BOOSTING SALES PRODUCTIVITY USING PERSONALIZED CONTENT GENERATOR FOR ONLINE SALES
One example method includes generating personalized content for online sales. Recorded calls and other sources are converted to text. The text is semantically processed and correlated with customer data including customer order data to identify content that impacted the purchase of a product. The content may be incorporated into an online product page to facilitate online sales.
1 . A method, comprising:
semantically extracting data from text obtained from a data source, wherein the extracted data from the data source includes questions, answers, and a product;
generating a score for each question and answer;
generating an insight for the product based on the score; and
incorporating the insight into an online product page of the product.
2 . The method of claim 1 , further comprising converting the data source to the extracted data, the extracted data including text.
3 . The method of claim 2 , further comprising segmenting the text into segments and determining questions and associated answers from the segments.
4 . The method of claim 3 , further comprising determining a number of semantically equivalent questions included in the text.
5 . The method of claim 4 , further comprising generating the score based on the number of semantically equivalent questions compared to a number of data sources including the data source.
6 . The method of claim 5 , wherein at least some of the data sources comprise a transcript of a recorded call.
7 . The method of claim 4 , wherein at least some of the data sources include crowd sourced data.
8 . The method of claim 1 , further comprising generating a knowledge graph to relate the insight to other products.
9 . The method of claim 1 , further comprising comparing the data source to with orders in order to correlate the questions and the answers with a purchase of the product or a non-purchase of the product.
10 . The method of claim 9 , further comprising generating the score of the questions and the answers based on whether the product was purchased.
11 . A non-transitory storage medium having stored therein instructions that are executable by one or more hardware processors to perform operations comprising:
semantically extracting data from text obtained from a data source, wherein the extracted data from the data source includes questions, answers, and a product;
generating a score for each question and answer;
generating an insight for the product based on the score; and
incorporating the insight into an online product page of the product.
12 . The method of claim 1 , further comprising converting the data source to the extracted data, the extracted data including text.
13 . The method of claim 2 , further comprising segmenting the text into segments and determining questions and associated answers from the segments.
14 . The method of claim 3 , further comprising determining a number of semantically equivalent questions included in the text.
15 . The method of claim 4 , further comprising generating the score based on the number of semantically equivalent questions compared to a number of data sources including the data source.
16 . The method of claim 5 , wherein at least some of the data sources comprise a transcript of a recorded call.
17 . The method of claim 4 , wherein at least some of the data sources include crowd sourced data.
18 . The method of claim 1 , further comprising generating a knowledge graph to relate the insight to other products.
19 . The method of claim 1 , further comprising comparing the data source to with orders in order to correlate the questions and the answers with a purchase of the product or a non-purchase of the product.
20 . The method of claim 9 , further comprising generating the score of the questions and the answers based on whether the product was purchased.