DETAILED ACTION
This non-final rejection is responsive to the claims filed 20 November 2024. Claims 1-20 are pending. Claims 1, 13, and 19 are independent claims.
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Claim Rejections - 35 USC § 102
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
(a)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention.
Claims 1-5, 13-17, 19, and 20 are rejected under 35 U.S.C. 102(a)(2) as being anticipated by Thomas (US 12,147,758 B1) hereinafter known as Thomas.
Regarding independent claim 1, Thomas teaches:
receiving a first user input instruction through an interaction component in a table interface, wherein the first user input instruction comprises table creation requirement information; (Thomas: Fig. 1 and col. 7, lines 2-27; Thomas teaches the user entering a natural language statement or inquiry (“Store sales by category”) into the task pane.)
invoking a language model based on the first user input instruction, to create a target table that satisfies the table creation requirement information; and (Thomas: Fig. 1 and col. 7, lines 2-27; Thomas teaches selecting a prompt template by which to create a prompt based on the user’s statement and submit the prompt to LLM service. The LLM generates a reply to the prompt including a description of a suggested pivot table based on the user’s query and the spreadsheet metadata.)
presenting the target table in the table interface. (Thomas: col. 7, lines 27-40; Thomas teaches configuring and displaying the pivot table.)
Regarding claim 2, Thomas further teaches:
The method according to claim 1, wherein the invoking a language model based on the first user input instruction, to create a target table that satisfies the table creation requirement information comprises: generating model input data using a preset template, based on the first user input instruction; processing the model input data based on the language model, to obtain target table data that satisfies the table creation requirement information; and parsing the target table data, and creating the target table in the table interface based on a parsing result. (Thomas: Figs. 6A-6E and col. 12, lines 14-46; Thomas teaches configuring Prompt (1) by identifying a prompt template based on the type of request in the input. Col. 12, lines 47-65 further teaches receiving Reply (1) based on Prompt (1) and further teaches parsing this Reply (1) to identify characteristics and values of the characteristics for a pivot table to be created and creating the table.)
Regarding claim 3, Thomas further teaches:
The method according to claim 2, wherein the target table data comprises one or more of the following: a number of tables comprised in the target table and a subject of each table, a field name in the table, an option of at least one field, example data in the table, and real data in the table. (Thomas: col. 13, lines 15-37; Thomas teaches a JSON description of a modification to the current pivot table, including changing the values of the Row characteristic from “Store” and “Category” to just “Category” and adding the value “Store” to the column characteristic. The foregoing teaches field name in the table.)
Regarding claim 4, Thomas further teaches:
The method according to claim 1, wherein the receiving a first user input instruction through an interaction component in a table interface comprises: receiving instruction content that is based on natural language and is input into an input box control in the interaction component, and determining the instruction content to be the first user input instruction; in response to a trigger operation on a preset shortcut instruction control in the interaction component, determining a preset shortcut instruction corresponding to the preset shortcut instruction control to be the first user input instruction; in response to the trigger operation on the preset shortcut instruction control in the interaction component, displaying a preset prompt corpus in the input box control in the interaction component, receiving instruction content that is based on the natural language and is input by a user into the input box control for the preset prompt corpus, and determining the preset prompt corpus and the instruction content to be the first user input instruction; or receiving the instruction content that is based on the natural language and input into the input box control in the interaction component, displaying, in the interaction component, a preset shortcut instruction control that matches the instruction content, and determining, in response to the trigger operation on the preset shortcut instruction control, the preset shortcut instruction corresponding to the preset shortcut instruction control to be the first user input instruction. (Thomas: Figs. 6A-6E and col. 12, lines 21-37; Thomas teaches receiving a natural language input from a user via the task pane of the user interface.)
Regarding claim 5, Thomas further teaches:
The method according to claim 1, wherein after the presenting the target table in the table interface, the method further comprises: receiving a second user input instruction through the interaction component, wherein the second user input instruction comprises field modification requirement information for the target table, and the field modification requirement information comprises requirement information for modifying an existing field, requirement information for deleting an existing field, or requirement information for adding a new field; and invoking the language model based on the second user input instruction, to perform field modification on the target table based on the field modification requirement information. (Thomas: Fig. 6D and col. 12, lines 66-67 to col. 13, lines 1-28; Thomas teaches receiving a second user input “Move Store to Columns” and submitting Prompt (2) to LLM.)
Regarding claims 13-17, 19, and 20, these claims recite an electronic device and a non-transitory computer-readable storage medium that performs the method of claims 1-5; therefore, the same rationale for rejection applies.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claims 6 and 18 are rejected under 35 U.S.C. 103 as being unpatentable over Thomas in view of Jiang (US 2025/0147987 A1) hereinafter known as Jiang.
Regarding claim 6, Thomas further teaches the method of claim 1.
