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 .
Claims 1-20 are pending and have been examined.
Claim Rejections - 35 USC § 101
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.
Claims 1-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
Regarding claim 1 and 14 the limitations of “obtaining a first prompt from a user; obtaining a first response to the first prompt, the first response generated by the language model; transmitting a second prompt from the user to the language model via an electronic communication interface; receiving, via the electronic communication interface, a second response to the second prompt from the language model; comparing the first prompt to the second prompt; comparing the first response to the second response; providing, on a display coupled to the computing device, a first prompt change record representing changes between the first prompt and the second prompt; and providing, on the display, a first response change record representing changes between the first response and the second response”, as drafted, are processes that, under broadest reasonable interpretation, covers performance of the limitation in the mind but for the recitation of generic computer components. More specifically, the mental process of a human thinking of a question and its response, thinking of another question and its response, and providing a comparison of the question and responses on paper using a pen or pencil. If a claim limitation, under its broadest reasonable interpretation, covers performance of the limitation in the mind but for the recitation of generic computer components, then it falls within the --Mental Processes-- grouping of abstract ideas. Accordingly, the claims recite an abstract idea.
Regarding claim 20 the limitations of “obtaining a first prompt; obtaining a first response to the first prompt, the first response generated using the language model; receiving a second prompt from a remote computing device via an electronic communication interface; generating a second response to the second prompt using the language model; comparing the first prompt to the second prompt; comparing the first response to the second response; transmitting, to the remote computing device via the electronic communication interface, a first prompt change record representing changes between the first prompt and the second prompt; and transmitting, to the remote computing device via the electronic communication interface, a first response change record representing changes between the first response and the second response”, as drafted, are processes that, under broadest reasonable interpretation, covers performance of the limitation in the mind but for the recitation of generic computer components. More specifically, the mental process of a human thinking of a question and its response, thinking of another question and its response, and providing a comparison of the question and responses on paper using a pen or pencil. If a claim limitation, under its broadest reasonable interpretation, covers performance of the limitation in the mind but for the recitation of generic computer components, then it falls within the --Mental Processes-- grouping of abstract ideas. Accordingly, the claims recite an abstract idea.
This judicial exception is not integrated into a practical application because the recitation of a system in claim 4 reads to generalized computer components, based upon the claim interpretation wherein the structure is interpreted using P0067-P0070 in the specification. 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 are directed to an 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 generalized computer components and a language model to think of a question and its response, think of another question and its response, and provide a comparison of the question and responses on paper using a pen or pencil. Mere instructions to apply an exception using a generic computer component cannot provide an inventive concept. The claims are not patent eligible.
With respect to claim 2 and 15, the claim recites “wherein the first prompt change record displays additions to the second prompt not present in the first prompt, and displays portions of the first prompt which are not present in the second prompt”, which reads on a human providing a comparison of the question and responses on paper using a pen or pencil. No additional limitations are present.
With respect to claim 3 and 16, the claim recites “wherein the additions to the second prompt not present in the first prompt are depicted underlined, and wherein the portions of the first prompt which are not present in the second prompt are depicted struck through”, which reads on a human providing a comparison of the question and responses on paper using a pen or pencil. No additional limitations are present.
With respect to claim 4 and 17, the claim recites “wherein the additions to the second prompt not present in the first prompt are depicted in a first color, and wherein the portions of the first prompt which are not present in the second prompt are depicted in a second color different from the first color”, which reads on a human providing a comparison of the question and responses on paper using a pen or pencil. No additional limitations are present.
With respect to claim 5 and 18, the claim recites “after receiving the second response, transmitting a third prompt to the language model via the electronic communication interface; receiving a third response to the third prompt from the language model via the electronic communication interface; comparing the third prompt to the second prompt; comparing the third response to the second response; providing, on the display, a second prompt change record representing changes between the second prompt and the third prompt; and providing, on the display, a second response change record representing changes between the second response and the third response”, which reads on a human thinking of another question and its response, and provide a comparison of the question and responses on paper using a pen or pencil. No additional limitations are present.
With respect to claim 6, the claim recites “receiving a request from the user to save the second prompt and the second response for comparison with subsequently received prompts and subsequently generated responses, and in response to receiving the request, storing the second prompt and the second response in a memory coupled to the computing device”, which reads on a human writing question and responses on paper. No additional limitations are present.
