DETAILED ACTION
Notice of Pre-AIA or AIA Status
1. 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 § 112
2. The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
3. Claims 4-5, 11-12, 18-19 are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor, or for pre-AIA the applicant regards as the invention.
Claim 4 recites
“4. The system of claim 1, wherein the machine-readable instructions further cause the computing device to at least:
generate a classifier neutral network model that is trained for identifying a respect prompt that is similar to the based at least in part on a training data generated for the prompt template.”
It seems something is missed after “the”. It is not clear what “identifying a respect prompt that is similar to”?
Claim 5 depends on Claim 4. Thus, Claim 5 is rejected as the same ground as Claim 4 by virtue of its dependency.
Claims 11 and 18 have the same issue as Claim 4. Claim 12 depends on Claim 11. Thus, Claim 12 is rejected as the same ground as Claim 11. Claim 19 depends on Claim 18. Thus, Claim 19 is rejected as the same ground as Claim 18.
Claim Rejections - 35 USC § 101
4. 35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
5. Claims 1-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to a judicial exception (i.e., a law of nature, a natural phenomenon, or an abstract idea) without significantly more.
Claim 1 recites
“1. A system, comprising:
a computing device comprising a processor and a memory; and
machine-readable instructions stored in the memory that, when executed by the processor, cause the computing device to at least:
identify a prompt that has been submitted by a client device for a large language model (LLM) service;
determine that the prompt fails to match an existing prompt template;
determine that the prompt and an unidentified prompt meet a similarity threshold based at least in part on a common prompt component shared between the prompt and the unidentified prompt; and
generate a prompt template for the LLM service based at least in part on the prompt and the unidentified prompt meeting the similarity threshold, the prompt template comprising the common prompt component and a placeholder.”
The limitations recited in the independent claims as drafted covers a mental process. The underlying abstract idea revolved around what happen once a human identifies that a prompt has been submitted, the human compares the submitted prompt with a list of existing prompt template and determines that the submitted prompt fails to match with any prompt in the list of the existing prompt template. Next, the human determines that the submitted prompt meet a similarity threshold with an unidentified prompt, the human could create a prompt template based on the unidentified prompt by reuse the common prompt component in the unidentified prompt.
The judicial exception is not integrated into a practical application. In particular, claims recite the additional limitations of “a computing device”, “a processor”, “a memory”, and “a non-transitory, computer-readable medium”. The additional element(s) or combination of elements such as a computing device, a processor, a memory and a non-transitory computer-readable medium in the claim(s) other than the abstract idea per se amount(s) to no more than (i) mere instructions to implement the idea on a computer, and/or (ii) recitation of generic computer structure that serves to perform generic computer functions that are well-understood, routine, and conventional activities previously known to the pertinent industry. Viewed as a whole, these additional claim element(s) do not provide meaningful limitation(s) to transform the abstract idea into a patent eligible application of the abstract idea such that the claim(s) amounts to significantly more than the abstract idea itself. Therefore, the claim(s) are rejected under 35 U.S.C. 101 as being directed to non-statutory subject matter. There is further no improvement to the computing device other than reuse the common prompt component in the unidentified prompt to generate a prompt template when a submitted prompt fails to match an existing prompt template. The mere recitation of a computing device, a processor, a memory and a non-transitory computer-readable medium and/or the like is akin of adding the word “apply it” and/or “use it” with a computer in conjunction with the abstract idea. The paragraph [0041] of the specification discloses “[0041] The client device 206 can be representative of a plurality of client devices that can be coupled to the network 212. The client device 206 can include a processor-based system such as a computer system. Such a computer system can be embodied in the form of a personal computer (e.g., a desktop computer, a laptop computer, or similar device), a mobile computing device (e.g., personal digital assistants, cellular telephones, smartphones, web pads, tablet computer systems, music players, portable game consoles, electronic book readers, and similar devices), media playback devices (e.g., media streaming devices, Blu-ray® players, digital video disc (DVD) players, set-top boxes, and similar devices), a videogame console, or other devices with like capability. The client device 206 can include one or more displays, such as liquid crystal displays (LCDs), gas plasma-based flat panel displays, organic light emitting diode (OLED) displays, electrophoretic ink (“E-ink”) displays, projectors, or other types of display devices. In some instances, the display can be a component of the client device 206 or can be connected to the client device 206 through a wired or wireless connection.”
As filed in the specification, the computer is listed as a general-purpose computer and are mainly used as an application thereof. Accordingly, these additional elements do not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea.
The claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception. As discussed above with respect to the integration of the abstract idea into a practical application, the additional element of using a computer is noted as a general computer. Mere instructions to apply an exception using a generic computer component cannot provide an inventive concept. The claims are not patent eligible.
The dependent claims further do not remedy the issues noted above. More specifically, Claims 2, 9 and 16 recites transmit the prompt to a classifier service. Receiving or transmitting data over a network, e.g., using the Internet to gather data, Symantec, 838 F.3d at 1321, 120 USPQ2d at 1362; Claims that amount to nothing more than an instruction to apply the abstract idea using a generic computer do not render an abstract idea eligible. Alice Corp., 573 U.S. at 223, 110 USPQ2d at 1983; Use of a computer or other machinery in its ordinary capacity for economic or other tasks. Affinity Labs v. DirecTV, 838 F.3d 1253, 1262, 120 USPQ2d 1201, 1207 (Fed. Cir. 2016) (cellular telephone); TLI Communications LLC v. AV Auto, LLC, 823 F.3d 607, 613, 118 USPQ2d 1744, 1748 (Fed. Cir. 2016) (computer server and telephone unit); Selecting information, based on types of information and availability of information in a power-grid environment, for collection, analysis and display, Electric Power Group, LLC v. Alstom S.A. 830 F.3d 1350, 1354-55, 119 USPQ2d 1739, 1742 (Fed. Cir. 2016). Claims 3, 10 and 17 recite generating training data by providing the prompt template to a sample generator LLM service. “a sample generator LLM service” is used to generating training data and do not include any details about how the “generating” is accomplished. See MPEP 2106.05(f). Claims 4, 11 and 18 recite generating a classifier neutral network model. There are no technical details on how the classifier neutral model is generated. Claims 5, 12 and 19 recites a mental process of adding the classifier neutral network model to a classifier service. Claims 6, 13 and 20 merely recites what kinds of the common prompt component. Claims 7 and 14 recites a mental process of receiving the prompt from an artificial intelligence.
For at least the supra provided reasons, claims 1-20 are rejected under 35 U.S.C. 101 as being directed to non-statutory subject matter.
Allowable Subject Matter
6. Claims 1-20 are allowed in view of the prior art of record. However, claims 1-20 are rejected under 101 abstract idea and claims 4-5, 11-12 and 18-19 are rejected under 112(b), for the application to pass to allowance these rejections need to be overcome. Any amendments to overcome the 101 and 112(b) rejections that results in any change in scope require further search and/or consideration in order to determine it allowability.
The following is a statement of reasons for the indication of allowable subject matter: the prior art(s) taken alone or in combination fail(s) to teach the following element(s) in combination with the other recited elements in the claim(s).
“determine that the prompt fails to match an existing prompt template;
determine that the prompt and an unidentified prompt meet a similarity threshold based at least in part on a common prompt component shared between the prompt and the unidentified prompt; and
generate a prompt template for the LLM service based at least in part on the prompt and the unidentified prompt meeting the similarity threshold, the prompt template comprising the common prompt component and a placeholder.” as recited in Claim 1.
Claims 8 and 15 recites the similar features as Claim 1.
The closest prior art found as following.
a. Subramanian et al. (US 12, 645,729 B1.) In this reference, Subramanian et al. disclose techniques for prompt template optimization with large language model (Subramanian et al. col. 5 lines 25-59) Users can interact with the prompt template optimization service 112 in various ways, generally via an interface 122 (e.g., an API). As illustrated, interface 122 can support prompt template optimization requests 110 from a client 102 or a service console 106. In some examples, the client 102 can be implemented as a remote application that embeds a service software development kit (SDK) 104, which is adapted to send prompt optimization requests 110 to the interface 122. In some examples, the service console 106 can be provided to users through a web-based interface accessed via a web browser allowing users to submit prompt template optimization requests 110 to the interface 122. Whether the client 102 or service console 106, the user interface can be a command line interface (CLI), a graphical user interface (GUI), a GUI with an integrated CLI, etc. In the illustrated example, the prompt template optimization service 112 includes a job manager 130. The job manager 130 manages jobs corresponding to individual prompt template optimization requests. In some examples, the job manager 130 may hide certain details of an optimization run from clients such as the underlying compute resources used in processing the request. However, in some examples, the client may have control over the type of compute resource used to run a job (e.g., selection a virtual machine or container, the performance specifications associated with the selection, etc.). The prompt template optimization service 112 is typically a multi-tenant service that is used by many clients at the same time, and individual prompt optimization jobs are isolated from one another in separate execution environments. In some examples, the prompt template optimization service 112 does not return an immediate solution to a prompt template optimization request 110. Rather, the service will schedule the job for execution, and an asynchronous notification is provided to the client when a job is completed.) In this reference, Subramanian et al. allows a user to customize the optimizer’s workflow by selecting various functions to control the processing of different stages of the workflows. The placeholder in the prompt template is updated based on the user’s selecting various functions. The updated prompt template includes the common prompt component and the updated placeholder. However, Subramanian et al. does not compare a submitted prompt with an initial prompt template stored in the database. Subramanian et al. does not generate a prompt template based on the initial prompt template by update the placeholder in the initial prompt template in response to determining that the submitted prompt and the initial prompt template meeting the similarity threshold. Thus, Subramanian et al. fail to teach and/or suggest the allowable subject matter.