Thomas further teaches:
wherein after the presenting the target table in the table interface, the method further comprises: receiving a third user input instruction through the interaction component, wherein the third user input instruction comprises data addition requirement information for the target table, and the data addition requirement information comprises data information to be added that is based on natural language; and invoking the language model based on the third user input instruction, to add the data information to be added to a … of the target table according to a field. (Thomas: col. 9, lines 41-55; Thomas teaches the user submitting a subsequent input to LLM service. Col. 13, lines 61-67 to col. 14, lines 1-26 further teaches adding data to the table.)
Thomas does not explicitly teach but Jiang teaches:
… row … (Jiang: ¶[0044]-¶[0047]; Jian teaches uses an LLM to generate text records which are stored in table. ¶[0166] further teaches that each row contains an instance of the data.)
Jiang is in the same field of endeavor as the present invention, since it is directed to using an LLM to generate table content. It would have been obvious, before the effective filing date of the claimed invention, to a person of ordinary skill in the art, to combine a method for generating tables using natural language queries and an LLM and adding column data as taught in Thomas with further adding rows as taught in Jiang. As such, it would have been obvious to one of ordinary skill in the art to modify the teachings of Thomas to include teachings of Jiang, because the combination would allow generating various text records.
Regarding claim 18, this claim recites an electronic device that performs the method of claim 6; therefore, the same rationale for rejection applies.
Claim 7 is rejected under 35 U.S.C. 103 as being unpatentable over Thomas in view of Jiang in view of Zhang (US 2018/0239748 A1) hereinafter known as Zhang.
Regarding claim 7, Thomas in view of Jiang further teaches the method of claim 6.
Thomas in view of Jiang does not explicitly teach but Zhang further teaches:
wherein the receiving a third user input instruction through the interaction component comprises: in response to a trigger operation for a cell in a row of the target table, displaying a thumbnail identifier of the interaction component in the cell; and in response to a trigger of the thumbnail identifier, displaying the interaction component, and receiving the third user input instruction through the interaction component. (Zhang: Fig. 12 and ¶[0046]; Zhang teaches displaying icon 318 adjacently to a selected cell. When a user selects this icon, the interface hides formula bar 316 and displays a configuration bar 320 filled with the text and clickable interactive parameter objects 330-338. Modifications to the text may cause pivot table to be updated accordingly.)
Zhang is in the same field of endeavor as the present invention, since it is directed to generating tables. It would have been obvious, before the effective filing date of the claimed invention, to a person of ordinary skill in the art, to combine a method for generating tables using natural language queries and an LLM and adding row data as taught in Thomas in view of Jiang with further using thumbnail identifiers to trigger operations taught in Zhang. As such, it would have been obvious to one of ordinary skill in the art to modify the teachings of Thomas and Jiang to include teachings of Zhang, because the combination would allow the user to modify the data, as suggested by Zhang: ¶[0046].
Claim 8 is rejected under 35 U.S.C. 103 as being unpatentable over Thomas in view of Zhang (US 2018/0239748 A1) hereinafter known as Zhang.
Regarding claim 8, Thomas further teaches the method of claim 1.
Thomas does not explicitly teach but Zhang teaches:
wherein the method further comprises: displaying the interaction component in response to a trigger operation on a thumbnail identifier of the interaction component that is displayed at a preset position in the table interface. (Zhang: Fig. 3 and ¶[0035]; Zhang teaches a clickable icon 318 to allow the user to being the process.)
Zhang is in the same field of endeavor as the present invention, since it is directed to generating tables. It would have been obvious, before the effective filing date of the claimed invention, to a person of ordinary skill in the art, to combine a method for generating tables using natural language queries and an LLM and adding row data as taught in Thomas in view of Jiang with further using thumbnail identifiers to trigger operations taught in Zhang. As such, it would have been obvious to one of ordinary skill in the art to modify the teachings of Thomas and Jiang to include teachings of Zhang, because the combination would allow the user to modify the data, as suggested by Zhang: ¶[0035].
Claim 9 is rejected under 35 U.S.C. 103 as being unpatentable over Thomas in view of Tan (US 2025/0077231 A1) hereinafter known as Tan
Regarding claim 9, Thomas further teaches the method of claim 1.
Thomas does not explicitly teach but Tan further teaches:
wherein during a process of invoking a language model based on the first user input instruction, to create a target table that satisfies the table creation requirement information, the method further comprises: displaying creation status prompt information and a preset operation instruction control for a current creation process in the interaction component, wherein the preset operation instruction control for the creation process comprises a retry control and/or an interruption control; and in response to a trigger operation on the retry control, stopping the current creation process, revoking the generated target table, and re-invoking the language model based on the first user input instruction, to create the target table that satisfies the table creation requirement information; or in response to a trigger operation on the interruption control, stopping the current creation process, and retaining or revoking the generated target table. (Tan: Fig. 2 and ¶[0063]-¶[0069]; Tan teaches a generated result content is a partial answer result and displaying a stop control to stop the generation of the answer result.)
