Use of neural networks for keyword generation

A system for identifying keywords, the system comprising:

• a processor;
• a memory coupled to the processor, wherein the memory includes instructions that when executed by the processor perform operations comprising:
• arranging a plurality of neurons into a bidirectional neural network comprising a plurality of layers, the layers including words and documents, the neurons associated with words forming a first layer, and the neurons associated with documents forming a second layer, each neuron having multiple inputs from other neurons, a single output connecting the neuron to other neurons, and a threshold function at the single output, wherein at least some of the neurons of the first layer have connections between them and represent keywords in the documents;
• wherein the neurons are connected by a plurality of connections, wherein each neuron is connected to only some of the other neurons, such that at least some of the word neurons have connections between them;
• wherein, in response to an input query, the neural network outputs a plurality of keywords associated with documents that are contextually relevant to the input query, and wherein, in response to input from a user, positions of the keywords on a display relative to each other are changed, such that a change in position of one keyword changes the position of other displayed keywords.

A method for identifying keywords comprising:

• arranging, using a processor, a plurality of neurons into a bidirectional neural network comprising a plurality of layers, the layers including words and documents, each neuron having multiple inputs from other neurons, a single output connecting the neuron to other neurons, and a threshold function at the single output,
• forming a first layer of the neural network from the neurons associated with words;
• forming a second layer of the neural network from the neurons associated with documents;
• forming a plurality of connections between the neurons, wherein each neuron is connected to only some of the other neurons, such that at least some of the word neurons have connections between them,
• wherein at least some of the neurons of the first layer have connections between them and represent keywords in the documents, and
• in response to an input query, outputting, to a user, a plurality of keywords associated with the documents;
• and
• in response to input from the user, changing positions of the keywords on a display relative to each other, such that a change in position of one keyword changes the position of other displayed keywords.