Content-based automatic input protocol selection

Abstract

Technologies for selecting an input protocol based on an input content are generally disclosed. In one example, a method for selecting an input protocol based on an input content can include: acquiring the input content; analyzing the input content; extracting one or more indivisible individual units from the input content; calculating a similarity between a first frequency of occurrence of the one or more indivisible individual units and a second frequency of occurrence of the one or more indivisible individual units, wherein the second frequency of occurrence of the one or more indivisible individual units is predetermined with a second value of frequency of occurrence; ranking the similarity; identifying the input protocol based on the similarity; and selecting a first ranked input protocol having a highest similarity.

1 . A method to suggest input content, the method comprising:
 accessing, by one or more computing devices, a prediction dictionary, wherein the prediction dictionary includes a topic domain prediction dictionary and a relationship prediction dictionary;   receiving, by the one or more computing devices, a one or more first input content; and   processing, by the one or more computing devices, at least a portion of the one or more first input content, wherein the processing includes:
 searching, by the one or more computing devices, the topic domain prediction dictionary and the relationship prediction dictionary; and 
 suggesting, based at least on the searching, by the one or more computing devices, a one or more second input content. 
   
     
     
         2 . The method of  claim 1 , wherein:
 the topic domain prediction dictionary includes a first topic domain and a second topic domain; and   each of the first topic domain and the second topic domain includes a different one of a business topic domain, a work topic domain, a school topic domain, an athletics topic domain, an activity topic domain, a calendar topic domain, a family topic domain, or a friendship topic domain.   
     
     
         3 . The method of  claim 1 , wherein:
 the relationship prediction dictionary includes a first type of relationship and a second type of relationship; and   each of the first type of relationship and the second type of relationship includes a different one of a business contact relationship, a school contact relationship, an athletic contact relationship, an activity contact relationship, an acquaintance relationship, a friend relationship, a family relationship, a spouse relationship, a classmate relationship, a coworker relationship, a business partner relationship, or a girlfriend or boyfriend relationship.   
     
     
         4 . The method of  claim 1 , wherein:
 the prediction dictionary includes a plurality of content items included in one or both of the topic domain prediction dictionary or the relationship prediction dictionary;   the plurality of content items include at least one of words, morphactins, sentences, punctuation marks, symbols, or emoticons; and   the method further comprises updating the prediction dictionary based on usage of the plurality of content items.   
     
     
         5 . The method of  claim 4 , wherein the updating includes deleting one or more of the plurality of content items from the prediction dictionary after a predetermined period of time in which the one or more of the plurality of content items are unused. 
     
     
         6 . The method of  claim 5 , further comprising updating the prediction dictionary by adding new content items to the prediction dictionary, including at least one of:
 adding to the topic domain prediction dictionary new content items from the one or more first input content determined to be associated with a topic domain of the topic domain prediction dictionary; or   adding to the relationship prediction dictionary new content items from the one or more first input content determined to be associated with a type of relationship of the relationship prediction dictionary;   
     
     
         7 . The method of  claim 1 , wherein:
 the searching includes searching in the topic domain prediction dictionary and the relationship prediction dictionary for any words that include the at least the portion of the one or more first input content, any combinations of words that include the at least the portion of the one or more first input content, or any sentences that include the at least the portion of the one or more first input content; and   the suggesting includes suggesting as the one or more second input content at least one of the following found in the topic domain prediction dictionary or the relationship prediction dictionary as a result of the searching:
 a particular word that includes the at least the portion of the one or more first input content; 
 a particular combination of words that includes the at least the portion of the one or more first input content or a remainder of the particular combination of words that excludes the at least the portion of the one or more first input content; or 
 a particular sentence that includes the at least the portion of the one or more first input content. 
   
     
     
         8 . A system to suggest an input content, the system comprising:
 a processor; and   a non-transitory computer-readable medium that includes computer-readable instructions stored thereon that are executable by the processor to perform or control performance of operations comprising:
 accessing a prediction dictionary, wherein the prediction dictionary includes a topic domain prediction dictionary and a relationship prediction dictionary; 
 receiving a one or more first input content; and 
 processing at least a portion of the one or more first input content, wherein the processing includes:
 searching the topic domain prediction dictionary and the relationship prediction dictionary; and 
 suggesting, based at least on the searching, a one or more second input content. 
 
