Real-time personalized suggestions for communications between participants

Abstract

Disclosed in some examples are methods, systems, machine-readable media, and devices which provide for real-time personalized suggestions for participants in a network-based communication service. The personalized suggestions may include options for taking actions, content suggestions, and smart replies. These suggestions may be based upon the current conversation and are delivered personally to each participant.

What is claimed is: 
     
         1 . A machine-readable medium that stores instructions which when performed by a machine, cause the machine to perform operations comprising:
 receiving, over a network, text of a network-based communication between a first device and a second device;   inputting the text of the communication to an intent model that is trained to detect a unique type of communicative intent in communication texts, wherein the communicative intent is a semantic meaning of the text of the communication that supports identifying suggestions associated with the following suggestion types: an action suggestion type, a content suggestion type, and a reply suggestion type;   receiving a set of one or more responses from the intent model, each response in the set indicating a calculated communicative intent of the communication;   generating a set of personalized suggestions based upon both the set of responses;   ranking the set of suggestions relative to one another;   selecting a first suggestion and a second suggestion from the set of suggestions based upon the ranking, wherein the first suggestion is a first suggestion type and the second suggestion is a second suggestion type, the first suggestion type and the second suggestion type being different suggestion types; and   sending the first suggestion and second suggestion to the first device for presentation.   
     
     
         2 . The machine-readable medium of  claim 1 , wherein the first suggestion is an action suggestion of the action suggestion type and wherein the operations further comprise:
 receiving a confirmation input from the first device, the confirmation input indicates a desire to perform an action corresponding to the action suggestion; and   responsive to receiving the confirmation input, sending a message to a computing device to implement the action.   
     
     
         3 . The machine-readable medium of  claim 1 , wherein the first suggestion is a content suggestion of the content suggestion type and wherein the operations further comprise:
 receiving a confirmation input from the first device, the confirmation input indicates a desire to receive content suggested by the content suggestion; and   responsive to receiving the confirmation input, sending the content to the first device.   
     
     
         4 . The machine-readable medium of  claim 1 , wherein the first suggestion is a reply suggestion of the reply suggestion type and wherein the operations further comprise:
 receiving a confirmation input from the first device, the confirmation input indicates a desire to send content suggested by the first suggestion; and   responsive to receiving the confirmation input, sending a reply text corresponding to the reply suggestion to a communications service hosting the network-based communication.   
     
     
         5 . The machine-readable medium of  claim 1 , wherein the operations further comprise populating the first suggestion with content based upon a user profile of a first user associated with the first device and information determined from a network-based service corresponding to the first suggestion. 
     
     
         6 . The machine-readable medium of  claim 1 , wherein the operations for ranking the set of suggestions relative to one another comprises utilizing a set of heuristics, the set of heuristics applying a priority based ordering based upon type of suggestions including the action suggestion type, the content suggestion type, and the reply suggestion type. 
     
     
         7 . The machine-readable medium of  claim 1 , wherein the operations for ranking the set of suggestions relative to one another is based upon a user model and a global model, the user model is specific to preferences of a first user of the first device and customized based upon past selection history of suggestions of the first user, the global model is based upon past selection history of a plurality of users. 
     
     
         8 . A computer-implemented method for providing personalized suggestions, the method comprising:
 using a computer processor:   receiving, over a network, text of a network-based communication between a first device and a second device;   inputting the text of the communication to an intent model that is trained to detect a unique type of communicative intent in communication texts, wherein the communicative intent is a semantic meaning of the text of the communication that supports identifying suggestions associated with the following suggestion types: an action suggestion type, a content suggestion type, and a reply suggestion type;   receiving a set of one or more responses from the intent model, each response in the set indicating a calculated communicative intent of the communication;   generating a set of personalized suggestions based upon both the set of responses;   ranking the set of suggestions relative to one another;   selecting a first suggestion and a second suggestion from the set of suggestions based upon the ranking, wherein the first suggestion is a first suggestion type and the second suggestion is a second suggestion type, the first suggestion type and the second suggestion type being different suggestion types; and   sending the first suggestion and second suggestion to the first device for presentation.   
     
