Machine learning approach for query resolution via a dynamic determination and allocation of expert resources

Abstract

The systems and methods described herein relate to mapping and identifying expert resources. The systems and methods described herein may provide a set of technologies, that work together as one solution, to effectively and efficiently resolve user questions. A cognitive engine may autonomously learn which experts have the knowledge to quickly solve a question or whether a previous question is similar enough to provide a solution instantly. Using machine learning, a know-how map may be created, linking all of the users of the system with their areas of expertise. Expert resources among the users may be mapped by determining connections between topics (and their corresponding tags) and calculating an expert score related to each topic for each user. These connections and expert scores are subsequently used during expert routing for each new question, to find those users with the expertise to give the best possible solution.

What is claimed is: 
     
         1 . A system configured to map expert resources within an organization or group of users and identify expert resources to route questions based on the mapped expert resources, the system comprising:
 a computer system comprising one or more physical processors programmed with computer program instructions that, when executed by the one or more physical processors, program the computer system to:
 access information indicating prior interactions with the system for a set of users, the set of users comprising at least a first user, a second user, and a third user; 
 identify indications of interest or expertise for a set of topics in the prior interactions by the set of users, wherein individual topics within the set of topics each correspond to one or more stored tags; 
 calculate, for individual users of the set of users, an expert score for one or more topics of the set of topics based on the identified indications of interest or expertise; 
 responsive to receipt of a question from the first user, determine a set of tags from the stored tags to associate with the question; 
 identify the second user and the third user as users to potentially route the question to based on the set of tags and the expert scores for at least the second user and the third user related to the set of tags, wherein an expert score of the second user for the set of tags is greater than an expert score of the third user for the set of tags; 
 determine that one or more questions routed to the second user have not been answered; 
 determine a number of unanswered questions routed to the second user, the number of unanswered questions including at least the one or more questions; 
 determine a number of unanswered questions routed to the third user, wherein the number of unanswered questions routed to the second user is greater than the number of unanswered questions routed to the third user; and 
 cause the question from the first user to be provided to the third user based on a determination that the number of unanswered questions routed to the second user is greater than the number of unanswered questions routed to the third user. 
   
     
     
         2 . The system of  claim 1 , wherein the computer system is further programmed to:
 responsive to receipt of a response by the third user to the question from the first user, prompt the first user for feedback related to the perceived quality of the response by the third user;   receive feedback responsive to the prompt;   determine at least a first topic of the question from the first user based on the first tag associated with the question; and   update the expert score of the third user for the first topic based on the feedback.   
     
     
         3 . The system of  claim 1 , wherein the identified indications of interest or expertise include indications of interest and indications of expertise, and wherein to calculate the expert score of the individual users of the set of users for a first topic of the set of topics, the computer system is further programmed to:
 apply a first weight to a first type of indication of interest related to the first topic and a second weight to a second type of indication of interest related to the first topic, wherein the second weight is greater than the first weight; and   apply a third weight to a first type of indication of expertise related to the first topic and a fourth weight to a second type of indication of expertise related to the first topic, wherein the third weight and fourth weight are each greater than the second weight, and wherein the fourth weight is greater than the third weight.   
     
     
         4 . The system of  claim 3 , wherein the information indicating prior interactions with the system comprises, for the individual users of the set of users, a viewing history indicating one or more views of prior questions received by the system or a search history indicating one or more searches within the system, wherein the first type of indication of interest comprises a view of a prior question related to the first topic and the second type of indication of interest comprises a search related to the first topic. 
     
     
         5 . The system of  claim 3 , wherein the information indicating prior interactions with the system comprises a record of contributions for the individual users of the set of users, wherein a contribution comprises a question posed to the system, a response submitted to the system, or feedback for a response submitted to the system, and wherein the first type of indication of expertise comprises a question or response related to the first topic and the second type of indication of expertise comprises feedback for a response related to the first topic. 
     
     
         6 . The system of  claim 1 , wherein the computer system is further programmed to:
 determine a number of questions routed to the second user during a previous predefined time period; and   determine a number of questions routed to the third user during the previous predefined time period,   wherein the question from the first user is provided to the third user based further on a determination that the number of questions routed to the second user during the previous predefined time period is greater than the number of questions routed to the third user during the previous predefined time period.   
     
