Many community and commercial web applications provide schemes to assist a user in completing a goal of some type. For example, in the context of an educational website, a user can be guided in how to research and prepare a paper on a scholarly topic.
This Summary is provided to introduce a selection of concepts, in a simplified form, that are further described below in the Detailed Description. This Summary is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to be used as an aid in determining the scope of the claimed subject matter.
Personalized task recommendation technique embodiments described herein generally involve recommending a particular task or tasks to a user that can be employed in furtherance of a desired goal based on observations of past users and how they accomplished this goal. The past users are chosen to be similar to each other in the manner in which they pursue the desired goal, as well as in their demographic characteristics. The tasks recommendations are personalized in that the user has demographic characteristics and/or workflow task choices which are similar with those of the group of past users.
In one exemplary embodiment, recommending one or more tasks for use in furthering a goal, involves first inputting a sequence of workflow tasks performed by an individual in furtherance of the desired goal in to a computer. This is repeated for multiple individuals. In addition, demographic information about each individual is input. The workflow and demographic data is used to establish groups of individuals. Each group exhibits a prescribed degree of workflow similarity between members in connection with furthering the desired goal and exhibits a prescribed degree of similarity in demographic information among the members.
Once the groups have been established, a user's request for assistance in accomplishing at least a portion of the desired goal can be input. The user will then be asked to provide certain demographic information. In addition, the user will be asked to identify any workflow tasks he or she performed in furtherance of the goal, or if the user is being monitored these workflow tasks will automatically be captured. Once the user's demographic information and/or previously performed workflow tasks are received and input, this data is employed to identify which of the previously established groups include members who are most similar to the user. One or more workflow task recommendations are then provided to the user. These tasks are based on the workflow tasks employed by the members of the group found to be most similar to the user, and are designed to assist the user in accomplishing at least a portion of the desired goal.
The specific features, aspects, and advantages of the disclosure will become better understood with regard to the following description, appended claims, and accompanying drawings where:
In the following description of personalized task recommendation technique embodiments reference is made to the accompanying drawings which form a part hereof, and in which are shown, by way of illustration, specific embodiments in which the technique may be practiced. It is understood that other embodiments may be utilized and structural changes may be made without departing from the scope of the technique.
The personalized task recommendation technique embodiments described herein are directed toward recommending a particular task or tasks to a user that can be employed in furtherance of a desired goal. In general, the task or tasks (which can be referred to as a workflow) recommended to the user are based on observations of past users and how they accomplished the desired goal.
The workflow that is recommended to a user is personalized in that it takes into account the demographic characteristics of the user and the workflow tasks they have taken. In general, this involves grouping the aforementioned past users into groups whose users accomplish a particular goal using a similar workflow and exhibit similar demographic characteristics. A new user wishing assistance in completing the particular goal is then associated with the group having similar demographic characteristics to the new user. A workflow based on the workflows of the associated group is then recommended to the new user.
The foregoing manner in which a workflow recommendation is personalized to a user based on workflows used by similar users is very advantageous because a wide variance in the skill level between users could make less personalized recommendations of little value. For example, in the context of an educational goal, such as writing an article on Civil War battles, the tasks performed by a grade school student in researching and writing the paper would be very different from a graduate student at university. A workflow tailored for a grade school student would be much too rudimentary to be of use to the graduate student, and a workflow tailored to the graduate student would be much too complex for the grade school student. Further, a generic workflow compiled from the workflows of users of varying levels might be too complex for the grade school student and too rudimentary for the gradate student
In one embodiment, the grouping of past users based on their workflows in working toward a particular goal and their demographics is accomplished as illustrated in
Once data has been gathered from enough users, groups of users that employ similar workflows in furtherance of a goal, and exhibit similar demographic characteristics, are identified (106). For instance, in the educational example described previously, for the goal of researching and writing an article, a group might be identified whose members are like-minded grade school students, while another group might be identified whose members are like-minded graduate students. While not shown in
In regard to the demographics used for both grouping the past users and associating a new user to a group, a variety of characteristics can be employed. For example, in an educational context some of the factors can be:
a) type of user (such as student, teacher, school administrator, and so on);
b) subject of study (such as math, history, music, and so on);
c) class teacher's name;
d) type of school (such as grade school, high school, university, and so on);
e) grade level;
f) location of the class (such as what school or university); and
g) time of the class.
