DETAILED ACTION
Claims 1, 2, 4-7, 9-15, 17-23 are pending. Claims 1, 2, 7, 9-10, 15, 17-19, 21 and 23 have been amended.
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
This non-final office action is in response to the applicant’s response received on 02/04/2026, for the final office action mailed on 11/18/2025.
Examiner’s Notes
Examiner has cited particular columns and line numbers, paragraph numbers, or figures in the references as applied to the claims below for the convenience of the applicant. Although the specified citations are representative of the teachings in the art and are applied to the specific limitations within the individual claim, other passages and figures may apply as well. It is respectfully requested from the applicant, in preparing the responses, to fully consider the references in entirety as potentially teaching all or part of the claimed invention, as well as the context of the passage as taught by the prior art or disclosed by the examiner.
Continued Examination Under 37 CFR 1.114
A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission filed on 02/04/2026 has been entered.
Response to Arguments
Applicant’s arguments with respect to rejection made under 35 U.S.C. § 103 have been considered but are moot in view of new ground(s) rejection.
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) 1,2, 5-7, 9, 10, 13-15, 17, 18 and 23 are rejected under 35 U.S.C. 103 as being unpatentable over Raman et al. (US-PGPUB-NO: 2019/0370160 A1) hereinafter Raman, in further view of Tang et al. (US-PGPUB-NO: 2025/0045185 A1) hereinafter Tang and Duong et al. (US-PGPUB-NO: 2024/0330167 A1) hereinafter Duong.
As per claim 1, Raman teaches an apparatus comprising: a memory; and a processor coupled to the memory (see Raman paragraph [0093], “The computing device 1000 includes a processor 1002, a memory 1004, a storage device 1006, a high-speed interface 1008 connecting to the memory 1004 and multiple high-speed expansion ports 1010, and a low-speed interface 1012 connecting to a low-speed expansion port 1014 and the storage device 1006.”), the processor configured to: receive a description of features of a software program to be tested from a user interface (see Raman paragraph [0038], “Beginning with requirements documentation, the described system generates test scenarios, which are used to create test cases once the application or system has been built. Requirements documentation (e.g., business requirements, functional requirements, use cases, user stories, and so forth) captures, for example, information related to the business process(es) that will be supported by the software, intended actions that will be performed through the software, managed data, rule sets, nonfunctional attributes (e.g., response time, accessibility, access and privilege), and so forth”); generate, a plurality of test steps and an executable automation script with a step definition that includes a mapping of the plurality of test steps to a plurality of code functions (see Raman paragraph [0068], “By way of example, a test scenario or list of scenarios may be included in what is called a feature file, where a formatted language, such as Gherkin, is used to write the scenarios in a human readable way. Such a feature file may be used in the generation of an automated testing script for an automation tool. Example automation tools include Unified Functional Testing (UFT), Tricentis Tosca™, Worksoft Certify™, and Selenium™. The testing automation tool provides a framework that can be used to provide support software structures, such as step definitions, for each of the test scenarios. Step definitions act as skeleton placeholders where automation code blocks may be implemented”), execute the plurality of steps on the software program by identifying corresponding code functions specified by the mapping in the step definition, and executing the identified code functions in an order of the plurality of test steps (see Raman paragraph [0068], “For example, each step in a given scenario may map to a step definition. The automation code block is implemented for each step definition and executed when the scenario is run by the testing framework. The automation code block may be written in a variety of programming language, such as Ruby, C++, Java, Scala, Python, and so forth, selected based on system requirements. Once generated, the step definitions and respective code blocks, may be referred to as an automated testing script. The testing automation tool provides an execution environment for these generated scripts, which may be run for acceptance and/or regression testing”).
Raman does not explicitly teach generate, based on execution of a large language model on the description. However, Tang generate, based on execution of a large language model on the description (see Tang paragraph [0042], “Based on these inputs 130 and 132, the finetuning/training service 102 generate a custom LLM for embedding, enhancement, and translation as described herein. As illustrated in FIG. 1, the custom LLM may be used be one or more components of the system to perform the described functionality).
