Cluster based node assignment in multi-dimensional feature space

Abstract

Techniques include accessing a set of clusters, where each cluster is defined to cover a portion of a multi-dimensional feature space, and each cluster is associated with a label of a plurality of labels. A plurality of content items is received from a plurality of data sources. The label is assigned to each of the plurality of content items using one or more label machine learning models. Using a feature-vector machine learning model, a set of feature vectors for the plurality of content items are identified. A feature vector is associated with a respective portion in the multi-dimensional feature space. Portions in the multi-dimensional feature space corresponding to the plurality of labels are identified. A cluster from the plurality of clusters is assigned to the feature vector based on a proximity of the feature vector to the plurality of clusters in the multi-dimensional feature space.

Description

[0001] - -,, , , .. . , - . - . . . , - - -- , - , , , ,. . , , . . - . -- . , ., , ., . , . , ’ , . , . . ,, . , , , , - - . . , . - - .. - . , - - . , , - .. , .- , - - . , , . , , - . - ,, , , , . - , . . , , - -.- . . - . - , - - , . , - ., . , - . , - . . -- - . - , , , , - . - - . ., . . , . . . .. , , . . ,. , . . . . -. . . . . . . . . .- . . . . . .- . . ,. . . . . ., , . . . . . - - . . . , ,.., " , , .. " " " " " . - . , , , , .. . , , , - , , . , - . . , , , ,. . , , , . . . .- . , , - . . . . ., , .., , . ,. ,. - , . , - , ,,. .- - . , . , , , ,. . .. - -- . . . - .. , . . , ., - -, , ,. , ,. , ,. , , , ,, -. . , ..,.., , . , ,, ,- , , ,. , ,- ., , , , . , . , . , . .. . , , , , ., , , , ,, . , . , , . . . , - . . . ,- - . . .. . . . . " , , , " ,. , , , . . . , , , . - ..- - - . - . ,- - - . .. . , - ,.., - . , , , , , - ., . - - . -- .. - . . , - ,. , . , . . . ., . .. . , . . , ,. , . , . , , , - , . , . - -- , - , - , , , ,. - . - , . . . . ,. ,, .. , . . . . . . , , .., .. , , ,,. - , . . - , . - , . .., - , , , , . - , . , , ..- , . , . . . ' , , , . . ' . , . . . , , . . ., ”. , " , . , . . . , .. . .. , .. . . , , . . . , , , , , , , . , - - .. , . . . . , , ,. , , ,, , , , ., , . , . . , - . . . , , . , , , . . . . . --,. , , , , ,. . , , , . , . . . . . . , , . . . . , .. , . , .. . . . . . , . , . . , , .. , . ,, ,. , . , . . , ., , . , ,.. , .. -. - , . , , . , . . , , , , ,. ,,. .- . . . , . . - . .. , . .. - .. . , . , , , . , . , ,. . . . , ,. ., , , , -. . .. ,, , . ,. ,. , . . , . , . . . . .. , , , . . . . , , ,. . , .. , . , . , . ,. - ,.. . -,. . , . , . , . . . . . . , . , , , , , . . , . ,, , , .. . , . , , . , , ., , .. , . , . . . - . . - - .. , . . . . . . , , ,’ .. , . , . . , . . .

