Apparatus and computer-implemented method for processing sensor data

A computer-implemented method for processing time series of sensor data, the method comprising the following steps:

• providing the sensor data in a first channel, wherein the first channel includes a first time series of the sensor data;
• assigning a first text to the first channel, the first text characterizing the sensor data and/or a dimension of the sensor data in the first channel;
• determining a first text coding depending on the first text, using a text encoder;
• determining a first channel position coding depending on the first text coding, using a neural network;
• determining a second text coding depending on a predetermined text, using the text encoder, wherein the predetermined text characterizes sensor data to be predicted and/or a dimension of the sensor data to be predicted;
• determining a second channel position coding depending on the second text coding, using the neural network;
• determining a first input variable of an encoder depending on the sensor data from the first channel and depending on the first channel position coding;
• determining a first input variable of a decoder, using the encoder, depending on the first input variable of the encoder;
• determining a second input variable of the decoder depending on the second channel position coding;
• and
• predicting a time series of sensor data using the decoder depending on the first input variable of the decoder and the second input variable of the decoder.

An apparatus for processing time series of sensor data, comprising:

• at least one processor;
• and
• at least one memory;
• wherein the at least one processor is configured to execute instructions, upon execution of which the apparatus executes a method, wherein the at least one memory stores the instructions, and wherein the method includes:
• providing the sensor data in a first channel, wherein the first channel includes a first time series of the sensor data,
• assigning a first text to the first channel, the first text characterizing the sensor data and/or a dimension of the sensor data in the first channel,
• determining a first text coding depending on the first text, using a text encoder,
• determining a first channel position coding depending on the first text coding, using a neural network,
• determining a second text coding depending on a predetermined text,
• using the text encoder, wherein the predetermined text characterizes sensor data to be predicted and/or a dimension of the sensor data to be predicted,
• determining a second channel position coding depending on the second text coding, using the neural network,
• determining a first input variable of an encoder depending on the sensor data from the first channel and depending on the first channel position coding,
• determining a first input variable of a decoder, using the encoder,
• depending on the first input variable of the encoder,
• determining a second input variable of the decoder depending on the second channel position coding, and
• predicting a time series of sensor data using the decoder depending on the first input variable of the decoder and the second input variable of the decoder.

A non-transitory computer-readable medium on which is stored a computer program including instructions for processing time series of sensor data, the method comprising the following steps:

• providing the sensor data in a first channel, wherein the first channel includes a first time series of the sensor data;
• assigning a first text to the first channel, the first text characterizing the sensor data and/or a dimension of the sensor data in the first channel;
• determining a first text coding depending on the first text, using a text encoder;
• determining a first channel position coding depending on the first text coding, using a neural network;
• determining a second text coding depending on a predetermined text, using the text encoder, wherein the predetermined text characterizes sensor data to be predicted and/or a dimension of the sensor data to be predicted;
• determining a second channel position coding depending on the second text coding, using the neural network;
• determining a first input variable of an encoder depending on the sensor data from the first channel and depending on the first channel position coding;
• determining a first input variable of a decoder, using the encoder, depending on the first input variable of the encoder;
• determining a second input variable of the decoder depending on the second channel position coding;
• and
• predicting a time series of sensor data using the decoder depending on the first input variable of the decoder and the second input variable of the decoder.