# US 2012/0254255 A1 · Apparatus and method for generating story according to user information

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

- Number: US 2012/0254255 A1
- Document ID: US20120254255A1
- Status: Published application
- Kind: A1
- Application number: 13/436,441
- Filed: 2012-03-30
- Published: 2012-10-04
- Earliest claimed: 2011-03-31
- Assignees: Changwon National University; Samsung Electronic Co., Ltd.
- Inventors: Hee-Seok Jeong; Young-Hee Park; Jeong-Won Cha
- Web page: https://patentgrep.com/patent/US20120254255A1

## CPC

- G06F 16/2465: {Query processing support for facilitating data mining operations in structured databases}
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

An apparatus and method summarize a user's daily life information. The apparatus includes an information collection unit, an analysis unit, a story generator, and a display unit. The information collection unit collects log information including user's daily life information, from at least one electronic device. The analysis unit analyzes the log information collected from the information collection unit and decides at least one topic representing the user's daily life information. The story generator generates at least one sentence representing the user's daily life information using the at least one topic decided in the analysis unit. The display unit displays the at least one sentence generated in the story generator.

## Claims

### Claim 1

An apparatus configured to summarize daily life information of a user, the apparatus comprising:
an information collection unit configured to collect log information comprising the daily life information from at least one electronic device;
an analysis unit configured to analyze the log information collected from the information collection unit and decide at least one topic representing the daily life information;
a story generator configured to generate at least one sentence representing the daily life information using the at least one topic decided by the analysis unit; and
a display unit configured to display the at least one sentence generated by the story generator.

### Claim 2 (depends on 1)

The apparatus of claim 1, wherein the analysis unit comprises:
a topic segment constructor configured to construct at least one topic segment comprising at least one candidate topic using the log information collected from the information collection unit;
an extractor configured to extract a sentence constituent element for constituting a sentence from each topic segment;
a topic decider configured to decide a topic for each topic segment based on a frequency of occurrence of a topic according to the sentence constituent element extracted in the extractor; and
an episode decider configured to select one topic segment for a reference time based on the frequency of occurrence of a topic comprised in each topic segment.

### Claim 3 (depends on 2)

The apparatus of claim 2, wherein the topic segment constructor is further configured to construct at least one topic segment using any one reference log information among a plurality of log information, map assistant log information to each topic segment based on a time of occurrence of the assistant log information, and construct a base segment using assistant log information mapped to no topic segment,
wherein the assistant log information represents log information excepting the reference log information among the plurality of log information.

### Claim 4 (depends on 2)

The apparatus of claim 2, wherein the extractor comprises an object name recognizer.

### Claim 5 (depends on 2)

The apparatus of claim 2, wherein the extractor is further configured to update the frequency of occurrence of a topic for a sentence constituent element extracted from each topic segment.

### Claim 6 (depends on 2)

The apparatus of claim 2, wherein the episode decider is further configured to select any one reference topic considering the frequency of occurrence of a topic of a topic segment selected at each reference time.

### Claim 7 (depends on 6)

The apparatus of claim 6, wherein, when reference topics of continuous topic segments are the same as each other, the episode decider is further configured to integrate the continuous topic segments comprising the same reference topic into one topic segment.

### Claim 8 (depends on 1)

The apparatus of claim 1, wherein the story generator is further configured to construct at least one middle sentence using a sentence constituent element comprised in an episode being set at a reference time, remove a middle sentence of a same meaning, add sentence connective verb ending and ending verb information to the middle sentence, and generate a sentence for the episode.

### Claim 9 (depends on 8)

The apparatus of claim 8, wherein the story generator is further configured to set the ending verb considering at least one of gender, area, and age.

### Claim 10 (depends on 1)

The apparatus of claim 1, wherein the story generator is further configured to generate at least one sentence representing the daily life information based on at least one of a reference topic representative of the daily life information, weather, and an emotion.

### Claim 11

A method for summarizing daily life information, the method comprising:
collecting log information comprising the daily life information from at least one electronic device;
analyzing the log information collected and deciding at least one topic representing the daily life information;
generating at least one sentence representing the daily life information using the at least one topic decided; and
displaying the generated at least one sentence.

### Claim 12 (depends on 11)

The method of claim 11, wherein deciding the topic comprises:
constructing at least one topic segment comprising at least one candidate topic using the collected log information;
extracting a sentence constituent element for constituting a sentence from each topic segment;
deciding a topic for each topic segment based on a frequency of occurrence of a topic according to the extracted sentence constituent element; and
selecting one topic segment for a reference time based on the frequency of occurrence of a topic comprised in each topic segment.

### Claim 13 (depends on 12)

The method of claim 12, wherein constructing the topic segment comprises:
constructing at least one topic segment using any one reference log information among a plurality of log information;
mapping assistant log information to each topic segment based on a time of occurrence of the assistant log information, and
when assistant log information mapped to no topic segment exists, constructing a base segment using the assistant log information mapped to no topic segment,
wherein the assistant log information represents log information excepting the reference log information among the plurality of log information.

### Claim 14 (depends on 12)

The method of claim 12, wherein extracting the sentence constituent element comprises:
extracting a sentence constituent element from data of a text form using an object name recognizer.

### Claim 15 (depends on 12)

The method of claim 12 further comprising:
after extracting the sentence constituent element, updating the frequency of occurrence of a topic for a sentence constituent element extracted from each topic segment.

### Claim 16 (depends on 12)

The method of claim 12, wherein selecting the topic segment comprises:
selecting any one reference topic considering the frequency of occurrence of a topic of a topic segment selected at each reference time.

### Claim 17 (depends on 16)

The method of claim 16 further comprising:
after selecting the reference topic, identifying if reference topics of continuous topic segments are the same as each other;
when the reference topics of the continuous topic segments are the same as each other, integrating the continuous topic segments comprising the same reference topic into one topic segment.

### Claim 18 (depends on 11)

The method of claim 11, wherein generating the sentence comprises:
constructing at least one middle sentence using a sentence constituent element comprised in an episode being set at a reference time;
removing a middle sentence of a same meaning; and
adding sentence connective verb ending and ending verb information to the middle sentence, and generating a sentence for the episode.

### Claim 19 (depends on 18)

The method of claim 18, wherein the story generator sets the ending verb considering at least one of gender, area, and age.

### Claim 20 (depends on 11)

The method of claim 11, wherein the story generator generates at least one sentence representing the daily life information based on at least one of a reference topic representative of the daily life information, weather, and an emotion.

### Claim 21

A portable terminal method for preventing incorrect input comprising:
a storage unit;
a controller;
one or more modules stored in the storage unit and configured for execution by the processor, the one or more modules including instructions to:
collect log information comprising the daily life information from at least one electronic device;
analyze the log information collected and deciding at least one topic representing the daily life information;
generate at least one sentence representing the daily life information using the at least one topic decided; and
display the generated at least one sentence

### Claim 22

A computer readable storage medium storing one or more programs, the one or more programs comprising instructions, which when executed by a portable electronic device with a touch-sensitive display, cause the portable electronic device to perform a method comprising:
collecting log information comprising the daily life information from at least one electronic device;
analyzing the log information collected and deciding at least one topic representing the daily life information;
generating at least one sentence representing the daily life information using the at least one topic decided; and
displaying the generated at least one sentence.