Raman and Tang are analogous art because they are in the same field of endeavor of software development. Therefore, it would have been obvious to one of ordinary skills in the art before the effective filing date of the claimed invention modify Raman’s teaching of generating and executing automated testing scripts with Tang’s teaching of using large language models for creating a multi-lingual, low-resource code translation dataset to incorporate the use of trained large language models to generate the test scripts/ test cases taught in Raman for a more optimized result, see Tang paragraph [0006], “In one aspect, a system comprises a memory and at least one processor, coupled to the memory, and operative to perform operations comprising generating one or more unit-test cases from a monolingual code corpus; filtering the generated unit-test cases to generate a corpus of unit-test cases which have acceptability scores exceeding one or more predefined thresholds; translating one or more of the code samples of the monolingual code corpus from a source language to a target language using a pretrained Large Language Model (LLM); translating the generated unit-test cases from the source language to the target language using a rules-based translator; validating the LLM-translated code samples using the translated unit-test cases; creating a parallel-data training corpus comprising the LLM-translated code samples that pass the validation; fine-tuning the pretrained large language model (LLM) using the parallel-data training corpus; translating a given code segment using the fine-tuned large language model (LLM); testing the translated given code segment; and facilitating deployment of the tested given code segment in the target language.”
Raman modified with Tang do no teach generate a diagram that includes the plurality of test steps and respective pass/fail indicators that result from execution of the plurality of test steps; and output the diagram via the user interface. However, Duong teaches generate a diagram that includes the plurality of test steps and respective pass/fail indicators that result from execution of the plurality of test steps; and output the diagram via the user interface (see Duong paragraph [0097], “In some embodiments, the system offers interactive visualizations of the test results. This could involve, for example, charts or graphs that visually represent the pass/fail distribution across test cases or highlight trends in execution times. Such visualizations can help users quickly grasp the overall testing outcome and identify areas requiring further investigation”).
Raman, Tang and Duong are analogous art because they are in the same field of endeavor of software development. Therefore, it would have been obvious to one of ordinary skills in the art before the effective filing date of the claimed invention modify Raman’s teaching of generating and executing automated testing scripts and Tang’s teaching of using large language models for creating a multi-lingual, low-resource code translation dataset with Duong’s teaching of intelligent process doe iterative software testing and developments to incorporate using a processing engine and gathering input in order to generate test cases based on the testing changes and extracted features to produce more reliable and less redundant test cases along with visualizing test results to provide users a better way to grasp the overall testing outcome and identify areas requiring further investigations.
As per claim 2, Raman modified with Tang and Duong teaches wherein the processor is further configured to receive user feedback about the plurality of test steps from the user interface, and execute the large language model on the plurality of test steps and the feedback to further train the large language model (see Duong paragraph [0086], “In some embodiments, the user interface provides real-time feedback during test script execution. For example, this feedback might include the current test case being executed, the actions being performed on the system under test, and the received responses. Additionally, the user interface can display the results of each test case, indicating whether the expected outcome was achieved (i.e., pass) or if a deviation from the expected behavior was encountered (i.e., fail)”).
As per claim 5, Raman modified with Tang and Duong teaches wherein the processor is further configured to generate and output a prompt on the user interface, and receive a response to the prompt via the user interface (see Duong paragraph [0053], “In some embodiments, the system identifies one or more inconsistencies within the user description, and prompts the user to address the inconsistencies before proceeding with code generation. In some embodiments, the system analyzes the user description for logical inconsistencies”).
As per claim 6, Raman modified with Tang and Duong teaches wherein the processor is further configured to train the large language model based on the prompt on the user interface and the response to the prompt received via the user interface (see Duong paragraph [0071], “In some embodiments, the system allows a user with programming experience to directly edit the generated code. This can enable the user to fine-tune the generated code for specific needs or integrate custom functionalities”)
As per claim 7, Raman modified with Tang and Duong teaches wherein the processor is configured to generate a plurality of test components for a software test case including a test specification, a test execution, a test recording, and a test verification based on execution of a GenAI model (see Tang paragraph [0043], “In one aspect, a computer program product comprises one or more tangible computer-readable storage media and program instructions stored on at least one of the one or more tangible computer-readable storage media, the program instructions executable by a processor, the program instructions comprising generating one or more unit-test cases 220 from a monolingual code corpus 216 (operation 262); filtering the generated unit-test cases 220 to generate a corpus of unit-test cases which have acceptability scores exceeding one or more predefined thresholds (operation 266); translating one or more of the code samples of the monolingual code corpus 216 from a source language to a target language using a pretrained Large Language Model (LLM) 224 (operation 270); translating the generated unit-test cases 220 from the source language to the target language (operation 274); validating the LLM-translated code samples 228 using the translated unit-test cases 236 (operation 278); creating a parallel-data training corpus comprising the LLM-translated code samples 228 that pass the validation (operation 282); fine-tuning the pretrained large language model (LLM) using the parallel-data training corpus; translating a given code segment using the fine-tuned large language model (LLM); testing the translated given code segment; and facilitating deployment of the tested given code segment in the target language”).