With respect to claim 7, the claim recites “wherein transmitting the second prompt comprises indicating one or more first contexts associated with the second prompt, wherein the second response is generated based at least in part on the one or more first contexts”, which reads on a human thinking of an answer to the question from the context of the question. No additional limitations are present.
With respect to claim 8, the claim recites “wherein the one or more first contexts indicate at least a region associated with the second prompt”, which reads on a human thinking of an answer to the question from the context region of the question. No additional limitations are present.
With respect to claim 9, the claim recites “wherein the one or more first contexts comprise at least a voice or a tone desired for the second response”, which reads on a human thinking of an answer to the question utilizing a desired tone. No additional limitations are present.
With respect to claim 10, the claim recites “wherein obtaining the first prompt comprises receiving the first prompt from the user, and wherein obtaining the first response comprises transmitting the first prompt to the language model via the electronic communication interface and receiving the first response via the electronic communication interface”, which reads on a human thinking of an answer to the question by utilizing a set of rules or instructions. No additional limitations are present.
With respect to claim 11 and 19, the claim recites “wherein obtaining the first prompt comprises receiving a selection of the first prompt from the user via an interface presented on the display and retrieving the first prompt from a memory coupled to the computing device, and wherein obtaining the first response comprises retrieving the first response from the memory”, which reads on a human reading a first question. No additional limitations are present.
With respect to claim 12, the claim recites “wherein the interface presented on the display comprises a plurality of selectable prompts, wherein each selectable prompt of the plurality of selectable prompts comprises a previously submitted prompt associated with a corresponding response previously generated by the language model”, which reads on a human providing questions and answers on paper. No additional limitations are present.
With respect to claim 13, the claim recites “before transmitting the second prompt, providing the first prompt and the first response on the display”, which reads on a human providing the first question and answer on paper using a pen or pencil. No additional limitations are present.
These claims further do not remedy the judicial exception being integrated into a practical application and further fail to include additional elements that are sufficient to amount to significantly more than the judicial exception.
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 1-20 are rejected under 35 U.S.C. 103 as being unpatentable over Callegari et al. (U.S. PG Pub No. 20240362422), hereinafter Callegari, in view of Zernik (U.S. PG Pub No. 20050010863).
Regarding claim 1 and 14 Callegari teaches:
(Claim 1) A computer-implemented method for the design and iteration of prompts submitted to a text-to-text language model (language model), the method performed by a computing device coupled to the language model and comprising: (P0022, FIG. 2 illustrates the assessment and revision shown in FIGS. 1A-1C performed for 1 through N iterations, to thereby generate corresponding generation 1 through generation N responses. As shown, the first iteration includes a first response generation stage, a response assessment stage, and a prompt revision stage, and the remaining iterations (here, second iteration is shown) repeat these stages as the revised response generation stage, response assessment stage, and prompt revision stage, until the Nth iteration in which a final response (generation N) is output in response to a final input.)
(Claim 14) A system for the design and iteration of prompts submitted to a text-to-text language model (language model), the system comprising: one or more processors; and a memory storing instructions that, when executed by the one or more processors, causes the system to perform operations comprising: (P0075, Computing system may embody the computing system 10, 110, 210 described above and illustrated in FIGS. 1A-1C.; P0022, FIG. 2 illustrates the assessment and revision shown in FIGS. 1A-1C performed for 1 through N iterations, to thereby generate corresponding generation 1 through generation N responses. As shown, the first iteration includes a first response generation stage, a response assessment stage, and a prompt revision stage, and the remaining iterations (here, second iteration is shown) repeat these stages as the revised response generation stage, response assessment stage, and prompt revision stage, until the Nth iteration in which a final response (generation N) is output in response to a final input.)
obtaining a first prompt from a user; (P0018, Receive, via the prompt interface (in some implementations, the prompt interface API), a prompt from the user including an instruction for the LLM to generate an output.)
obtaining a first response to the first prompt, the first response generated by the language model; (P0018, The LLM may be configured to receive the prompt and produce a first response.)
