# US 2016/0259638 A1 · Software patch management incorporating sentiment analysis

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

- Number: US 2016/0259638 A1
- Document ID: US20160259638A1
- Status: Published application
- Kind: A1
- Application number: 14/744,315
- Filed: 2015-06-19
- Published: 2016-09-08
- Earliest claimed: 2015-03-04
- Assignees: International Business Machines Corporation
- Applicants: International Business Machines Corporation
- Inventors: Kaoutar El Maghraoui; Joefon Jann; Pratap C. Pattnaik; Clifford A. Pickover
- Web page: https://patentgrep.com/patent/US20160259638A1

## CPC

- G06F 8/65: Updates (security arrangements therefor G06F21/57)
- G06F 40/30: Semantic analysis
- G06F 8/71: Version control (security arrangements therefor G06F21/57); Configuration management
- G06F 40/253: Grammatical analysis; Style critique
- G06N 20/00: Machine learning
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

A method and system are provided. The method includes generating, by a machine-based sentiment prediction generator, respective machine-determined sentiment predictions for each of a plurality of software patches using sentiment analysis. The method further includes setting, by a sentiment-based confidence value generator, a confidence value for each of the plurality of software patches based on the machine-determined sentiment predictions. The method also includes at least one of selecting and prioritizing, by a software patch selector and prioritizer, at least one of the plurality of software patches based on the respective confidence value therefor.

## Claims

### Claim 1

A method, comprising:
generating, by a machine-based sentiment prediction generator, respective machine-determined sentiment predictions for each of a plurality of software patches using sentiment analysis;
setting, by a sentiment-based confidence value generator, a confidence value for each of the plurality of software patches based on the machine-determined sentiment predictions; and
at least one of selecting and prioritizing, by a software patch selector and prioritizer, at least one of the plurality of software patches based on the respective confidence value therefor.

### Claim 2 (depends on 1)

The method of claim 1, further comprising providing, by a software patch providing device, to a user device the least one of the plurality of software patches based on at least one of a selection result and a prioritization result.

### Claim 3 (depends on 1)

The method of claim 1, wherein said setting step comprises adjusting a confidence value for a given one of the plurality of software patches based on a sentiment analysis result for the given one of the plurality of software patches.

### Claim 4 (depends on 1)

The method of claim 1, further comprising determining, by a software patch application time determination device, an application time for at least one of the plurality of software patches based on the respective confidence value therefor.

### Claim 5 (depends on 1)

The method of claim 1, wherein at least one of selecting and prioritizing at least one of the plurality of software patches comprises generating a ranked list of at least two of the plurality of software patches based on the respective confidence value therefor.

### Claim 6 (depends on 1)

The method of claim 1, wherein the sentiment analysis is of at least one of, at least one user, at least one group, and at least one organization.

### Claim 7 (depends on 1)

The method of claim 1, further comprising tracking, by a sentiment tracker, a sentiment relating to at least one of the plurality of software patches over a given time period.

### Claim 8 (depends on 7)

The method of claim 7, wherein the given time period relates to a help-desk transcript.

### Claim 9 (depends on 7)

The method of claim 7, wherein the sentiment analysis comprises performing natural language processing to determine one or more of the machine-determined sentiment predictions.

### Claim 10 (depends on 1)

The method of claim 1, wherein the sentiment analysis comprises:
building a sentiment analysis graph, where graph nodes represent at least one of respective users and respective software patches, and edges indicate sentiment between the respective users and the respective software patches; and
clustering the respective users into one of at least three clusters that include a positive sentiment cluster, a negative sentiment cluster, and a neutral sentiment cluster.

### Claim 11 (depends on 10)

The method of claim 10, wherein the sentiment analysis further comprises attaching to each of the at least three clusters a respective metric or features vector that comprises common features among users within the same cluster.

### Claim 12 (depends on 1)

The method of claim 1, wherein the machine-determined sentiment predictions are generated using culturally aware sentiment analysis that, in turn, uses automatically triggered questions formulated to elicit culturally distinguishable answers.

### Claim 13 (depends on 11)

The method of claim 11, further comprising adjusting or overriding a machine-determined sentiment prediction using a graphical user interface having a plurality of potentially applicable sentiment designations.

### Claim 14 (depends on 13)

The method of claim 13, wherein the plurality of potential overriding sentiment designations comprise positive, negative, and neutral.

### Claim 15 (depends on 14)

The method of claim 14, further comprising learning, by a sentiment learning device, from at least one of user-overridden or user-adjusted sentiment values for a given machine-determined sentiment prediction for a given one of the plurality of software patches.

### Claim 16 (depends on 1)

The method of claim 1, further comprising minimizing a time period for generating a particular machine-generated sentiment prediction by reusing a prior machine-generated sentiment prediction for a same user, a same group, and a same company, relating to at least one of a same software patch and a similar software patch.

### Claim 17 (depends on 1)

The method of claim 1, further comprising identifying, by a sentiment analysis benefit likelihood determination device, certain ones of the plurality of software patches for which the sentiment analysis has a likelihood of providing a benefit.

### Claim 18 (depends on 1)

The method of claim 1, further comprising considering, by the software patch selector and prioritizer, software patch dependencies along with sentiment dependencies for at least one of a user, a group, and an organization, in an environment where multiple software patches have a likelihood of being installed.
