# US 2021/0342555 A1 · Electronic apparatus, controlling method of thereof and non-transitory computer readable recording medium

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

- Number: US 2021/0342555 A1
- Document ID: US20210342555A1
- Status: Published application
- Kind: A1
- Application number: 17/377,599
- Filed: 2021-07-16
- Published: 2021-11-04
- Earliest claimed: 2017-03-23
- Assignees: Samsung Electronics Co., Ltd.
- Applicants: Samsung Electronics Co., Ltd.
- Inventors: Chang-hwan CHOI; Ji-hwan YUN; Man-un JEONG
- Web page: https://patentgrep.com/patent/US20210342555A1

## CPC

- G06F 40/40: Processing or translation of natural language (natural language analysis G06F40/20; semantic analysis G06F40/30)
- G06F 40/30: Semantic analysis
- G06N 3/0442: characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
- G06N 3/045: Combinations of networks
- G06N 3/084: Backpropagation, e.g. using gradient descent
- G06N 3/09: Supervised learning
- G06N 3/092: Reinforcement learning
- H04L 51/02: using automatic reactions or user delegation, e.g. automatic replies or chatbot-generated messages
- H04L 51/04: Real-time or near real-time messaging, e.g. instant messaging [IM]
- G06N 3/006: based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
- 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
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)

## Abstract

An electronic apparatus includes an input unit comprising input circuitry configured to receive a natural language input, a communicator comprising communication circuitry configured to perform communication with a plurality of external chatting servers, and a processor configured to analyze a characteristic of the natural language and a characteristic of the user and to identify a chatting server corresponding to the natural language from among the plurality of chatting servers, and to control the communicator to transmit the natural language to the identified chatting server in order to receive a response with respect to the natural language.

## Claims

### Claim at position 1

1-19 (canceled)

### Claim 20

An electronic apparatus, comprising:
an input unit comprising input circuitry;
a communicator comprising communication circuitry configured to perform communication with a plurality of second AI (Artificial Intelligence) models; and
a processor configured to:
receive at least one sentence through the input unit,
based on the at least one sentence being input to a first AI model, obtain, through the first AI model, identification information of a second AI model corresponding to the at least one sentence from among the plurality of second AI models according to a characteristic of the at least one sentence, and
control, based on the identification information of the second AI model corresponding to the at least one sentence, the communicator to transmit information of the at least one sentence to the second AI model corresponding to the at least one sentence in order to receive a response with respect to the at least one sentence by the second AI model corresponding to the at least one sentence.

### Claim 21 (depends on 20)

The electronic apparatus as claimed in claim 20, wherein the processor is further configured to:
perform a preprocessing of a natural language input including the at least one sentence,
analyze a characteristic of the preprocessed natural language and the characteristic of the user and identify a chatting server corresponding to the preprocessed natural language from among the plurality of second AI models, and
control the communicator to transmit the preprocessed natural language to the identified chatting server.

### Claim 22 (depends on 21)

The electronic apparatus as claimed in claim 21, wherein the processor is further configured to:
with respect to each of the plurality of second AI models, determine at least one of: a first matching score with respect to the preprocessed natural language, a second matching score with respect to a dialogue pattern including the preprocessed natural language, a third matching score with respect to emotion of the user and a fourth matching score with respect to the characteristic of the user,
with respect to each of the plurality of second AI models, determine a final matching score with respect to each of the plurality of second AI models using at least one of the first to fourth matching scores, and
identify a chatting server having a highest final matching score among the plurality of second AI models as the chatting server corresponding to the preprocessed natural language.

### Claim 23 (depends on 22)

The electronic apparatus as claimed in claim 22, wherein the first matching score is determined based on weighted values given to words of the preprocessed natural language and a Term Frequency/Inverse Document Frequency (TF/IDF) value,
wherein the second matching score is determined based on a similarity to pre-stored dialogue pattern data,
wherein the third matching score is determined based on sentiment analysis and emotion analysis of the preprocessed natural language, and
wherein the fourth matching score is determined based on at least one of: age, gender, region and education of the user.

### Claim 24 (depends on 20)

The electronic apparatus as claimed in claim 20, further comprising:
a memory configured to store history information of dialogues performed with the second AI model corresponding to at least context information with respect to a situation in which the at least one sentence is input.

### Claim 25 (depends on 20)

The electronic apparatus as claimed in claim 20, wherein the processor is further configured to:
in response to receiving an additional natural language through the input unit after receiving a natural language input including the at least one sentence, identify a second AI model corresponding to the additional natural language from among the plurality of second AI models by analyzing a characteristic of the additional natural language and the characteristic of the user, and
in response to the second AI model corresponding to the natural language being different from the second AI model corresponding to the additional natural language, control the communicator to transmit the additional natural language to the second AI model corresponding to the additional natural language.

