# US 12,585,879 B2 · Artificial intelligence assisted network operations reporting and management

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

- Number: US 12,585,879 B2
- Document ID: US12585879B2
- Status: Granted
- Kind: B2
- Application number: 18/338,075
- Filed: 2023-06-20
- Published: 2024-12-26
- Granted: 2026-03-24
- Earliest claimed: 2023-06-20
- Assignees: T-Mobile Innovations LLC
- Applicants: T-Mobile Innovations LLC
- Inventors: Oliver Coudert; Bharatwajan Raman
- Web page: https://patentgrep.com/patent/US12585879B2

## CPC

- G06F 40/30: Semantic analysis
- G06F 40/40: Processing or translation of natural language (natural language analysis G06F40/20; semantic analysis G06F40/30)
- H04L 41/16: using machine learning or artificial intelligence
- H04L 41/22: comprising specially adapted graphical user interfaces [GUI]
- H04W 16/18: Network planning tools
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)
- H04W: WIRELESS COMMUNICATION NETWORKS (broadcast communication H04H; communication systems using wireless links for non-selective communication, e.g. wireless extensions H04M1/72)

## Abstract

Systems, methods, and devices are disclosed herein for an application service that utilizes a large language model (LLM) to assist with performing management tasks associated with a wireless communications network. In an implementation, the application service receives natural language input indicative of a management task to complete with respect to the network. The application service identifies a context of the management task, which helps constrain the LLM to the appropriate domain(s). The application service generates a prompt that incorporates the task and the context and submits the prompt to the LLM. The application service receives from the LLM a reply that includes a plan that details a series of steps and associated resources of the domain for completing the management task. Upon receiving the LLM's reply, the application service performs the management task based on the provided plan.

## Claims

### Claim 1

A method for managing wireless network operations, the method comprising:
receiving natural language input indicative of a management task to complete with respect to a wireless communications network;
utilizing a natural langue processing model to tokenize the natural language input to generate tokens, analyze the tokens to identify a named entity, identify a grammatical relation between words of the natural langue input, and identify a context of the management task based on the named entity and the grammatical relation that will constrain a large language model (LLM) to a domain of the wireless communications network;
generating a prompt that identifies the management task and the context;
submitting the prompt to the LLM to elicit a reply indicating a plan for completing the management task that includes a list of steps and associated resources of the domain;
receiving the reply from the LLM, including the plan;
generating, based on the reply, a second prompt that identifies the plan and a template of the domain;
submitting the second prompt to the LLM to elicit a second reply that indicates access requirements for extracting, from a database of the domain, information related to the management task;
receiving the second reply from the LLM, wherein the second reply includes the access requirements; and
in response, automatically performing the management task based on the plan.

### Claim 2 (depends on 1)

The method of claim 1, wherein the context constrains the LLM to the domain, exclusive of multiple other domains, wherein the domain comprises one of a network infrastructure domain, a network operations domain, a data services domain, a voice services domain, and a sales domain, and wherein the multiple other domains include remaining ones of the network infrastructure domain, the network operations domain, the data services domain, the voice services domain, and the sales domain.

### Claim 3 (depends on 2)

The method of claim 2, wherein the management task comprises a report associated with the domain, and wherein performing the management task comprises:
accessing a database associated with the domain;
extracting from the database, information related to the management task; and
generating a report based on the information.

### Claim 4 (depends on 3)

The method of claim 3, wherein the report comprises a graphical representation of the information.

### Claim 5 (depends on 1)

The method of claim 1, wherein the wireless communications network comprises multiple domains, wherein the multiple domains are each associated with respective domain-specific features, and wherein the context comprises the domain-specific features of the multiple domains.

### Claim 6 (depends on 1)

The method of claim 1 wherein automatically performing the management task based on the plan comprises automatically performing the management task based on the plan and the access requirements in response to receiving the reply and the second reply from the LLM.

### Claim 7 (depends on 1)

The method of claim 1, wherein the access requirements comprise an algorithm, and wherein performing the management task comprises accessing the database of the domain using the algorithm.

### Claim 8 (depends on 1)

The method of claim 1, wherein performing the management task based on the plan comprises generating at least one of a graph, a chart, a word document, a slide presentation, and an animation.

### Claim 9 (depends on 1)

The method of claim 1, wherein performing the management task based on the plan comprises changing an operating parameter of an asset of the wireless communications network.

