-
公开(公告)号：US20230418815A1
公开(公告)日：2023-12-28
申请号：US17849056
申请日：2022-06-24
Applicant: Microsoft Technology Licensing, LLC
Inventor： Benjamin Goth ZORN , Carina Suzana NEGREANU , Neil Blunt TORONTO , Brian Paul SLININGER , Andrew Donald GORDON , Advait SARKAR , Sruti Srinivasa RAGAVAN
IPC: G06F16/2452 , G06F8/41 , G06F40/20
CPC classification number: G06F16/24522 , G06F8/436 , G06F8/427 , G06F40/20
Abstract: The generation of a response to a task prompt that represents a task to perform on declarative code. The response is generated with the aid of a language model that was trained on imperative code. The declarative code includes declarations about data. A task prompt represents a task to perform on the declarative code. At least a portion of the declarative code and at least a portion of the task prompt are converted into input imperative code. The input imperative code is then caused to be provided as input to the language model, resulting in the language model generating output imperative code. At least a portion of the output imperative code is then converted into a response to the task prompt.
-
公开(公告)号：US20250068837A1
公开(公告)日：2025-02-27
申请号：US18734203
申请日：2024-06-05
Applicant: Microsoft Technology Licensing, LLC
Inventor： Benjamin Goth ZORN , Marc Manuel Johannes BROCKSCHMIDT , Pallavi CHOUDHURY , Oleksandr POLOZOV , Rishabh SINGH , Saswat PADHI
IPC: G06F40/18 , G06F16/338 , G06N3/04 , G06N3/08 , G06N5/046
Abstract: Systems, methods, and computer-readable storage devices are disclosed for improved table identification in a spreadsheet. One method including: receiving a spreadsheet including at least one table; identifying, using machine learning, one or more classes of a plurality of classes for each cell of the received spreadsheet, wherein the plurality of classes include corners and not-a-corner; and inducing at least one table in the received spreadsheet based on the one or more identified classes for each cell of the received spreadsheet.
-
Patent Agency Ranking
3.发明申请公开(公告)号：US20200019603A1
公开(公告)日：2020-01-16
申请号：US16034447
申请日：2018-07-13
Applicant: Microsoft Technology Licensing, LLC
Inventor： Benjamin Goth ZORN , Marc Manuel Johannes BROCKSCHMIDT , Pallavi CHOUDHURY , Oleksandr POLOZOV , Rishabh SINGH , Saswat PADHI
Abstract: Systems, methods, and computer-readable storage devices are disclosed for improved table identification in a spreadsheet. One method including: receiving a spreadsheet including at least one table; identifying, using machine learning, one or more classes of a plurality of classes for each cell of the received spreadsheet, wherein the plurality of classes include corners and not-a-corner; and inducing at least one table in the received spreadsheet based on the one or more identified classes for each cell of the received spreadsheet.
-
4.发明公开公开(公告)号：US20240241703A1
公开(公告)日：2024-07-18
申请号：US18154741
申请日：2023-01-13
Applicant: Microsoft Technology Licensing, LLC
Inventor： Benjamin Goth ZORN , Kasra FERDOWSIFARD , John Herbert Martin WILLIAMS , Carina Suzana NEGREANU , Andrew Donald GORDON , Advait SARKAR , Ian Zachariah DROSOS , Neil Blunt TORONTO
Abstract: A mechanism to show how code is operating with different sets of input. After accessing the code that is to be evaluated along with the multiple input sets for that code, the computing system generates a multi-dimensional array of values. This is done by, for each of at least some of the multiple input sets, generating a corresponding intermediate value set of one or more intermediate values that are generated as the code operates upon the corresponding input set to generate a corresponding output value set. Then, the computing system causes a multi-dimensional array of values to be visualized using a multi-dimensional representation. In this multi-dimensional visualization, input sets are represented in at least one dimension against at least one intermediate value of the corresponding intermediate value set in at least another dimension.
-
公开(公告)号：US20240232545A9
公开(公告)日：2024-07-11
申请号：US17969922
申请日：2022-10-20
Applicant: Microsoft Technology Licensing, LLC
Inventor： Benjamin Goth ZORN , Carina Suzana NEGREANU , Neil Blunt TORONTO , Brian Paul SLININGER , Andrew Donald GORDON , Advait SARKAR , Elnaz NOURI , Vu Minh LE , Christian Leopold Bejamin POELITZ , Shraddha Govind BARKE , Sruti Srinivasa RAGAVAN
Abstract: The indirect querying of models to determine capabilities possessed by the model. Such indirect queries take the form of model input that potentially includes a natural language input user data. Such model input is structured such that the output of the model is either not natural language at all, or else is natural language that is not semantically responsive to the natural language input. Nevertheless, the output is evaluated to estimate or determine the capability possessed by the model. Thus, models may be more fully utilized to their better potential.
-
公开(公告)号：US20240143928A1
公开(公告)日：2024-05-02
申请号：US17976570
申请日：2022-10-28
Applicant: Microsoft Technology Licensing, LLC
Inventor： Benjamin Goth ZORN , Carina Suzana NEGREANU , Advait SARKAR , Andrew Donald GORDON , John Herbert Martin WILLIAMS , Xieyang LIU , Neil Blunt TORONTO , Sruti Srinivasa RAGAVAN , Brian Paul SLININGER
IPC: G06F40/30 , G06F40/166 , G06F40/40
CPC classification number: G06F40/30 , G06F40/166 , G06F40/40
Abstract: The automated generation of a natural language explanation of what code does. The code is structured to perform tasks because the code itself semantically specifies that those tasks are to be performed. A task-centric representation of the code is automatically generated that includes a task representation of each of some or all of the tasks to be performed as specified by the code. Natural language utterances are then automatically generated by generating a corresponding natural language utterance that semantically describes in natural language the corresponding task represented by the corresponding task representation. Controls are rendered for each natural language utterance that each permit a user to edit the corresponding natural language utterance. After editing, the code itself may be automatically modified or regenerated to reflect the changed natural language utterances.
-
公开(公告)号：US20240135113A1
公开(公告)日：2024-04-25
申请号：US17969922
申请日：2022-10-19
Applicant: Microsoft Technology Licensing, LLC
Inventor： Benjamin Goth ZORN , Carina Suzana NEGREANU , Neil Blunt TORONTO , Brian Paul SLININGER , Andrew Donald GORDON , Advait SARKAR , Elnaz NOURI , Vu Minh LE , Christian Leopold Bejamin POELITZ , Shraddha Govind BARKE , Sruti Srinivasa RAGAVAN
Abstract: The indirect querying of models to determine capabilities possessed by the model. Such indirect queries take the form of model input that potentially includes a natural language input user data. Such model input is structured such that the output of the model is either not natural language at all, or else is natural language that is not semantically responsive to the natural language input. Nevertheless, the output is evaluated to estimate or determine the capability possessed by the model. Thus, models may be more fully utilized to their better potential.
-
-
-
-
-
-
Search Results
7
records
(took 0.014 seconds)