### Claim 26 (depends on 25)

The electronic apparatus as claimed in claim 25, wherein the processor is further configured to control the communicator to transmit history information of dialogues performed with the second AI model corresponding to the natural language and context information together with the additional natural language to the second AI model corresponding to the additional natural language.

### Claim 27 (depends on 20)

The electronic apparatus as claimed in claim 20,
wherein the characteristic of the at least one sentence is a matching score with respect to each of the plurality of second AI models.

### Claim 28 (depends on 27)

The electronic apparatus as claimed in claim 27, wherein the first chatting server is a chatting server configured to provide a response corresponding to the natural language input using pre-stored response data base,
wherein the second chatting server includes a chatting server configured to provide a response by identifying a context of the natural language input using a first response model, and
wherein the third chatting server includes a chatting server configured to provide a response by inferring a question included in the natural language input using a second response model.

### Claim 29

A method for controlling an electronic apparatus, the method comprising:
receiving at least one sentence as an input;
based on the at least one sentence being input to a first AI model, obtaining through the first AI model identification information of a second AI model corresponding to the at least one sentence from among a plurality of second AI models according to at least a characteristic of the at least one sentence,
transmitting, based on the identification information of the second AI model corresponding to the at least one sentence, information regarding the at least one sentence to the second AI model corresponding to the at least one sentence and receiving a response with respect to the at least one sentence.

### Claim 30 (depends on 29)

The method as claimed in claim 29, further comprising:
performing a preprocessing of a natural language including the at least one sentence,
wherein the identifying comprises analyzing a characteristic of the preprocessed natural language and the characteristic of the user and identifying a chatting server corresponding to the preprocessed natural language from among the plurality of second AI models, and
wherein the transmitting comprises transmitting the preprocessed natural language to the identified chatting server.

### Claim 31 (depends on 30)

The method as claimed in claim 30, wherein the identifying further comprises:
with respect to each of the plurality of second AI models, determining a first matching score with respect to the preprocessed natural language, a second matching score with respect to a dialogue pattern including the preprocessed natural language, a third matching score with respect to emotion of the user and a fourth matching score with respect to the characteristic of the user;
with respect to each of the plurality of second AI models, determining a final matching score for each of the plurality of second AI models using at least one of the first to fourth matching scores; and
identifying a second AI model having a highest final matching score among the plurality of second AI models as the chatting server corresponding to the preprocessed natural language.

### Claim 32 (depends on 32)

The method as claimed in claim 32, wherein the first matching score is determined based on weighted values given to words of the preprocessed natural language and a Term Frequency/Inverse Document Frequency (TF/IDF) value,
wherein the second matching score is determined based on a similarity to pre-stored dialogue pattern data,
wherein the third matching score is determined based on sentiment analysis and emotion analysis of the preprocessed natural language, and
wherein the fourth matching score is determined based on at least one of: age, gender, region and education of the user.

### Claim 33 (depends on 29)

The method as claimed in claim 29, further comprising:
storing history information of dialogues performed with the second AI model corresponding to a natural language including the at least one sentence and context information with respect to a situation in which the natural language is input.

### Claim 34 (depends on 29)

The method as claimed in claim 29, further comprising:
receiving an additional natural language from the user after receiving a natural language input including the at least one sentence;
identifying a second AI model corresponding to the additional natural language from among the plurality of second AI models by analyzing a characteristic of the additional natural language and the characteristic of the user; and
in response that the second AI model corresponding to the natural language being different from the second AI model corresponding to the additional natural language, transmitting the additional natural language to the second AI model corresponding to the additional natural language.

### Claim 35 (depends on 34)

The method as claimed in claim 34, wherein the transmitting of the additional natural language comprises transmitting history information of dialogues performed with the second AI model corresponding to the natural language and context information together with the additional natural language to the second AI model corresponding to the additional natural language.

### Claim 36 (depends on 29)

The method as claimed in claim 29,
wherein the characteristic of the at least one sentence comprises matching score with respect to each of the plurality of second AI models.

### Claim 37 (depends on 18)

The method as claimed in claim 18, wherein the first chatting server is a chatting server configured to provide a response corresponding to the natural language input using pre-stored response data base,
wherein the second chatting server is a chatting server configured to provide a response by identifying a context of the natural language input using a first response model, and
wherein the third chatting server is a chatting sever configured to provide a response by inferring a question included in the natural language input using a second response model.

### Claim 38

A computer program product comprising commands stored in non-transitory computer-readable recording medium, the commands, when executed by a processor, causing an electronic apparatus, to perform operations comprising:
receiving at least one sentence as an input;
based on the at least one sentence being input to a first AI model, obtaining through the first AI model identification information of a second AI model corresponding to the at least one sentence from among a plurality of second AI models according to at least a characteristic of the at least one sentence,
transmitting, based on the identification information of the second AI model corresponding to the at least one sentence, information regarding the at least one sentence to the second AI model corresponding to the at least one sentence and receiving a response with respect to the at least one sentence.
