Predicting performance of content and electronic messages among a system of networked computing devices

• US 10,346,449 B2
• Filed: 10/12/2017
• Issued: 07/09/2019
• Est. Priority Date: 10/12/2017
• Status: Active Grant

• Current Assignee: Spredfast, Inc. (Khoros LLC)
• Original Assignee: Spredfast, Inc. (Khoros LLC)
• Inventors: Senftleber, Michael, Kerns, Christopher, Schriftman, Marc
• Primary Examiner(s): Vo, Huyen X
• Application Number:
  US15/782,642
• Publication Number:
  US 20190114356A1
• Time in Patent Office: 635 Days
• Field of Search: 704 1- 10, 704230-277
• CPC Class Codes: G06F 16/313 Selection or weighting of terms for indexing
• CPC Class Codes: G06F 40/247 Thesauruses; Synonyms
• CPC Class Codes: G06F 40/279 Recognition of textual entities
• CPC Class Codes: G06Q 30/0246 Traffic
• CPC Class Codes: H04L 51/063 Content adaptation, e.g. replacement of unsuitable content
• CPC Class Codes: H04L 51/222 using geographical location information, e.g. messages transmitted or received in proximity of a certain spot or area
• CPC Class Codes: H04L 51/234 for tracking messages

Abstract

Various embodiments relate generally to data science and data analysis, computer software and systems, and control systems to provide a platform to facilitate implementation of an interface, and, more specifically, to a computing and data storage platform that implements specialized logic to predict effectiveness of content in electronic messages as a function, for example, modifiable portions of the content. In some examples, a method may include receiving data signals to cause formation of an electronic message, determining a component of the electronic message, identifying one or more message performance criteria, characterizing the component to identify a component attribute, predicting the component attribute matches at least one of the message performance criteria, and transmitting the electronic message.

Claims

1. A method comprising:

receiving data signals to cause formation of an electronic message;

determining a component of the electronic message;

identifying one or more message performance criteria with which to form the electronic message;

characterizing the component to identify a component attribute;

predicting the component attribute matches at least one of the message performance criteria;

modifying the electronic message to form a modified electronic message configured to enhance a rate of propagation at which the electronic message is conveyed as a function of the message performance criteria;

transmitting the modified electronic message via a network for presentation on user interfaces on a plurality of computing devices;

monitoring performance of one or more of message components of the modified electronic message;

determining an effectiveness of the modified electronic message is at an effectiveness value; and

implementing another electronic message responsive to the effectiveness value,

wherein identifying the one or more message performance criteria comprises identifying one or more message performance curves associated with at least one performance metric to generate an engagement value per unit time as the effectiveness value, wherein a message performance curve includes data representing a rate of change of a performance metric at a point in time subsequent to a time at which the electronic message is transmitted.

2. The method of claim 1 wherein the component of the electronic message comprises one or more of a word, a topic, and a message attribute.

3. The method of claim 2 wherein the message attribute comprises one or more of a channel type, a topic, a word, a phrase, a synonym, a language, a reading level, and a geographic location, wherein the reading level is associated with a complexity value representative of a complexity level of the component.

4. The method of claim 1 wherein a performance metric includes a value indicative of one or more performance metrics including data representing an engagement metric, an impression metric, a link activation metric, a shared indication metric, and a follower indication metric.

5. The method of claim 1 further comprising:

predicting that a value of the component characteristic does not comport to the message performance criteria.

6. The method of claim 5 further comprising:

accessing a data repository to identify an alternate component for the electronic message;

matching an alternate component attribute associated with the alternate component against the message performance criteria; and

detecting the alternate component attribute comports with the message performance criteria.

7. The method of claim 6 wherein the alternate component includes a synonym as the component attribute.

8. The method of claim 1 further comprising:

selecting automatically an alternate component;

embedding the alternate component in place of the component; and

transmitting the modified electronic message.

9. The method of claim 1 further comprising:

accessing a repository storing a corpus of electronic messages; and

generating performance metric values for components for the corpus of electronic messages,

wherein the components includes one or more of words, topics and the component attribute.

10. The method of claim 9 further comprising:

generating one or more synonyms for a word;

computing performance metric values for the one or more synonyms; and

assigning a performance metric value to each of the one or more synonyms.

11. The method of claim 9 further comprising:

generating a graphical representation of predicted values of the component attribute for the electronic message; and

presenting the predicted values of the component attribute as predicted values of a performance metric as the graphical representation in a user interface.

12. The method of claim 11 further comprising:

monitoring a performance metric associated with the component as a function of time to detect a performance metric value at a unit of time; and

updating the graphical representation based on a detected performance metric value.

13. The method of claim 11 further comprising:

detecting a performance metric value does not comport with a predicted value of the performance metric; and

receiving a data signal representing a request to generate an adjusted electronic message to include an alternate component associated with an alternate performance metric value.

14. The method of claim 9 further comprising:

storing the components of the electronic messages in the repository;

analyzing the components of the electronic messages to form clustered groupings of data associate with component attributes; and

generating one or more performance curves for the clustered groupings.

15. An apparatus comprising:

a memory including executable instructions; and

a processor, responsive to executing the instructions, is configured to;

receive data signals to cause formation of an electronic message;

determine a component of the electronic message;

identify one or more message performance criteria with which to form the electronic message;

characterize the component to identify a component attribute;

predict the component attribute matches at least one of the message performance criteria;

modify the electronic message to form a modified electronic message configured to enhance a rate of propagation at which the electronic message is conveyed as a function of the message performance criteria;

transmit the modified electronic message via a network for presentation on user interfaces on a plurality of computing devices;

monitor performance of one or more of message components of the modified electronic message;

determine an effectiveness of the modified electronic message is at an effectiveness value; and

implement another electronic message responsive to the effectiveness value,

wherein the processor is further configured to;

identify one or more message performance curves associated with at least one performance metric, wherein a message performance curve includes data representing a rate of change of a performance metric at a point in time subsequent to a time at which the electronic message is transmitted.

16. The apparatus of claim 15 wherein the component of the electronic message comprises one or more of a word, a topic, and a message attribute.

17. The apparatus of claim 16 wherein the message attribute comprises one or more of a channel type, a topic, a word, a phrase, a synonym, a language, a reading level, a synonym, and a geographic location.