     
         9 . The method of  claim 8 , wherein the first suggestion is an action suggestion of the action suggestion type and wherein the method further comprises:
 receiving a confirmation input from the first device, the confirmation input indicates a desire to perform an action corresponding to the action suggestion; and   responsive to receiving the confirmation input, sending a message to a computing device to implement the action.   
     
     
         10 . The method of  claim 8 , wherein the first suggestion is a content suggestion of the content suggestion type and wherein the operations further comprise:
 receiving a confirmation input from the first device, the confirmation input indicates a desire to receive content suggested by the content suggestion; and   responsive to receiving the confirmation input, sending the content to the first device.   
     
     
         11 . The method of  claim 8 , wherein the first suggestion is a reply suggestion of the reply suggestion type and wherein the operations further comprise:
 receiving a confirmation input from the first device, the confirmation input indicates a desire to send content suggested by the first suggestion; and   responsive to receiving the confirmation input, sending a reply text corresponding to the reply suggestion to a communications service hosting the network-based communication.   
     
     
         12 . The method of  claim 8 , wherein the operations for ranking the set of suggestions relative to one another comprises utilizing a set of heuristics, the set of heuristics applying a priority based ordering based upon type of suggestions including the action suggestion type, the content suggestion type, and the reply suggestion type. 
     
     
         13 . The method of  claim 8 , wherein the operations for ranking the set of suggestions relative to one another is based upon a user model and a global model, the user model is specific to preferences of a first user of the first device and customized based upon past selection history of suggestions of the first user, the global model is based upon past selection history of a plurality of users. 
     
     
         14 . A system, the system comprising:
 a processor;   a memory, communicatively coupled to the processor and including instructions, which when performed by the processor, causes the system to perform operations comprising:   receiving, over a network, text of a network-based communication between a first device and a second device;   inputting the text of the communication to an intent model that is trained to detect a unique type of communicative intent in communication texts, wherein the communicative intent is a semantic meaning of the text of the communication that supports identifying suggestions associated with the following suggestion types: an action suggestion type, a content suggestion type, and a reply suggestion type;   receiving a set of one or more responses from the intent model, each response in the set indicating a calculated communicative intent of the communication;   generating a set of personalized suggestions based upon both the set of responses;   ranking the set of suggestions relative to one another;   selecting a first suggestion and a second suggestion from the set of suggestions based upon the ranking, wherein the first suggestion is a first suggestion type and the second suggestion is a second suggestion type, the first suggestion type and the second suggestion type being different suggestion types; and   sending the first suggestion and second suggestion to the first device for presentation.   
     
     
         15 . The system of  claim 14 , wherein the first suggestion is an action suggestion of the action suggestion type and wherein the operations further comprise:
 receiving a confirmation input from the first device, the confirmation input indicates a desire to perform an action corresponding to the action suggestion; and   responsive to receiving the confirmation input, sending a message to a computing device to implement the action.   
     
     
         16 . The system of  claim 15 , wherein the first suggestion is a content suggestion of the content suggestion type and wherein the operations further comprise:
 receiving a confirmation input from the first device, the confirmation input indicates a desire to receive content suggested by the content suggestion; and   responsive to receiving the confirmation input, sending the content to the first device.   
     
     
         17 . The system of  claim 14 , wherein the first suggestion is a reply suggestion of the reply suggestion type and wherein the operations further comprise:
 receiving a confirmation input from the first device, the confirmation input indicates a desire to send content suggested by the first suggestion; and   responsive to receiving the confirmation input, sending a reply text corresponding to the reply suggestion to a communications service hosting the network-based communication.   
     
     
         18 . The system of  claim 14 , wherein the operations further comprise: populating the first suggestion with content based upon a user profile of a first user associated with the first device and information determined from a network-based service corresponding to the first suggestion. 
     
     
         19 . The system of  claim 14 , wherein the operations for ranking the set of suggestions relative to one another comprises utilizing a set of heuristics, the set of heuristics applying a priority based ordering based upon type of suggestions including the action suggestion type, the content suggestion type, and the reply suggestion type. 
     
     
         20 . The system of  claim 14 , wherein the operations for ranking the set of suggestions relative to one another is based upon a user model and a global model, the user model is specific to preferences of a first user of the first device and customized based upon past selection history of suggestions of the first user, the global model is based upon past selection history of a plurality of users.