   
     
     
         9 . The non-transitory computer-readable medium of  claim 8 , wherein:
 the topic domain prediction dictionary includes a first topic domain and a second topic domain; and   each of the first topic domain and the second topic domain includes a different one of a business topic domain, a work topic domain, a school topic domain, an athletics topic domain, an activity topic domain, a calendar topic domain, a family topic domain, or a friendship topic domain.   
     
     
         10 . The non-transitory computer-readable medium of  claim 8 , wherein:
 the relationship prediction dictionary includes a first type of relationship and a second type of relationship; and   each of the first type of relationship and the second type of relationship includes a different one of a business contact relationship, a school contact relationship, an athletic contact relationship, an activity contact relationship, an acquaintance relationship, a friend relationship, a family relationship, a spouse relationship, a classmate relationship, a coworker relationship, a business partner relationship, or a girlfriend or boyfriend relationship.   
     
     
         11 . The non-transitory computer-readable medium of  claim 8 , wherein:
 the prediction dictionary includes a plurality of content items included in one or both of the topic domain prediction dictionary or the relationship prediction dictionary;   the plurality of content items include at least one of words, morphactins, sentences, punctuation marks, symbols, or emoticons;   the operations further comprise updating the prediction dictionary based on usage of the plurality of content items, including deleting one or more of the plurality of content items from the prediction dictionary after a predetermined period of time in which the one or more of the plurality of content items are unused; and   the operations further comprise updating the prediction dictionary by adding new content items to the prediction dictionary, including at least one of:
 adding to the topic domain prediction dictionary new content items from the one or more first input content determined to be associated with a topic domain of the topic domain prediction dictionary; or 
 adding to the relationship prediction dictionary new content items from the one or more first input content determined to be associated with a type of relationship of the relationship prediction dictionary; 
   
     
     
         12 . The non-transitory computer-readable medium of  claim 8 , wherein:
 the searching includes searching in the topic domain prediction dictionary and the relationship prediction dictionary for any words that include the at least the portion of the one or more first input content, any combinations of words that include the at least the portion of the one or more first input content, or any sentences that include the at least the portion of the one or more first input content; and   the suggesting includes suggesting as the one or more second input content at least one of the following found in the topic domain prediction dictionary or the relationship prediction dictionary as a result of the searching:
 a particular word that includes the at least the portion of the one or more first input content; 
 a particular combination of words that includes the at least the portion of the one or more first input content or a remainder of the particular combination of words that excludes the at least the portion of the one or more first input content; or 
 a particular sentence that includes the at least the portion of the one or more first input content. 
   
     
     
         13 . A method to suggest input content, the method comprising:
 accessing, by one or more computing devices, a prediction dictionary, wherein the prediction dictionary includes a topic domain prediction dictionary and a relationship prediction dictionary, and wherein the topic domain prediction dictionary includes a first topic domain and a second topic domain, and the relationship prediction dictionary includes a first type of relationship and a second type of relationship;   receiving, by the one or more computing devices, a one or more first input content; and   processing, by the one or more computing devices, at least a portion of the one or more first input content, wherein the processing includes:
 determining, by the one or more computing devices, that the at least the portion of the one or more first input content relates to the first topic domain and the first type of relationship; 
 searching, based at least on the determining, by the one or more computing devices, the first topic domain in the topic domain prediction dictionary and the first type of relationship in the relationship prediction dictionary; and 
 suggesting, based at least on the searching, by the one or more computing devices, a one or more second input content. 
   
     
     
         14 . The method of  claim 13 , wherein the processing further includes modifying, by the one or more computing devices, the prediction dictionary based on the at least the portion of the one or more first input content. 
     
     
         15 . The method of  claim 13 , wherein the relationship prediction dictionary is based on one or more previous communication records of one or more users. 
     
     
         16 . The method of  claim 15 , wherein the one or more previous communication records are associated with one or both of the first type of relationship or the second type of relationship and wherein the relationship prediction dictionary includes one or more frequently used or featured words, morphactins, punctuation marks, or sentences extracted from the one or more previous communication records. 
     
     
         17 . The method of  claim 13 , wherein the topic domain prediction dictionary is based on one or more previous communication records of one or more users. 
     
     
         18 . The method of  claim 17 , wherein the one or more previous communication records are associated with one or both of the first topic domain or the second topic domain and wherein the topic domain prediction dictionary includes one or more frequently used or featured words, morphactins, punctuation marks, or sentences extracted from the one or more previous communication records. 
     
