# US 2015/0106340 A1 · System for automatically detecting abnormalities statistical data on usage, method therefor, and apparatus applied to same

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

- Number: US 2015/0106340 A1
- Document ID: US20150106340A1
- Status: Published application
- Kind: A1
- Application number: 14/396,437
- Filed: 2013-12-12
- Published: 2015-04-16
- Earliest claimed: 2012-12-24
- Assignees: Korea Institute of Science & Technology Information
- Applicants: Korea Institute of Science & Technology Information
- Inventors: Young Im Jung; Jay Hoon Kim; Jeong Hwan Kim; Ho Nam Choi; Hwan Min Kim
- Web page: https://patentgrep.com/patent/US20150106340A1

## CPC

- G06F 16/2365: {Ensuring data consistency and integrity}
- G06Q 30/0201: Market modelling; Market analysis; Collecting market data
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- 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

The present invention discloses a system for automatically detecting abnormalities in statistical data on usage, to a method for same, and to an apparatus applied to same. Namely, the present invention can increase the reliability and accuracy of statistical data on usage by: collecting statistical data on usage, the data relating to the usage of electronic information from a plurality of information-providing platform apparatuses each issuing separate electronic information; and, from among the collected statistical data on usage, determining, as data to be subjected to abnormality detection, only the statistical data on usage that corresponds to a reference data format, and detecting abnormalities for each type from the statistical data on usage determined as the data to be subjected to abnormality detection.

## Claims

### Claim 1

A system for automatically detecting an abnormality, the system comprising:
a plurality of information supplier platform apparatuses configured to generate statistical usage data related to the use of electronic information; and
an abnormality detection apparatus configured to collect the statistical usage data related to the use of the electronic information from the plurality of information supplier platform apparatuses, determine statistical usage data that matches a standard data format among the collected statistical usage data as a target subject to abnormality detection, detect a predetermined abnormality for each type in the statistical usage data determined as the target subject to the abnormality detection, and generate a notification message for notifying of the detected abnormality for each type.

### Claim 2

An apparatus for detecting an abnormality, the apparatus comprising:
a detection target determination unit configured to determine statistical usage data that matches a standard data format among statistical usage data related to the use of electronic information collected from a plurality of information supplier platform apparatuses issuing the electronic information as a target subject to abnormality detection; and
an abnormality detection unit configured to detect a predetermined abnormality for each type from the statistical usage data determined as the target subject to the abnormality detection and notify of the detected abnormality for each type.

### Claim 3 (depends on 2)

The apparatus of claim 2, further comprising a message transmission unit configured to, when the collected statistical usage data does not match the standard data format or when the abnormality for each type is identified from the statistical usage data determined as the target subject to the abnormality detection, generate a notification message for notifying of a corresponding state and transmit the notification message to a corresponding information supplier platform apparatus.

### Claim 4 (depends on 2)

The apparatus of claim 2, wherein the standard data format includes an Extensible Markup Language (XML) data format and the detection target determination unit determines statistical usage data having a document standard defined in the XML data format as the target subject to the abnormality detection.

### Claim 5 (depends on 2)

The apparatus of claim 2, wherein the statistical usage data includes at least one of identification information for identifying the statistical usage data of the electronic information collected from the plurality of information supplier platform apparatuses, statistical figure information on the use of the electronic information, and usage type information for identifying a usage type of the electronic information by a user.

### Claim 6 (depends on 5)

The apparatus of claim 5, wherein the abnormality detection unit identifies whether there are two or more statistical usage data for electronic information collected from a particular information supplier platform apparatus based on the identification information, identifies statistical figure information of each of the two or more statistical usage data when it is identified that there are two or more statistical usage data, and detects, as one of the abnormality for each type, a case where it is identified that statistical figure information of the two or more statistical usage data are different from each other.

### Claim 7 (depends on 6)

The apparatus of claim 6, wherein the abnormality for each type is detected based on an abnormality detection period designated to include two or more unit periods and the abnormality detection unit identifies whether a sum of statistical figure information in each of the two or more unit periods matches statistical figure information during the abnormality detection period and detects, as the abnormality for each type, a case where it is identified that the sum of the statistical figure information in each of the two or more unit periods does not match the statistical figure information during the abnormality detection period.

### Claim 8 (depends on 7)

The apparatus of claim 7, wherein the statistical figure information in the two or more unit periods is divided based on the usage type information and the abnormality detection unit identifies whether a sum of the statistical figure information in each of the two or more unit periods divided based on the usage type information matches the statistical figure information during the abnormality detection period and detects, as the abnormality for each type, a case where each of the sums of the statistical figure information does not match the statistical figure information during the abnormality detection period.

### Claim 9 (depends on 7)

The apparatus of claim 7, wherein the abnormality for each type is detected based on a trend of a change in the statistical figure information in each of the two or more unit periods and the abnormality detection unit identifies a difference of the trend of the change in the statistical figure information in each of the two or more unit periods and detects, as the abnormality for each type, a case where it is identified that the difference of the trend of the change in statistical figure information in a particular unit period of the two or more unit periods is larger than or equal to a threshold.

