# US 2026/0099533 A1 · Raw Content Storage and Analysis Using Topic Maps

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

- Number: US 2026/0099533 A1
- Document ID: US20260099533A1
- Status: Published application
- Kind: A1
- Application number: 19/398,208
- Filed: 2025-11-24
- Published: 2026-04-09
- Earliest claimed: 2024-08-30
- Assignees: Oracle International Corporation
- Applicants: Oracle International Corporation
- Inventors: Jean-Francois Verrier
- Web page: https://patentgrep.com/patent/US20260099533A1

## CPC

- G06F 16/358: Browsing; Visualisation therefor
- G06F 16/3329: Natural language query formulation
- G06F 16/3334: {Selection or weighting of terms from queries, including natural language queries}
- G06F 40/103: Formatting, i.e. changing of presentation of documents (automatic justification G06F40/189; automatic line break hyphenation G06F40/191)
- G06F 40/284: Lexical analysis, e.g. tokenisation or collocates
- G06F 40/30: Semantic analysis
- G06N 3/0475: Generative networks
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

Techniques for receiving, storing, analyzing, and utilizing raw content are disclosed. The system receives raw text from a user, including a first tag and second tags. The system identifies and removes formatting attributes in the raw text, including whitespace characters, to generate a normalized input. The system stores the normalized input in target dataset(s) and parses the normalized input for the first tag and the second tags. In this case, the first tag corresponds to one or more topics, and the second tags represent a computing system associated with corresponding portions of the normalized input. The system analyses the first tag and the second tags to identify the topics. The system generates one or more topic maps for the target dataset(s) based on the first tag and the one or more second tags. The topic map(s) include one or more references to content items within the target dataset(s).

## Claims

### Claim 1

One or more non-transitory computer-readable media comprising instructions that, when executed by one or more hardware processors, cause performance of operations comprising:
receiving raw text from a user; wherein the raw text comprises a first tag and one or more second tags;
identifying one or more formatting attributes in the raw text;
removing the one or more formatting attributes, comprising one or more whitespace characters, to generate a normalized input;
storing the normalized input in one or more target datasets; and
generating one or more topic maps for the one or more target datasets based on the first tag and the one or more second tags; wherein the one or more topic maps comprise one or more references to content items within the one or more target datasets.

### Claim 2 (depends on 1)

The one or more non-transitory computer-readable media of claim 1, wherein the generating the one or more topic maps comprises:
parsing the normalized input for the first tag and the one or more second tags; wherein the first tag corresponds to one or more topics and the one or more second tags represent a computing system associated with corresponding portions of the normalized input;
analyzing the first tag and the one or more second tags to identify the one or more topics; and
for each topic of the one or more topics:
generating a topic description based on the first tag, the one or more second tags, and the content items in the one or more target datasets that are relevant to the topic;
identifying a set of references to the first tag, the one or more second tags, and the content items in the set of one or more target datasets that are relevant to the topic; and
creating the topic map comprising the topic, the topic description, and the set of references;
wherein the one or more topic maps comprise the topic maps generated for the one or more topics.

### Claim 3 (depends on 1)

The one or more non-transitory computer-readable media of claim 1, further comprising:
receiving a first query;
selecting a second tag, from the one or more second tags, that corresponds to the first query;
identifying a subset of the one or more topic maps corresponding to the first query and the second tag;
generating a prompt for a generative artificial intelligence agent comprising a language model based on the first query, the identified subset of the one or more topic maps, and the selected second tag;
transmitting the prompt to the generative artificial intelligence agent;
receiving one or more results from the generative artificial intelligence agent; and
storing the one or more results for the first query.

### Claim 4 (depends on 3)

The one or more non-transitory computer-readable media of claim 3, wherein the identifying a subset of the one or more topic maps comprises:
generating a vector representation of the first query;
comparing the vector representation of the first query to one or more respective vector representations of the topic maps; and
selecting a subset of one or more topic maps based on one or more similarity measures for the vector representation of the first query and the one or more respective vector representations of the topic maps.

### Claim 5 (depends on 3)

The one or more non-transitory computer-readable media of claim 3, wherein the selecting the second tag that corresponds to the first query comprises:
parsing the first query to identify one or more references to a computing system named or described in the first query;
determining a second tag, from the one or more second tags, that matches the identified computing system; and
selecting the determined second tag as the second tag that corresponds to the first query.

### Claim 6 (depends on 3)

The one or more non-transitory computer-readable media of claim 3, wherein the operations further comprise:
receiving a second query; and
presenting, in response to receiving the second query, the one or more results on a display.

### Claim 7 (depends on 6)

The one or more non-transitory computer-readable media of claim 6, wherein the presenting the one or more results on a display comprises:
formatting the one or more results from the generative artificial intelligence agent into a hypertext markup language.

### Claim 8 (depends on 7)

The one or more non-transitory computer-readable media of claim 7, wherein the formatting the one or more results comprises:
receiving a uniform resource locator;
determining one or more formatting parameters associated with the uniform resource locator; and
rendering the one or more results based on the formatting parameters.

