DETAILED ACTION
This action is responsive to the amendments filed 4/28/2026.
Claims 1-19 are pending. Claims 1, 2, 4, 5, 12, 14, 15, 17 and 18 are currently amended, and Claim 19 is new.
The rejections under 35 U.S.C. § 112 are withdrawn in view of the amendments.
The rejections under 35 U.S.C. § 102 are maintained.
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)(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.
Claims 1-18 are rejected under 35 U.S.C. 102(a)(2) as being anticipated by Sobhy Deraz, U.S. PGPUB No. 2024/0303441 (“Deraz”).
With regard to Claim 1, Deraz teaches a content generation system for generating a content, comprising:
at least one user interface, at least one memory, at least one processor configured to execute at least one program stored in said at least one memory and connected to said at least one memory ([0110]), wherein said at least one program is programmed to be executed by said at least one processor to:
(A) utilize both a Large Language Model (LLM) that operates using communicative human language information entered through said at least one user interface, and a plurality of pieces of visualization software programmed to respectively output a plurality of types visual information using text information ([0040] describes a spreadsheet program accessible through a user interface, where the operational environment also includes a LLM service. [0088] describes that the LLM interacts with a spreadsheet environment, which includes a plurality of software routines which can be selected for performing requested tasks. Additionally, [0092] describes that queries can be generated for different data analysis tools such as Excel Insights or Excel Data Analysis, where [0095] describes that the LLM classifies the input to determine which supporting tool to query),
(B) acquire first communicative human language information to be included in the content by the LLM using at least a part of the communicative human language information entered through said at least one user interface (Fig. 6A-6C show that determining a routine includes a user’s natural language input. [0094] describes that user inputs are submitted to the LLM making queries regarding the spreadsheet data; [0095] describes that the LLM acquires at least a sample of the spreadsheet data as well as column and row headers, and that classification of the input is used to select a tool),
(C) acquire second communicative human language information by the LLM for selecting one of the plurality of pieces of the visualization software that is configured to generate the visual information to be included in the content, based on at least a part of the communicative human language information entered through said at least one user interface, and select the one piece of visualization software based on the acquired second communicative human language information (Fig. 6A shows that the prompt template received for instructing the system as described at [0088], which specifies a plurality of software routines and specifies that the system can select one of the routines for carrying out a specific task; the prompt also includes additional contextual textual information from the spreadsheet. [0095] describes that for selecting a tool, the system uses contextual information from additional inputs),
(D) acquire the visual information to be included in the content by operating the selected piece of visualization software using the text information, which is based on an output of the LLM in correspondence to the communicative human language information entered through said at least one user interface ([0089] describes that a selected routine acquires the data to be used in generating the visualization. [0095] describes that the user input provides both the query and the information used to query the tool for carrying out visualization tasks such as a What If analysis or Forecasting),
(E) generate the content including at least a part of the first communicative human language information, or a modification thereof, acquired from (B), and at least a part of the visual information, or a modification thereof, acquired from (D) ([0096] describes that the LLM passes the task to the next node to execute the analysis. [0090] describes a scenario where a table is created using the spreadsheet data and column names), and
(F) output the generated content through said at least one user interface ([0053]-[0054] describe that outputs can be displayed as suggestions for adding to an existing or new workbook, including created scenarios and tables. [0089] further describes outputs including routines for creating charts and tables).
With regard to Claim 2, Deraz teaches that each of the plurality of visualization software is selected by the content generation system, not by a user. [0095] describes that the LLM classifies a user’s input in order to determine which supporting tool or service to query to provide the proper response. Figs. 6B and 6C show that when selecting between routines, the system receives input which does not specify a visualization routine.
With regard to Claim 3, Deraz teaches that the content generation system is configured so as not to be embedded in any specific visualization software and not to be associated only with any specific visualization software. [0040] describes that the application service and LLM service operate by hosting a productivity application. The productivity application can be a spreadsheet application, however the environment is not limited to a specific software or exclusively associated therewith; the spreadsheet environment may operate in the context of another application such as a presentation or word processing application.
With regard to Claim 4, Deraz teaches that one of the plurality of pieces of visualization software is data visualization software or includes a visual-based model. [0040] describes that the software includes a spreadsheet application, where [0089] describes creation of visualizations such as tables and charts. [0095] describes additional available tools for additional modeling and visualization options.
With regard to Claim 5, Deraz teaches that the at least one program is programmed to be executed by the at least one processor such that: in the step (C), if the second communicative human language information acquired by the LLM includes information indicating a name of one of the plurality of pieces of visualization software, then the one piece of visualization software is selected based on that name, or a web search is performed using the second communicative human language information acquired by the LLM, and then the one piece of visualization software is selected based on information acquired from the web search. [0095] describes that a user input is converted into a request template, which specifies a specific type of analysis that is then used to select the particular tool or service, using the specific name.
With regard to Claim 6, Deraz teaches that the communicative human language information entered through said at least one user interface includes subject matter of the content, and the content is generated to promote a user’s understanding or provide detailed explanations or descriptions about the subject matter included in the communicative human language information entered through said at least one user interface. [0095] describes that the various types of content analysis available respond to particular queries. Fig. 7B shows that user inputs request information on particular subjects such as customer preferences, business growth, discounts, etc.
With regard to Claim 7, Deraz teaches that the communicative human language information entered through said at least one user interface includes subject matter of the content and is a query that consists of a command, a request, or a question, or a combination thereof, and the content is generated to explain or describe the subject matter in accordance with the query. Fig. 7B shows various questions for which content is generated include various subjects related to the data, and questions thereabout. [0096] describes that the LLM generates the responses, which are passed to the proper service for performing the task.