transmitting a second prompt from the user to the language model via an electronic communication interface; (P0018, The first response may be output to the user, who may also optionally request revision if not satisfied with the first response.; P0029, The user may manually submit the revised prompt in an effort to improve on the first response.)
receiving, via the electronic communication interface, a second response to the second prompt from the language model; (P0023, To provide a response revision instruction to the LLM to generate the revised response (which may be output as the generation response) based on the revised prompt.)
comparing the first prompt to the second prompt; comparing the first response to the second response; (Fig. 7, Prompt and Revised Prompt.; P0018, If the user is not satisfied with the next response generated based on the revised prompt … revision is repeated for at least another iteration … if the current response is acceptable by either the user or predefined criteria, then the revised response is output to the user.)
providing, on a display coupled to the computing device, a first prompt change record representing changes between the first prompt and the second prompt; and (Fig. 7, Prompt and Revised Prompt.; P0031, A prompt evolution settings interface is provided. It will be appreciated that the least one processor can be further configured to cause a prompt revision element to be displayed, and in response to user input selecting the prompt revision element, outputting the revised prompt to the user. In the prompt evolution settings interface, a selector is presented by which a user can provide user input indicating whether prompts should be refined, which serves as the prompt revision element, and can indicate using an input field a user-specified number of iterations for assessment and revision, if desired.)
providing, on the display, a first response change record representing changes between the first response and the second response. (Fig. 7, Response and Revised Response.; P0031, A prompt evolution settings interface is provided. It will be appreciated that the least one processor can be further configured to cause a prompt revision element to be displayed, and in response to user input selecting the prompt revision element, outputting the revised prompt to the user. In the prompt evolution settings interface, a selector is presented by which a user can provide user input indicating whether prompts should be refined, which serves as the prompt revision element, and can indicate using an input field a user-specified number of iterations for assessment and revision, if desired.)
Callegari does not specifically teach:
comparing the first prompt to the second prompt; comparing the first response to the second response;
providing, on a display coupled to the computing device, a first prompt change record representing changes between the first prompt and the second prompt; and
providing, on the display, a first response change record representing changes between the first response and the second response.
Zernik, however, teaches:
comparing the first prompt to the second prompt; comparing the first response to the second response; (P0014, Visual mapping and comparison of the documents. At least one subsection of the first document is juxtaposed relative to an output of a corresponding at least one subsection of the second document to visually emphasize a comparison therebetween. Differences established on a word-by-word basis between the outputted first and second document subsections are highlighted with difference highlighting, and similarities established on a word-by-word basis between the outputted first and second document subsections are highlighted with similarity highlighting different from the difference highlighting.)
providing, on a display coupled to the computing device, a first prompt change record representing changes between the first prompt and the second prompt; and (P0015, At least two selected ones of the document subsections are juxtaposed relative to one another, to visually emphasize correspondences therebetween, in response to comparison selecting the selected document subsections for comparison with one another. Differences identified among the selected document subsections are highlighted with difference highlighting, and similarities identified among the selected document subsections are highlighted with similarity highlighting different from the difference highlighting.)
providing, on the display, a first response change record representing changes between the first response and the second response. (P0015, At least two selected ones of the document subsections are juxtaposed relative to one another, to visually emphasize correspondences therebetween, in response to comparison selecting the selected document subsections for comparison with one another. Differences identified among the selected document subsections are highlighted with difference highlighting, and similarities identified among the selected document subsections are highlighted with similarity highlighting different from the difference highlighting.)
It would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to compare changes in prompt and response. It would have been obvious to combine the references because comparison has to be made to pinpoint similarities and differences in two different versions before a decision can be made by a professional. Zernik P0002.
Regarding claim 2 and 15 Callegari in view of Zernik teach claim 1 and 14.
Callegari does not specifically teach:
wherein the first prompt change record displays additions to the second prompt not present in the first prompt, and displays portions of the first prompt which are not present in the second prompt.
Zernik, however, teaches:
wherein the first prompt change record displays additions to the second prompt not present in the first prompt, and displays portions of the first prompt which are not present in the second prompt. (P0014, Visual mapping and comparison of the documents. At least one subsection of the first document is juxtaposed relative to an output of a corresponding at least one subsection of the second document to visually emphasize a comparison therebetween. Differences established on a word-by-word basis between the outputted first and second document subsections are highlighted with difference highlighting, and similarities established on a word-by-word basis between the outputted first and second document subsections are highlighted with similarity highlighting different from the difference highlighting.)
