SYSTEM AND METHOD FOR PROVIDING PREDICTIVE CONTACTS

Abstract

Disclosed herein are systems, methods, and non-transitory computer-readable storage media for providing predictive contacts. A system configured to practice the method first analyzes a communication history and a current usage context of a user. Based on the analysis, the system ranks contacts that the user is likely to communicate with from a list of contacts to yield ranked contacts. The system identifies a respective motive for ranking each contact, and presents a predictive list of contacts based at least in part on the ranked contacts, wherein each ranked contact in the predictive list of contacts includes at least part of the respective motive. The system can update the predictive list of contacts in real time as the current usage context changes. The communication history can include, for example, emails, instant messages, phone calls, video conferences, and calendar events. The motive can include a user interaction history with a particular contact.

Description

BACKGROUND

1. Technical Field

The present disclosure relates to managing contacts and more specifically to providing a context-sensitive list of predictive contacts.

2. Introduction

Traditional approaches to contacts require users to manually manage and maintain their contacts. This approach is workable when the list of contacts tends to be more static, but when the list of contacts is more dynamic, manual contact management quickly becomes difficult and excessively time consuming to maintain. When a list of contacts grows too large, users often simply revert to a search of LDAP, Post, Active Directory, or other similar directories to obtain contact information.

Further, traditional approaches to listing contacts are static. These static approaches to listing contacts can waste user time. For example, a user must search for a contact even if the contact was recently used. Some existing approaches attempt to sort contacts in a predictive order, but these approaches are based on a limited set of information, do not take in to account a current user context, and do not indicate why or how the list of contacts are ordered in a particular way.

One significant shortfall of the approaches known in the art is that they do not provide a mechanism whereby, at any given time, given a set of communication sessions (email, voice, chat, etc) and their interactions (missed, answered), present solutions do not provide a way of predicting which contacts the user needs. Also, the present solutions do not provide transparency showing how or why a set of contacts is ordered in a particular way and do not account for a sufficiently broad interaction/communication data set.

SUMMARY

Additional features and advantages of the disclosure will be set forth in the description which follows, and in part will be obvious from the description, or can be learned by practice of the herein disclosed principles. The features and advantages of the disclosure can be realized and obtained by means of the instruments and combinations particularly pointed out in the appended claims. These and other features of the disclosure will become more fully apparent from the following description and appended claims, or can be learned by the practice of the principles set forth herein.

Disclosed are systems, methods, and non-transitory computer-readable storage media for providing predictive contacts. A system configured to practice the method first analyzes a communication history and a current usage context of a user. The communication history can include emails, instant messaging, phone calls, video conferences, and calendar events. Based on the analysis, the system ranks contacts that the user is likely to communicate with from a list of contacts to yield ranked contacts and identifies a respective motive for ranking each contact. The motive can include a history of interactions between the user and a respective contact. Then the system presents a predictive list of contacts based at least in part on the ranked contacts, wherein each ranked contact in the predictive list of contacts includes at least part of the respective motive. In one regard, the system updates the predictive list of contacts in real time as the current usage context changes.

In one variation, the system further identifies a likely communication modality for each ranked contact, and presents, as part of the predictive list of contacts, the likely communication modality. In another variation, the system receives from the user a request to ignore one respective motive. In response, the system reranks the contacts based on the request to ignore the one respective motive, and presents an updated predictive list of contacts based at least in part on the reranked contacts.

BRIEF DESCRIPTION OF THE DRAWINGS

In order to describe the manner in which the above-recited and other advantages and features of the disclosure can be obtained, a more particular description of the principles briefly described above will be rendered by reference to specific embodiments thereof which are illustrated in the appended drawings. Understanding that these drawings depict only exemplary embodiments of the disclosure and are not therefore to be considered to be limiting of its scope, the principles herein are described and explained with additional specificity and detail through the use of the accompanying drawings in which:

FIG. 1 illustrates an example system embodiment;

FIG. 2 illustrates an exemplary communications environment;

FIG. 3 illustrates an exemplary list of predictive contacts; and

FIG. 4 illustrates an example method embodiment.

DETAILED DESCRIPTION

Various embodiments of the disclosure are discussed in detail below. While specific implementations are discussed, it should be understood that this is done for illustration purposes only. A person skilled in the relevant art will recognize that other components and configurations may be used without parting from the spirit and scope of the disclosure.