With regard to Claim 8, Deraz teaches that the first communicative human language information in the content has a larger text count than the communicative human language information entered through said at least one user interface. [0089] describes examples where users create a variety of tables and charts using information such as a shopping list. [0090] describes that columns can be added to the existing content as well.
With regard to Claim 9, Deraz teaches that the first communicative human language information and the visual information included in the content are mutually related and are also related to subject matter of the content. [0095]-[0096] describe that the analyses is carried out and the content generated by identifying the type of analysis requested based on the contextual information, including data and headers from the spreadsheet.
With regard to Claim 10, Deraz teaches that the visual information is added to supplement explanations or descriptions made by the communicative human language information in the content. [0095] describes that the various data analyses are of a type to provide additional understanding of the content, such as forecasting or what if analysis. [0092] describes additional use of Insights and other data analysis tools.
With regard to Claim 11, Deraz teaches that the visual information is either an image which is static visual information, or a video which is dynamic visual information, and the image encompasses visualizations, and the video encompasses animations or simulations. [0089] describes that the system can create pivot charts in response to user input.
With regard to Claim 12, Deraz teaches that at least one program is further programmed to be executed by said at least one processor to utilize the one piece of visualization software after the one piece of visualization software is selected, as the one piece of visualization software to be selected is not determined before the start of use of the content generation system. [0095] describes that the tool or service that is to be used to carry out a particular analysis is determined by the LLM in response to the prompt entered by the user, and not before the system has begun to be used. Figs 6B and 6C show that a general inquiry from a user causes the response to identify the routine to be used.
With regard to Claim 13, Deraz teaches a system for generating a content in response to an input in communicative human language, the system being configured to communicate with:
a user terminal device configured to receive the input in the communicative human language, to thereby generate communicative human language (CHL) information, and output the generated content (Fig. 1, devices 130 entering data into spreadsheets),
a first server configured to provide a Large Language Model (LLM), and a second server configured to provide a plurality of pieces of visualization software (Fig. 1, application service 110 and LLM service 120), the system comprising:
a processor; and a non-transitory storage medium containing program instructions ([0110]), execution of which by the processor causes the system to:
receive the CHL information from the user terminal device; send the CHL information to the first server, to thereby obtain a first output of the LLM, the first output including output content in the communicative human language ([0095]);
resend the CHL information to the first server, to thereby obtain a second output of the LLM, the second output including information designating one of the plurality of pieces of visualization software ([0095]);
further resend the CHL information to the first server, to thereby obtain a third output of the LLM, the third output including text information for the designated one of the plurality of pieces of visualization software ([0095]);
send the text information to the second server, to thereby obtain output content including visual information from the designated one of the plurality of pieces of visualization software ([0095]-[0096]);
generate the content based on both the output content in the communicative human language, and the output content including the visual information ([0095]-[0096]; and
send the generated content to the user terminal device to be outputted thereby ([0090], [0096]).
Claim 16 recites a method carried out by the system of Claim 12, and the claim is similarly rejected.
With regard to Claim 14, Deraz teaches that at least one of the first and second servers include a plurality of server devices that communicate with one another ([0042]-[0043]).
Claim 17 recites a method carried out by the system of Claim 14, and the claim is similarly rejected.
With regard to Claim 15, Deraz teaches that the content generated by the system further includes at least one of a modification of the output content in the communicative human language, and a modification of the output content including the visual information ([0090]).
Claim 18 recites a method carried out by the system of Claim 15, and the claim is similarly rejected.
With regard to Claim 19, Deraz teaches that each of the plurality of pieces of visualization software is stored in a server device that is separate from, and communicates with, the content generation system. [0040] describes that a spreadsheet application is provided to endpoints such as computing devices. Therefore, each of the routines and queryable tools are resident on a server separate from the accessing endpoint devices.
Response to Arguments
Applicant's arguments have been fully considered but they are not persuasive. Applicant argues with regard to the independent claims that Deraz is inapplicable to the amended claims, because Deraz selects among built-in spreadsheet capabilities, and because of this, Deraz does not teach the claimed “plurality of pieces of software.” Examiner notes that Deraz also discloses selection between additional visualization tools, such as Excel Insights and Excel Analyze Data tool, as explained in the above rejection.
However, Deraz is properly relied upon for the claimed “plurality of pieces of visualization software,” because the broadest reasonable interpretation of this limitation includes both the multiple data analysis engines, as well as the multiple different routines for producing different types of visualizations. While Applicant does not offer a specific interpretation for what is meant by “plurality of pieces of visualization software,” p. 11 of the response appears to hold the fact that Deraz is limited to selecting elements of a single spreadsheet application as distinguishing from this claimed feature.
The broadest reasonable interpretation of “piece of software” includes portions of a greater single application. A definition of the word “piece” is a portion or fragment of a whole. Therefore, a routine within a spreadsheet application is a “piece” of the application. As an application is software, a routine within an application constitutes a “piece of software” under the broadest reasonable interpretation of those terms. As spreadsheet applications are capable of producing many different types of visualizations, they fall under the broadest reasonable interpretation of a “visualization software,” and a routine within that application that produces a particular type of visualization would be a “piece of visualization software.”
Collectively, then, the plurality of routines and tools available within the application would be a “plurality of pieces of visualization software” under the broadest reasonable interpretation of the term. As Deraz teaches various ways in which an LLM can select from among the various pieces of visualization software in response to a user’s natural language input, Deraz anticipates the claims for the reasons given in the above rejection.
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 KEITH D BLOOMQUIST whose telephone number is (571)270-7718. The examiner can normally be reached M-F, 8:30-5 PM. 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, Kieu Vu can be reached at 571-272-4057. 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.
/KEITH D BLOOMQUIST/Primary Examiner, Art Unit 2171
6/12/2026
Prosecution Insights