### Claim 10

A computing apparatus comprising:
one or more computer-readable storage media;
one or more processors operatively coupled with the one or more computer-readable storage media; and
program instructions stored on the one or more computer-readable storage media that, when executed by the one or more processors, direct the computing apparatus to at least:
receive natural language input indicative of a management task to complete with respect to a wireless communications network;
utilize a natural langue processing model to tokenize the natural language input to generate tokens, analyze the tokens to identify a named entity, identify a grammatical relation between words of the natural langue input, and identify a context of the management task based on the named entity and the grammatical relation that will constrain a large language model (LLM) to a domain of the wireless communications network;
generate a prompt that identifies the management task and the context;
submit the prompt to the LLM to elicit a reply indicating a plan for completing the management task that includes a list of steps and associated resources of the domain;
receive the reply from the LLM, including the plan;
generate, based on the reply, a second prompt that identifies the plan and a template of the domain;
submit the second prompt to the LLM to elicit a second reply that indicates access requirements for extracting, from a database of the domain, information related to the management task;
receive the second reply from the LLM, wherein the second reply includes the access requirements; and
in response, automatically perform the management task based on the plan.

### Claim 11 (depends on 10)

The computing apparatus of claim 10, wherein the context constrains the LLM to the domain, exclusive of multiple other domains, wherein the domain comprises one of a network infrastructure domain, a network operations domain, a data services domain, a voice services domain, and a sales domain, and wherein the multiple other domains include remaining ones of the network infrastructure domain, the network operations domain, the data services domain, the voice services domain, and the sales domain.

### Claim 12 (depends on 11)

The computing apparatus of claim 11, wherein the management task comprises a report associated with the domain, and wherein to perform the task the program instructions direct the computing apparatus to:
access a database associated with the domain;
extract from the database, information related to the management task; and
generate a report based on the information.

### Claim 13 (depends on 12)

The computing apparatus of claim 12, wherein the report comprises a graphical representation of the information.

### Claim 14 (depends on 10)

The computing apparatus of claim 10, wherein the program instructions further direct the computing apparatus to automatically perform the management task based on the plan and the access requirements in response to receiving the reply and the second reply.

### Claim 15 (depends on 10)

The computing apparatus of claim 10, wherein to perform the management task based on the plan, the program instructions direct the computing apparatus to generate at least one of a graph, a chart, a word document, a slide presentation, and an animation.

### Claim 16

One or more computer-readable storage media having program instructions stored thereon that, when executed by one or more processors operatively coupled with the one or more computer-readable storage media, direct a computing device to:
receive natural language input indicative of a management task to complete with respect to a wireless communications network;
utilize a natural langue processing model to tokenize the natural language input to generate tokens, analyze the tokens to identify a named entity, identify a grammatical relation between words of the natural langue input, and identify a context of the management task based on the named entity and the grammatical relation that will constrain a large language model (LLM) to a domain of the wireless communications network;
generate a prompt that identifies the management task and the context;
submit the prompt to the LLM to elicit a reply indicating a plan for completing the management task that includes a list of steps and associated resources of the domain;
receive the reply from the LLM, including the plan;
generate, based on the reply, a second prompt that identifies the plan and a template of the domain;
submit the second prompt to the LLM to elicit a second reply that indicates access requirements for extracting, from a database of the domain, information related to the management task;
receive the second reply from the LLM, wherein the second reply includes the access requirements; and
in response, automatically perform the management task based on the plan.

### Claim 17 (depends on 16)

The one or more computer-readable storage media of claim 16, wherein the context constrains the LLM to the domain, exclusive of multiple other domains, wherein the domain comprises one of a network infrastructure domain, a network operations domain, a data services domain, a voice services domain, and a sales domain, and wherein the multiple other domains include remaining ones of the network infrastructure domain, the network operations domain, the data services domain, the voice services domain, and the sales domain.

### Claim 18 (depends on 17)

The one or more computer-readable storage media of claim 17, wherein the management task comprises a report associated with the domain, and wherein to perform the task the program instructions direct the computing device to:
access a database associated with the domain;
extract from the database, information related to the management task; and
generate a report based on the information.

### Claim 19 (depends on 18)

The one or more computer-readable storage media of claim 18, wherein the report comprises a graphical representation of the information.

### Claim 20 (depends on 19)

The one or more computer-readable storage media of claim 19, wherein the program instructions further direct the computing device to automatically perform the management task based on the plan and the access requirements in response to receiving the reply and the second reply.
