System and method of content brief generation using machine learning
A method and apparatus of a device for generating one or more content briefs is described. In an exemplary embodiment, the device receives a strategy for generating the plurality of content briefs, wherein each of the plurality of content briefs is a structured document that is used to guide creation of content. In addition, the device may collect a collection of content and generate a plurality of content clusters using unsupervised machine learning to cluster the content collection with the received strategy. Furthermore, the device may generate the plurality of content briefs from the plurality of content clusters.
1. A non-transitory machine-readable medium having executable instructions to cause one or more processing units to perform a method to generate a plurality of content briefs, the method comprising:
receiving a strategy for generating the plurality of content briefs, wherein each of the plurality of content briefs is a structured document that is used to guide creation of content;
collecting a collection of content;
generating a plurality of content clusters by:
generating features for the collection of content using unsupervised machine learning, wherein the generating involves a feedforward neural network comprising a probabilistic language model and an encoder, the encoder acting as a conditional summary, the encoder comprising an encoder function implementing an attention-based model; and
clustering the content collection using the generated features and the received strategy; and
generating the plurality of content briefs from the plurality of content clusters.
2. The non-transitory machine-readable medium of claim 1 , further comprising:
generating a tone of voice for each of the plurality of content briefs, wherein the tone of voice for a content brief is a style to be used for a voice of the content brief.
3. The non-transitory machine-readable medium of claim 1 , further comprising:
generating an intended audience for each of the plurality of content briefs, wherein the intended audience for a content brief is a type of audience that is a target for the content brief.
4. The non-transitory machine-readable medium of claim 3 , wherein the intended audience is an advertising segment.
5. The non-transitory machine-readable medium of claim 1 , further comprising:
generating a matching persona for each of the plurality of content briefs.
6. The non-transitory machine-readable medium of claim 1 , further comprising:
generating a purpose for each of the plurality of content briefs, wherein the purpose for a content brief is type of purpose for the content brief.
7. The non-transitory machine-readable medium of claim 1 , further comprising:
generating a set of one of more influencers for each of the plurality of content briefs, wherein an influencer for a content brief is a social media presence that would boost a presence for the content associated for that content brief.
8. The non-transitory machine-readable medium of claim 1 , further comprising:
generating a set of one or more relevant sources for each of the plurality of content briefs, wherein a relevant source for a content brief is a content source to be used for the generation of the content associated with that content brief.
9. The non-transitory machine-readable medium of claim 1 , further comprising:
generating a set of one or more potential questions for each of the plurality of content brief, wherein a potential question for a content brief is a question that is used by a content creator for generating the content associated with the content brief.
10. The non-transitory machine-readable medium of claim 1 , wherein the strategy includes one or more information types of at least one of a content strategy, persona strategy, and channel strategy.
11. The non-transitory machine-readable medium of claim 1 , further comprising:
computing one or more content brief characteristics for each of the plurality of content briefs.
12. The non-transitory machine-readable medium of claim 3 , wherein a headline characteristic is selected from the group consisting of exclusivity, demand, and emotionality.
13. A method to generate a plurality of content briefs, the method comprising:
receiving a strategy for generating the plurality of content briefs, wherein each of the plurality of content briefs is a structured document that is used to guide creation of content;
collecting a collection of content;
generating a plurality of content clusters by:
generating features for the collection of content using unsupervised machine learning, wherein the generating involves a feedforward neural network comprising a probabilistic language model and an encoder, the encoder acting as a conditional summary, the encoder comprising an encoder function implementing an attention-based model; and
clustering the content collection using the generated features and the received strategy; and
generating the plurality of content briefs from at least the plurality of content clusters.
14. The method of claim 13 , further comprising:
generating a tone of voice for each of the plurality of content briefs, wherein the tone of voice for a content brief is a style to be used for a voice of the content brief.
15. The method of claim 13 , further comprising:
generating an intended audience for each of the plurality of content briefs, wherein the intended audience for a content brief is a type of audience that is a target for the content brief.
16. The method of claim 13 , further comprising:
generating a matching persona for each of the plurality of content briefs.
17. The method of claim 13 , further comprising:
generating a purpose for each of the plurality of content briefs, wherein the purpose for a content brief is type of purpose for the content brief.
18. The method of claim 13 , further comprising:
generating a set of one of more influencers for each of the plurality of content briefs, wherein an influencer for a content brief is a social media presence that would boost a presence for the content associated for that content brief.
19. The method of claim 13 , further comprising:
generating a set of one or more relevant sources for each of the plurality of content briefs, wherein a relevant source for a content brief is a content source to be used for the generation of the content associated with that content brief.
20. The method of claim 13 , further comprising:
generating a set of one or more potential questions for each of the plurality of content brief, wherein a potential question for a content brief is a question that is used by a content creator for generating the content associated with the content brief.