System and method using large language models for the analysis of textual data associated with oil and gas operations

Abstract

The disclosure provides automated analysis of oil and gas textual data that uses one or more LLMs and designed prompts or prompt chains. The prompts, referred to a curated domain prompts, use oil and gas domain knowledge to simulate human thinking and analysis. The curated domain prompts are pre-configured such that users do not need to create prompts for analyzing the textual data. In one example, a method of automatically analyzing oil and gas textual data, includes: (1) obtaining a curated domain prompt that identifies an oil and gas operation event and a parameter associated with the oil and gas operation event, (2) automatically extracting, using a large language model (LLM), event data from oil and gas textual data based on the oil and gas operation event and the parameter, and (3) automatically generating an event summary that correlates the oil and gas operation event and the event data.

What is claimed is: 
     
         1 . An automated analyzer for reviewing oil & gas textual data, comprising:
 an interface configured to provide a curated domain prompt that identifies an oil and gas operation event and a parameter associated with the oil and gas operation event; and 
 one or more processors to perform operations including:
 directing a large language model (LLM) in extracting event data from oil and gas textual data based on the oil and gas operation event and the parameter, and 
 providing an event summary that correlates the oil and gas operation event and the event data. 
 
 
     
     
         2 . The analyzer as recited in  claim 1 , wherein the extracting includes filtering the oil and gas textual data based on the oil and gas operation event and automatically extracting the event data from the filtered oil and gas textual data. 
     
     
         3 . The analyzer as recited in  claim 1 , wherein the event summary is in a structured format. 
     
     
         4 . The analyzer as recited in  claim 1 , wherein the oil and gas textual data includes unstructured text. 
     
     
         5 . The analyzer as recited in  claim 1 , wherein the LLM is an online LLM. 
     
     
         6 . The analyzer as recited in  claim 1 , wherein the LLM is an offline LLM. 
     
     
         7 . The analyzer as recited in  claim 6 , wherein the offline LLM is a fine-tuned model. 
     
     
         8 . The analyzer as recited in  claim 1 , wherein the directing includes sending the curated domain prompt and at least a portion of the oil and gas textual data to the LLM. 
     
     
         9 . A method of automatically analyzing oil and gas textual data, comprising:
 obtaining a curated domain prompt that identifies an oil and gas operation event and a parameter associated with the oil and gas operation event;   automatically extracting, using a large language model (LLM), event data from oil and gas textual data based on the oil and gas operation event and the parameter, and   automatically generating an event summary that correlates the oil and gas operation event and the event data.   
     
     
         10 . The method as recited in  claim 9 , further comprising filtering the oil and gas textual data based on the oil and gas operation event, wherein the automatically extracting the event data is from the filtered oil and gas textual data. 
     
     
         11 . The method as recited in  claim 9 , wherein the event summary includes the parameters, the event data associated with the parameters, and the oil and gas operation event for each of the parameters. 
     
     
         12 . The method as recited in  claim 9 , wherein the oil and gas textual data includes pre-operation, active operation, and post operation textual data for the oil and gas operation event. 
     
     
         13 . The method as recited in  claim 9 , wherein the LLM is an offline LLM. 
     
     
         14 . The method as recited in  claim 9 , wherein the oil and gas textual data includes unstructured text. 
     
     
         15 . The method as recited in  claim 9 , wherein the automatically extracting includes augmented generation by the LLM. 
     
     
         16 . The method as recited in  claim 9 , wherein the automatically generating includes generating the event summary into a structured format identified in the domain prompt. 
     
     
         17 . The method as recited in  claim 9 , further comprising obtaining the oil and gas textual data and the curated domain prompt from a data reservoir. 
     
     
         18 . A textual analysis system for oil and gas textual data, comprising:
 a data reservoir configured to store oil and gas textual data; and   an automated analyzer for reviewing the oil and gas textual data, including:
 an interface configured to receive a curated domain prompt that identifies an oil and gas operation event and a parameter associated with the oil and gas operation event; and 
 one or more processors to perform operations including:
 instructing a large language model (LLM) to extract event data from oil and gas textual data based on the oil and gas operation event and the parameter, and 
 receiving an event summary from the LLM that correlates the oil and gas operation event and the event data. 
 
   
     
     
         19 . The well operation textual analysis system as recited in  claim 18 , wherein the instructing includes sending the curated domain prompt and the oil and gas textual data to the LLM. 
     
     
         20 . The well operation textual analysis system as recited in  claim 18 , wherein the operations further include sending the event summary to a well operation system for enacting or altering a well operation.