Google patents method for handling variable-length data in AI models
Google has filed a patent application for a method that helps computer programs process data of varying lengths using a specific type of data structure called a tensor array. This approach allows machine learning models to handle inputs that change in size by organizing the calculations into a directed graph that runs steps in a specific order.
In the filing’s own words
Methods, systems, and apparatus, including computer programs encoded on computer storage media, for efficiently processing dynamic length tensors of a machine learning model represented by a computational graph. A program is received that specifies a dynamic, iterative computation that can be performed on input data for processing by a machine learning model. A directed computational graph representing the machine learning model is generated that specifies the dynamic, iterative computation as one or more operations using a tensor array object. Input is received for processing by the machine learning model and the directed computational graph representation of the machine learning model is executed with the received input to obtain output.
What exactly they claim (claim 1)
1. A computer-implemented method comprising: receiving a program specifying a dynamic, iterative computation that can be performed on input data for processing by a machine learning model; generating a directed computational graph representing the machine learning model that specifies the dynamic, iterative computation as one or more operations using a tensor array object, wherein the tensor array object is an object containing a dynamically-sized array of tensors that ensures sequential execution of its operations; receiving an input for processing by the machine learning model; and executing the directed computational graph representation of the machine learning model with the received input to obtain output.
Facts
- Company
- Google (Google LLC)
- Official title
- DYNAMIC-LENGTH STATEFUL TENSOR ARRAY
- Publication number
- US20260329936A1
- Application number
- 19642121
- Filed
- Apr 8, 2026
- Published
- Oct 22, 2026
- Inventors
- 1
- Claims
- 20
Classified under
G06F 16/9024 Physics & computingG06F 17/16 Physics & computingG06N 3/084 Physics & computingG06N 3/105 Physics & computingG06N 20/00 Physics & computingMore from Google in AI & software
- Google patents video search that answers questions using AI descriptions Sep 15, 2026
- Google patents photo tool that removes people and their gear Sep 15, 2026
- Google patents AI that writes live meeting notes and summaries Sep 15, 2026
- Google patents AI tool that turns messy emergency notes into clear messages Sep 3, 2026
- Google patents AI that clicks through apps to finish tasks for you Sep 24, 2026
Summaries are simplified from the filing’s own abstract and first claim. A patent filing is not a product announcement.
Patent data and drawings: U.S. Patent and Trademark Office (USPTO). Nebula is not affiliated with or endorsed by the USPTO.