     
         19 . The method of  claim 13 , wherein the first topic domain includes a business topic domain, a work topic domain, a school topic domain, an athletics topic domain, an activity topic domain, a calendar topic domain, a family topic domain, or a friendship topic domain. 
     
     
         20 . The method of  claim 13 , wherein the first type of relationship includes a business contact relationship, a relationship school contact relationship, an athletic contact relationship, an activity contact relationship, an acquaintance relationship, a friend relationship, a family relationship, a spouse relationship, a classmate relationship, a coworker relationship, a business partner relationship, or a girlfriend or boyfriend relationship. 
     
     
         21 . The method of  claim 13 , wherein the first input content includes text or an image. 
     
     
         22 . The method of  claim 13 , wherein the first input content includes one or more words, one or more symbols, and/or one or more emoticons. 
     
     
         23 . The method of  claim 13 , wherein the prediction dictionary includes one or more words, one or more symbols, and/or one or more emoticons. 
     
     
         24 . The method of  claim 13 , further comprising processing at least a portion of a one or more third input content that designates a different recipient than the one or more first input content, wherein the processing the at least the portion of the one or more third input content includes:
 determining that the at least the portion of the one or more third input content relates to the second topic domain that is different than the first topic domain and to the second type of relationship that is different than the first type of relationship;   searching, based at least on the determining, the second topic domain in the topic domain prediction dictionary and the second type of relationship in the relationship prediction dictionary; and   suggesting, based at least on the searching, a one or more fourth input content from the second topic domain or the second type of relationship.   
     
     
         25 . A system to suggest an input content, the system comprising:
 a processor; and   non-transitory computer-readable medium that includes computer-readable instructions stored thereon that are executable by the processor to perform or control performance of operations comprising:
 accessing a prediction dictionary, wherein the prediction dictionary includes a topic domain prediction dictionary and a relationship prediction dictionary, and wherein the topic domain prediction dictionary includes a first topic domain and a second topic domain, and the relationship prediction dictionary includes a first type of relationship and a second type of relationship; 
 receiving a one or more first input content; and 
 processing at least a portion of the one or more first input content, wherein the processing includes:
 determining that the at least the portion of the one or more first input content relates to the first topic domain and the first type of relationship; 
 searching, based at least on the determining, the first topic domain in the topic domain prediction dictionary and the first type of relationship in the relationship prediction dictionary; and 
 suggesting, based at least on the searching, a one or more second input content. 
 
   
     
     
         26 . The system of  claim 25 , wherein the processing further includes modifying the prediction dictionary based on the at least the portion of the one or more first input content. 
     
     
         27 . The system of  claim 25 , wherein:
 one or both of the relationship prediction dictionary and the topic domain prediction dictionary is based on one or more previous communication records of one or more users;   each of the one or more previous communication records is associated with one or more of the first type of relationship, the second type of relationship, the first topic domain, or the second topic domain; and   the relationship prediction dictionary and the topic domain prediction dictionary each include one or more frequently used or featured words, morphactins, punctuation marks, or sentences extracted from the one or more previous communication records.   
     
     
         28 . The system of  claim 25 , wherein:
 the first topic domain includes a business topic domain, a work topic domain, a school topic domain, an athletics topic domain, an activity topic domain, a calendar topic domain, a family topic domain, or a friendship topic domain; and   the first type of relationship includes a business contact relationship, relationship school contact relationship, an athletic contact relationship, an activity contact relationship, an acquaintance relationship, a friend relationship, a family relationship, a spouse relationship, a classmate relationship, a coworker relationship, a business partner relationship, or a girlfriend or boyfriend relationship.   
     
     
         29 . The system of  claim 25 , wherein the operations further comprise processing at least a portion of a one or more third input content that designates a different recipient than the one or more first input content, wherein the processing the at least the portion of the one or more third input content includes:
 determining that the at least the portion of the one or more third input content relates to the second topic domain that is different than the first topic domain and to the second type of relationship that is different than the first type of relationship;   searching, based at least on the determining, the second topic domain in the topic domain prediction dictionary and the second type of relationship in the relationship prediction dictionary; and   suggesting, based at least on the searching, a one or more fourth input content from the second topic domain or the second type of relationship.