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 .
Response to Amendment
This communication is responsive to the applicant’s amendment dated 4/28/2026. The applicant amended claims 1-8, 10, and 12-20. Claim 11 has been cancelled and new claim 21 has been added.
Response to Arguments
Applicant’s arguments with respect to 35 U.S.C. 112, see Remarks (pg. 7, line 6 – pg. 7, line 12), filed 4/28/2026, with respect to claims 4 and 15 have been fully considered and are persuasive. The 35 U.S.C. 112 rejection of claims 4 and 15 has been withdrawn.
Applicant's arguments with respect to 35 U.S.C. 101 (see Remarks pg. 7, line 13 – pg. 12, line 14) filed 4/28/2026 have been fully considered but they are not persuasive.
The applicant argues that a human cannot prompt a selected LLM via a customized prompt to generate a translation. The examiner believes there is nothing technical about this prompt. The examiner views the customized prompt as instructions to a translator with context of the two or more languages. A human can give a translator a prompt to make a translation. In the recited claim, the LLM is taking the place of a translator and not doing anything else. The customized prompt is not in any way that a human can’t understand it. The involvement of the LLM is generically recited in the claim language. The applicant argues that the office is silent with respect to identification of any abstract idea beyond repeating the “mental process” category, which the applicant believes is a significant oversimplification. MPEP § 2106.04(a)(2) provides further explanation on the abstract idea groupings. It should be noted that these groupings are not mutually exclusive, i.e., some claims recite limitations that fall within more than one grouping or sub-grouping. For example, a claim reciting performing mathematical calculations using a formula that could be practically performed in the human mind may be considered to fall within the mathematical concepts grouping and the mental process grouping. Accordingly, examiners should identify at least one abstract idea grouping, but preferably identify all groupings to the extent possible, if a claim limitation(s) is determined to fall within multiple groupings and proceed with the analysis in Step 2A Prong Two. As shown, the examiner needs to identify at least one but can identify more. There is no requirement to identify more than one. If the identified limitation(s) falls within at least one of the groupings of abstract ideas, it is reasonable to conclude that the claim recites an abstract idea in Step 2A Prong One. Since the claim under the BRI falls within at least one abstract idea category in the form of a mental process it is reasonable to conclude that the claim recites an abstract idea in Step 2A Prong One. Therefore, the 35 U.S.C. 101 rejection is maintained.
Applicant’s arguments with respect to 35 U.S.C. 103 (See Remarks, pg. 12, line 15 – pg. 14, line 14) for claims 1-10 and 12-21 have been considered but are moot because the new ground of rejection does not rely on any reference applied in the prior rejection of record for any teaching or matter specifically challenged in the argument. Given the amendments, a new group of rejection is provided.
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 1-10 and 12-21 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
Independent claim 1, 12, and 21 recite, “dynamically generate a customized prompt for a selected large language model (LLM), wherein the customized prompt concatenates a system instruction, a text input associated with two or more languages, and an indication of an output language that is different than the two or more languages, wherein the system instruction comprises a translation indication and an output format”, “prompt the selected LLM via the customized prompt to generate a translation output, wherein the translation output is an idiomatic translation of the input text when the translation indication indicates the idiomatic translation, wherein the translation output comprises one or more expressions that are natural to a native speaker of the output language”, and “output the translation output as one or more of speech output or text output in accordance with the output format”.
The limitation of generating a customized prompt, as drafted, is a process, under its broadest reasonable interpretation, covers performance of the limitation in the mind but for the recitation of generic computer components. That is, other than reciting “a memory”, and “one or more processors” nothing in the claim precludes the step from practically being performed in the mind. For example, “generate” in the context of this claim encompasses creating instructions, which a human can do in the mind. Next, the limitation of prompting a LLM to generate a translation, as drafted, is a process, under its broadest reasonable interpretation, covers performance of the limitation in the mind but for the recitation of generic computer components. That is, other than reciting the elements listed above, nothing in the claim precludes the step from practically being performed in the mind. For example, “prompt” in the context of this claim encompasses proving instructions for a translation, which a human can do by proving instructions to a translator. Next, the limitation of outputting a translation, under its broadest reasonable interpretation, covers performance of the limitation in the mind but for the recitation of generic computer components. That is, other than reciting the elements listed above, “output” in the context of this claim encompasses proving a translation, which a human can do in the mind or with a pen and paper.
The judicial exception is not integrated into a practical application. In particular, the claim only recites the additional elements, using “a memory”, and “one or more processors” to perform the recited limitations. These elements in these steps are recited at a high-level of generality such that is amounts no more than mere instructions to apply the exception using generic computer component. Accordingly, this additional element does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea. The claim is directed to an abstract idea.
