Product configurator with artificial intelligence based knowledge enrichment
AssigneeOracle International Corporation
InventorLatha Rajendran
Life of this patent
Estimating the term…
Abstract
Embodiments are directed to operating a cloud based product configurator. Embodiments store, as vectorized data in a vector database product, information corresponding to a first product to be configured. While configuring the first product, embodiments receive a query regarding the first product. Embodiments augment the query in response to a context based semantic search of the vector database using the query. Embodiments prompt a large language model (“LLM”) using the augmented query and receiving an LLM response. Embodiments the provide the LLM response in response to the query.
Claims20
A method of operating a cloud based product configurator, the method comprising:
- storing, as vectorized data in a vector database, product information corresponding to a first product to be configured, the product information comprising structured and unstructured documents, the unstructured documents comprising at least an image, wherein the storing comprises generating vector embeddings of the structured and unstructured documents;
- while configuring the first product via interacting with the product configurator, receiving a query regarding the first product, wherein configuring the first product comprises generating for the first product a configuration, a price and a quote;
- augmenting the query in response to a context based semantic search of the vector database using the query, wherein the augmented query comprises the query and the response to a context based semantic search of the vector database;
- prompting a large language model (LLM) using the augmented query and receiving an LLM response;
- and
- providing the LLM response in response to the query.
A non-transitory computer readable medium having instructions stored thereon that, when executed by one or more processors, cause the processor to operate a cloud based product configurator, the operating comprising:
- storing, as vectorized data in a vector database, product information corresponding to a first product to be configured, the product information comprising structured and unstructured documents, the unstructured documents comprising at least an image, wherein the storing comprises generating vector embeddings of the structured and unstructured documents;
- while configuring the first product via interacting with the product configurator, receiving a query regarding the first product, wherein configuring the first product comprises generating for the first product a configuration, a price and a quote;
- augmenting the query in response to a context based semantic search of the vector database using the query, wherein the augmented query comprises the query and the response to a context based semantic search of the vector database;
- prompting a large language model (LLM) using the augmented query and receiving an LLM response;
- and
- providing the LLM response in response to the query.
A cloud based product configurator system comprising:
- a vector database;
- a large language model (LLM);
- one or more processors coupled to the vector database and LLM, the processors configured to:
- store, as vectorized data in the vector database, product information corresponding to a first product to be configured, the product information comprising structured and unstructured documents, the unstructured documents comprising at least an image, wherein the storing comprises generating vector embeddings of the structured and unstructured documents;
- while configuring the first product via interacting with the product configurator, receive a query regarding the first product, wherein configuring the first product comprises generating for the first product a configuration, a price and a quote;
- augment the query in response to a context based semantic search of the vector database using the query, wherein the augmented query comprises the query and the response to a context based semantic search of the vector database;
- prompting the LLM using the augmented query and receiving an LLM response;
- and
- provide the LLM response in response to the query.
Dependencies are inferred from the claim text.