Cognitive lexicon learning and predictive text replacement

• US 10,460,032 B2
• Filed: 03/17/2017
• Issued: 10/29/2019
• Est. Priority Date: 03/17/2017
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Catalano, Pasquale A., Crimmins, Andrew G., Tsfasman, Arkadiy O., Werner, John S.
• Primary Examiner(s): Shin, Seong-Ah A
• Application Number:
  US15/461,511
• Publication Number:
  US 20180267954A1
• Time in Patent Office: 956 Days
• Field of Search: 704 9, 704235, 704257, 704270
• CPC Class Codes: G06F 40/242 Dictionaries
• CPC Class Codes: G06F 40/247 Thesauruses; Synonyms
• CPC Class Codes: G06F 40/284 Lexical analysis, e.g. tokenisation or collocates
• CPC Class Codes: H04L 51/52 for supporting social networking services
• CPC Class Codes: H04W 4/14 Short messaging services, e.g. short message services [SMS] or unstructured supplementary service data [USSD]

Abstract

A method comprising of receiving a first communication content directed to a user. The first communication content includes one or a combination of the following: content read by the user and content written by the user. The method also comprises of generating tokens corresponding to the first communication content by applying natural language processing and generating a token frequency index for the user, based on the tokens generated from the first communication content. The method determines a lexicon reading level for the user, based on the token frequency index generated for the user. The lexicon reading level indicates a reading level of the user. The method adds the lexicon reading level to a lexicon profile of the user. The method modifies a second communication content by replacing tokens with synonyms of the tokens based on comparing the difficulty ratings of the tokens with the user'"'"'s lexicon reading level.

Claims

1. A computer-implemented method for determining a lexicon reading level of a user, the computer-implemented method comprising:

receiving a set of email messages, each email message being previously written by the user;

generating tokens corresponding to words in the set of email messages, the tokens being identified in a word list, the word list associating words with respectively corresponding difficulty ratings;

generating a token frequency index assigned to the user, based on the tokens generated from the set of email messages;

determining the lexicon reading level of the user based on the token frequency index and a source of difficulty ratings of the tokens according to the word list;

adding the lexicon reading level of the user to a lexicon profile;

identifying, by an applet, a web page loaded by a web-browser;

retrieving, from the lexicon profile, the lexicon reading level of the user;

performing a tokenization of the web page;

generating a plurality of tokens, based on the tokenization;

determining a difficulty rating of a first token of the plurality of tokens;

determining whether the difficulty rating of the first token differs from the lexicon reading level of the user;

responsive to determining the difficulty rating of the first token exceeds the lexicon reading level of the user, replacing the first token with a replacement token;

modifying the web page to include the replacement token for the first token; and

displaying to the user the modified web page;

wherein;

the lexicon reading level of the user indicates a reading level of the user; and

the replacement token includes a synonym of the first token that is consistent with the lexicon reading level of the user according to the word list.

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

determining a second difficulty rating of a second token of the plurality of tokens;

responsive to determining the second difficulty rating of the second token does not exceed the lexicon reading level of the user, replacing the second token with an advanced token;

wherein;

the advanced token includes a synonym of the second token, the synonym having an assigned difficulty rating that is higher than the lexicon reading level of the user according to the word list.

3. A computer program product determining a lexicon reading level of a user, the computer program product comprising:

one or more computer-readable storage media, and program instructions stored on the one or more computer-readable storage media, executable by one or more processors, the stored program instructions comprising;

program instructions to receive a set of email messages, each email message being previously written by the user;

program instructions to generate tokens corresponding to words in the set of email messages, the tokens being identified in a word list, the word list associating words with respectively corresponding difficulty ratings;

program instructions to generate a token frequency index assigned to the user, based on the tokens generated from the set of email messages;

program instructions to determine the lexicon reading level of the user based on the token frequency index and a source of difficulty ratings of the tokens according to the word list;

program instructions to add the lexicon reading level to a lexicon profile of the user;

program instructions to identify, by an applet, a web page loaded by a web-browser;

program instructions to retrieve, from the lexicon profile, the lexicon reading level;

program instructions to perform a tokenization of the web page;

program instructions to generate a plurality of tokens, based on the tokenization;

program instructions to determine a difficulty rating of a first token of the plurality of tokens;

program instructions to determine whether the difficulty rating differs from the lexicon reading level;

program instructions to, responsive to determining the difficulty rating of the first token exceeds the lexicon reading level, replace the first token with a replacement token;

program instructions to modify the web page to include the replacement token for the first token; and

program instructions to display to the user the modified web page;

wherein;

the lexicon reading level indicates a reading level of the user; and

the replacement token includes a synonym of the first token that is consistent with the lexicon reading level according to the word list.

4. The computer program product of claim 3, the stored program instructions further comprising:

program instructions to determine a second difficulty rating of a second token of the plurality of tokens;

program instructions to, responsive to determining the second difficulty rating of the second token does not exceed the lexicon reading level of the user, replacing the second token with an advanced token;

wherein;

the advanced token includes a synonym of the second token, the synonym having an assigned difficulty rating that is higher than the lexicon reading level of the user according to the word list.

5. A computer system determining a lexicon reading level of a user, the computer system comprising:

one or more computer processors;

one or more computer readable storage device;

program instructions stored on the one or more computer readable storage devices for execution by at least one of the one or more computer processors, the stored program instructions comprising;

program instructions to receive a set of email messages, each email message being previously written by the user;

program instructions to generate tokens corresponding to words in the set of email messages, the tokens being identified in a word list, the word list associating words with respectively corresponding difficulty ratings;

program instructions to generate a token frequency index assigned to the user, based on the tokens generated from the set of email messages;

program instructions to determine the lexicon reading level of the user based on the token frequency index and a source of difficulty ratings of the tokens according to the word list;

program instructions to add the lexicon reading level to a lexicon profile of the user;

program instructions to identify, by an applet, a web page loaded by a web-browser;

program instructions to retrieve, from the lexicon profile, the lexicon reading level;

program instructions to perform a tokenization of the web page;

program instructions to generate a plurality of tokens, based on the tokenization;

program instructions to determine a difficulty rating of a first token of the plurality of tokens;

program instructions to determine whether the difficulty rating differs from the lexicon reading level of the user;

program instructions to, responsive to determining the difficulty rating of the first token exceeds the lexicon reading level, replace the first token with a replacement token;

program instructions to modify the web page to include the replacement token for the first token; and

program instructions to display to the user the modified web page;

wherein;

the lexicon reading level indicates a reading level of the user; and

the replacement token includes a synonym of the first token that is consistent with the lexicon reading level.

6. The computer system of claim 5, the stored program instructions further comprising:

program instructions to determine a second difficulty rating of a second token of the plurality of tokens;

program instructions to, responsive to determining the second difficulty rating of the second token does not exceed the lexicon reading level of the user, replace the second token with an advanced token;

wherein;

the advanced token includes a synonym of the second token, the synonym having an assigned difficulty rating that is higher than the lexicon reading level of the user according to the word list.