It would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to display changes in prompt. It would have been obvious to combine the references because comparison has to be made to pinpoint similarities and differences in two different versions before a decision can be made by a professional. Zernik P0002.
Regarding claim 3 and 16 Callegari in view of Zernik teach claim 2 and 15.
Callegari does not specifically teach:
wherein the additions to the second prompt not present in the first prompt are depicted underlined, and wherein the portions of the first prompt which are not present in the second prompt are depicted struck through.
Zernik, however, teaches:
wherein the additions to the second prompt not present in the first prompt are depicted underlined, and wherein the portions of the first prompt which are not present in the second prompt are depicted struck through. (P0003, The most familiar method used to compare documents is the so-called “underline strikeout” method, such as is employed in the widely-used Microsoft® Word program. In this method, a first document is compared to a second document, and those words or phrases that are deleted in going from the first document to the second document are highlighted with a “strikeout” indicator on a computerized output device, while those that are added from the first to the second document are highlighted with an “underline” indicator on the output device.)
It would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to display changes in prompt. It would have been obvious to combine the references because comparison has to be made to pinpoint similarities and differences in two different versions before a decision can be made by a professional. Zernik P0002.
Regarding claim 4 and 17 Callegari in view of Zernik teach claim 2 and 15.
Callegari does not specifically teach:
wherein the additions to the second prompt not present in the first prompt are depicted in a first color, and wherein the portions of the first prompt which are not present in the second prompt are depicted in a second color different from the first color.
Zernik, however, teaches:
wherein the additions to the second prompt not present in the first prompt are depicted in a first color, and wherein the portions of the first prompt which are not present in the second prompt are depicted in a second color different from the first color. (P0080, The overall highlighting scheme chosen for a given implementation of this invention can take the form of what is shown as an example here (i.e., rectangles around differences, nothing for similarities, and underlines for actively selected similarities), or any other form obvious to someone of ordinary skill. Thus, such highlighting schemes can involve outputting different fonts, different colors, different word cases, different emphasis (e.g., bold, italic, underlines, superscripts, subscripts, flashing text, etc.), and any other sort of output differences.)
It would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to display changes in prompt. It would have been obvious to combine the references because comparison has to be made to pinpoint similarities and differences in two different versions before a decision can be made by a professional. Zernik P0002.
Regarding claim 5 and 18 Callegari in view of Zernik teach claim 1 and 14.
Callegari further teaches:
after receiving the second response, transmitting a third prompt to the language model via the electronic communication interface; (P0022, FIG. 2 illustrates the assessment and revision shown in FIGS. 1A-1C performed for 1 through N iterations, to thereby generate corresponding generation 1 through generation N responses.)
receiving a third response to the third prompt from the language model via the electronic communication interface; (P0023, To provide a response revision instruction to the LLM to generate the revised response (which may be output as the generation response) based on the revised prompt.)
comparing the third prompt to the second prompt; comparing the third response to the second response; (Fig. 7, Prompt and Revised Prompt.; P0018, If the user is not satisfied with the next response generated based on the revised prompt … revision is repeated for at least another iteration … if the current response is acceptable by either the user or predefined criteria, then the revised response is output to the user.)
providing, on the display, a second prompt change record representing changes between the second prompt and the third prompt; and
providing, on the display, a second response change record representing changes between the second response and the third response.
Callegari does not specifically teach:
comparing the third prompt to the second prompt; comparing the third response to the second response;
providing, on the display, a second prompt change record representing changes between the second prompt and the third prompt; and
providing, on the display, a second response change record representing changes between the second response and the third response.