b. Khan et al. (US 2026/0080185 A1.) In this reference, Khan et al. discloses techniques for creating custom prompt templates (Khan et al. [0058] FIG. 4D illustrates an exemplary UI form for creating custom prompt templates to be utilized in the prompt generator system. The UI form allows a business or user to generator a reusable prompt template that can be associated with any actionable field type across multiple different platforms. In some aspects, the custom prompt template may include descriptors for the prompt template including, but not limited to, the prompt (or field) type 420, prompt template name 422, and the API name 424. The UI form further provides capabilities to add a plurality of external data references. Each external data reference may have a label 428, API name 430, and object 432. In aspects, object 432 is an object reference to a method that calls the contextual database. Once the custom prompt template is completed, a business can add it to the prompt template library and integrate it in actionable fields across multiple business platforms. For example, a prompt template may be embedded into a plurality of actionable fields across a plurality of interfaces, invocable actions, and generative AI chatbots.) In this reference, Khan et al. allows the user to enter the description into the box to create the custom prompt template. However, Khan et al. does not compare a submitted prompt with an unidentified prompt template. Khan et al. does not generate a prompt template based on the unidentified prompt template by using the common prompt component in the unidentified prompt template in response to determining that the submitted prompt and the unidentified prompt template meeting the similarity threshold. Thus, Khan et al. fail to teach and/or suggest the allowable subject matter.
c. Safavi et al. (US 2025/0094714 A1.) In this reference, Safavi et al. disclose techniques for generate a structured prompt template (Safavi et al. [0045] Subsequently, at operation 214, the dialogue tracking tool 150 generates the structured prompt template for the state prediction model based on labeling instructions, the structured valid state list, and the turn-by-turn structured dialogue. It should be appreciated that the structured prompt template does not include any example input-output pairs (e.g., zero-shot). For example, as illustrated in FIG. 4, the structured prompt template may be generated by appending the turn-by-turn structured dialogue to the structured valid state list and the labeling instructions. In an example shown in FIG. 4, the structured prompt template is in a hierarchical XML-structured format, which is human-readable and flexible while still being highly structured. The structured prompt template is inputted to the state prediction model (e.g., GPT4), which provide a structured output representation. The structured input and output representation helps provide coherence and consistency to the inputs and outputs, allowing the state prediction model to accurately determine and tag the conversation state.) In this reference, Safavi et al. generates the structured prompt template by appending the turn-by-turn structured dialogue to the structured valid state list and the labeling instructions. However, Safavi et al. does not compare a submitted prompt with an unidentified prompt template. Safavi et al. does not generate a prompt template based on the unidentified prompt template by using the common prompt component in the unidentified prompt template in response to determining that the submitted prompt and the unidentified prompt template meeting the similarity threshold. Thus, Safavi et al. fail to teach and/or suggest the allowable subject matter.
Conclusion
7. The prior art made of record and not relied upon is considered pertinent to applicant’s disclosure. See PTO-892.
a. Telkar et al. (US 2026/0093574 A1.) In this reference, Telkar et al. disclose techniques for generating a prompt based on a prompt template.
b. Kurian et al. (US 2025/0245216 A1.) In this reference, Kurian et al. disclose techniques for generating prompts based on a prompt template.
c. Gan et al. (US 2026/0087363 A1.) In this reference, Gan et al. disclose techniques for generating a response based on the generator prompt template.
8. Any inquiry concerning this communication or earlier communications from the examiner should be directed to THUYKHANH LE whose telephone number is (571)272-6429. The examiner can normally be reached Mon-Fri: 9am-5pm.
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 C. 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. 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.
/THUYKHANH LE/Primary Examiner, Art Unit 2655
Prosecution Insights