsive search result documents; col 2 l. 59 – col 3 l 20: search result documents; col 11 l. 50-52: SRDs; col 12 l. 5-14).
Regarding claim 20 Gray teaches The computer program product of claim 16 wherein the summary response includes references to documentation associated with the index (fig 7A1 784; col 27 l 63-col 28 l 1: linkified portions; source identifier; corresponding to search result document).
10. Claims 7, 12, 18 are rejected under 35 U.S.C. 103 as being unpatentable over Gray in view of Hadley et al (8,856,134) in further view of Volkovs et al (2018/0196800).
Regarding claim 7 Gray teaches The method of claim 1, wherein the selected index includes documentation associated with the selected index (figures 7A1-7A3) but does not specifically teach the selected index includes embeddings from aircraft-related documentation.
Hadley teaches aircraft-related documentation and it would have been obvious to one of ordinary skill in the art before the effective filing date to incorporate Hadley for improved and customized retrieval of information related to aircraft maintenance (as discussed in claim 4 above).
Hadley also teaches the maintenance documents may be indexed…using a unique indexer (col 6 l. 18-19), but does not specifically teach where Volkovs teaches embeddings from documentation (0006 document embeddings).
It would have been obvious to one of ordinary skill in the art before the effective filing date to incorporate the embeddings for improved storage and retrieval of documentation, leading to more efficient document/knowledge referencing, and to:
Represent documents as numerical vectors, and characterize the document for various purposes (Volkovs 0004).
Regarding claim 12 Gray teaches The system of claim 11, wherein the UI is further configured to display a drop down menu icon including a selectable list of searchable indexes (figures 7A1-7B3),
But does not specifically teach where Hadley and Volkovs teaches wherein the searchable indexes include embeddings from aircraft maintenance documentation associated with the searchable indexes, respectively.
Rejected for similar rationale and reasoning as claim 7 (and 4 above)
Regarding claim 18 Gray, Hadley, and Volkovs teach The computer program product of claim 16, wherein the index includes embeddings from aircraft-related documentation associated with the index.
Claim recites limitations similar to claim 7 and is Rejected for similar rationale and reasoning
Conclusion
11. The prior art made of record and not relied upon is considered pertinent to applicant's disclosure: See PTO-892.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to SHAUN A ROBERTS whose telephone number is (571)270-7541. The examiner can normally be reached Monday-Friday 9-5 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, Andrew Flanders can be reached on 571-272-7516. 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.
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 or access to the automated information system, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/SHAUN ROBERTS/Primary Examiner, Art Unit 2655
Prosecution Insights