Zernik, however, teaches:
comparing the third prompt to the second prompt; comparing the third response to the second response; (P0014, Visual mapping and comparison of the documents. At least one subsection of the first document is juxtaposed relative to an output of a corresponding at least one subsection of the second document to visually emphasize a comparison therebetween. Differences established on a word-by-word basis between the outputted first and second document subsections are highlighted with difference highlighting, and similarities established on a word-by-word basis between the outputted first and second document subsections are highlighted with similarity highlighting different from the difference highlighting.)
providing, on the display, a second prompt change record representing changes between the second prompt and the third prompt; and (P0015, At least two selected ones of the document subsections are juxtaposed relative to one another, to visually emphasize correspondences therebetween, in response to comparison selecting the selected document subsections for comparison with one another. Differences identified among the selected document subsections are highlighted with difference highlighting, and similarities identified among the selected document subsections are highlighted with similarity highlighting different from the difference highlighting.)
providing, on the display, a second response change record representing changes between the second response and the third response. (P0015, At least two selected ones of the document subsections are juxtaposed relative to one another, to visually emphasize correspondences therebetween, in response to comparison selecting the selected document subsections for comparison with one another. Differences identified among the selected document subsections are highlighted with difference highlighting, and similarities identified among the selected document subsections are highlighted with similarity highlighting different from the difference highlighting.)
It would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to compare changes in prompt and response. It would have been obvious to combine the references because comparison has to be made to pinpoint similarities and differences in two different versions before a decision can be made by a professional. Zernik P0002.
Regarding claim 6 Callegari in view of Zernik teach claim 1.
Callegari further teaches:
receiving a request from the user to save the second prompt and the second response for comparison with subsequently received prompts and subsequently generated responses, and in response to receiving the request, storing the second prompt and the second response in a memory coupled to the computing device. (P0033, User gating, which are places where user input is requested before the prompt generation proceeds to the next stage. In response to the inputted prompt, the LLM is configured, according to the prompt evolution settings, to display the response having response text, along with a gating control, which asks the user “Would you like to assess this response and revise your prompt?” or similar wording. YES and NO selectors, are displayed, by which the user can input a command to stop or proceed with revision.; Fig. 7, Example of prompt and response iteration.)
Regarding claim 7 Callegari in view of Zernik teach claim 1.
Callegari further teaches:
wherein transmitting the second prompt comprises indicating one or more first contexts associated with the second prompt, wherein the second response is generated based at least in part on the one or more first contexts. (P0026, The prompt is passed to the embeddings module. … A tokenizer is provided to convert the context text to context text embeddings. … Prompt input vector and are fed as the first input to the LLM. In response to the first input, the LLM generates the first response.)
Regarding claim 8 Callegari in view of Zernik teach claim 7.
Callegari further teaches:
wherein the one or more first contexts indicate at least a region associated with the second prompt. (P0026, The prompt is passed to the embeddings module. … A tokenizer is provided to convert the context text to context text embeddings. … Prompt input vector and are fed as the first input to the LLM. In response to the first input, the LLM generates the first response.)
Regarding claim 9 Callegari in view of Zernik teach claim 7.
Callegari further teaches:
wherein the one or more first contexts comprise at least a voice or a tone desired for the second response. (P0027, The assessment and revision engine of the prompt generation module is configured to generate a text instruction including an assessment instruction to assess the response. It will be appreciated that the text instruction may be user-inputted via the prompt interface. The response and the assessment instruction are each passed through the tokenizer to produce respective response text embeddings and assessment instruction text embeddings, which are in turn concatenated along with the prior prompt input vector to form the concatenated prompt input vector for the response assessment stage. The concatenated prompt input vector for the response assessment stage is fed to the LLM to thereby generate a response including the assessment report, which can include contents such as discussed above.; P0032, The user has also inputted the same text instruction which will be used by the LLM as control input (see FIG. 3). It will be appreciated that many LLMs are configured to utilize grounding inputs and control inputs during training, for example, using different attention mechanisms and/or different loss terms for each, to thereby tune the models to generate a response that is responsive to the text instruction (control input) and written in a style or manner that takes into account the information in the context (grounding input).)
Regarding claim 10 Callegari in view of Zernik teach claim 1.
