# US 2022/0286746 A1 · Reception device and reception method and transmission device and transmission method

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

- Number: US 2022/0286746 A1
- Document ID: US20220286746A1
- Status: Published application
- Kind: A1
- Application number: 17/637,039
- Filed: 2020-05-19
- Published: 2022-09-08
- Earliest claimed: 2019-08-30
- Assignees: Sony Group Corporation
- Applicants: Sony Group Corporation
- Inventors: YOICHI YAGASAKI; YOSHIYUKI KOBAYASHI
- Web page: https://patentgrep.com/patent/US20220286746A1

## CPC

- H04N 21/466: Learning process for intelligent management, e.g. learning user preferences for recommending movies {(services using the results of monitoring in broadcast systems H04H60/61)}
- G06N 3/0464: Convolutional networks [CNN, ConvNet]
- G06N 3/09: Supervised learning
- H04N 21/234363: {by altering the spatial resolution, e.g. for clients with a lower screen resolution}
- H04N 21/23614: {Multiplexing of additional data and video streams (arrangements for simultaneous broadcast of plural pieces of information H04H20/28)}
- H04N 21/251: {Learning process for intelligent management, e.g. learning user preferences for recommending movies (details of learning user preferences for the retrieval of video data in a video database G06F16/739; computer systems using learning methods G06N3/08)}
- H04N 21/4341: {Demultiplexing of audio and video streams}
- H04N 21/4348: {Demultiplexing of additional data and video streams}
- H04N 21/435: Processing of additional data, e.g. decrypting of additional data, reconstructing software from modules extracted from the transport stream
- H04N 21/4385: Multiplex stream processing, e.g. multiplex stream decrypting
- H04N 21/439: Processing of audio elementary streams
- H04N 21/440263: {by altering the spatial resolution, e.g. for displaying on a connected PDA}
- H04N 21/6547: comprising parameters, e.g. for client setup
- G06N 3/045: Combinations of networks
- G06N 3/084: Backpropagation, e.g. using gradient descent
- H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

A reception device for receiving information associated with content quality improvement is provided. The reception device includes a reception unit that receives a stream generated by multiplexing content and attribute information associated with a weighting factor of a learning model learned to process the content and an acquisition unit that acquires the attribute information by demultiplexing the received stream. The attribute information includes information associated with at least one of a type of the content to which the weighting factor is to be applied, a data size of the weighting factor to be updated, position information indicating a position of the weighting factor to be updated in the learning model, and accuracy of data regarding the weighting factor.

## Claims

### Claim 1

A reception device comprising:
a reception unit that receives a stream generated by multiplexing content and attribute information associated with a weighting factor of a learning model learned to process the content; and
an acquisition unit that acquires the attribute information by demultiplexing the received stream.

### Claim 2 (depends on 1)

The reception device according to claim 1, wherein the learning model includes a learning model for improving quality of the content.

### Claim 3 (depends on 1)

The reception device according to claim 1, wherein
the content includes a picture, and
the learning model includes a learning model for improving image quality of the picture.

### Claim 4 (depends on 3)

The reception device according to claim 3, wherein the learning model includes a learning model for performing a super-resolution process or high dynamic range rendering for the picture.

### Claim 5 (depends on 1)

The reception device according to claim 1, wherein
the content includes an audio signal, and
the learning model includes a learning model for improving sound quality of the audio signal.

### Claim 6 (depends on 5)

The reception device according to claim 5, wherein the learning model includes a learning model for expanding a bandwidth of audio.

### Claim 7 (depends on 1)

The reception device according to claim 1, wherein the attribute information includes information associated with at least one of a type of the content to which the weighting factor is to be applied, a data size of the weighting factor to be updated, position information indicating a position of the weighting factor to be updated in the learning model, and accuracy of data regarding the weighting factor.

### Claim 8 (depends on 1)

The reception device according to claim 1, wherein
the reception unit receives the stream on which the weighting factor is further multiplexed, and
the acquisition unit further acquires the weighting factor when the stream is demultiplexed.

### Claim 9 (depends on 1)

The reception device according to claim 1, wherein
the reception unit receives the stream on which location information indicating a location of the weighting factor is further multiplexed, and
the acquisition unit further acquires the weighting factor in reference to the location information acquired by demultiplexing the stream.

### Claim 10 (depends on 8)

The reception device according to claim 8, further comprising:
a processing unit that updates the learning model in reference to the acquired weighting factor and the acquired attribute information, and processes the content.

### Claim 11 (depends on 1)

The reception device according to claim 1, further comprising:
a processing unit that processes the content in reference to the learning model;
a memory that stores a weighting factor; and
a controller that controls input and output of the weighting factor to and from the memory, wherein
the reception unit receives the stream on which information associated with a time at which application of the weighting factor is started is further multiplexed, and
the controller supplies the weighting factor read from the memory to the processing unit, in reference to the time acquired by demultiplexing the stream.

### Claim 12 (depends on 1)

The reception device according to claim 1, further comprising:
a memory that includes a memory region for storing the weighting factor for each identification information; and
a controller that controls input and output of the weighting factor to and from the corresponding memory region in the memory in reference to the identification information, wherein
the controller supplies the weighting factor read from the corresponding memory region of the memory to the processing unit, in reference to the identification information indicating the weighting factor whose application is to be started and a command indicating a time at which application of the weighting factor is to be started.

### Claim 13 (depends on 12)

The reception device according to claim 12, wherein the reception unit receives the stream on which the identification information indicating the weighting factor whose application is to be started and the command indicating the time at which application of the weighting factor is to be started are further multiplexed.

### Claim 14 (depends on 1)

The reception device according to claim 1, further comprising:
a memory that stores the weighting factor; and
a controller that controls input and output of the weighting factor to and from the memory, wherein
the controller further controls output of the weighting factor read from the memory to an outside.

### Claim 15

A reception method comprising:
a reception step of receiving a stream generated by multiplexing content and attribute information associated with a weighting factor of a learning model learned to process the content; and
an acquisition step of acquiring the attribute information by demultiplexing the received stream.

### Claim 16

A transmission device comprising:
a multiplexing unit that generates a stream by multiplexing content and attribute information associated with a weighting factor of a learning model learned to process the content; and
a transfer unit that transfers the multiplexed stream to a predetermined transfer medium.

### Claim 17 (depends on 16)

The transmission device according to claim 16, further comprising:
a learning unit that learns the weighting factor.

### Claim 18 (depends on 17)

The transmission device according to claim 17, wherein
the content includes a picture, and
the learning unit learns a weighting factor for improving image quality of the picture.

### Claim 19 (depends on 16)

The transmission device according to claim 16, wherein the attribute information includes information associated with at least one of a type of the content to which the weighting factor is to be applied, a data size of the weighting factor to be updated, position information indicating a position of the weighting factor to be updated in the learning model, and accuracy of data regarding the weighting factor.

### Claim 20

A transmission method comprising:
a multiplexing step of generating a stream by multiplexing content and attribute information associated with a weighting factor of a learning model learned to process the content; and
a transfer step of transferring the multiplexed stream to a predetermined transfer medium.
