System and method for brain-machine interface learning

The present invention relates to a system and method for brain-machine interface learning. According to one embodiment of the present invention, when a learner of a brain-machine interface moves an external device, motor information and distance information according to a motion of the external device are transmitted to the learner through a brain stimulation signal, whereby the efficiency of learning the brain-machine interface can advantageously be increased. In addition, a brain region of the learner is stimulated through a brain stimulation signal generated according to a preferred direction of a nerve cell, whereby the efficiency of learning the brain-machine interface can advantageously be increased.

The abstract as published by the patent office, from WO2021095978A1. It describes the invention; it is not a statement of what is protected.

• Interface and electrodes

  Peripheral interfaces

• Implant electronics

  Chips and on-implant computing

• Decoding

  Neural decoding · Motor decoding

• Stimulation

  Stimulation

What the filing appears to be about, read by published rules from its title, abstract and classification codes (A61B5/377, A61F2/72, A61F2002/5036, A61F2002/704, G06F3/015). The claims define what a patent protects, and they are not read here.

Interface and electrodes

Everything downstream works with what the contacts pick up. Their number, size and distance from the neurons set the ceiling on the signal. The problem behind it: more contacts, closer to neurons, that still record after years in tissue that reacts to them.

Implant electronics

An implant has room for very little, so functions that fill a rack in the laboratory have to fit on a chip. The problem behind it: fitting channel count, computing and safety functions into a volume and a heat budget the body accepts.

Decoding

This is the step that turns brain activity into a command or a word. Its accuracy and speed are what a user experiences. The problem behind it: accuracy that holds over months without frequent recalibration, for more than one user and one task.

Why the layer matters to the field, not a judgement of this filing. A patent family shows that protection was sought. It does not show that the technology was built, is used in a product, or works in people. The whole stack

One invention, published 2 times in 2 offices. Each publication opens in Espacenet.

• South KoreaKR102149615B128 Aug 2020 · grant
• International (PCT)a route to several countries, not a countryWO2021095978A120 May 2021

1. 13 Nov 2019First filingEarliest priority, at South Korea. The family is counted in this year.
2. 3 Dec 2019ApplicationFiled at International (PCT).
3. 28 Aug 2020First publicationKR102149615B1, South Korea.
4. 28 Aug 2020Grant publishedKR102149615B1, South Korea.

Dates as the offices published them. Records of lapses, withdrawals and changes of owner have not been read for this family, and whether a patent is in force today is not assessed.

• Bibliographic data, family members and office records: European Patent Office, Open Patent Services (the DOCDB and INPADOC databases), read 7 Oct 2026.
• The record itself, with its claims and description: WO2021095978A1 in Espacenet
• Counted as a BCI patent family: title or abstract names the field; classified G06F3/015 (input arrangements based on nervous-system activity); cites a family already accepted. How families are found and judged