Audience-based optimization of communication media

• US 10,540,694 B2
• Filed: 03/28/2019
• Issued: 01/21/2020
• Est. Priority Date: 06/29/2017
• Status: Active Grant

• Current Assignee: Tyler Peppel
• Original Assignee: Tyler Peppel
• Inventors: Peppel, Tyler
• Primary Examiner(s): Brown, Luis A
• Application Number:
  US16/368,010
• Publication Number:
  US 20190220903A1
• Time in Patent Office: 299 Days
• Field of Search: 705 1449, 705 1443, 705 1452, 705 1472, 705 1466, 705 1467, 705 1473
• CPC Class Codes: G06F 40/205 Parsing
• CPC Class Codes: G06F 40/211 Syntactic parsing, e.g. based on context-free grammar [CFG] or unification grammars
• CPC Class Codes: G06F 40/253 Grammatical analysis; Style critique
• CPC Class Codes: G06F 40/279 Recognition of textual entities
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: G06F 40/40 Processing or translation of natural language natural language analysis G06F40/20; semantic analysis G06F40/30
• CPC Class Codes: G06F 40/56 Natural language generation
• CPC Class Codes: G06Q 30/0271 Personalized advertisement
• CPC Class Codes: G06V 30/10 Character recognition
• CPC Class Codes: G06V 30/153 using recognition of characters or words
• CPC Class Codes: G06V 30/246 using linguistic properties, e.g. specific for English or German language

Abstract

Introduced here are communication optimization platforms configured to improve comprehension, persuasion, or clarity of communications. Initially, a communication optimization platform can acquire input sample(s) that are associated with a source audience. The communication optimization platform can then create a linguistic profile for the source audience by examining the content of the input sample(s). Additionally or alternatively, the communication optimization platform may produce a psychographic profile that specifies various characteristics of the source audience, such as personality, opinions, attitudes, interests, etc. The communication optimization platform can then generate, based on the linguistic profile and/or the psychographic profile, affinity language for communicating with a target audience. By incorporating the affinity language into communications, the communication optimization platform can increase appeal to the target audience.

Claims

1. A computer-implemented method for improving comprehension, persuasion, or clarity of written communications, the method comprising:

acquiring, by a communication optimization platform, multiple input samples corresponding to a source audience from at least one source;

for each input sample of the multiple input samples,

identifying, by the communication optimization platform, a linguistic feature by performing one or more Natural Language Processing techniques;

generating, by the communication optimization platform, a fingerprint indicative of the corresponding linguistic feature;

producing, by the communication optimization platform, a linguistic model based on the multiple fingerprints of the multiple input samples;

producing, by the communication optimization platform, a psychographic model based on the multiple linguistic features of the multiple input samples;

generating, by the communication optimization platform, affinity language based on the linguistic model and the psychographic model;

incorporating, by the communication optimization platform, the affinity language into a written communication; and

publishing, by the communication optimization platform, the written communication on a media channel, thereby causing the written communication to be displayed to a target audience.

2. The computer-implemented method of claim 1, further comprising:

acquiring, by the communication optimization platform, multiple reference samples from at least one reference source;

labeling, by the communication optimization platform, each reference sample of the multiple reference samples with at least one psychological attribute; and

creating, by the communication optimization platform, a training set from the labeled reference samples;

wherein said generating is based on a comparison of the linguistic model to the training set.

3. The computer-implemented method of claim 1, wherein each input sample of the multiple input samples includes audio media.

4. The computer-implemented method of claim 3, further comprising:

performing, by the communication optimization platform, a natural language processing (NLP) operation on the multiple input samples to identify words spoken within each input sample.

5. The computer-implemented method of claim 1, wherein each input sample of the multiple input samples includes video media.

6. The computer-implemented method of claim 5, further comprising:

performing, by the communication optimization platform,

an optical character recognition (OCR) operation on the multiple input samples to identify words written within each input sample,

a natural language processing (NLP) operation on the multiple input samples to identify words spoken within each input sample, or

any combination thereof.

7. A non-transitory computer-readable medium with instructions stored thereon that, when executed by a processor, cause the processor to perform operations comprising:

acquiring a first set of input samples corresponding to a source audience;

examining the first set of input samples to identify a first linguistic feature by performing a natural language processing (NLP) operation;

generating a fingerprint indicative of the first linguistic feature of the first set of input samples;

producing

a linguistic model for the source audience based on the fingerprint, and

a psychographic model for the source audience based on the first linguistic feature;

generating affinity language based on the linguistic model and the psychographic model;

incorporating at least some of the affinity language into a communication to be presented to a target audience that shares a characteristic in common with the source audience;

determining that a presence of the affinity language in the communication is likely to increase a likelihood of eliciting a particular response from the target audience upon presentation of the communication; and

causing presentation of the communication to the target audience.

8. The non-transitory computer-readable medium of claim 7 wherein the communication is an advertisement, and wherein the particular response is a purchase of an advertised item.

9. The non-transitory computer-readable medium of claim 7, said acquiring comprises:

interfacing with at least one source from which the first set of input samples are acquired,

wherein the at least one source includes a network-accessible database, a computer program executing on a computing device associated with each member of the source audience, an Internet cookie, or any combination thereof.

10. The non-transitory computer-readable medium of claim 7, wherein the source audience and the target audience at least partially overlap.

11. The non-transitory computer-readable medium of claim 7, wherein the characteristic is an interest in a product, and wherein each member of the source audience is a past purchaser of the product and each member of the target audience is a potential purchaser of the product.

12. The non-transitory computer-readable medium of claim 7, wherein the operations further comprise:

performing influence analysis to generate an influence metric indicative of the likelihood of eliciting the particular response from the target audience.

13. The non-transitory computer-readable medium of claim 12, wherein the operations further comprise:

determining whether the influence metric exceeds a threshold;

responsive to a determination that the influence metric does not exceed the threshold,

incorporating either the same affinity language into the communication in some other manner or different affinity language into the communication.

14. The non-transitory computer-readable medium of claim 13, wherein said determining and said incorporating are repeated until the influence metric exceeds the threshold.

15. The non-transitory computer-readable medium of claim 7, wherein the operations further comprise:

acquiring a second set of input samples corresponding to the target audience; and

determining an effect of the communication on behavior of the target audience by examining content of each input sample in the second set of input samples.