# US 2022/0012599 A1 · Meta-heuristics based on heat maps for software discovery

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

- Number: US 2022/0012599 A1
- Document ID: US20220012599A1
- Status: Published application
- Kind: A1
- Application number: 16/924,320
- Filed: 2020-07-09
- Published: 2022-01-13
- Earliest claimed: 2020-07-09
- Assignees: International Business Machines Corporation
- Applicants: International Business Machines Corporation
- Inventors: TOMASZ ANDRZEJ STOPA; Grzegorz Sawina; Marcin Labenski
- Web page: https://patentgrep.com/patent/US20220012599A1

## CPC

- G06N 5/01: Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
- G06F 16/148: {File search processing}
- G06N 3/04: Architecture, e.g. interconnection topology
- G06N 3/0499: Feedforward networks
- G06N 3/08: Learning methods
- G06N 3/082: modifying the architecture, e.g. adding, deleting or silencing nodes or connections
- G06N 3/09: Supervised learning
- H04L 41/0853: by actively collecting configuration information or by backing up configuration information
- G06N 3/045: Combinations of networks
- G06N 3/048: Activation functions
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- 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)

## Abstract

An initial software scan is performed to detect a set of software deployed on an endpoint. An ongoing scan of the endpoint is performed to map a set of file directories associated with each software within the set of software. Via the ongoing scan, a usage frequency for each mapped file directory is determined. A heat map is generated for each mapped file directory, according to usage frequency, using a randomized meta-heuristic. A request is received for a software discovery scan result. The software discovery scan, based on the heat map, is performed in response to the request. The result of the software discovery scan is provided to a user.

## Claims

### Claim 1

A computer-implemented method for software discovery, the method comprising:
performing an initial software scan to detect a set of software deployed on an endpoint;
performing an ongoing scan of the endpoint to map a set of file directories associated with each software within the set of software;
determining, via the ongoing scan, a usage frequency for each mapped file directory;
generating a heat map for each mapped file directory, according to the usage frequency, using a randomized meta-heuristic;
receiving a request for a software discovery scan result;
performing, in response to the request, a software discovery scan based on the heat map; and
providing the software discovery scan result to a user.

### Claim 2 (depends on 1)

The method of claim 1, wherein the ongoing scan further comprises updating the heat map according to randomized sampling of the set of file directories.

### Claim 3 (depends on 2)

The method of claim 2, wherein the randomized sampling is performed according to the randomized meta-heuristic.

### Claim 4 (depends on 3)

The method of claim 3, wherein the randomized meta-heuristic includes a simulated annealing algorithm for determining a logical distance between two accessed files.

### Claim 5 (depends on 4)

The method of claim 4, wherein the two accessed files are a first file and a second, subsequently accessed, file.

### Claim 6 (depends on 4)

The method of claim 4, wherein the simulated annealing algorithm is performed using a neural network, and wherein the neural network is trained by at least adjusting a weight or bias of the neural network.

### Claim 7 (depends on 6)

The method of claim 6, wherein the neural network is provisioned using a cloud computing environment.

### Claim 8

A computer program product for software discovery, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a device to cause the device to:
perform an initial software scan to detect a set of software deployed on an endpoint;
perform an ongoing scan of the endpoint to map a set of file directories associated with each software within the set of software;
determine, via the ongoing scan, a usage frequency for each mapped file directory;
generate a heat map for each mapped file directory, according to the usage frequency, using a randomized meta-heuristic;
receive a request for a software discovery scan result;
perform, in response to the request, a software discovery scan based on the heat map; and
provide the software discovery scan result to a user.

### Claim 9 (depends on 8)

The computer program product of claim 8, wherein the ongoing scan further comprises updating the heat map according to randomized sampling of the set of file directories.

### Claim 10 (depends on 9)

The computer program product of claim 9, wherein the randomized sampling is performed according to the randomized meta-heuristic.

### Claim 11 (depends on 10)

The computer program product of claim 10, wherein the randomized meta-heuristic includes a simulated annealing algorithm for determining a logical distance between two accessed files.

### Claim 12 (depends on 11)

The computer program product of claim 11, wherein the two accessed files are first file and a second, subsequently accessed, file.

### Claim 13 (depends on 11)

The computer program product of claim 11, wherein the simulated annealing algorithm is performed using a neural network, and wherein the neural network is trained by at least adjusting a weight or bias of the neural network.

### Claim 14 (depends on 13)

The computer program product of claim 13, wherein the neural network is provisioned using a cloud computing environment.

### Claim 15

A system for software discovery, comprising:
a memory with program instructions included thereon; and
a processor in communication with the memory, wherein the program instructions cause the processor to:
perform an initial software scan to detect a set of software deployed on an endpoint;
perform an ongoing scan of the endpoint to map a set of file directories associated with each software within the set of software;
determine, via the ongoing scan, a usage frequency for each mapped file directory;
generate a heat map for each mapped file directory, according to the usage frequency, using a randomized meta-heuristic;
receive a request for a software discovery scan result;
perform, in response to the request, a software discovery scan based on the heat map; and
provide the software discovery scan result to a user.

### Claim 16 (depends on 15)

The system of claim 15, wherein the ongoing scan further comprises updating the heat map according to randomized sampling of the set of file directories.

### Claim 17 (depends on 16)

The system of claim 16, wherein the randomized sampling is performed according to the randomized meta-heuristic.

### Claim 18 (depends on 17)

The system of claim 17, wherein the randomized meta-heuristic includes a simulated annealing algorithm for determining a logical distance between two accessed files.

### Claim 19 (depends on 18)

The system of claim 18, wherein the two accessed files are first file and a second, subsequently accessed, file.

### Claim 20 (depends on 19)

The system of claim 19, wherein the simulated annealing algorithm is performed using a neural network, and wherein the neural network is trained by at least adjusting a weight or bias of the neural network.