As per claims 9, 10 and 13-15, these are the method claims to apparatus claims 1, 2 and 5-7, respectively. Therefore, they are rejected for the same reasons as above.
As per claims 17 and 18, these are the computer-readable medium claims to apparatus claims 1 and 2, respectively. Therefore, they are rejected for the same reasons as above.
As per claim 23, Raman modified with Tang and Duong teaches wherein the processor is configured to generate a document that includes a first column storing input activities performed during execution, a second column storing expected outcomes, and a third column storing actual results observed during execution (see Duong paragraph [0059], “Next, the description processing component utilizes the identified elements to generate a structured representation. This structured representation refers to a formalized capture of the key elements extracted from the user's test script description. The structured representation acts as a bridge between the user's natural language description and the code that will ultimately be generated for the test script. This representation captures the elements identified during description processing, such as, for example, actions, expected responses, and data values, and potentially the sequence or relationships between them”)
Claim(s) 4, 12 and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Raman (US-PGPUB-NO: 2019/0370160 A1), Tang (US-PGPUB-NO: 2025/0045185 A1) and Duong (US-PGPUB-NO: 2024/0330167 A1), in further view of Hart et al. (US-PGPUB-NO: 2024/0265281 A1) hereinafter Hart.
As per claim 4, Raman modified with Tang and Duong do not explicitly teach wherein the processor is further configured to execute the large language model on best practices documents of software test cases to further train the large language model to understand best practices. However, Hart teaches wherein the processor is further configured to execute the large language model on best practices documents of software test cases to further train the large language model to understand best practices (see Hart paragraph [0042], “The finetuning/training service 102 fine tunes a large language model based on based on both generic inputs 130 and specific input 132. The generic inputs 130 include natural language input data, such as, for example, an architectural description or other knowledge of the platform and/or domain, descriptions of capabilities and functionalities of the various libraries, frameworks, extensions, and packages (paid or otherwise) available to the platform, descriptions of best practices for working with the platform and its frameworks, or a combination thereof”).
Raman, Tang, Duong and Hart are analogous art because they are in the same field of endeavor of software development. Therefore, it would have been obvious to one of ordinary skills in the art before the effective filing date of the claimed invention modify Raman’s teaching of generating and executing automated testing scripts, Tang’s teaching of using large language models for creating a multi-lingual, low-resource code translation dataset and Duong’s teaching of intelligent process doe iterative software testing and developments with Hart’s teaching of providing software related answer based on a trained model to incorporate using best practices in order to fine tune a machine learning model in order to provide best methods for working with a platform and frameworks of a software.
As per claim 12, this is the method claim to apparatus claim 4. Therefore, it is rejected for the same reasons as above.
As per claim 20, this is the computer-readable medium claim to apparatus claim 4. Therefore, it is rejected for the same reasons as above.
Claim(s) 11, 19 and 21 are rejected under 35 U.S.C. 103 as being unpatentable over Raman (US-PGPUB-NO: 2019/0370160 A1), Tang (US-PGPUB-NO: 2025/0045185 A1) and Duong (US-PGPUB-NO: 2024/0330167 A1), in further view of Sharma et al. (US-PGPUB-NO: 2023/0251960 A1) hereinafter Sharma.
As per claim 11, Raman modified with Tang and Duong do not explicitly teach wherein the processor is further configured to receive a call via an application programming interface (API) with an identifier of a programming language, and in response, generate the software test case for the software program within the identified programming language. However, Sharma teaches wherein the processor is further configured to receive a call via an application programming interface (API) with an identifier of a programming language, and in response, generate the software test case for the software program within the identified programming language (see Sharma paragraph [0094], “Process 600 includes step/operation 601, at which a query describing a testing change is received. In some examples, the query may be received from a client computing entity 102, such as via an application programming interface (API). That is, in various embodiments, the query is an API query, request, call, and/or the like that is handled by providing a corresponding API response, such as a change report. In various embodiments, the testing change is described by text data within the query in the form of natural language. Generally, the testing change may be a modification, addition, or removal of a test step, a test case, a non-standardized or standardized test description, a test module, a test outcome requirement, and/or the like”).
