Systems and methods for instant generation of human understandable audience insights
Systems and methods for generating human readable natural language summary for campaign audience are provided. The system includes a memory storing a database including audience segments and tags related to the audience segments. A computer server is in communication with the memory and the database, the computer server programmed to: obtain campaign delivery feed data related to a plurality of campaigns from at least one advertiser in a preset time period; obtain audience feed data including tag information from a data provider; cluster the tag information to find term frequencies for each term in the tag information; identify human understandable terms from the clustered tag information by removing noisy terms; and generate a human understandable report using the human understandable terms in a timely fashion.
1. A system comprising:
a processor and a non-transitory storage medium accessible to the processor;
a memory storing a database comprising audience segments and tags related to the audience segments; and
a computer server in communication with the memory and the database, the computer server programmed to:
obtain campaign delivery feed data related to a plurality of campaigns from at least one advertiser in a preset time period;
obtain audience feed data including tag information from a data provider, wherein the audience feed data is segmented into one or more audience segments;
cluster the tag information to find term frequencies for each term in the tag information;
generate a cluster group of audience feed data, the cluster group comprising audience feed data from across a plurality of different audience segments sharing a common high-frequency term;
identify understandable terms from the clustered tag information by removing noisy terms from the cluster group; and
generate a performance report by inserting the understandable terms into a report template.
2. The system of claim 1 , wherein the computer server is programmed to obtain user identifications using the campaign delivery feed data related to the plurality of campaigns from at least one advertiser.
3. The system of claim 2 , wherein the computer server is programmed to obtain audience feed data comprising the tag information from a plurality of social networks using the user identifications, wherein the user identifications is encrypted and only understandable by the computer server during the preset time period.
4. The system of claim 1 , wherein the computer server is programmed to cluster the tag information to identify common properties of audience segments in the plurality of campaigns.
5. The system of claim 1 , wherein the computer server is programmed to detect an agency name using term frequency results from a search engine.
6. The system of claim 5 , wherein the computer server is programmed to generate a regular expression that includes at least one of the agency name and a predefined black-list word.
7. The system of claim 6 , wherein the computer server is programmed to detect a meaningful part in the clustered tag information by using the regular expression to remove a non-meaningful part in the clustered tag information.
8. The system of claim 7 , wherein the computer server is programmed to generate the performance report by inserting the understandable terms and the meaningful part into the report template.
9. A non-transitory storage medium configured to store processor executable instructions that, when executed by a processor, cause the processor to:
obtain campaign delivery feed data related to a plurality of campaigns from at least one advertiser in a preset time period, the campaign delivery feed data comprising user identifications;
obtain audience feed data including tag information from a data provider, wherein the audience feed data is segmented into one or more audience segments;
cluster the tag information to find term frequencies for each term in the tag information;
generate a cluster group of audience feed data, the cluster group comprising audience feed data from across a plurality of different audience segments sharing a common high-frequency term;
identify understandable terms from the clustered tag information by removing noisy terms from the cluster group; and
generate a performance report by inserting the understandable terms into a report template.
10. The non-transitory storage medium of claim 9 , wherein the user identifications are encrypted and only understandable by a preset device during the preset time period.
11. The non-transitory storage medium of claim 9 , further configured to store processor executable instructions that, when executed by the processor, cause the processor to:
cluster the tag information to identify common properties of audience segments in the plurality of campaigns; and
detect an agency name using term frequency results from a search engine.
12. The non-transitory storage medium of claim 11 , further configured to store processor executable instructions that, when executed by the processor, cause the processor to:
generate a regular expression that includes at least one of the agency name and a predefined black-list word;
detect a meaningful part in the clustered tag information by using the regular expression to remove a non-meaningful part in the clustered tag information; and
generate the performance report by inserting the understandable terms and the meaningful part into the report template.