# US 2022/0277404 A1 · Pattern Identification in Time-Series Social Media Data, and Output-Dynamics Engineering for a Dynamic System Having One or More Multi-Scale Time-Series Data Sets

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

- Number: US 2022/0277404 A1
- Document ID: US20220277404A1
- Status: Published application
- Kind: A1
- Application number: 17/748,173
- Filed: 2022-05-19
- Published: 2022-09-01
- Earliest claimed: 2016-01-15
- Assignees: Carnegie Mellon University
- Applicants: Carnegie Mellon University
- Inventors: Radu Marculescu; Huan-Kai Peng
- Web page: https://patentgrep.com/patent/US20220277404A1

## CPC

- H04L 67/535: {Tracking the activity of the user (network monitoring arrangements H04L43/00; recording of computer activity G06F11/34)}
- G06N 7/01: Probabilistic graphical models, e.g. probabilistic networks
- G06N 20/00: Machine learning
- G06N 20/10: using kernel methods, e.g. support vector machines [SVM]
- G06Q 10/44: Identification of trends within social networks, e.g. identification of trending topics
- G06Q 30/0282: Rating or review of business operators or products
- H04L 51/216: Handling conversation history, e.g. grouping of messages in sessions or threads
- H04L 51/52: for supporting social networking services
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR

## Abstract

In some aspects, computer-implemented methods of identifying patterns in time-series social-media data. In an embodiment, the method includes applying a deep-learning methodology to the time-series social-media data at a plurality of temporal resolutions to identify patterns that may exist at and across ones of the temporal resolutions. A particular deep-learning methodology that can be used is a recursive convolutional Bayesian model (RCBM) utilizing a special convolutional operator. In some aspects, computer-implemented methods of engineering outcome-dynamics of a dynamic system. In an embodiment, the method includes training a generative model using one or more sets of time-series data and solving an optimization problem composed of a likelihood function of the generative model and a score function reflecting a utility of the dynamic system. A result of the solution is an influence indicator corresponding to intervention dynamics that can be applied to the dynamic system to influence outcome dynamics of the system.

## Claims

### Claim 1

A computer-implemented method of engineering outcome dynamics of a dynamic system that includes one or more multi-scale time-series data sets, the computer-implemented method comprising:
training a generative model using each of the one or more multi-scale time-series data sets;
providing an optimization problem composed of a likelihood function of the generative model and a score function that reflects a utility of the dynamic system;
solving the optimization problem so as to determine an influence indicator indicating an influence scheme for influencing the outcome dynamics; and
providing the influence indicator to an outcome-dynamics influencing system.

### Claim 2 (depends on 1)

The computer-implemented method according to claim 1, wherein the generative model comprises a recursive convolutional Bayesian model (RCBM).

### Claim 3 (depends on 2)

The computer-implemented method according to claim 2, wherein the RCBM uses a convolutional operator that carries out a scale-and-copy task.

### Claim 4 (depends on 1)

The computer-implemented method according to claim 1, wherein the computer-implemented method is configured for a particular application, and the score function is selected based on the particular application.

### Claim 5 (depends on 4)

The computer-implemented method according to claim 4, wherein the score function is a pattern-matching score function.

### Claim 6 (depends on 4)

The computer-implemented method according to claim 4, wherein the score function is a profit-maximization score function.

### Claim 7 (depends on 4)

The computer-implemented method according to claim 4, wherein the particular application comprises a social-media marketing campaign.

### Claim 8 (depends on 1)

The computer-implemented method according to claim 1, wherein the particular application comprises event-alert notification.

### Claim 9 (depends on 1)

The computer-implemented method according to claim 1, wherein the one or more multi-scale time-series data sets includes a social-media data set.

### Claim 10 (depends on 9)

The computer-implemented method according to claim 9, wherein the social-media data set comprises a social-media data stream.

### Claim 11 (depends on 1)

The computer-implemented method according to claim 1, wherein the one or more multi-scale time-series data sets includes video data.

### Claim 12

A machine-readable storage medium containing computer-executable instructions for performing a method of engineering outcome dynamics of a dynamic system that includes one or more multi-scale time-series data sets, the computer-implemented method comprising:
training a generative model using each of the one or more multi-scale time-series data sets;
providing an optimization problem composed of a likelihood function of the generative model and a score function that reflects a utility of the dynamic system;
solving the optimization problem so as to determine an influence indicator indicating an influence scheme for influencing the outcome dynamics; and
providing the influence indicator to an outcome-dynamics influencing system.

### Claim 13 (depends on 12)

The machine-readable storage medium of claim 12, wherein the generative model comprises a recursive convolutional Bayesian model (RCBM).

### Claim 14 (depends on 13)

The machine-readable storage medium of claim 13, wherein the RCBM uses a convolutional operator that carries out a scale-and-copy task.

### Claim 15 (depends on 12)

The machine-readable storage medium of claim 12, wherein the computer-implemented method is configured for a particular application, and the score function is selected based on the particular application.

### Claim 16 (depends on 15)

The machine-readable storage medium of claim 15, wherein the score function is a pattern-matching score function.

### Claim 17 (depends on 15)

The machine-readable storage medium of claim 15, wherein the score function is a profit-maximization score function.

### Claim 18 (depends on 15)

The machine-readable storage medium of claim 15, wherein the particular application comprises a social-media marketing campaign.

### Claim 19 (depends on 12)

The machine-readable storage medium of claim 12, wherein the particular application comprises event-alert notification.

### Claim 20 (depends on 12)

The machine-readable storage medium of claim 12, wherein the one or more multi-scale time-series data sets includes a social-media data set.
