DETAILED ACTION
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Claims 1-15 have been submitted for examination and are pending further prosecution by the United States Patent & Trademark Office.
Allowable Subject Matter
Claims 3-6 and 11 are objected to as being dependent upon a rejected base claim, but would be allowable if rewritten in independent form including all of the limitations of the base claim and any intervening claims.
Claim Objections
The following claims are objected to because of informalities and antecedence issues. It is suggested Applicants amend these claims as follows:
Claim 5
-- wherein the request relating to generating the application is included in a function call request for calling the function transmitted to the information processing apparatus, the function call request generated by the generative AI system based on the specification setting of the function . --
Claim 14
-- a communication terminal including second circuity configured to receive input of a chat message and transmit the chat message via a network to the information processing apparatus, the first circuity being configured to transmit the chat message to a generative artificial intelligence (AI) system via the network, the first circuitry and the second circuitry being configured to operate in cooperation to: --
Claim 15
-- transmitting the chat message to a generative artificial intelligence (AI) system via the network; --
Appropriate correction is required.
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.
Claims 1, 2, 9, 10 and 12-15 are rejected under 35 U.S.C. 102(a)(1) as being anticipated by US 20240386058 A1 - hereinafter "Thomas".
With respect to claim 1, Thomas teaches,
An information processing apparatus comprising circuitry configured to: - "Application service 110 may be implemented in software in the context of one or more server computers co-located or distributed across one or more data centers." [0034]; Fig. 1
receive a chat message input to a communication terminal via a network from the communication terminal; - "Application service 110 hosts an application, such as a spreadsheet application (e.g., Microsoft Excel®), to endpoints such as computing devices 130 which execute applications that provide a local user experience and that interface with application service 110." [0032]. "In some scenarios, the application displays in the user interface of the application a task pane or a chat interface by which the application can receive user-supplied natural language inputs and display responses to the inputs based on the replies generated by the LLM." [0028]; Fig. 1. "In user experience 143, application service 120 displays a message to initiate a dialog or conversation with the user for assisting the user in editing the chart. In response to the message, the user enters a natural language input in task pane 144 by keying in a text entry which expresses the user's interest or question: “make the series red.”" [0037]
transmit the chat message to a generative artificial intelligence (AI) system via the network; - "Application service 110 creates a prompt based on the user's statement along with contextual information of the chart indicating that the FY22 data series is currently selected. Application service 110 submits the prompt to LLM service 120." [0037] "LLM service 120 hosts LLM 121 which is representative of a generative pretrained transformer (GPT) computing architecture such as GPT-3®, GPT-3.5, ChatGPT®, or GPT-4." [0032]
transmit, to the generative AI system, at least once:
information for calling a function to be executed - "In the prompt provided to LLM service 120, application service 110 may specify tasks (information) to be performed by LLM service 120. Tasks in the prompt can include classifying the input according to a type..." [0051] "...the prompt tasks the LLM service with determining a classification of the natural language input and including the classification in the reply. In some implementations, to modify the visualization, the application generates source code based on the reply from the LLM service when the classification of the natural language input is a command." [0006]. "Prompt engine 305 (function) generates chart commands or source code for modifying chart 503 based on the output and submits the commands to the execution queue." [0069]; for generating an application based on a parameter included in a request relating to generating the application; and - This limitation recites an intended use.
setting information for generating the parameter; - "In an implementation, the application includes in the prompt a representation of the chart to which the user input refers. The format of the representation is a data structure which includes chart design and format properties which define the chart." [0025]
receive, from the generative AI system, the request generated by the generative AI system based on the chat message, the setting information, and the information for calling the function; and - "The application service receives a reply to the prompt from the LLM service (step 207). The reply to the prompt may include one or more commands (request), suggestions, recommendations, explanations, descriptions, etc., generated based on the prompt and in accordance with any rules, instructions, or parameters provided in the prompt." [0045] "Application service 110 receives the reply to the first user input from LLM service 120 and generates a response based on the reply. Based on LLM service 120 classifying the input as a command, application service 110 generates source code to modify the color of the data series per the user's request, where the source code is based on a chart property (setting information) and property value extracted from the reply." [0053] "Prompt engine 305 (function) generates chart commands or source code for modifying chart 503 based on the output and submits the commands to the execution queue." [0069]
execute the function to generate the application based on the parameter included in the request received from the generative AI system. - "Application service 110 receives the reply to the first user input from LLM service 120 and generates a response based on the reply. Based on LLM service 120 classifying the input as a command, application service 110 generates source code (generate the application) to modify the color of the data series per the user's request, where the source code is based on a chart property and property value (parameter) extracted from the reply." [0053] "Application 301, of which application service 110 is representative, includes charting engine 303, prompt engine 305, and user interface 307." [0056] "Prompt engine 305 (function) of application 301 generates prompts for LLM 330 based on user input received from a user through user interface 307, e.g., in a task pane of user interface 307 and receives replies to the prompts from LLM 330." [0056] "Upon receiving LLM 330′s reply, prompt engine 305 post-processes the reply to generate chart commands for modifying chart 503. Post-processing the reply includes extracting information from the reply according to the output formatting rules. Prompt engine 305 generates chart commands or source code for modifying chart 503 based on the output and submits the commands to the execution queue." [0069]
With respect to claim 2, Thomas teaches,
wherein the circuitry is configured to transmit, to the communication terminal, a reply message generated by the generative AI system as a response to the chat message transmitted to the generative AI system. - "In some scenarios, the application displays in the user interface of the application a task pane or a chat interface by which the application can receive user-supplied natural language inputs and display responses to the inputs based on the replies generated by the LLM." [0028]
With respect to claim 9, Thomas teaches,