Callegari further teaches:
wherein obtaining the first prompt comprises receiving the first prompt from the user, and wherein obtaining the first response comprises transmitting the first prompt to the language model via the electronic communication interface and receiving the first response via the electronic communication interface. (P0017, The prompt interface may be a portion of a graphical user interface (GUI) for accepting user input and presenting information to a user.; P0018, Receive, via the prompt interface (in some implementations, the prompt interface API), a prompt from the user including an instruction for the LLM to generate an output. … The LLM may be configured to receive the prompt and produce a first response.; P0019, The client computing device may be responsible for communicating between the user operating the client computing device and the server computing device which executes the LLM program and contains the LLM, via an application programming interface (API) of the LLM program.)
Regarding claim 11 and 19 Callegari in view of Zernik teach claim 1 and 14.
Callegari further teaches:
wherein obtaining the first prompt comprises receiving a selection of the first prompt from the user via an interface presented on the display and retrieving the first prompt from a memory coupled to the computing device, and wherein obtaining the first response comprises retrieving the first response from the memory. (P0017, The prompt interface may be a portion of a graphical user interface (GUI) for accepting user input and presenting information to a user.; P0018, Receive, via the prompt interface (in some implementations, the prompt interface API), a prompt from the user including an instruction for the LLM to generate an output. … The LLM may be configured to receive the prompt and produce a first response.; P0019, The client computing device may be responsible for communicating between the user operating the client computing device and the server computing device which executes the LLM program and contains the LLM, via an application programming interface (API) of the LLM program.; P0017, The computing system includes a computing device having at least one processor, memory, and storage device,; P0026, The first response is passed back to the prompt generation module, where it may be displayed or otherwise presented to the user, or simply held in memory for background processing.)
Regarding claim 12 Callegari in view of Zernik teach claim 11.
Callegari further teaches:
wherein the interface presented on the display comprises a plurality of selectable prompts, wherein each selectable prompt of the plurality of selectable prompts comprises a previously submitted prompt associated with a corresponding response previously generated by the language model. (Fig. 7, Display of intermediate prompts and responses. User can scroll, view, and choose prompts.)
Regarding claim 13 Callegari in view of Zernik teach claim 1.
Callegari further teaches:
before transmitting the second prompt, providing the first prompt and the first response on the display. (Fig. 7, First prompt and first response displayed and asking user if they would like to revise the prompt in the next iteration.; P0025, The prompt generation module is configured to present the prompt interface that is displayed in the GUI, and to receive input data from the user that forms the prompt.; P0026, The LLM generates the first response. The first response is passed back to the prompt generation module, where it may be displayed or otherwise presented to the user.)
Regarding claim 20 Callegari teaches:
A computer-implemented method for the design and iteration of prompts submitted to a text-to-text language model(language model), the method performed by a computing device coupled to the language model and comprising: (P0022, FIG. 2 illustrates the assessment and revision shown in FIGS. 1A-1C performed for 1 through N iterations, to thereby generate corresponding generation 1 through generation N responses. As shown, the first iteration includes a first response generation stage, a response assessment stage, and a prompt revision stage, and the remaining iterations (here, second iteration is shown) repeat these stages as the revised response generation stage, response assessment stage, and prompt revision stage, until the Nth iteration in which a final response (generation N) is output in response to a final input.)
obtaining a first prompt; (P0018, Receive, via the prompt interface (in some implementations, the prompt interface API), a prompt from the user including an instruction for the LLM to generate an output.)
obtaining a first response to the first prompt, the first response generated using the language model; (P0018, The LLM may be configured to receive the prompt 30 and produce a first response.)
receiving a second prompt from a remote computing device via an electronic communication interface; (P0018, The first response may be output to the user, who may also optionally request revision if not satisfied with the first response.; P0029, The user may manually submit the revised prompt in an effort to improve on the first response.; P0074, Methods and processes described herein may be tied to a computing system of one or more computing devices. In particular, such methods and processes may be implemented as a computer-application program or service.
