4 results about "Change order" patented technology

Systems, methods, and computer-readable media are provided for generating a prompt that specifies a plurality of fields and corresponding values of record(s). The prompt specifies a data structure to use for filling in components of a change order and includes a particular natural language description of a particular issue that caused the change order. A large language model is prompted with the prompt to generate a result based at least in part on the corresponding values of the record(s). The result from the large language model includes a particular data structure comprising particular values of a particular change order, which may then be displayed on a user interface along with an option to save the particular change order. Information from the record(s) and / or result(s) from the large language model may indicate whether or not manual labor, financial resources, and / or other resources are impacted by the change, and an impact may be stored in association with the change order reflecting a corresponding type of impact. The user interface may display another option to provide natural language input to modify the particular change order, causing the large language model to be re-prompted to generate another result to trigger change order creation.

Systems, methods, and computer-readable media are provided for generating a prompt that specifies a plurality of fields and corresponding values of record(s). The prompt specifies a data structure to use for filling in components of a change order and includes a particular natural language description of a particular issue that caused the change order. A large language model is prompted with the prompt to generate a result based at least in part on the corresponding values of the record(s). The result from the large language model includes a particular data structure comprising particular values of a particular change order, which may then be displayed on a user interface along with an option to save the particular change order. Information from the record(s) and / or result(s) from the large language model may indicate whether or not manual labor, financial resources, and / or other resources are impacted by the change, and an impact may be stored in association with the change order reflecting a corresponding type of impact. The user interface may display another option to provide natural language input to modify the particular change order, causing the large language model to be re-prompted to generate another result to trigger change order creation.

This invention relates to the field of application development technology and provides a method for identifying duplicate change orders in engineering projects. First, engineering information is correlated and integrated to obtain an intermediate dataset with a logical order of project implementation. Text extraction and data cleaning are then performed on the intermediate dataset to form change order text data. Next, the change order text data are paired based on instruction keywords to form an instruction control group. Then, a dual-thread similarity framework is used to calculate the similarity between two change order text data in the instruction control group to obtain first and second similarity data. If the first and second similarity data meet the duplication condition, the instruction control group is considered as a duplicate change order. In this way, duplicate change orders can be automatically identified, allowing for timely detection of problems and mitigation of company losses.

The application discloses an embedded device automatic testing method and a terminal. The method comprises the following steps: receiving a change order, and acquiring an associated module corresponding to a changed module in the change order; the changed module and the associated module are marked as to-be-tested modules corresponding to the change order; when a new version is detected, a target change order corresponding to the new version is acquired, and target to-be-tested modules corresponding to the target change order are acquired; an execution case set of each target to-be-tested module is determined; and a test case in the execution case set of each target to-be-tested module is executed on a to-be-tested device. The application realizes automatic analysis and matching of test cases, and improves the test efficiency of the embedded device.