# US 2012/0254078 A1 · Markov modeling of service usage patterns

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

- Number: US 2012/0254078 A1
- Document ID: US20120254078A1
- Status: Published application
- Kind: A1
- Application number: 13/157,006
- Filed: 2011-06-09
- Published: 2012-10-04
- Earliest claimed: 2011-03-28
- Assignees: Google Inc.
- Inventors: Karan BHATNAGAR; Rohan KHOT
- Web page: https://patentgrep.com/patent/US20120254078A1

## CPC

- G06N 7/01: Probabilistic graphical models, e.g. probabilistic networks
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

A system for analyzing service usage utilizing Markov models. Records of client requests to the service are extracted from at least one log. The records are grouped by client and sorted by timestamp. A pattern of requests that form an action is detected. Each action has a time. A probability is calculated of a transition from a precedent action to a subsequent action, where the precedent action has a time prior to the subsequent action. A delay time is also calculated between a precedent action and a subsequent action. A probability is calculated for a delay time, such as the likelihood that a delay from a precedent action to a subsequent action will fall within a given time interval.

## Claims

### Claim 1

A computer-implemented method for modeling service usage, comprising:
extracting a plurality of records from at least one log, each record having a timestamp and at least one request;
grouping the extracted records by client;
sorting a group of client records by timestamp;
detecting an action comprising a pattern of requests, where the action has a time;
calculating, by a processor, the probability of a transition from a precedent action to a subsequent action, where the precedent action has a time prior to the time of the subsequent action;
calculating, a delay time for a precedent action and a subsequent action, where the delay time is the difference between the precedent action time and the subsequent action time; and
calculating the probability of a delay time for a transition from the precedent action to the subsequent action.

### Claim 2 (depends on 1)

The computer-implemented method of claim 1, wherein the pattern comprises a plurality of requests from one record.

### Claim 3 (depends on 1)

The computer-implemented method of claim 1, wherein the pattern comprises a plurality of requests from one record.

### Claim 4 (depends on 1)

The computer-implemented method of claim 1, wherein a client is at least one from the group of a computer, a user, an application, a process and a peer.

### Claim 5

A computer-implemented method for modeling service usage, comprising:
extracting a plurality of records from at least one log, each record having a timestamp and at least one request;
grouping the extracted records by client;
sorting a group of client records by timestamp;
detecting an action comprising a pattern of requests, where the action has a time;
calculating, by a processor, the probability of a transition from a precedent action to a subsequent action, where the precedent action has a time prior to the time of the subsequent action.

### Claim 6 (depends on 5)

The computer-implemented method of claim 5, wherein the pattern comprises a plurality of requests from one record.

### Claim 7 (depends on 5)

The computer-implemented method of claim 5, wherein the pattern comprises a plurality of requests from one record.

### Claim 8 (depends on 5)

The computer-implemented method of claim 5, wherein a client is at least one from the group of a computer, a user, an application, a process and a peer.

### Claim 9 (depends on 5)

The computer-implemented method of claim 5, wherein the detecting a set of requests that form a pattern in the sorted group comprises using an N-gram model to detect the pattern.

### Claim 10 (depends on 5)

The computer-implemented method of claim 5, wherein the detecting a set of requests that form a pattern in the sorted group comprises using a FP growth model to detect the pattern.

### Claim 11 (depends on 5)

The computer-implemented method of claim 5, wherein an action comprises opening a user interface.

### Claim 12 (depends on 5)

The computer-implemented method of claim 5, further comprising:
calculating a delay time for a precedent action and a subsequent action, where the delay time is the difference between the precedent action time and the subsequent action time; and
calculating the probability of a delay time for a transition from the precedent action to the subsequent action.

### Claim 13 (depends on 12)

The computer-implemented method of claim 12, wherein the calculating the probability of a delay time comprises calculating the likelihood that the delay time falls within a given time interval.

### Claim 14

An apparatus for determining system usage, comprising:
a log interface that extracts a plurality of records from at least one log, each record having at least one request and a timestamp;
a client grouping module that groups the extracted records by client;
a sorter that sorts group of client records by timestamp;
a pattern detector that detects a set of requests in at least one record in the sorted group that form a pattern comprising an action, where an action has a time;
a transition probability module that calculates the probability of a transition from a precedent action to a subsequent action, where the precedent action has a time prior to the time of the subsequent action.

### Claim 15 (depends on 14)

The system of claim 14, wherein a client is at least one from the group of a computer, a user, an application, a process and a peer.

### Claim 16 (depends on 14)

The system of claim 14, wherein the pattern detector detects a pattern of requests in the sorted group using an N-gram model to detect the pattern.

### Claim 17 (depends on 14)

The system of claim 14, wherein the pattern detector detects a pattern of requests in the sorted group using a FP growth model to detect the pattern.

### Claim 18 (depends on 14)

The system of claim 14, further comprising a delay time probability module that calculates a delay time between the time of a precedent action and the time of a subsequent action, where the delay time is the difference between the precedent action time and the subsequent action time and further calculates the probability of a delay time for a transition from the precedent action to the subsequent action.

### Claim 19 (depends on 18)

The system of claim 18, wherein the probability of a delay time comprises the likelihood that the delay time falls within a given time interval.

### Claim 20

A non-transitory computer readable medium storing a plurality of instructions that cause a computer to perform a method comprising:
extracting a plurality of records from at least one log, each record having a timestamp and at least one request;
grouping the extracted records by client;
sorting a group of client records by timestamp;
detecting a set of requests in at least one record in the sorted group that form a pattern comprising an action, wherein the action has a time;
calculating the probability of a transition from a precedent action to a subsequent action, where the precedent action has a time prior to the time of the subsequent action.

### Claim 21 (depends on 20)

The non-transitory computer readable medium of claim 20 storing a plurality of instructions that cause a computer to further perform a method comprising detecting a set of requests that form a pattern in the sorted group by using an N-gram model to detect the pattern.

### Claim 22 (depends on 20)

The non-transitory computer readable medium of claim 20 storing a plurality of instructions that cause a computer to further perform a method comprising detecting a set of requests that form a pattern in the sorted group by using a FP growth model to detect the pattern.

### Claim 23 (depends on 20)

The non-transitory computer readable medium of claim 20 storing a plurality of instructions that cause a computer to further perform a method comprising
calculating a delay time for a precedent action and a subsequent action, where the delay time is the difference between the precedent action time and the subsequent action time; and
calculating the probability of a delay time for a transition from the precedent action to the subsequent action.

### Claim 24 (depends on 23)

The non-transitory computer readable medium of claim 23 storing a plurality of instructions that cause a computer to further perform a method wherein the calculating the probability of a delay time comprises calculating the likelihood that the delay time falls within a given time interval.
