Spiking neural network-based data processing method, computing core circuit, and chip

A data processing method based on a spiking neural network, comprising:

• performing encoding processing on at least one first pulse sequence to obtain a second pulse sequence corresponding to each first pulse sequence, wherein the first pulse sequence comprises a pulse of at least one neuron in a current computing core circuit to be transmitted, and the pulses to be transmitted in the first pulse sequence have consecutive transmitting addresses;
• determining a first route packet corresponding to at least one second pulse sequence;
• and
• sending the first route packet to at least one destination computing core circuit,
• wherein values of the pulses in the first pulse sequence comprise a first value and a second value, and
• performing encoding processing on at least one first pulse sequence to obtain the second pulse sequence corresponding to the first pulse sequence comprises:
• determining a quantity of consecutive first values before each second value in the first pulse sequence;
• and
• determining, according to the determined quantity of consecutive first values before each second value in the first pulse sequence, the second pulse sequence corresponding to the first pulse sequence, wherein the determined quantity of consecutive first values before each second value in the first pulse sequence is represented in binary, and is determined as the second pulse sequence corresponding to the first pulse sequence.