The claim does 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 elements of using “a memory” and “one or more processors” to perform the recited limitations amounts to no more than mere instructions to apply the exception using generic computer components. Mere instructions to apply an exception using generic computer components cannot provide an inventive concept. The claim is not patent eligible.
Dependent claims 2-10 and 13-20 are also rejected for the same reasons provided in independent claim 1, 12, and 21 above. The dependent claim, including the further recited limitation, does not integrate the abstract idea into a practical application and the additional elements, taken individually and in combination do not contribute to an inventive concept. In other words, the dependent claim is directed to an abstract idea without significantly more.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
Claims 1-3, 6, 12-14, 17, and 21 are rejected under 35 U.S.C. 103 as being unpatentable over Kochura et al. US 20180165275 A1 (hereinafter Kochura) in view of Vasiltschenko et al. US 20250181336 A1 (hereinafter Vasiltschenko).
Regarding independent claim 1, 12, and 21 Kochura teaches a method implemented by one or more processors of a multilingual idiomatic translation computer system, the method / a multilingual idiomatic translation computer system / a non-transitory machine-readable medium comprising one or more sets of instructions that, when executed by one or more processors of a multilingual idiomatic translation computer system, cause the one or more processors, comprising:
memory comprising instructions stored thereon and one or more processors coupled to the memory and configured to execute the instructions to cause the multilingual idiomatic translation computer system to: (FIG. 1, 112, 114, 116; [0074])
a text input associated with two or more languages (FIG. 2, 202, [0046] “the electronic medium may be a direct text communication between two entities”; [0036] “in an electronic communication between two entities, such as a communication between mobile phone (180) and tablet (184), two or more languages may be embedded therein with one or more idioms present”)
and an indication of an output language that is different than the two or more languages (FIG. 4, 416, 422)
wherein the translation output is an idiomatic translation of the input text when the translation indication indicates the idiomatic translation, wherein the translation output comprises one or more expressions that are natural to a native speaker of the output language ([0038] “return a translation of the idiom with respect to the expression within the communication”); and
output the translation output as one or more of speech output or text output in accordance with the output format ([0038] “The returned idiom translation is presented on the visual display.”);
Kochura fails to teach dynamically generate a customized prompt for a selected large language model (LLM), wherein the customized prompt concatenates a system instruction, wherein the system instruction comprises a translation indication and an output format; prompt the selected LLM via the customized prompt to generate a translation output
However, Vasiltschenko teaches dynamically generate a customized prompt for a selected large language model (LLM), wherein the customized prompt concatenates a system instruction, wherein the system instruction comprises a translation indication and an output format (FIG. 1, 110, 111, 101; [0014] “prompt 110 comprises an instruction to generate source code. In other embodiments, prompt 110 comprises source code to be processed by the LLM to extract code elements to be translated as described herein. In some embodiments, the prompt specifies a parts of the source code that includes text values to be extracted. Additionally, instruction 111 may specify a file 112 to store extracted code elements”);
prompt the selected LLM via the customized prompt to generate a translation output (FIG. 1, 110, 111, 101; [0014])
Kochura in view of Vasiltschenko are considered to be analogous to the claimed invention because both are the same field of translation systems. Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified the techniques identification and translation of idioms and explanations of idioms of Kochura with the technique of prompting an LLM to perform translations taught by Vasiltschenko in order to improve techniques for enabling software code for different languages (see Vasiltschenko [Abstract]).
Regarding claim 2 and 13, Kochura in view of Vasiltschenko teaches all of the limitations of claim 1 and 12, upon which claims 2 and 13 depend.
Additionally, Kochura teaches wherein the system instruction contains one or more elements comprising a direct instruction for multilingual detection for the text input([0074] “Computer readable program instructions for carrying out operations of the present embodiments may be assembler instructions, instruction-set-architecture (ISA) instructions, machine instructions, machine dependent instructions, microcode, firmware instructions….”).
Regarding claim 3 and 14, Kochura in view of Vasiltschenko teaches all of the limitations of claim 1 and 12, upon which claims 3 and 14 depend.
Additionally, Kochura teaches wherein the translation output is a polished translation of the input text when the translation indication indicates a polished translation wherein the polished translation comprises a rephrasing of the translation output into a neutral tone (FIG. 3, 314, [0050] examiner interprets the second language idiom as the polished translation; [0033] “the emotion may be detected based on emphasis of a particular syllable, pitch, tone”).
Regarding claims 6 and 17, Kochura in view of Vasiltschenko teaches all of the limitations of claim 1 and 12, upon which claims 6 and 17 depend.