     
         7 . The system of  claim 1 , wherein the computer system is further programmed to:
 determine a number of responses by the second user during a previous predefined time period to questions provided to the second user; and   determine a number of responses by the third user during the previous predefined time period to questions provided to the third user,   wherein the question from the first user is provided to the third user based further on a determination that the number of responses by the second user during the previous predefined time period is greater than the number of responses by the third user during the previous predefined time period.   
     
     
         8 . The system of  claim 1 , wherein to cause the question from the first user to be provided to the third user, the computer system is further programmed to:
 determine a language of the question from the first user;   obtain an indication of a language proficiency of the second user; and   cause the question from the first user to be provided to the third user based on a determination that the second user is not suitable to provide a solution to the question based on the language of the question and the language proficiency of the second user.   
     
     
         9 . The system of  claim 1 , wherein the computer system is further programmed to:
 credit a game account of the first user a first number of points based on the receipt of the question from the first user;   responsive to receipt of a response by the third user to the question from the first user, credit a game account of the third user a second number of points based on the receipt of the response to the question, wherein the second number of points is greater than the first number of points;   determine that the total number of points in the game account of the third user exceeds a third number of points, wherein the third number of points comprises a predefined threshold number of points to level up; and   cause a notification to be provided to the third user based on the determination that the total number of points in the game account of the third user exceeds the third number of points, wherein the notification indicates that the third user has leveled up.   
     
     
         10 . The system of  claim 1 , wherein the computer system is further programmed to:
 generate a user interface configured to receive the question from the first user, wherein the user interface includes a textual input component configured to receive user input indicating the question;   responsive to receipt of user input by the first user indicating the question via the textual input component, identify one or more keywords from the user input;   determine a fourth tag to associate with the question from the first user based on at least one of the one or more keywords;   determine that the stored tags do not include the fourth tag, wherein the fourth tag corresponds to a new topic;   responsive to the determination that the stored tags do not include the fourth tag, cause the fourth tag to be added to the stored tags;   identify indications of interest or expertise for the new topic in the prior interactions by the set of users; and   calculate, for the individual users of the set of users, an expert score for the new topic based on the identified indications of interest or expertise.   
     
     
         11 . A method of mapping expert resources within an organization or group of users and identifying expert resources to route questions based on the mapped expert resources, the method being implemented in a computer system having one or more physical processors programmed with computer program instructions that, when executed by the one or more physical processors, program the computer system to perform the method, the method comprising:
 accessing, by the computer system, information indicating prior interactions with the system for a set of users, the set of users comprising at least a first user, a second user, and a third user;   identifying, by the computer system, indications of interest or expertise for a set of topics in the prior interactions by the set of users, wherein individual topics within the set of topics each correspond to one or more stored tags;   calculating, by the computer system, for individual users of the set of users, an expert score for one or more topics of the set of topics based on the identified indications of interest or expertise;   receiving, by the computer system, a question from the first user;   determining, by the computer system, a set of tags from the stored tags to associate with the question;   identifying, by the computer system, the second user and the third user as users to potentially route the question to based on the set of tags and the expert scores for at least the second user and the third user related to the set of tags, wherein an expert score of the second user for the set of tags is greater than an expert score of the third user for the set of tags;   determining, by the computer system, that one or more questions routed to the second user have not been answered;   determining, by the computer system, a number of unanswered questions routed to the second user, the number of unanswered questions including at least the one or more questions;   determining, by the computer system, a number of unanswered questions routed to the third user, wherein the number of unanswered questions routed to the second user is greater than the number of unanswered questions routed to the third user; and   causing, by the computer system, the question from the first user to be provided to the third user based on a determination that the number of unanswered questions routed to the second user is greater than the number of unanswered questions routed to the third user.   
     
     
         12 . The method of  claim 11 , the method further comprising:
 receiving, by the computer system, a response by the third user to the question from the first user;   prompting, by the computer system, the first user for feedback related to the perceived quality of the response by the third user;   receiving, by the computer system, feedback responsive to the prompt;   determining, by the computer system, at least a first topic of the question from the first user based on the first tag associated with the question; and   updating, by the computer system, the expert score of the third user for the first topic based on the feedback.   
     