[0002] . ' - . , , , , ,. ", . " ,, .. , “ . ,” . - . . =. “”” . , “ . . - .. =. """ , """ , . , , . , , ., , .. . - .. . . . . , . . . , ,. , . .. . - . - -. . . . - .. . , . , .,, . _ , = - - . - -- , , . . , . . ,, ,, . .,, . . , . - . , - - . . . . , .- . . ,,,,,,,,, . . ,. -. . . ,, , . . , . . . , , , , . . , . . , . . . . ,, . .,, , , . , , , , . , . . , .- . ., , , . . , . . ,. , .. , .. , , , - . , . , , ,- . , . , - . , . , . . .. , , , ,, ,, , . . , , . . .-. .-. , ., , . , , . . , , . , ' . . . ., , . , , ., . , , .. ,. , -, ,..,,- ,. , , . , , , , , , , , , ,., , . .. . , , . , , , , ,-,. . , ., ,. , . . .- - - - - . . - ., , , - . , ,. . - -. . , - . . , ., , . . . , . . , , . , , . . . . . , , .,, .. , , , ., . . . . ,, , . . - .,. , . . , , .. . ,. ,, .., , , , , - , - . , , , , , , , , , , . . , , .. . . , , , , ., , , -,. . . - . - - -- - . - , , . , , , - . , . . . . . , , - . . - , .. , . , . . - , . ., . , - . . , , . . . , , , ,, . , , , , . . - , -- , . , , , , , , , . . , , ., . , , . , . . . - , , , . . .. . , ,, , ,, ® , ., , ,®- , ..,-®,®,™, , ™, ,.., ...,®,®, ,..,®, ,®-, , .. ..,®, ,, . , ..,- , - , . , , , , , . -,, - , , , , ,, , , , ..,®, - , . , ,. , ,- , , ,®, , ,- ,.., , , , . . . , , - ., ,®,, , , , ,, , . ,, , ,, .®, ,®- - , ,, ,.., , , -. , , , . , . , , .. , - ..,. ,, , .- , . , ., , , ,-, . . , , , - . , , , - .. - - . ., , , . ., . , , , , , . . . , . , .. , ,., , . , , . . . , .., ' , ' . . ’ , , , , . ,.., , ', , , , . . , , ,. ,, , , . , , ., , , , ,. , , - . ,. , , , , , , , , , .. , , ., , . , , . , , ,, , . , , , , , . - , , , - , - ., , , . , ' .. . , , , . , .., . , . ,, ,. , .. , , , , ,. , . , . , . , . , ,. . , ,, , , , ..., . .., . ., ,. , , . , , , ",". . ,- . , - , , ,, , . . , . , , , , , , , , ,, . , , , , . ., . ., , , , , . , , . , , , . . , ... , , , . ., . , , . , , . , , . , . , . .., . , . , . ., , ', ., , , . , , ,. . , . . , ’ . , , -, ., . . , , . ., . , . . , - , . - , . . , ., , , , , , , ., , . ,. , . , ,. , , . , , , . - , , , , , . , . . , - , . , . , . - . , . , , , . , , , , , , ,, ,, . ,® ®, ® . ® .., " ".., . , . ..,®, , , , ,, , , , , , , , , . , , , ,, , , . , , , , , . - . , , , - ,. , , , , ,, . , , , , , ,, ,., , - . - .., , , . .. . - . -. , - , . . - , , . , -, , . , , , , . , . , , ,- , ® ,., , .®, ,-, , -®,®,®, , -®,®,®, . - . . , - , ,, , , , . , - - , ,®, ,, - ,,®, . - , , , ,. - , ,- - , - ,, , ,, , , - , . , - -,. ,. , . ,, , . , .., , ,, . . . , . ., . . , . , . . , ,, .., , ,- . , , , , . , . .., , , , . , , . , , - ,®,®. , - , , , - . , , , , , .., , . , . , , , . ..,®,®, , ..,®, , ,- , , , ,, . . . , . . . , ., , , . , , . , , , . . .. - ,, , . . , , , . , , , , - , , . - , . ,. ,, , , , . ,- .,, , . , . . . , ,, , , , , .. , , .

Claims

AMENDED CLAIMS received by the International Bureau on 26 June 2025 (26.06.2025)1. A computer-implemented method, the method comprising: receiving an input content item; for the input content item, generating a prompt to a natural language machine learning model, wherein the prompt comprises: a plurality of entity relationship types, at least one example output entity relationship type and output entities for an example content item, and a request to determine, for the input content item, which entity relationship type of the plurality of entity relationship types and which entities correspond to the input content item; causing execution of the prompt to determine a particular entity relationship type and two or more entities that correspond to the input content item; determining at least a particular feature vector of at least a particular entity of the two or more entities; accessing a set of clusters from a plurality of clusters, wherein each cluster is defined to include entities and relationships between entities; determining, for assigning to the particular feature vector, a cluster from the plurality of clusters, based on a proximity, in a multi-dimensional feature space of a feature vector machine learning model, of the particular feature vector to a plurality of feature vectors representing at least a plurality of stored entities defined for the plurality of clusters; and assigning the particular feature vector to the determined cluster; and using the determined cluster to respond to a query about the particular entity.

2. The computer-implemented method of claim 1, wherein the determined cluster is updated based on the assigning of the particular feature vector to the determined cluster.

3. The computer-implemented method of claim 1 or claim 2, further comprising: determining the proximity based on a similarity score for each of the plurality of feature vectors representing at least the plurality of stored entities defined for the plurality of clusters.

4. The computer-implemented method of claim 3, wherein the determining the cluster for assigning to the particular feature vector comprises determining a cluster with a highest similarity score among the plurality of clusters.

5. The computer-implemented method of claim 4, wherein, for another particular entity relationship type and another two or more entities that correspond to another input content item, a new cluster is assigned to another particular feature vector of at least another entity of the two or more other entities when the similarity score between the other particular feature vector and each of the plurality of feature vectors is below a predefined threshold.

6. The computer-implemented method of any of claims 1-5, wherein the plurality of entity relationship types includes acquisitions, joint ventures, mergers, bankruptcy, layoffs, lawsuits, or funding.

7. The computer-implemented method of any of claims 1-6, wherein each of the plurality of clusters include nodes and edges, the nodes are associated with entities and the edges associated with relationship-types.

8. A system comprising: one or more processors; and a memory coupled to the one or more processors, the memory storing a plurality of instructions executable by the one or more processors, the plurality of instructions that when executed by the one or more processors cause the one or more processors to perform a set of operations comprising the operations recited in any of claims 1-7.

9. A transitory or non-transitory computer-readable medium storing a plurality of instructions executable by one or more processors that, when executed by the one or more processors, cause the one or more processors to perform operations comprising the operations recited in any of claims 1-7.

Images