# US 2026/0017263 A1 · Method for Obtaining a Search Result for a Search Query within a Database System of a Plant

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

- Number: US 2026/0017263 A1
- Document ID: US20260017263A1
- Status: Published application
- Kind: A1
- Application number: 19/263,696
- Filed: 2025-07-09
- Published: 2026-01-15
- Earliest claimed: 2024-07-11
- Assignees: ABB Schweiz AG
- Applicants: ABB Schweiz AG
- Inventors: Ruomu Tan; Nicolai Schoch; Divyasheel Sharma; Reuben Borrison
- Web page: https://patentgrep.com/patent/US20260017263A1

## CPC

- G06F 16/2455: Query execution
- G06F 16/338: Presentation of query results
- G06F 16/2477: {Temporal data queries}
- G06F 16/248: Presentation of query results
- G06F 16/3329: Natural language query formulation
- G06F 30/20: Design optimisation, verification or simulation (optimisation, verification or simulation of circuit designs G06F30/30)
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

A method for obtaining a search result for a search query within a database system of a plant, the database system configured for storing multimodal operating data of the plant, the method comprising: obtaining the search query indicative of an operating characteristic in the operating of the plant to be searched within the database system; executing the search query by an artificial intelligence/machine learning, AI/ML, search component within the database system for finding the searched operating characteristic and time intervals of the operating characteristic among different data modalities of the multimodal data therein; and obtaining a search result indicative of the operating characteristic and its time intervals found by the execution of the search query by the AI/ML search component.

## Claims

### Claim 1

A method for obtaining a search result for a search query within a database system of a plant, the database system storing multimodal operating data of the plant, the method comprising:
obtaining the search query indicative of an operating characteristic in the operating of the plant to be searched within the database system;
executing the search query by an artificial intelligence/machine learning (AI/ML), search component within the database system for finding the searched operating characteristic and time intervals of the operating characteristic among different data modalities of the multimodal data therein; and
obtaining a search result indicative of the operating characteristic and its time intervals found by the execution of the search query by the AI/ML search component.

### Claim 2 (depends on 1)

The method of claim 1, wherein the AI/ML search component is a generative AI/ML search component based on at least a Large Language Model (LLM) and/or a multimodal model.

### Claim 3 (depends on 1)

The method of claim 1, wherein the database system contains data representations of the multimodal operating data in a joint embedding space.

### Claim 4 (depends on 3)

The method of claim 3, wherein the data representations of the multimodal operating data are contextually linked with one another by an information model and/or a knowledge graph.

### Claim 5 (depends on 1)

The method of claim 1, wherein the operating characteristic is an operating parameter of the plant and/or an operating problem of the plant.

### Claim 6 (depends on 1)

The method of claim 1, wherein the search query comprises natural language text, a function, a time series of values, and/or an image indicative of the operating characteristic.

### Claim 7 (depends on 1)

The method of claim 1, wherein the multimodal operating data in the database system is at least from one or more of: time series data, text data, log data, and/or image data.

### Claim 8 (depends on 1)

The method of claim 1, wherein the multimodal operating data in the database system stores one or more of: process variables data, process topology data, analytical model data, operating manual data, event log data, alarm log data, and/or maintenance log data.

### Claim 9 (depends on 1)

The method of claim 1, wherein the search result is configured as a visualization of the found operating characteristic over a timeline including the time intervals.

### Claim 10 (depends on 1)

The method of claim 1, wherein the method (100) further comprises determining a state of the plant for one of the time intervals indicated by the search result, the state being indicative of several operating characteristics of the plant based on the multimodal operating data of the database system.

### Claim 11 (depends on 10)

The method of claim 10, wherein the method further comprises navigating through the determined state of the plant along a timeline including the time interval on a user interface of a data processing system, the several operating characteristics of the state changing while navigating the timeline based on the multimodal operating data of the database system.

### Claim 12 (depends on 1)

The method of claim 1, wherein the method (100) further comprises utilizing the search result for analyzing, planning and/or simulating an operation of the plant.

### Claim 13 (depends on 1)

The method of claim 1, wherein the search query is received on a user interface of a data processing system and the search result is provided on the user interface.

### Claim 14

A computer program comprising a set of computer executable instructions stored in tangible media that, when executed by a computer, cause the computer to carry out a method for obtaining a search result for a search query within a database system of a plant, the database system storing multimodal operating data of the plant, the method comprising:
instructions for obtaining the search query indicative of an operating characteristic in the operating of the plant to be searched within the database system;
instructions for executing the search query by an artificial intelligence/machine learning (AI/ML), search component within the database system for finding the searched operating characteristic and time intervals of the operating characteristic among different data modalities of the multimodal data therein; and
instructions for obtaining a search result indicative of the operating characteristic and its time intervals found by the execution of the search query by the AI/ML search component.