wherein, when the application is an application in which data is registered in a table, the parameter is one or more field names of the table. - "Data of a data visualization can include tabular data (e.g., spreadsheet data or table data). Properties of visualizations include —but are not limited to—design or format properties (e.g., style, size, color, visibility, border, fill, etc.) of elements of a visualization (e.g., chart title, chart type, chart axes, chart area, tick marks, legend, etc.). Properties of data visualizations can also include the data source, such as tabular data within the application environment or data imported from an external source." [0020]
With respect to claim 10, Thomas teaches,
communicate via the network with an application service that executes the application; and request the application service to generate the application by specifying the parameter. - "Application 301, of which application service 110 is representative, includes charting engine 303, prompt engine 305, and user interface 307." [0056] "The chart command is executed by charting engine 303 to modify the chart. Charting engine 303 sends an updated configuration of the chart to user interface 307 for display." [0060] "Prompt engine generates a chart command (e.g., executable source code) based on the property identifier and value (parameter) extracted from the reply and submits the chart command or source code to application 301 to modify the chart and update the display in user interface 307." [0065]
With respect to claim 12, Thomas teaches,
generate the setting information for generating the parameter, - "In an implementation, the application includes in the prompt a representation of the chart to which the user input refers. The format of the representation is a data structure which includes chart design and format properties which define the chart." [0025]; display an instruction urging to input precondition information for generating the application on a screen for receiving an input of the chat message, and generate the setting information including the precondition information input in response to the instruction. - "An application, implemented in software on one or more computing devices, receives a natural language (NL) input from a user in the context of a spreadsheet or other application environment capable of hosting data and generates a prompt based on the natural language input and a visualization of data, such as a chart associated with spreadsheet data." [0017] "Properties of visualizations include —but are not limited to—design or format properties (e.g., style, size, color, visibility, border, fill, etc.) of elements of a visualization (e.g., chart title (precondition), chart type, chart axes, chart area, tick marks, legend, etc.)." [0020] "As illustrated in operational environment 100, property settings for the chart are presented to the user in chart menu 142 which may be surfaced in user experience 141 in response to the user making a selection to view the chart properties from an application menu, right-clicking the chart, or by other user input." [0036] "In user experience 143, application service 120 displays a message to initiate a dialog or conversation with the user for assisting the user in editing the chart." [0037]
With respect to claim 13, Thomas teaches,
wherein the precondition information indicates at least one of...a name of the application. - "Properties of visualizations include —but are not limited to—design or format properties (e.g., style, size, color, visibility, border, fill, etc.) of elements of a visualization (e.g., chart title, chart type, chart axes, chart area, tick marks, legend, etc.)." [0020]
With respect to claim 14, Thomas teaches,
An application generation system comprising: - Figs. 1 & 7
The remaining limitations are rejected using the mapping from analogous claim 1.
With respect to claim 15, Thomas teaches,
A method for generating an application, the method comprising:
The remaining limitations are rejected using the mapping from analogous claim 1.
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 of this title, 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.
Claim 7 is rejected under 35 U.S.C. 103 as being unpatentable over US 20240386058 A1 - hereinafter "Thomas", in view of US 20250001296 A1 (Examiner relies on provisional date of 6/29/23 for priority) - hereinafter "Fulks".
With respect to claim 7, Thomas does not explicitly teach,
wherein, when the circuitry fails to generate the application, the circuitry is configured to transmit, to the generative AI system, an error message indicating failure in generating the application and the chat message, and receive another request relating to generating the application as a response to the error message and the chat message.
However, in the analogous field of natural language analysis, Fulks teaches:
"In some examples, the generative AI system 615 also has access, as input(s), to compiler output(s) 120, interpreted compiler output(s) 130, and/or visual content 320, so that the content 620 generated by the generative AI system 615 can reference these. For instance the generative AI system 615 can generate the content 620 to be able to review and analyze the user's code from the prompt 105 in light of the user's question in the prompt 605 and an error message in the compiler output(s) 120, allowing the generative AI system 615 to generate the content 620 to explain the error message in further detail in the specific context of the user's own code from the prompt 105." [0045]
It would have been obvious for one of ordinary skill in the art before the effective filing date of the invention to implement Thomas with Fulks' teachings because doing so would provide Thomas' system with the ability to provide personalized help in identifying and/or correcting errors with the code, as suggested by Fulks [0031].
Claim 8 is rejected under 35 U.S.C. 103 as being unpatentable over US 20240386058 A1 - hereinafter "Thomas", in view of US 20060236310 A1 - hereinafter "Domeika".
With respect to claim 8, Thomas does not explicitly teach,
wherein, when generating the application has failed a predetermined number of times, the circuitry is configured to transmit a notification indicating that generating the application has failed to the communication terminal.
However, in the analogous field of software development, Domeika teaches:
"Further, if after a plurality of compilations, the example compiler 100 cannot generate object code that satisfies the target or threshold values, the compiler 100 provides a user with comparisons of performance characteristics associated with the object code to enable the user to make informed decisions regarding performance tradeoffs that may enable the compiler 100 to generate object code having performance characteristics that are acceptable, or are relatively similar to, the target performance characteristic values or threshold values." [0015]
It would have been obvious for one of ordinary skill in the art before the effective filing date of the invention to implement Thomas with Domeika's teachings because doing so would provide Thomas' system with the ability to generate software applications that satisfy user-defined performance characteristics, as suggested by Domeika (Abstract).
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure. US 20240311088 A1 discloses iteratively generating a software application based on user interactions with a chat module and an AI system.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to GEOFFREY R ST LEGER whose telephone number is (571)270-7720. The examiner can normally be reached M-F (IFP) ~9:00-5:00 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, Hyung S Sough can be reached at 571-272-6799. 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.
/GEOFFREY R ST LEGER/Primary Examiner, Art Unit 2192
Prosecution Insights