# US 2025/0156637 A1 · Transformer-based hybrid recommendation model with contextual feature support

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2025/0156637 A1
- Document ID: US20250156637A1
- Status: Published application
- Kind: A1
- Application number: 18/505,293
- Filed: 2023-11-09
- Published: 2025-05-15
- Earliest claimed: 2023-11-09
- Assignees: Oracle International Corporation
- Applicants: Oracle International Corporation
- Inventors: Cesare Bernardis; Damien Hilloulin; Rhicheek Patra; Sungpack Hong; Hassan Chafi
- Web page: https://patentgrep.com/patent/US20250156637A1

## CPC

- G06F 40/284: Lexical analysis, e.g. tokenisation or collocates
- G06F 16/9535: Search customisation based on user profiles and personalisation
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

In a computer-implemented embodiment, an interaction machine learning model is trained based on many interactions on many resources. A context lexical token is inferred that represents a current operational context of a user. The context lexical token is inserted into a sequence of other inferred lexical tokens. From the context lexical token within the sequence of tokens, the interaction machine learning model infers a predicted resource that will be accessed next. In an embodiment, accelerated matchmaking entails suitability measurement by a dot product of a) a dynamically inferred user embedding that is based on the context lexical token and b) a statically inferred item embedding.

## Claims

### Claim 1

A method comprising:
training, based on a plurality of interactions on a plurality of resources, an interaction machine learning model;
generating a context lexical token that represents an operational context that occurs after said training the interaction machine learning model; and
inferring by the interaction machine learning model, from the context lexical token, a predicted resource of said plurality of resources that will be accessed next.

### Claim 2 (depends on 1)

The method of claim 1 wherein said inferring the predicted resource that will be accessed is based on at least one selected from a group consisting of:
a lexical token that represents a user in the operational context,
a temporal sequence of interaction lexical tokens that each represents a respective distinct interaction that was already caused by a particular user, and
a plurality of padding lexical tokens that do not represent data.

### Claim 3 (depends on 1)

The method of claim 1 wherein said inferring the predicted resource that will be accessed is based on a sequence of lexical tokens that comprises:
the context lexical token,
a temporal sequence of interaction lexical tokens that each represents a respective distinct interaction that was already caused by a particular user, and
between the context lexical token and said temporal sequence of interaction lexical tokens, a predefined lexical token that does not represent data.

### Claim 4 (depends on 1)

The method of claim 1 further comprising inferring a particular lexical token that is a fixed-size embedding of an object, wherein the particular lexical token is selected from a group consisting of the context lexical token and an interaction lexical token that represents a respective distinct access of a respective resource by a particular user.

### Claim 5 (depends on 4)

The method of claim 4 further comprising dropout training an artificial neural network to perform said inferring the particular lexical token.

### Claim 6 (depends on 1)

The method of claim 1 further comprising inferring a respective fixed-size embedding of each resource in the plurality of resources.

### Claim 7 (depends on 6)

The method of claim 6 further comprising generating a multidimensional index of said fixed-size embeddings of the plurality of resources.

### Claim 8 (depends on 7)

The method of claim 7 further comprising using the predicted resource that will be accessed as a lookup key to retrieve, from the multidimensional index, a nearest neighbors subset of the fixed-size embeddings of the plurality of resources.

### Claim 9 (depends on 8)

The method of claim 8 wherein:
said inferring the predicted resource that will be accessed comprises generating a fixed-size embedding of the predicted resource;
said using the predicted resource that will be accessed as the lookup key comprises using the fixed-size embedding of the predicted resource as the lookup key.

### Claim 10 (depends on 9)

The method of claim 9 further comprising selecting, filtering, or ranking the nearest neighbors subset of the plurality of resources based on a respective dot product of the fixed-size embedding of the predicted resource and each fixed-size embeddings of the nearest neighbors subset of the fixed-size embeddings of the plurality of resources.

### Claim 11 (depends on 1)

The method of claim 1 wherein said inferring the predicted resource that will be accessed is based on a temporal sequence of interactions that occurred after said plurality of interactions.

### Claim 12

One or more non-transitory computer-readable media storing instructions that, when executed by one or more processors, cause:
training, based on a plurality of interactions on a plurality of resources, an interaction machine learning model;
generating a context lexical token that represents an operational context that occurs after said training the interaction machine learning model; and
inferring by the interaction machine learning model, from the context lexical token, a predicted resource of said plurality of resources that will be accessed next.

### Claim 13 (depends on 12)

The one or more non-transitory computer-readable media of claim 12 wherein said inferring the predicted resource that will be accessed is based on at least one selected from a group consisting of:
a lexical token that represents a user in the operational context,
a temporal sequence of interaction lexical tokens that each represents a respective distinct interaction that was already caused by a particular user, and
a plurality of padding lexical tokens that do not represent data.

### Claim 14 (depends on 12)

The one or more non-transitory computer-readable media of claim 12 wherein said inferring the predicted resource that will be accessed is based on a sequence of lexical tokens that comprises:
the context lexical token,
a temporal sequence of interaction lexical tokens that each represents a respective distinct interaction that was already caused by a particular user, and
between the context lexical token and said temporal sequence of interaction lexical tokens, a predefined lexical token that does not represent data.

### Claim 15 (depends on 12)

The one or more non-transitory computer-readable media of claim 12 wherein:
the instructions further cause inferring a particular lexical token that is a fixed-size embedding of an object;
the particular lexical token is selected from a group consisting of the context lexical token and an interaction lexical token that represents a respective distinct access of a respective resource by a particular user.

### Claim 16 (depends on 15)

The one or more non-transitory computer-readable media of claim 15 wherein the instructions further cause dropout training an artificial neural network to perform said inferring the particular lexical token.

### Claim 17 (depends on 12)

The one or more non-transitory computer-readable media of claim 12 wherein the instructions further cause inferring a respective fixed-size embedding of each resource in the plurality of resources.

### Claim 18 (depends on 17)

The one or more non-transitory computer-readable media of claim 17 wherein the instructions further cause generating a multidimensional index of said fixed-size embeddings of the plurality of resources.

### Claim 19 (depends on 18)

The one or more non-transitory computer-readable media of claim 18 wherein the instructions further cause using the predicted resource that will be accessed as a lookup key to retrieve, from the multidimensional index, a nearest neighbors subset of the fixed-size embeddings of the plurality of resources.

### Claim 20 (depends on 12)

The one or more non-transitory computer-readable media of claim 12 wherein said inferring the predicted resource that will be accessed is based on a temporal sequence of interactions that occurred after said plurality of interactions.
