Language decoding method and device, electronic equipment and storage medium

The invention discloses a language decoding method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining an electroencephalogram decoding result of a current time step, the electroencephalogram decoding result comprising an electroencephalogram decoding score corresponding to each preset syllable; expanding the historical candidate sentences of the previous time step based on the candidate words associated with the preset syllables to obtain a corresponding expanded sentence set; for each extended sentence, determining a comprehensive language decoding score of the extended sentence based on a historical comprehensive language decoding score of a previous time step, a first linguistic probability score of the extended sentence and a corresponding electroencephalogram decoding score; determining a candidate sentence sequence of the current time step based on the comprehensive language decoding score of each extended sentence; and performing sentence ending detection based on the candidate sentence sequence of the current time step, and determining to-be-output language content of the current time step according to a detection result of the sentence ending detection. According to the method and the device, the accuracy, the understandability and the interaction naturalness of the output language content are improved.

The abstract as published by the patent office, from CN122220477A. It describes the invention; it is not a statement of what is protected.

• Decoding

  Neural decoding

What the filing appears to be about, read by published rules from its title, abstract and classification codes. The claims define what a patent protects, and they are not read here.

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 1 office. Each publication opens in Espacenet.

• ChinaCN122220477A16 Jun 2026CN122220477B25 Aug 2026 · grant

1. 15 May 2026First filingEarliest priority, at China. The family is counted in this year.
2. 16 Jun 2026First publicationCN122220477A, China.
3. 25 Aug 2026Grant publishedCN122220477B, China.

Dates as the offices published them. Office records are in the offices' own words and are a selection: refusals, lapses and withdrawals, and records that name an owner. Each concerns one member of the family, not the family as a whole, and another member in the same office may stand. Whether a patent is in force today is not assessed.

Organisation

NeuroXess · 65 families identified

Technology

EEG

• 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: CN122220477A in Espacenet
• Counted as a BCI patent family: filed by 上海脑虎科技有限公司, an organisation already in the graph; describes neural hardware or methods without naming the field. How families are found and judged