### Claim 10 (depends on 7)

The apparatus of claim 7, wherein the abnormality for each type is detected based on a reference value designated in connection with the statistical figure information in each of the two or more unit periods and the abnormality detection unit identifies a difference between the statistical figure information in the two or more unit periods and the reference value and detects, as the abnormality for each type, a case where it is identified that the difference between the statistical figure information and the reference value is larger than or equal to a threshold.

### Claim 11

A method of automatically detecting an abnormality, the method comprising:
generating statistical usage data related to the use of electronic information by each of a plurality of information supplier platform apparatuses;
collecting the statistical usage data related to the use of the electronic information from the plurality of information supplier platform apparatuses by an abnormality detection apparatus;
determining statistical usage data that matches a standard data format among the collected statistical usage data as a target subject to abnormality detection by the abnormality detection apparatus;
detecting a predetermined abnormality for each type from the statistical usage data determined as the target subject to the abnormality detection by the abnormality detection apparatus; and
generating a notification message for notifying of the detected abnormality for each type by the abnormality detection apparatus.

### Claim 12

A method of automatically detecting an abnormality, the method comprising:
collecting statistical usage data related to the use of electronic information from a plurality of information supplier platform apparatuses issuing the electronic information;
determining statistical usage data that matches a standard data format among the collected statistical usage data as a target subject to abnormality detection; and
detecting a predetermined abnormality for each type from the statistical usage data determined as the target subject to the abnormality detection.

### Claim 13 (depends on 12)

The method of claim 12, further comprising, when the collected statistical usage data does not match the standard data format or when the abnormality for each type is identified from the statistical usage data determined as the target subject to the abnormality detection, generating a notification message for notifying of a corresponding state and transmitting the notification message to a corresponding information supplier platform apparatus.

### Claim 14 (depends on 12)

The method of claim 12, wherein the standard data format includes an Extensible Markup Language (XML) data format and the determining of the statistical usage data that matches the standard data format among the collected statistical usage data as the target subject to the abnormality detection comprises determining statistical usage data having a document standard defined in the XML data format as the target subject to the abnormality detection.

### Claim 15 (depends on 12)

The method of claim 12, wherein the statistical usage data includes at least one of identification information for identifying the statistical usage data of the electronic information collected from the plurality of information supplier platform apparatuses, statistical figure information on the use of the electronic information, and usage type information for identifying a usage type of the electronic information by a user.

### Claim 16 (depends on 15)

The method of claim 15, wherein the detecting of the predetermined abnormality for each type from the statistical usage data determined as the target subject to the abnormality detection comprises identifying whether there are two or more statistical usage data for electronic information collected from a particular information supplier platform apparatus based on the identification information, identifying statistical figure information of each of the two or more statistical usage data when it is identified that there are two or more statistical usage data, and detecting, as one of the abnormality for each type, a case where it is identified that statistical figure information of the two or more statistical usage data are different from each other.

### Claim 17 (depends on 16)

The method of claim 16, wherein the abnormality for each type is detected based on an abnormality detection period designated to include two or more unit periods and the detecting of the predetermined abnormality for each type from the statistical usage data determined as the target subject to the abnormality detection comprises identifying whether a sum of statistical figure information in the two or more unit periods matches statistical figure information during the abnormality detection period and detecting, as the abnormality for each type, a case where it is identified that the sum of the statistical figure information does not match the statistical figure information during the abnormality detection period.

### Claim 18 (depends on 17)

The method of claim 17, wherein the statistical figure information in the two or more unit periods is divided based on the usage type information and the detecting of the predetermined abnormality for each type from the statistical usage data determined as the target subject to the abnormality detection comprises identifying whether each of sums of the statistical figure information in the two or more unit periods divided based on the usage type information matches the statistical figure information during the abnormality detection period and detecting, as the abnormality for each type, a case where each of the sums of the statistical figure information does not match the statistical figure information during the abnormality detection period.

### Claim 19 (depends on 17)

The method of claim 17, wherein the abnormality for each type is detected based on a trend of a change in the statistical figure information in each of the two or more unit periods and the detecting of the predetermined abnormality for each type from the statistical usage data determined as the target subject to the abnormality detection comprises identifying a difference of the trend of the change in the statistical figure information in each of the two or more unit periods and detecting, as the abnormality for each type, a case where it is identified that the difference of the trend of the change in statistical figure information in a particular unit period of the two or more unit periods is larger than or equal to a threshold.

### Claim 20 (depends on 17)

The method of claim 17, wherein the abnormality for each type is detected based on a reference value designated in connection with the statistical figure information in each of the two or more unit periods and the detecting of the predetermined abnormality for each type from the statistical usage data determined as the target subject to the abnormality detection comprises identifying a difference between the statistical figure information in the two or more unit periods and the reference value and detecting, as the abnormality for each type, a case where it is identified that the difference between the statistical figure information and the reference value is larger than or equal to a threshold.
