DETAILED ACTION
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 .
This office action is in response to applicant’s amendment filed on 05/26/2026.
Claims 1-20 are pending and examined.
Response to Arguments
Applicant’s arguments filed on 05/26/2026 have been fully considered. However, they are not persuasive.
Applicant argued that Almaer does not teach the amended claim limitations of “generate a transcript including a series of steps, wherein the series of steps includes (i) at least one user step including a computer-readable input and (ii) at least one assistant step including corresponding computer-readable code generated by the LLM in response to the computer-readable input of the at least one user step, and wherein the at least one assistant step has a type that is either (a) an observation type including computer-readable code that, when executed, causes the system to observe the digital environment, or (b) an action type including computer-readable code that, when executed, causes the system to modify the digital environment”. The examiner respectfully disagrees. Almaer discloses the above (paragraph, [0066]; a LLM that receiving chat-like inputs and generating chat-like outputs (a series of steps); paragraph [0079]; storing a database, each query in association with a corresponding user request from which the query was generated (storing the steps in a database); the user request corresponds to one user step including a computer-readable input; the generated query corresponds to one assistant step including corresponding computer-readable code generated by the LLM in response to the computer-readable input of the at least one user step; paragraphs [0077]-[0078]; upon processing a data request from a user, the code generation engine may generate a query that corresponds to the data request for the endpoint, the data request can be retrieve certain resources (data objects, field values of objects), which corresponds to the at least one assistant step has a type that is either (a) an observation type including computer-readable code that, when executed, causes the system to observe the digital environment; the query executes to observe a property in the digital environment). Applicant also argued Almaer does not teach other amended claim limitations, please see the revised claim 1 rejection below.
The examiner is available for a phone interview with applicant.
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 1-6 and 8-20 are rejected under 35 U.S.C. 102(a)(2) as being anticipated by Almaer et al. (US PGPUB 2024/0362209) hereinafter Almaer.
Per claim 1, Almaer discloses a non-transitory, computer-readable storage medium comprising instructions recorded thereon, wherein the instructions, when executed by at least one data processor of a system, cause the system to (paragraph [0023]; a computer system with a processor and memory); input a series of instructions to a large language model (LLM) to generate computer-readable code for performing a plurality of tasks within a digital environment, wherein at least one of the instructions includes a context of the digital environment, and wherein the computer-readable code is executable by the data processor of the system to perform the plurality of tasks (paragraphs [0013][0030][0031]; a user enter data requests (instructions) to a LLM, the LLM generates codes/queries for performing data retrieval tasks; each data request including at least one data request parameter (context)); generate a transcript including a series of steps, wherein the series of steps includes (i) at least one user step including a computer-readable input and (ii) at least one assistant step including corresponding computer-readable code generated by the LLM in response to the computer-readable input of the at least one user step, (paragraph, [0066]; a LLM that receiving chat-like inputs and generating chat-like outputs (a series of steps); paragraph [0079]; storing a database, each query in association with a corresponding user request from which the query was generated (storing the steps in a database); the user request corresponds to one user step including a computer-readable input; the generated query corresponds to one assistant step generated by the LLM); wherein the at least one assistant step has a type that is either (a) an observation type including computer-readable code that, when executed, causes the system to observe the digital environment, or (b) an action type including computer-readable code that, when executed, causes the system to modify the digital environment (paragraphs [0077]-[0078]; upon processing a data request from a user, the code generation engine may generate a query that corresponds to the data request for the endpoint, the data request can be retrieve certain resources (data objects, field values of objects), the query (observation type) executes to observe a property in the digital environment); store, as the transcript is generated, a representation of each of a plurality of states of the transcript, wherein each state includes a portion of the transcript that corresponds to a task of the plurality of tasks; access a stored representation of a first state of the plurality of states, wherein the first state includes the at least one assistant step; and execute computer-readable code associated with the first state, using a context of the environment corresponding to the first state, to reperform a corresponding task in the digital environment, based on the type of the at least one assistant step (paragraph [0079]; storing a database, each query in association with a corresponding user request from which the query was generated (storing the steps in a database), each user request/query pair corresponds to a representation of a state of a transcript, the query corresponds to a task; the stored queries may include both accepted queries and rejected queries; paragraphs [0036]-[0040][0107]; in response to a user request, the system may return a cached query corresponding to the previous data request (i.e. accessing a stored query); the cached query is the same type of as the current user request (requesting to observe a property); an endpoint executes the query and provides a response (if execution is successful or failure); a success response includes field values (context parameters)).
Per claim 2, Almaer further discloses wherein inputting a respective instruction in the series of instructions to the LLM comprises: receiving a natural language command to perform a corresponding task; and generating the respective instruction based on the natural language command (paragraph [0031]; an LLM to automatically generate queries which may be suitable for the endpoint based on a natural language statement of a user request).
Per claim 3, Almaer further discloses wherein generating the respective instruction based on the natural language command comprises: adding a context of the digital environment corresponding to the natural language command to the respective instruction (paragraphs [0031][0023]; an LLM to automatically generate queries which may be suitable for the endpoint based on a natural language statement of a user request; the user request includes at least one request parameter (context)).