The foregoing examples are not intended to be complete, but just a sampling of the demographic characteristics that can be used for grouping past and new users in an educational context. Further, other factors can apply to applications not having an educational context. Generally, the personalized task recommendation technique embodiments described herein can be implemented for any application in which a sequence of tasks is performed in furtherance of a goal. The demographic characteristics employed would be tailored to the specific application.
It is further noted that the demographic characteristics involved in grouping past and new users can be modified at any time. When a characteristic is added, modified or deleted, the past users can be re-grouped depending on the availability of any new data needed for the regrouping effort. The demographics input for any new user could then be conformed to the new set of characteristics.
The grouping of past users can also be updated each time a new user's demographics and workflow pattern for a goal are available to the implementing computer. Generally, the new user's data would be added to that of the past users, and the user groups would be regrouped.
In regard to the method employed to group the past users for a particular goal based on their workflows and demographics, many different conventional grouping techniques can be employed. In one implementation, the workflow and demographic data is used to identify common traits among user or the tasks, and use these traits to group the users. For instance, the traits can include, but are not limited to, personality (e.g., a student learner type may be visual learner vs. hands-on learner), or the type of project the workflow represents (e.g., a research paper vs. presentation), or the technology required to complete the task (e.g., presentation software as compared to a word processor).
In one embodiment, the recommendation of a workflow task or tasks to a new user in connection with a particular goal (that has a group associated with it), is accomplished as illustrated in
The requested workflow tasks recommendations are then provided to the new user based on the workflows of the members of the most similar group (206). As the workflow patterns of members within a group may not be identical depending on the grouping methods employed, the workflow tasks recommended to the user may not be the exact tasks employed by all the past users, but instead tasks based on a compilation of the workflows of the group members. Here again, many different methods can be employed to compile the past user workflows. For example, in a dynamic group, a probability technique could be employed. More particularly, suppose a minimum prescribed percent of past users in the group had task Y as the next task in series. In such a case, task Y is deemed to be next task and is suggested to a user. This prescribed percentage could also be variable and changed as desired. In a pre-defined group, the “past” user workflows would simply be the ones defined up front, or added over time as desired. It is noted that here again the foregoing examples would be appropriate methods, but not the only ones.
In regard to identifying which previously established groups associated with a goal under consideration has members that are most similar to a new user, it is noted that the degree of similarity needed to associate the new user to a group, regardless of the similarity-determining method employed, can vary. For example, the minimum similarly measure needed to associate the new user to a group can vary depending on the context of the desired goal. In addition, if it is determined that the new user is not similar enough to any groups under a current minimum similarity measure, the minimum measure can be increased by a prescribed degree.
A brief, general description of a suitable computing environment in which portions of the personalized task recommendation technique embodiments described herein may be implemented will now be described. The technique embodiments are operational with numerous general purpose or special purpose computing system environments or configurations. Examples of well known computing systems, environments, and/or configurations that may be suitable include, but are not limited to, personal computers, server computers, hand-held or laptop devices, multiprocessor systems, microprocessor-based systems, set top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments that include any of the above systems or devices, and the like.
Device 10 may also contain communications connection(s) 22 that allow the device to communicate with other devices. Device 10 may also have input device(s) 24 such as keyboard, mouse, pen, voice input device, touch input device, camera, etc. Output device(s) 26 such as a display, speakers, printer, etc. may also be included. All these devices are well know in the art and need not be discussed at length here.
The personalized task recommendation technique embodiments described herein may be further described in the general context of computer-executable instructions, such as program modules, being executed by a computing device. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The embodiments described herein may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.
It is noted that any or all of the aforementioned embodiments throughout the description may be used in any combination desired to form additional hybrid embodiments. In addition, although the subject matter has been described in language specific to structural features and/or methodological acts, it is to be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are disclosed as example forms of implementing the claims.