Additionally, Kochura teaches wherein the text input comprises a phrase in one of the two or more languages and correlated with one of the one or more expressions ([0036] “in an electronic communication between two entities, such as a communication between mobile phone (180) and tablet (184), two or more languages may be embedded therein with one or more idioms present”).
Claims 5 and 16 are rejected under 35 U.S.C. 103 as being unpatentable over Kochura in view of Vasiltschenko, as shown above in claim 1, in further view of Waibel et al. US 20110307241 A1 (hereinafter Waibel).
Regarding claim 5 and 16, Kochura in view of Vasiltschenko teaches all of the limitations of claim 1 and 12, upon which claim 5 and 16 depend.
Additionally, Kochura teaches execute the instructions to further cause the multilingual idiomatic translation computer system to (FIG. 1, 110)
Kochura in view of Vasiltschenko fails to teach wherein the one or more processors are further configured to process a voice speech by one or more users into the text input, wherein the voice speech is transcribed into the text input by a selected speech-to-text model
However, Waibel teaches wherein the one or more processors are further configured to
process a voice speech by one or more users into the text input, wherein the voice speech is transcribed into the text input by a selected speech-to-text model (FIG. 1; ASR modules 2 and 9 [0044]; [0052] “The resulting text of the user's speech is displayed via the GUI on the device screen 13 at step 28”).
Kochura in view of Vasiltschenko in view of Waibel are considered to be analogous to the claimed invention because all are the same field of translation systems. Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified the techniques of generating translations of Kochura in view of Vasiltschenko with the technique of selecting speech-to-text models taught by Waibel in order to improve speech-to-speech translation systems for cross-lingual communication (see Waibel [0003]).
Claims 7-9 and 18-19 are rejected under 35 U.S.C. 103 as being unpatentable over Kochura in view of Vasiltschenko as shown above in claim 1, in further view of Sagie (US 20140365200 A1).
Regarding claim 7 and 18, Kochura in view of Vasiltschenko teaches all of the limitations of claim 1 and 12, upon which claims 7 and 18 depend.
Kochura in view of Vasiltschenko fails to teach wherein the one or more processors are further configured to execute the instructions to further cause the multilingual idiomatic translation computer system to perform an LLM selection procedure to select the selected LLM among a group of candidate LLMs.
However, Sagie teaches wherein the one or more processors are further configured to execute the instructions to further cause the multilingual idiomatic translation computer system to perform an LLM selection procedure to select the selected LLM among a group of candidate LLMs ([0011] “applying the plurality of speech recognition engines includes utilization of a language model or a modifier that is selected in accordance with a translation profile”)
Kochura in view of Vasiltschenko in view of Sagie are considered to be analogous to the claimed invention because both are the same field of translation systems. Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified the translation techniques of Kochura in view of Waibel with the technique of language model selection taught by Sagie in order to improve automatic speech translation (see Sagie [0001]).
Regarding claim 8, Kochura in view of Vasiltschenko in view of Sagie teaches all of the limitations of claim 7, upon which claim 8 depends.
Additionally, Sagie teaches wherein the LLM selection procedure uses an LLM selection prompt instructing each of the group of candidate LLMs to perform the idiomatic translation ([0144] “The user may be prompted to indicate (e.g., by operating a control) which of several candidate transcripts or translations is preferred, or to correct a candidate transcript or translation”).
Regarding claim 9, Kochura in view of Vasiltschenko in view of Sagie teaches all of the limitations of claim 7, upon which claim 9 depends.
Additionally, Sagie teaches wherein the LLM selection procedure uses a predefined set of text input texts ([0049] “The electronic speech signal may be received by translation processor 16 via input channel 15”, examiner interprets a channel to have a predefined threshold limit).
Regarding claim 19, Kochura in view of Vasiltschenko in view of Sagie teaches all of the limitations of claim 18, upon which claim 19 depends.
Additionally, Sagie teaches wherein the LLM selection procedure uses a predefined set of text input texts and an LLM selection prompt instructing each candidate LLM to perform the idiomatic translation ([0011] “applying the plurality of speech recognition engines includes utilization of a language model or a modifier that is selected in accordance with a translation profile, the translation profile being specific to at least one of a speaker of the spoken speech, a population of speakers, or a context of the spoken speech”).
Claims 10 and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Kochura in view of Waibel, as shown above in claim 1, in further view of Woo (US 20240393942 A1).
Regarding claim 10, Kochura in view of Vasiltschenko teaches all of the limitations of claim 1, upon which claim 10 depends.
Kochura in view of Vasiltschenko fails to teach obtaining a reference input comprising a file name, wherein the text input is generated based on the reference input.
