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 Arguments
Applicant's arguments have been fully considered but they are not persuasive.
Carrara fails to disclose or teach that the information in response to the query comprises code explanations (i.e., an explanation of the function of code snippets) in the plain language format, information for debugging the test script code, and/or information for code optimization, as now claimed in claim 1.
Contrary to applicant’s assertion, Carrara par. [0100] discloses code explanations (e.g. “whether the code 1102 has the ability to perform a specific function”) providing information for debugging and/or optimization (e.g. “satisfy a specified performance metric … throughput in excess of 100 units per week? reduce energy consumption … hardware compatibility … complies with a specified industrial standard”) and provides the answers in plain text (e.g. “provide answers to these questions as plain text”). This demonstrates that querying an LLM for information about a code was within the ordinary level of skill in the art. Further applying this query to generated code would have been well within an ordinary level of creativeness.
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.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claim(s) 1-3, 5-7 and 9-14 is/are rejected under 35 U.S.C. 103 as being unpatentable over US 2024/0241817 to Tahvili et al. (Tahvili) in view of US 2024/0276264 to Rossetto (Rossetto) in view of US 2025/0085700 to Carrara et al. (Carrara) in view of US 2025/0053804 to Naressi et al. (Naressi).
Claims 1 and 12: Tahvili discloses a method for generating code for a mobile communication test system, comprising the steps of:
receiving information on a test scenario at an inputting environment (par. [0078] “receives a requirement specification 20 as input”), wherein the information is received in a plain language format (par. [0072] “requirement specification … provided … in non-formal natural language descriptions”);
preprocessing the received information (par. [0023] “extracting the textual features from the test case specification”); and
automatically generating a test script code for the mobile communication test system based on the received information (par. [0079] “selects/generates one or more test scripts 30”); and
postprocessing the test script code (par. [0026] “generating a label vector for each of the plurality of available test scripts”);
wherein the test script code is configured in such a way that, when it is executed by the mobile communication test system, it causes the mobile communication test system to generate a test routine according to the test scenario (par. [0079] “perform a test according to the specifications of the test case specification 25”), wherein the test routine adheres to a mobile communication standard (par. [0071] “test scripts of network nodes”, par. [0004] “wireless communication systems pursuant to 3GPP”).
Tahvili does not explicitly disclose the mobile communication test system is a mobile communication tester.
Rossetto teaches a mobile communication tester (par. [0009] “a device under test by a mobile communication tester”).
It would have been obvious to generate and execution test scripts for a mobile communication tester. Those of ordinary skill in the art would have been motivated to do so as a known means of providing the testing which would have produced only the expected results.
Tahvili and Rossetto do not teach:
wherein the test script code is generated by a trainable large language model;
receiving a query on the generated text script code, wherein the large language model is configured to provide information on the test script based on the query; and
wherein the information on the test script code comprises code explanations in the plain language format, information for debugging the test script code, and/or information for cod optimization.
Carrara teaches:
script code generated by a trainable large language model (par. [0070] “generative AI model 226 to generate control code 908 … a large language model (LLM)”),
receiving a query on the generated text script code, wherein the large language model is configured to provide information on the test script based on the query (par. [0100] “submit, via the chat interface … specific questions about the code”); and
wherein the information on the test script code comprises code explanations in the plain language format, information for debugging the test script code, and/or information for code optimization (par. [0100] “the generative AI component 210 can interpret the user’s query … to ascertain a suitable answer … performance metric … hardware compatibility or requirements for the code … provide answers to these questions as plain text chat responses”).
It would have been obvious at the time of filing to generate the test script with a large language model and query the LLM for code explanations. Those of ordinary skill in the art would have been motivated to do so as a known means of generating such code which would have produced only the expected results.
Tahvili, Rossetto and Carrara do not teach:
wherein the preprocessing comprises verifying the language prompts containing the received information on the test scenario are compatible with the trainable large language model.
Naressi teaches:
preprocessing comprises verifying the language prompts containing the received information on the test scenario are compatible with the trainable large language model (e.g. par. [0022] “represent a question asked by the user but in a format that is used by the computing device”, note that his appears to correspond to what is disclosed, e.g., at applicant’s par. [0070]).
It would have been obvious at the time of filing to verify compatibility of the language prompts. Those of ordinary skill in the art would have been motivated to do so to as a known means of representing a prompt to a large language model which would have produced only the expected results.
Tahvili, Rossetto, Carrara and Naressi do not explicitly teach:
postprocessing the test script code by applying a code checker and/or by carrying out a syntax checking;
Mori teaches:
postprocessing code by applying a code checker and/or by carrying out a syntax checking (par. [0072] “post-processing such as … syntax check”).
It would have been obvious before the effective filing date of the claimed invention to post-process the generated script code. Those of ordinary skill in the art would have been motivated to do so to ensure the code will properly compile and execute.
Claim 2: Tahvili, Rossetto, Carrara, Naressi and Mori teach the method of claim 1,
wherein the test routine comprises a generation and/or a reception of at least one communication signal by the mobile communication tester, wherein the at least one communication signal adheres to the mobile communication standard (par. [0140] “network node 1000 … configured to provide communication with other nodes”).
Claim 3: Tahvili, Rossetto, Carrara, Naressi and Mori teach the method of claim 1,
wherein the mobile communication standard is a 3GPP based standard (Tahvili par. [0004] “wireless communication systems pursuant to 3GPP”).
Claim 5: Tahvili, Rossetto, Carrara, Naressi and Mori the method of claim 1, including:
Python or a Python based programming language (Tahvili par. [0048] “implemented in the Python programming language”); and
wherein the test script code is generated in a programming language (Tahvili par. [0074] “test scripts … provided in different programming languages”).
It would have been obvious at the time of filing to implement the test scripts in Python. Those of ordinary skill in the art would have been motivated to do so as a known programming language which would have produced only the expected results.
Claims 6 and 13: Tahvili, Rossetto, Carrara, Naressi and Mori teach claims 1 and 12, further comprising the step of:
outputting the generated test script code (Tahvili par. [0077] “output via a user interface 120 as generated test scripts 30”).
Claim 9: Tahvili, Rossetto, Carrara, Naressi and Mori teach the method of claim 1,
wherein the large language model is trained by training data (Tahvili par. [0077] “a model training function 144 … that generate a trained model 148, Carrara par. [0070] “The model 226 can be trained”), wherein the training data comprises any combination of: instrument documentation of the mobile communication tester (par. [0005] “trained using … industrial standards data”), information on communication standards (Carrara par. [0005] “industrial protocol data”), test specifications, and previously generated test script code (Carrara par. [0005] “code samples”).
Claim 11: Tahvili, Rossetto, Carrara, Naressi and Mori teach the method of claim 1, further comprising the step of:
executing the test script code with the mobile communication tester to generate the test routine according to the test scenario (Rossetto par. [0009] “a device under test by a mobile communication tester”).
Conclusion
THIS ACTION IS MADE FINAL. 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 JASON D MITCHELL whose telephone number is (571)272-3728. The examiner can normally be reached Monday through Thursday 7:00am - 4:30pm and alternate Fridays 7:00am 3:30pm.
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, Lewis Bullock can be reached at (571)272-3759. 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.
/Jason D Mitchell/Primary Examiner, Art Unit 2199
Prosecution Insights