     
         13 . The method of  claim 11 , wherein the identified indications of interest or expertise include indications of interest and indications of expertise, wherein calculating the expert score of the individual users of the set of users for a first topic of the set of topics comprises:
 applying, by the computer system, a first weight to a first type of indication of interest related to the first topic and a second weight to a second type of indication of interest related to the first topic, wherein the second weight is greater than the first weight; and   applying, by the computer system, a third weight to a first type of indication of expertise related to the first topic and a fourth weight to a second type of indication of expertise related to the first topic, wherein the third weight and fourth weight are each greater than the second weight, and wherein the fourth weight is greater than the third weight.   
     
     
         14 . The method of  claim 13 , wherein the information indicating prior interactions with the system comprises, for the individual users of the set of users, a viewing history indicating one or more views of prior questions received by the system or a search history indicating one or more searches within the system, wherein the first type of indication of interest comprises a view of a prior question related to the first topic and the second type of indication of interest comprises a search related to the first topic. 
     
     
         15 . The method of  claim 13 , wherein the information indicating prior interactions with the system comprises a record of contributions for the individual users of the set of users, wherein a contribution comprises a question posed to the system, a response submitted to the system, or feedback for a response submitted to the system, and wherein the first type of indication of expertise comprises a question or response related to the first topic and the second type of indication of expertise comprises feedback for a response related to the first topic. 
     
     
         16 . The method of  claim 11 , the method further comprising:
 determining, by the computer system, a number of questions routed to the second user during a previous predefined time period; and   determining, by the computer system, a number of questions routed to the third user during the previous predefined time period,   wherein the question from the first user is provided to the third user based further on a determination that the number of questions routed to the second user during the previous predefined time period is greater than the number of questions routed to the third user during the previous predefined time period.   
     
     
         17 . The method of  claim 11 , the method further comprising:
 determining, by the computer system, a number of responses by the second user during a previous predefined time period to questions provided to the second user; and   determining, by the computer system, a number of responses by the third user during the previous predefined time period to questions provided to the third user,   wherein the question from the first user is provided to the third user based further on a determination that the number of responses by the second user during the previous predefined time period is greater than the number of responses by the third user during the previous predefined time period.   
     
     
         18 . The method of  claim 11 , wherein causing the question from the first user to be provided to the third user comprises:
 determining, by the computer system, a language of the question from the first user;   obtaining, by the computer system, an indication of a language proficiency of the second user; and   causing, by the computer system, the question from the first user to be provided to the third user based on a determination that the second user is not suitable to provide a solution to the question based on the language of the question and the language proficiency of the second user.   
     
     
         19 . The method of  claim 11 , the method further comprising:
 crediting, by the computer system, a game account of the first user a first number of points based on the receipt of the question from the first user;   receiving, by the computer system, a response by the third user to the question from the first user;   crediting, by the computer system, a game account of the third user a second number of points based on the receipt of the response to the question, wherein the second number of points is greater than the first number of points;   determining, by the computer system, that the total number of points in the game account of the third user exceeds a third number of points, wherein the third number of points comprises a predefined threshold number of points to level up; and   causing, by the computer system, a notification to be provided to the third user based on the determination that the total number of points in the game account of the third user exceeds the third number of points, wherein the notification indicates that the third user has leveled up.   
     
     
         20 . The method of  claim 11 , the method further comprising:
 generating, by the computer system, a user interface configured to receive the question from the first user, wherein the user interface includes a textual input component configured to receive user input indicating with the question;   receiving, by the computer system, user input of the first user indicating the question via the textual input component;   identifying, by the computer system, one or more keywords from the user input;   determining, by the computer system, a fourth tag to associate with the question from the first user based on at least one of the one or more keywords;   determining, by the computer system, that the stored tags do not include the fourth tag, wherein the fourth tag corresponds to a new topic;   responsive to the determination that the stored tags do not include the fourth tag, causing, by the computer system, the fourth tag to be added to the stored tags;   identifying, by the computer system, indications of interest or expertise for the new topic in the prior interactions by the set of users; and   calculating, by the computer system, for the individual users of the set of users, an expert score for the new topic based on the identified indications of interest or expertise for the new topic.