Raman, Tang, Duong and Sharma are analogous art because they are in the same field of endeavor of software development. Therefore, it would have been obvious to one of ordinary skills in the art before the effective filing date of the claimed invention modify Raman’s teaching of generating and executing automated testing scripts, Tang’s teaching of using large language models for creating a multi-lingual, low-resource code translation dataset and Duong’s teaching of intelligent process doe iterative software testing and developments with Sharma’s teaching of machine learning techniques for automated software testing configuration management providing software related answer based on a trained model to incorporate using a machine learning model and gathering input in order to generate test cases based on the testing changes and extracted features to produce more reliable and less redundant test cases.
As per claim 19, this is the computer-readable medium claim to method claim 11. Therefore, it is rejected for the same reasons as above.
As per claim 21, Raman modified with Tang, Duong and Sharma teaches wherein the processor is configured to execute the plurality of test steps through a test execution service based on an API call received by the test execution service from the large language model (see Sharma paragraph [0094], “Process 600 includes step/operation 601, at which a query describing a testing change is received. In some examples, the query may be received from a client computing entity 102, such as via an application programming interface (API). That is, in various embodiments, the query is an API query, request, call, and/or the like that is handled by providing a corresponding API response, such as a change report. In various embodiments, the testing change is described by text data within the query in the form of natural language. Generally, the testing change may be a modification, addition, or removal of a test step, a test case, a non-standardized or standardized test description, a test module, a test outcome requirement, and/or the like”).
Claim(s) 22 is rejected under 35 U.S.C. 103 as being unpatentable over Raman (US-PGPUB-NO: 2019/0370160 A1), Tang (US-PGPUB-NO: 2025/0045185 A1) and Duong (US-PGPUB-NO: 2024/0330167 A1), in further view of Zotikov et al. (US-PGPUB-NO: 2025/0080563 A1) hereinafter Zotikov.
As per claim 22, Raman modified with Tang and Duong do not explicitly teach wherein the processor is configured to generate a simulated security threat test case based on the execution of the large language model, and execute the simulated security threat test case on the software program. However, Zotikov teaches wherein the processor is configured to generate a simulated security threat test case based on the execution of the large language model, and execute the simulated security threat test case on the software program (see Zotikov paragraph [0049], “The testing unit 110 (for example, a testing processor on which the testing unit 110 executes) is configured to execute a series of tests which simulate attacks on the target device 130. The security unit 120 (for example, a security processor on which the security unit 120 executes) is configured to monitor the target device 130 and respond to the simulated attacks of the testing unit 110, when detected, by triggering an alert, internal log entry, and/or suitable preventative measures, among other possibilities”).
Raman, Tang, Duong and Zotikov are analogous art because they are in the same field of endeavor of software development. Therefore, it would have been obvious to one of ordinary skills in the art before the effective filing date of the claimed invention modify Raman’s teaching of generating and executing automated testing scripts, Tang’s teaching of using large language models for creating a multi-lingual, low-resource code translation dataset and Duong’s teaching of intelligent process doe iterative software testing and developments with Zotikov’s teaching of simulation of cyberattacks with execution confirmation to incorporate using simulated attacks in order to provide better security and hacking defense when testing for security threats within an application/test cases.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Zhang et al. (US-PGPUB-NO: 2024/0256423 A1) teaches improvement using large language models.
Yalla et al. (US-PAT-NO: 10,949,337 B1) teaches utilizing neural network and artificial intelligence models to select and execute test cases in a software development platform.
Kulkarni et al. (US-PGPUB-NO: 2019/0213116 A1) teaches generation of automated testing scripts by converting manual test cases.
Takawale et al. (US-PGPUB-NO: 2019/0213115 A1) teaches utilizing artificial intelligence to test cloud applications.
Venkataraman et al. (US-PGPUB-NO: 2019/0196949 A1) teaches test scenario and knowledge graph extractor.
Tahvili et al. (US-PGPUB-NO: 2024/0241817 A1) teaches artificial intelligence based on cognitive test script generation.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to LENIN PAULINO whose telephone number is (571)270-1734. The examiner can normally be reached Week 1: Mon-Thu 7:30am - 5:00pm Week 2: Mon-Thu 7:30am - 5:00pm and Fri 7:30am - 4:00pm EST.
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, Bradley Teets can be reached at (571) 272-3338. 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.
/LENIN PAULINO/Examiner, Art Unit 2197
Prosecution Insights