Summarization and processing of email on a client computing device based on content contribution to an email thread using weighting techniques
View Patent ↗Systems, methods, and computer-readable media are disclosed for enhancing an email application to automatically analyze an email thread and generate a compact content summary. The content summary is based on relative content contributions provided by the constituent email messages in the email thread. The content summary may be presented in a special window without disturbing or modifying the email thread or its constituent email messages. The distinctive content summary disclosed herein comprises certain sentences that are automatically gleaned from the email thread, analyzed relative to other sentences, and presented in a chronological sequence so that the user can quickly determine what the email thread is about and/or the current status of the conversation. The content summary is based on email weights, word weights, and intersecting sentence pairs.
1. A method for automatically analyzing an email-thread and generating a content summary of the email-thread, the method comprising:
identifying, by a computing device that executes an email application, the email-thread comprising email messages;
generating the content summary of the email-thread, by the computing device, based at least in part on:
(i) an email-weight assigned to each email message in the email-thread,
(ii) a word-weight assigned to certain words in each email message in the email-thread, and
(iii) an intersection-score assigned to identified intersecting sentence pairs selected from sentences in the email messages in the email-thread,
wherein the first sentence and the second sentence in a respective intersecting sentence pair have a set of words in common;
wherein the content summary of the email-thread is based on relative content contributions by one or more email messages in the email-thread; and
wherein the intersection-score for a respective intersecting sentence pair is based on:
(a) word-weights of the set of words in common belonging to the first sentence, weighted by the email-weight of the email message comprising the first sentence, and
(b) word-weights of the set of words in common belonging to the second sentence, weighted by the email-weight of the email message comprising the second sentence.
2. The method of claim 1 wherein the email-thread is a fraction of a collective size of the email messages in the email-thread.
3. The method of claim 1 wherein the email-thread is a fraction of a collective size of the email messages in the email-thread, and
wherein the fraction is defined according to a predefined formula which is based at least in part on a number of email messages in the email-thread.
4. The method of claim 1 wherein the email-weight assigned to each email message in the email-thread is based on a chronological position of the respective email message within the email-thread.
5. The method of claim 1 wherein the word-weight assigned a respective word in each email message in the email-thread is based on one or more measures of frequency of the respective word in one or more email messages in the email-thread.
6. The method of claim 1 further comprising:
displaying the content summary of the email-thread which comprises listing in chronological order unique sentences chosen from highest-scoring intersecting sentence pairs.
7. A method for summarizing a thread of emails, the method comprising:
identifying, by a computing device that executes an email application, an email-thread comprising email messages which are related based on replies to one or more of the email messages;
for each email message in the email-thread:
(i) assigning an email-weight to the respective email message based on a proximity of the respective email message to a chronological median of the email-thread, and
(ii) assigning a word-weight to some words in the respective email message,
wherein the word-weight is based on a frequency measure of the respective word, and
wherein the word-weight is further based on the email-weight of the respective email message comprising the respective word;
identifying one or more intersecting sentence pairs selected from sentences in the email messages in the email-thread,
wherein a first sentence in a respective intersecting sentence pair has a set of words in common with a second sentence in the respective intersecting sentence pair;
assigning an intersection-score to each identified intersecting sentence pair, wherein the intersection-score is based on one or more of:
(a) word-weights of the words in the set belonging to the first sentence in the respective intersecting sentence pair, weighted by the email-weight of the email message comprising the first sentence, and
(b) word-weights of the words in the set belonging to the second sentence in the respective intersecting sentence pair, weighted by the email-weight of the email message comprising the second sentence;
composing a summary of the email-thread which comprises listing in chronological order unique sentences chosen from highest-scoring intersecting sentence pairs; and
causing the summary of the email-thread to be displayed to a user of the computing device.
8. The method of claim 7 wherein the intersection-score assigned to each intersecting sentence pair in the first seta is further based on summing:
(A) a first sum of the word-weights of the words in the set belonging to the first sentence in the respective intersecting sentence pair, which first sum is weighted by the email-weight of the email message comprising the first sentence, and
(B) a second sum of the word-weights of the words in the set belonging to the second sentence in the respective intersecting sentence pair, which second sum is weighted by the email-weight of the email message comprising the second sentence.
9. The method of claim 7 wherein the email-weight for a given email message negatively correlates to the proximity of the respective email message to the chronological median of the email-thread.
10. The method of claim 7 wherein a first email message that is closer to the beginning or end of the email-thread than a second email message receives a higher email-weight than the second email message.
11. The method of claim 7 wherein the word-weight assigned to a given word is higher when the word appears in a first word-frequency table generated from emails that were classified as important, as compared to when the word appears in a second word-frequency table generated from emails that were classified as not-important.
12. A computer-readable medium, excluding transitory propagating signals, storing instructions that, when executed by at least one computing device comprising one or more processors and computer-readable memory for storing the instructions, cause the computing device to perform operations comprising:
executing an email application;
identifying an email-thread comprising email messages related based on one more replies to one or more of the email messages;
generating a content summary of the email-thread, based on:
(i) an email-weight assigned to each email message in the email-thread,
(ii) a word-weight assigned to certain words in each email message in the email-thread, and
(iii) an intersection-score assigned to identified intersecting sentence pairs selected from sentences in the email messages in the email-thread,
wherein the first sentence and the second sentence in a respective intersecting sentence pair have a set of words in common; and
wherein the content summary of the email-thread is based on relative content contributions by one or more email messages in the email-thread;
wherein the intersection-score assigned to each intersecting sentence pair is based on summing:
(A) a first sum of the word-weights of the set of words in common belonging to the first sentence in the respective intersecting sentence pair, which first sum is weighted by the email-weight of the email message comprising the first sentence, and
(B) a second sum of the word-weights of the set of words in common belonging to the second sentence in the respective intersecting sentence pair, which second sum is weighted by the email-weight of the email message comprising the second sentence; and
wherein the operations further comprise: causing the content summary of the email-thread to be displayed to a user of the computing device which comprises listing in chronological order unique sentences chosen from highest-scoring intersecting sentence pairs.
13. The computer-readable medium of claim 12 wherein the email-weight assigned to each email message in the email-thread is based on a chronological position of the respective email message within the email-thread.
14. The computer-readable medium of claim 12 wherein the word-weight assigned a respective word in each email message in the email-thread is based on one or more measures of frequency of the respective word in one or more email messages in the email-thread.