Immortal, On Thu, Nov 21, 2019 at 9:10 PM <[email protected]> wrote:
> I need a full visual drawing of the system, > The best explanations are in the patents. The earlier patent concentrates on the parsing methodology, while the later patent concentrates on what to do with it. *Natural language processing for analyzing internet content and finding solutions to needs expressed in text <https://patents.justia.com/patent/9805018>* *Patent number: *9805018 *Abstract: *A natural language processing methodology to automatically transform push advertising into pull advertising. Text found in forum, blog, and social media postings throughout the Internet is grammatically analyzed to identify potential customers who have expressed a clear problem. Only parsing rules with the least likely elements present are evaluated. In response, personalized replies are produced that contain pertinent and useful information about a potential product or service. Those replies appear to come from other Internet users, thus converting expressed needs of user/prospects into discussions with sales technicians. *Type: *Grant *Filed: *July 18, 2014 *Date of Patent: *October 31, 2017 *Inventor: *Steven E. Richfield *Natural language processing for analyzing internet content and finding solutions to needs expressed in text <https://patents.justia.com/patent/8788263>* *Patent number: *8788263 *Abstract: *A natural language processing methodology to automatically transform push advertising into pull advertising. Text found in forum, blog, and social media postings throughout the Internet is grammatically analyzed to identify potential customers who have expressed a clear problem. Only parsing rules with the least likely elements present are evaluated. In response, personalized replies are produced that contain pertinent and useful information about a potential product or service. Those replies appear to come from other Internet users, thus converting expressed needs of user/prospects into discussions with sales technicians. *Type: *Grant *Filed: *March 15, 2013 *Date of Patent: *July 22, 2014 *Inventor: *Steven E. Richfield I'm not seeing it... How's it different from GPT-2? GPT-2 is taught data, > learns relationships, and can predict a word based on the data. "Reflection > of data to get the new data." > Machine learning will never ever be able to do this stuff in a million years. Much too much is simply NOT on digital media - like common slang terms for symptoms. However, it isn't too difficult to hand code the knowledge needed to reverse-engineer most biological and other system failures. The concept here is to provide a mechanism to code knowledge so that it can forever forward be used to solve problems, where each piece of coded knowledge is but a fragment of larger problems. *Steve Richfield* *Artificial General Intelligence List <https://agi.topicbox.com/latest>* / > AGI / see discussions <https://agi.topicbox.com/groups/agi> + participants > <https://agi.topicbox.com/groups/agi/members> + delivery options > <https://agi.topicbox.com/groups/agi/subscription> Permalink > <https://agi.topicbox.com/groups/agi/T26a5f8008aa0b4f8-Mc1ce2d249900dff5bdc36338> > ------------------------------------------ Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/T26a5f8008aa0b4f8-Md88fa26ce400188a33debab6 Delivery options: https://agi.topicbox.com/groups/agi/subscription