P0078, Individual components of the logic processor optionally may be distributed among two or more separate devices, which may be remotely located and/or configured for coordinated processing. Aspects of the logic processor may be virtualized and executed by remotely accessible, networked computing devices configured in a cloud-computing configuration.)
generating a second response to the second prompt using the language model; (P0023, To provide a response revision instruction to the LLM to generate the revised response (which may be output as the generation response) based on the revised prompt.)
comparing the first prompt to the second prompt; comparing the first response to the second response; (Fig. 7, Prompt and Revised Prompt.; P0018, If the user is not satisfied with the next response generated based on the revised prompt … revision is repeated for at least another iteration … if the current response is acceptable by either the user or predefined criteria, then the revised response is output to the user.)
transmitting, to the remote computing device via the electronic communication interface, a first prompt change record representing changes between the first prompt and the second prompt; and (P0078, Individual components of the logic processor optionally may be distributed among two or more separate devices, which may be remotely located and/or configured for coordinated processing. Aspects of the logic processor may be virtualized and executed by remotely accessible, networked computing devices configured in a cloud-computing configuration.; Fig. 7, Prompt and Revised Prompt.; P0031, A prompt evolution settings interface is provided. It will be appreciated that the least one processor can be further configured to cause a prompt revision element to be displayed, and in response to user input selecting the prompt revision element, outputting the revised prompt to the user. In the prompt evolution settings interface, a selector is presented by which a user can provide user input indicating whether prompts should be refined, which serves as the prompt revision element, and can indicate using an input field a user-specified number of iterations for assessment and revision, if desired.)
transmitting, to the remote computing device via the electronic communication interface, a first response change record representing changes between the first response and the second response. (P0078, Individual components of the logic processor optionally may be distributed among two or more separate devices, which may be remotely located and/or configured for coordinated processing. Aspects of the logic processor may be virtualized and executed by remotely accessible, networked computing devices configured in a cloud-computing configuration.; Fig. 7, Response and Revised Response.; P0031, A prompt evolution settings interface is provided. It will be appreciated that the least one processor can be further configured to cause a prompt revision element to be displayed, and in response to user input selecting the prompt revision element, outputting the revised prompt to the user. In the prompt evolution settings interface, a selector is presented by which a user can provide user input indicating whether prompts should be refined, which serves as the prompt revision element, and can indicate using an input field a user-specified number of iterations for assessment and revision, if desired.)
Callegari does not specifically teach:
comparing the first prompt to the second prompt; comparing the first response to the second response;
transmitting, to the remote computing device via the electronic communication interface, a first prompt change record representing changes between the first prompt and the second prompt; and
transmitting, to the remote computing device via the electronic communication interface, a first prompt change record representing changes between the first response and the second response.
Zernik, however, teaches:
comparing the first prompt to the second prompt; comparing the first response to the second response; (P0014, Visual mapping and comparison of the documents. At least one subsection of the first document is juxtaposed relative to an output of a corresponding at least one subsection of the second document to visually emphasize a comparison therebetween. Differences established on a word-by-word basis between the outputted first and second document subsections are highlighted with difference highlighting, and similarities established on a word-by-word basis between the outputted first and second document subsections are highlighted with similarity highlighting different from the difference highlighting.)
transmitting, to the remote computing device via the electronic communication interface, a first prompt change record representing changes between the first prompt and the second prompt; and (P0015, At least two selected ones of the document subsections are juxtaposed relative to one another, to visually emphasize correspondences therebetween, in response to comparison selecting the selected document subsections for comparison with one another. Differences identified among the selected document subsections are highlighted with difference highlighting, and similarities identified among the selected document subsections are highlighted with similarity highlighting different from the difference highlighting.)
transmitting, to the remote computing device via the electronic communication interface, a first prompt change record representing changes between the first response and the second response. (P0015, At least two selected ones of the document subsections are juxtaposed relative to one another, to visually emphasize correspondences therebetween, in response to comparison selecting the selected document subsections for comparison with one another. Differences identified among the selected document subsections are highlighted with difference highlighting, and similarities identified among the selected document subsections are highlighted with similarity highlighting different from the difference highlighting.)
It would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to compare changes in prompt and response. It would have been obvious to combine the references because comparison has to be made to pinpoint similarities and differences in two different versions before a decision can be made by a professional. Zernik P0002.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to DANIEL WONSUK CHUNG whose telephone number is (571)272-1345. The examiner can normally be reached Monday - Friday (7am-4pm)[PT].
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, PIERRE-LOUIS DESIR can be reached at (571)272-7799. 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.
/DANIEL W CHUNG/Examiner, Art Unit 2659
/PIERRE LOUIS DESIR/Supervisory Patent Examiner, Art Unit 2659