Tan is analogous to the present invention, since it is reasonably pertinent to the problem faced by the inventor, i.e. interrupting a generation request. It would have been obvious, before the effective filing date of the claimed invention, to a person of ordinary skill in the art, to combine a method for generating tables using natural language queries and an LLM as taught in Thomas with further an interrupt taught in Tan. As such, it would have been obvious to one of ordinary skill in the art to modify the teachings of Thomas to include teachings of Tan, because the combination would allow the user to stop the generation, as suggested by Tan: ¶[0065].
Claims 10 and 12 are rejected under 35 U.S.C. 103 as being unpatentable over Thomas in view of Reddy (US 2024/0303424 A1) hereinafter known as Reddy.
Regarding claim 10, Thomas further teaches the method of claim 1.
Thomas does not explicitly teach but Reddy further teaches:
wherein after the presenting the target table in the table interface, the method further comprises: displaying a preset operation instruction control for the target table in the interaction component, wherein the preset operation instruction control for the target table comprises one or more of an acceptance control, a retry control, and a discard control; and in response to a trigger operation on the acceptance control, completing creation of the target table, and exiting the interaction component; in response to a trigger operation on the retry control, revoking the target table, and re-invoking the language model based on the first user input instruction, to create the target table that satisfies the table creation requirement information; or in response to a trigger operation on the discard control, revoking the target table. (Reddy: ¶[0098]; Reddy teaches adding graphical buttons that allow the user to insert the table.)
Reddy is in the same field of endeavor as the present invention, since it is directed to using an LLM to generate table content. It would have been obvious, before the effective filing date of the claimed invention, to a person of ordinary skill in the art, to combine a method for generating tables using natural language queries and an LLM and adding data as taught in Thomas with further using a preset operation to add the table taught in Reddy. As such, it would have been obvious to one of ordinary skill in the art to modify the teachings of Thomas to include teachings of Reddy, because the combination would allow the user to insert the table, as suggested by Reddy: ¶[0098].
Regarding claim 12, Thomas further teaches the method of claim 1.
Thomas does not explicitly teach but Reddy further teaches:
wherein the method further comprises: for a user input instruction that is based on natural language and is input into an input box control in the interaction component, when it is determined that the language model fails to perform processing, displaying second prompt information in the interaction component, wherein the second prompt information is used to indicate that the user input instruction fails to be processed or is used to prompt a user to input another instruction. (Reddy: ¶[0068]; Reddy teaches the LLM generating explanations in the event none of the suggestions are deemed suitable. The explanation may include suggestions for additional information which, if included with the input, may be more successful in generating a suggestion.)
Reddy is in the same field of endeavor as the present invention, since it is directed to using an LLM to generate table content. It would have been obvious, before the effective filing date of the claimed invention, to a person of ordinary skill in the art, to combine a method for generating tables using natural language queries and an LLM and adding data as taught in Thomas with further indicating the user to provide another instruction taught in Reddy. As such, it would have been obvious to one of ordinary skill in the art to modify the teachings of Thomas to include teachings of Reddy, because the combination would allow the user to insert additional information that are deemed suitable, as suggested by Reddy: ¶[0068].
Claim 11 is rejected under 35 U.S.C. 103 as being unpatentable over Thomas in view of Xu (CN 110688829 B) hereinafter known as Xu.
Regarding claim 11, Thomas further teaches the method of claim 1.
Thomas does not explicitly teach but Xu further teaches:
wherein the method further comprises: displaying first prompt information in response to a trigger operation on another area outside the interaction component, wherein the first prompt information comprises prompt information for accepting or discarding the generated target table or prompt information for interrupting a current creation process. (Xu: pg. 3, last paragraph to pg. 4, first paragraph; Xu teaches a cancel option.)
Xu is in the same field of endeavor as the present invention, since it is directed to generating tables. It would have been obvious, before the effective filing date of the claimed invention, to a person of ordinary skill in the art, to combine a method for generating tables using natural language queries and an LLM and adding data as taught in Thomas with further a cancel button taught in Xu. As such, it would have been obvious to one of ordinary skill in the art to modify the teachings of Thomas to include teachings of Xu, because the combination would allow packing up the preview page, as suggested by Xu: pg. 3, last paragraph to pg. 4, first paragraph; Xu teaches a cancel option.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to ALEX OLSHANNIKOV whose telephone number is (571)270-0667. The examiner can normally be reached M-F 9:30-6.
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, Scott Baderman can be reached at 571-272-3644. 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.
/ALEKSEY OLSHANNIKOV/Primary Examiner, Art Unit 2118
Prosecution Insights