### Claim 9

A method comprising:
receiving raw text from a user; wherein the raw text comprises a first tag and one or more second tags;
identifying one or more formatting attributes in the raw text;
removing the one or more formatting attributes, comprising one or more whitespace characters, to generate a normalized input;
storing the normalized input in one or more target datasets; and
generating one or more topic maps for the one or more target datasets based on the first tag and the one or more second tags; wherein the one or more topic maps comprise one or more references to content items within the one or more target datasets;
wherein the method is performed by at least one device including a hardware processor.

### Claim 10 (depends on 9)

The method of claim 9, wherein the generating the one or more topic maps comprises:
parsing the normalized input for the first tag and the one or more second tags; wherein the first tag corresponds to one or more topics and the one or more second tags represent a computing system associated with corresponding portions of the normalized input;
analyzing the first tag and the one or more second tags to identify the one or more topics; and
for each topic of the one or more topics:
generating a topic description based on the first tag, the one or more second tags, and the content items in the one or more target datasets that are relevant to the topic;
identifying a set of references to the first tag, the one or more second tags, and the content items in the set of one or more target datasets that are relevant to the topic; and
creating the topic map comprising the topic, the topic description, and the set of references; and
wherein the one or more topic maps comprise the topic maps generated for the one or more topics.

### Claim 11 (depends on 9)

The method of claim 9, further comprising:
receiving a first query;
selecting a second tag, from the one or more second tags, that corresponds to the first query;
identifying a subset of the one or more topic maps corresponding to the first query and the second tag;
generating a prompt for a generative artificial intelligence agent comprising a language model based on the first query, the identified subset of the one or more topic maps, and the selected second tag;
transmitting the prompt to the generative artificial intelligence agent;
receiving one or more results from the generative artificial intelligence agent; and
storing the one or more results for the first query.

### Claim 12 (depends on 11)

The method of claim 11, wherein the identifying a subset of the one or more topic maps comprises:
generating a vector representation of the first query;
comparing the vector representation of the first query to one or more respective vector representations of the topic maps; and
selecting a subset of one or more topic maps based on one or more similarity measures for the vector representation of the first query and the one or more respective vector representations of the topic maps.

### Claim 13 (depends on 11)

The method of claim 11, wherein the selecting the second tag that corresponds to the first query comprises:
parsing the first query to identify one or more references to a computing system named or described in the first query;
determining a second tag, from the one or more second tags, that matches the identified computing system; and
selecting the determined second tag as the second tag that corresponds to the first query.

### Claim 14 (depends on 11)

The method of claim 11, wherein the method further comprises:
receiving a second query; and
presenting, in response to receiving the second query, the one or more results on a display.

### Claim 15 (depends on 14)

The method of claim 14, wherein the presenting the one or more results on a display comprises:
formatting the one or more results from the generative artificial intelligence agent into a hypertext markup language.

### Claim 16 (depends on 15)

The method of claim 15, wherein the formatting the one or more results comprises:
receiving a uniform resource locator;
determining one or more formatting parameters associated with the uniform resource locator; and
rendering the one or more results based on the formatting parameters.

### Claim 17

A system comprising:
one or more hardware processors;
one or more non-transitory computer-readable media; and
program instructions stored on the one or more non-transitory computer-readable media that, when executed by the one or more hardware processors, cause the system to perform operations comprising:
receiving raw text from a user; wherein the raw text comprises a first tag and one or more second tags;
identifying one or more formatting attributes in the raw text;
removing the one or more formatting attributes, comprising one or more whitespace characters, to generate a normalized input;
storing the normalized input in one or more target datasets; and
generating one or more topic maps for the one or more target datasets based on the first tag and the one or more second tags; wherein the one or more topic maps comprise one or more references to content items within the one or more target datasets;
parsing the normalized input for the first tag and the one or more second tags; wherein the first tag corresponds to one or more topics and the one or more second tags represent a computing system associated with corresponding portions of the normalized input;
analyzing the first tag and the one or more second tags to identify the one or more topics; and
for each topic of the one or more topics:
generating a topic description based on the first tag, the one or more second tags, and the content items in the one or more target datasets that are relevant to the topic;
identifying a set of references to the first tag, the one or more second tags, and the content items in the set of one or more target datasets that are relevant to the topic; and
creating the topic map comprising the topic, the topic description, and the set of references;
wherein the one or more topic maps comprise the topic maps generated for the one or more topics;
receiving a first query;
selecting a second tag, from the one or more second tags, that corresponds to the first query;
identifying a subset of the one or more topic maps corresponding to the first query and the second tag;
generating a prompt for a generative artificial intelligence agent comprising a language model based on the first query, the identified subset of the one or more topic maps, and the selected second tag;
transmitting the prompt to the generative artificial intelligence agent;
receiving one or more results from the generative artificial intelligence agent;
storing the one or more results for the first query.
