Storing entries in and retrieving information from an embedding object memory
The method improves information storage and retrieval in embedded object memories by generating and managing semantic embeddings through spatial storage operations, addressing inefficiencies in existing methods.
Patent Information
- Authority / Receiving Office
- HK · HK
- Patent Type
- Applications
- Current Assignee / Owner
- MICROSOFT TECHNOLOGY LICENSING LLC
- Filing Date
- 2026-04-20
- Publication Date
- 2026-07-10
AI Technical Summary
Existing methods for storing and retrieving information from embedded object memories are inefficient and lack effective mechanisms for managing semantic embeddings.
The method involves receiving content data, generating semantic embeddings using models, associating them with source data references, and performing spatial storage operations to insert and retrieve embeddings from an embedded object memory.
Enhances the efficiency of storing and retrieving semantic embeddings by leveraging semantic embeddings and spatial storage operations, enabling effective management and retrieval of information.
Smart Images
Figure 00000000_0000_ABST
Abstract
Description
HK Application no : <S1_APPLICATION_NO> Our Ref : SHPA26 / 11332 <deadline> <iinitial><letter_date>This abstract provides methods, systems, and media for storing entries in and retrieving information from an embedded object memory. In some examples, a content item with content data is received. The content data associated with the content item can be provided to one or more semantic embedding models that generate semantic embeddings. From one or more semantic embedding models, one or more semantic embeddings can be received. The one or more semantic embeddings can then be inserted into the embedded object memory. The semantic embedding can be associated with a corresponding indication of a reference to source data associated with the semantic embedding. Furthermore, the insertion can trigger a spatial storage operation to store a vector representation of one or more semantic embeddings. Multiple sets of stored embeddings can be received from the embedded object memory based on the provided input to determine the action.< / iinitial> < / deadline>
Claims
CLAIMS1. A method for storing an entry in an embedding object memory, the method comprising: receiving a content item, the content item having one or more content data; providing one of the content data associated with the content item to one or more semantic embedding models, wherein the one or more semantic embedding models generate one or more semantic embeddings; receiving, from one or more of the semantic embedding models, one or semantic embeddings, wherein a collection of semantic embeddings is associated with a first semantic embedding model of the one or more semantic embedding models, and wherein the collection of semantic embeddings comprises a first semantic embedding generated by the first semantic embedding model for at least one content data from the respective content item; inserting the one or more semantic embeddings into the embedding object memory, wherein the embedding object memory stores one or more semantic embeddings from the collection of semantic embeddings, wherein the one or more semantic embeddings are associated with a respective indication corresponding to a reference to source data associated with the one or more semantic embeddings, and wherein the insertion triggers a spatial storage operation to store a vector representation of the one or more semantic embeddings; and providing the embedding object memory.
2. The method of claim 1, wherein the vector representation is stored in at least one of an approximate nearest neighbor (ANN) tree, a k-d tree, or a multidimensional tree.
3. The method of claim 1, wherein the semantic embedding models comprise a generative large language model (LLM).
4. The method of claim 1 , wherein the content data are a plurality of content data that are each a respective one of audio content data, visual content data, gaze content data, weather content data, news content data, calendar content data, email content data, or location content data.
5. The method of claim 1 , wherein the embedding object memory is stored at a location that is different than the location of the source data.
6. The method of claim 1, wherein the one or more semantic embedding models comprise a version, wherein each of the semantic embeddings generated by each of the respective models comprise metadata corresponding to the version, and wherein the method further comprises: providing an updated semantic embedding model to replace at least one of the semantic embedding models, the updated semantic embedding model comprising an updated version that is different than the version of the at least one of the semantic embedding models;receiving, from the updated semantic embedding model, an updated one or more semantic embeddings corresponding to the one or more semantic embeddings generated by the at least one of the semantic embedding models; and inserting the updated semantic embeddings in the embedding object memory with metadata corresponding to the updated version.
7. The method of claim 6, further comprising: deleting the one or more semantic embeddings corresponding to the updated semantic embeddings, the one or more semantic embeddings having metadata corresponding to a version that is different than the updated version.
8. A method for retrieving information from an embedding object memory, the method comprising: receiving an input embedding, wherein the input embedding is generated by a machinelearning model; retrieving a plurality of collections of stored semantic embeddings, from the embedding object memory, based on the input embedding, wherein the plurality of collections of stored semantic embeddings each correspond to respective content data; retrieving a subset of semantic embeddings from at least one of the plurality of collections of stored semantic embeddings based on a similarity to the input embedding; determining, based on the subset of semantic embeddings and the input embedding, an action; and providing the action as an output.
9. The method of claim 8, wherein each semantic embedding of the subset of semantic embeddings is associated with source data corresponding to the respective content data, wherein the determining an action comprises: locating the source data; and determining the action based on the input embedding and the source data.
10. The method of claim 9, wherein the source data includes one or more of audio files, text files, or image files.
11. The method of claim 8, wherein the retrieving a subset of embeddings comprises: determining a respective similarity between the input embedding and each embedding of the plurality of collections of stored semantic embeddings; determining an ordered ranking of the one or more similarities or that one or more of the similarities are less than a predetermined threshold; andretrieving the subset of semantic embeddings with similarities to the input embedding that are less than the predetermined threshold or based on the ordered ranking, thereby retrieving subsets of semantic embeddings from at least one of the collections of semantic embeddings that are determined to be related to the input embedding.
12. The method of claim 11, wherein the similarities are distances.
13. The method of claim 8, further comprising, prior to receiving the input embedding: receiving user-input; and generating the input embedding based on the user-input.
14. The method of claim 8, further comprising: adapting a computing device to perform the action.
15. A method for inserting entries into and retrieving information from an embedding object memory, the method comprising: receiving a content item, the content item having one or more content data; providing one of the content data associated with the content item to one or more semantic embedding models, wherein the one or more semantic embedding models generate one or more semantic embeddings; receiving, from one or more of the semantic embedding models, one or more semantic embeddings, wherein a collection of semantic embeddings is associated with a first semantic embedding model of the one or more semantic embedding models, and wherein the collection of semantic embeddings comprises a first semantic embedding generated by the first semantic embedding model for at least one content data from the respective content item; inserting the one or more semantic embeddings into the embedding object memory, wherein the embedding object memory stores one or more semantic embeddings from the collection of semantic embeddings, and wherein the one or more semantic embeddings are associated with a respective indication corresponding to a reference to source data associated with the one or more semantic embeddings; receiving an input embedding; retrieving a plurality of collections of stored semantic embeddings, from the semantic object memory, based on the input embedding; retrieving a subset of semantic embeddings from at least one of the plurality of collections of stored semantic embeddings based on a similarity to the input embedding; and providing the subset of semantic embeddings as an output.