As discussed earlier, from any branch of the impression network we can extract information, logic, and decision and generate new knowledge by combining different types of impressions. So now consider the sentence “Apple juice can be a good base flavor for water”. This statement should not be stored in the impression network like such a nice well grammatical format. Simply consider that our network has the impression of “apple”, “juice”, and “water” and these impressions are staying in impression lifecycle in a database table format
impression_table impression_lifecycle_table
id id
type imp_ref
sight time
taste applied_factor
touch sight
sound taste
smell touch
identity_code sound
smell
Now the algorithm found a new object “Apple” and put its initial sense value to impression_table, at the same time a lifecycle will be started by taking ref id of the “Apple” in the impression_table. So in the time and applied_factor field of impression_table, we found some unit value like 5 unit in “time” field and 10 unit pressure in “applied_factor” field. And also we will get new affected values for “sight”, “touch”, “sound”, “smell”. Simple saying if any factors (like time, pressure, gravity, heat ...etc) applied on an impression we will get some changes and these changes are continuous process. We see a green apple ripe and turn into radish color after passing certain period and effect of certain weather affect (temperature). For example if we consider the apple ripening process, we will see with the passing of time an apple grew bigger (size change in sight affect) and radish (color change in sight affect), so if we want to keep the event in the above database tables, we have to put different sense values for different unit of time values for the same impression reference. After that we can extract any information like “An apple needs 10 days to ripe” by applying NLP on the database. That means we are storing data or building the impression network according to soul algorithm and extracting or use information by using NLP.
No comments:
Post a Comment