Per claim 4, Almaer further discloses wherein the stored representation of the first state includes a first natural language command and a first set of computer-readable code generated by the LLM in response to the first natural language command, and wherein the instructions when executed further cause the system to, after accessing the stored representation of the first state: (paragraphs [0036]-[0040][0107]; in response to a user request, the system may return a cached query corresponding to the previous data request (i.e. accessing a stored query); an endpoint executes the query and provides a response (if execution is successful or failure); output, for display to a user, the first natural language command; in response to receiving an input from the user to modify the first natural language command, causing the LLM to regenerate the first set of computer-readable code based on the modified first natural language command; and executing the regenerated first set of computer-readable code (Fig. 4; paragraph [0094][0105][0106]; the requesting user may then modify the generated query, incorporate the query into source code, or otherwise manipulate the code of the generated query; provides, to the LLM, a further input prompt for instructing the LLM to generate a revised query, the input prompt may include the error data associated with the generated query, that is, a representation of the error data may be inserted in an input prompt to the LLM with instructions to generate a new query corresponding to the first user request).
Per claim 5, Almaer further discloses recommends, to the user, a modification to the first natural language command (Fig. 4; paragraph [0094][0105][0106]; provides, to the LLM, a further input prompt for instructing the LLM to generate a revised query, the input prompt may include the error data associated with the generated query (i.e. providing a recommended modification to the first command)).
Per claim 6, Almaer further discloses wherein storing the representation of each of the plurality of states of the transcript comprises: storing each state of the plurality of states in a corresponding data structure (paragraphs [0041][0066]; a LLM model like ChatGPT is designed for processing natural language, receiving chat-like inputs and generating chat-like outputs (a transcript recording inputs and corresponding outputs); query may be stored, in a database, in association with an indication of the first data request; i.e. storing a pair (a state) of a data request (instruction) and a query (corresponding task) in a database).
Per claim 8, Almaer further discloses wherein the stored representation of the first state includes the context of the environment corresponding to the first state (paragraphs [0023][0041][0066]; query may be stored, in a database, in association with an indication of the first data request; i.e. storing a pair (a state) of a data request (instruction) and a query (corresponding task) in a database; each data request contains at least one request parameter (context)).
Per claim 9, Almaer further discloses wherein executing the code using the context of the environment corresponding to the first state comprises: accessing the context from a stored representation of a second state that is associated with the first state (paragraphs [0023][0041][0066]; a generated query may be stored, in a database, in association with an indication of the first data request; i.e. storing a data request (instruction) and a query (generated) in a database; paragraph 0105][0106]; provides, to the LLM, a further input prompt for instructing the LLM to generate a revised query; the input prompt (a first state) may include the error data associated with the generated query (context from a stored representation of a second state); the revised query is executed).
Per claim 10, Almaer further discloses wherein a state of the plurality of states includes an instruction and a set of computer-readable code generated by the LLM in response to the instruction. (paragraphs [0023][0041][0066]; query may be stored, in a database, in association with an indication of the first data request; i.e. storing a pair (a state) of a data request (instruction) and a query (generated code) in a database).
Per claim 11, Almaer further discloses wherein a state of the plurality of states includes an instruction, a first set of computer-readable code generated by the LLM in response to the instruction, and a second set of computer-readable code generated by the LLM based on the first set of computer-readable code (paragraphs [0023][0041][0066]; a query may be stored, in a database, in association with an indication of the first data request; i.e. storing a data request (instruction) and a query (generated) in a database; paragraph 0105][0106]; provides, to the LLM, a further input prompt for instructing the LLM to generate a revised query (a second set of computer-readable code generated by the LLM based on the first set of computer-readable code); the input prompt may include the error data associated with the generated query; the revised query and input prompt is also saved in the database).
Claims 11-16 recite similar limitations as claims 1-5. Therefore, claims 11-16 are rejected under similar rationales as claims 1-5.
Claims 17-20 recite similar limitations as claims 1-4. Therefore, claims 17-20 are rejected under similar rationales as claims 1-4.
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.
Claim 7 is rejected under 35 U.S.C. 103 as being unpatentable over Almaer, in view of
Tan et al. (US PGPUB 2006/0184556) hereinafter Tan.
Per claim 7, Almaer discloses storing the representation of each of the plurality of states of the transcript in a database, but does not teach generating a compressed representation of each of the plurality of states; and storing the compressed representation of each of the plurality of states in a corresponding data structure. However, storing data in database in a compressed format is well known concept in the field of the art, as evidenced in Tan (paragraph [0008]). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine Almaer and Tan to store representation of each of the plurality of states in a compressed format in a database, in order to save storage space.
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). 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.
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure. See PTO-892 form.
Yang et al. (US PGPUB 2022/0103491) disclose a conversation engine performs conversations with users using chatbots customized for performing a set of tasks that can be performed using an online system. A state manager stores a data structure storing a set of state variables, each state variable tracking an attribute of the conversation. An attribute may represent the type of task being currently processed in the conversation. The state manager may store an array of state variables as representation of the state of a chatbot.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to HANG PAN whose telephone number is (571)270-7667. The examiner can normally be reached 9 AM to 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, Chat Do can be reached at 571-272-3721. 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.
/HANG PAN/Primary Examiner, Art Unit 2193
Prosecution Insights