However, Woo teaches obtaining a reference input comprising a file name, wherein the text input is generated based on the reference input ([0059] “The “user language keypad list” may be stored in a variable in the form of an array, in a file with a specific name, or in a specific table in a database. As exemplified in DRAWING 7, the Environment Setting Manager program of the character input interface references the languages stored in the user language list”).
Kochura in view of Vasiltschenko in view of Woo are considered to be analogous to the claimed invention because both are the same field of translation systems. Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified the translation techniques of Kochura in view of Vasiltschenko with the technique of using a file name reference input taught by Woo in order to improve supporting efficient and convenient language activities of users by integrating and providing services related to input and output of natural language, such as text input, speech recognition, machine translation, and speech synthesis, using an extended keypad in any mobile computing device consisting of input, computation, and output, which includes a personal computer, a smartphone, a tablet PC, or a smartwatch, and in holographic or augmented reality simulating the same (see Woo [0001]).
Regarding claim 20, Kochura in view of Vasiltschenko teaches all of the limitations of 12, upon which claim 20 depends.
Kochura in view of Vasiltschenko fails to teach wherein the one or more processors are further configured to execute the instructions to further cause the multilingual idiomatic translation computer system to obtain a reference input comprising a file name, wherein the text input is generated based on the reference input.
However, Woo teaches further wherein the one or more processors are further configured to execute the instructions to further cause the multilingual idiomatic translation computer system to obtain a reference input comprising a file name, wherein the text input is generated based on the reference input ([0059]).
Kochura in view of Vasiltschenko in view of Woo are considered to be analogous to the claimed invention because both are the same field of translation systems. Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified the translation techniques of Kochura in view of Vasiltschenko with the technique of using a file name reference input taught by Woo in order to improve supporting efficient and convenient language activities of users by integrating and providing services related to input and output of natural language, such as text input, speech recognition, machine translation, and speech synthesis, using an extended keypad in any mobile computing device consisting of input, computation, and output, which includes a personal computer, a smartphone, a tablet PC, or a smartwatch, and in holographic or augmented reality simulating the same (see Woo [0001]).
Allowable Subject Matter
Claim 4 and 15 are objected to as being dependent upon a rejected base claim, but would be allowable if rewritten in independent form including all of the limitations of the base claim and any intervening claims.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Koyama et al. (US 5541838 A) teaches a translation machine is provided with an idiom registering capability. If a header standing for a idiom contains two or more variable parts, these parts are represented by representative symbols. With this representing method, the idiom is allowed to be easily registered and retrieved. This makes it possible to shorten the registering time, reduce the translating toil and prevent increase of information storage capacity. The translation machine includes an input unit, a storing unit, an output unit, an idiom registering unit, and a translating unit for performing a routine translating operation. The idiom registering unit operates to register an idiom header with two or more representative symbols standing for words or word trains sharing a predetermined attribute.
Horvitz (US 20060293893 A1) teaches architecture that interacts with a user, or users of different tongues to enhance speech translation. A recognized concept or situation is sensed and/or converged upon, and disambiguated with mixed-initiative user interaction with a device to provide simplified inferences about user communication goals in working with others who speak another language. Reasoning is applied about communication goals based on the concept or situation at the current focus of attention or the probability distribution over the likely focus of attention, and the user or user's conversational partner is provided with appropriately triaged choices and, images, text and/or speech translations for review or perception. The inferences can also process an utterance or other input from a user as part of the evidence in reasoning about a concept, situation, goals, and/or disambiguating the latter. The system's best understanding of the question, need, or intention at the crux of the communication can be echoed back to the user for confirmation. Context-sensitive focusing of recognition and information gathering components can be provided based on the listening, and can employ words recognized from prior or current user utterances to further focus the inference.
Sharifi et al. (US 20240202469 A1) teaches automatically translating a customized automated assistant from a first language to a new language, so that the automated assistant can interpret spoken utterances in the new language and respond to such spoken utterances in the new language. For example, a customized automated assistant can be configured for use in a first language through the developer(s) providing input(s) that are in the first language, and thereafter automatically translated to a distinct second language for which no developer input is provided. The deployment of the customized automated assistant for utilization with the second language can be selective. For example, it can be selective in that it is only automatically deployed and/or is only suggested for deployment in response to determining that one or more objective criteria, that indicate accuracy and/or robustness of the second language translation of the customized automated assistant, are satisfied.
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.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to ZEESHAN SHAIKH whose telephone number is (703)756-1730. The examiner can normally be reached Monday-Friday 7:30AM-5:00PM.
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, Richemond Dorvil can be reached at (571) 272-7602. 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.
/ZEESHAN MAHMOOD SHAIKH/Examiner, Art Unit 2658
/RICHEMOND DORVIL/Supervisory Patent Examiner, Art Unit 2658
Prosecution Insights