The present disclosure addresses the need in the art for providing predictive contacts based on context. A system, method and non-transitory computer-readable media are disclosed which provide predictive contacts. A brief introductory description of a basic general purpose system or computing device in FIG. 1 which can be employed to practice the concepts is disclosed herein. Afterward, the disclosure turns to a more detailed description of the methods and environments in which the system can provide predictive contacts. The disclosure now turns to FIG. 1.

With reference to FIG. 1, an exemplary system 100 includes a general-purpose computing device 100, including a processing unit (CPU or processor) 120 and a system bus 110 that couples various system components including the system memory 130 such as read only memory (ROM) 140 and random access memory (RAM) 150 to the processor 120. The system 100 can include a cache of high speed memory connected directly with, in close proximity to, or integrated as part of the processor 120. The system 100 copies data from the memory 130 and/or the storage device 160 to the cache for quick access by the processor 120. In this way, the cache provides a performance boost that avoids processor 120 delays while waiting for data. These and other modules can control or be configured to control the processor 120 to perform various actions. Other system memory 130 may be available for use as well. The memory 130 can include multiple different types of memory with different performance characteristics. It can be appreciated that the disclosure may operate on a computing device 100 with more than one processor 120 or on a group or cluster of computing devices networked together to provide greater processing capability. The processor 120 can include any general purpose processor and a hardware module or software module, such as module 1162, module 2164, and module 3166 stored in storage device 160, configured to control the processor 120 as well as a special-purpose processor where software instructions are incorporated into the actual processor design. The processor 120 may essentially be a completely self-contained computing system, containing multiple cores or processors, a bus, memory controller, cache, etc. A multi-core processor may be symmetric or asymmetric.

The system bus 110 may be any of several types of bus structures including a memory bus or memory controller, a peripheral bus, and a local bus using any of a variety of bus architectures. A basic input/output (BIOS) stored in ROM 140 or the like, may provide the basic routine that helps to transfer information between elements within the computing device 100, such as during start-up. The computing device 100 further includes storage devices 160 such as a hard disk drive, a magnetic disk drive, an optical disk drive, tape drive or the like. The storage device 160 can include software modules 162, 164, 166 for controlling the processor 120. Other hardware or software modules are contemplated. The storage device 160 is connected to the system bus 110 by a drive interface. The drives and the associated computer readable storage media provide nonvolatile storage of computer readable instructions, data structures, program modules and other data for the computing device 100. In one aspect, a hardware module that performs a particular function includes the software component stored in a non-transitory computer-readable medium in connection with the necessary hardware components, such as the processor 120, bus 110, display 170, and so forth, to carry out the function. The basic components are known to those of skill in the art and appropriate variations are contemplated depending on the type of device, such as whether the device 100 is a small, handheld computing device, a desktop computer, or a computer server.

Although the exemplary embodiment described herein employs the hard disk 160, it should be appreciated by those skilled in the art that other types of computer readable media which can store data that are accessible by a computer, such as magnetic cassettes, flash memory cards, digital versatile disks, cartridges, random access memories (RAMs) 150, read only memory (ROM) 140, a cable or wireless signal containing a bit stream and the like, may also be used in the exemplary operating environment. Non-transitory computer-readable storage media expressly exclude media such as energy, carrier signals, electromagnetic waves, and signals per se.

To enable user interaction with the computing device 100, an input device 190 represents any number of input mechanisms, such as a microphone for speech, a touch-sensitive screen for gesture or graphical input, keyboard, mouse, motion input, speech and so forth. An output device 170 can also be one or more of a number of output mechanisms known to those of skill in the art. In some instances, multimodal systems enable a user to provide multiple types of input to communicate with the computing device 100. The communications interface 180 generally governs and manages the user input and system output. There is no restriction on operating on any particular hardware arrangement and therefore the basic features here may easily be substituted for improved hardware or firmware arrangements as they are developed.

For clarity of explanation, the illustrative system embodiment is presented as including individual functional blocks including functional blocks labeled as a “processor” or processor 120. The functions these blocks represent may be provided through the use of either shared or dedicated hardware, including, but not limited to, hardware capable of executing software and hardware, such as a processor 120, that is purpose-built to operate as an equivalent to software executing on a general purpose processor. For example the functions of one or more processors presented in FIG. 1 may be provided by a single shared processor or multiple processors. (Use of the term “processor” should not be construed to refer exclusively to hardware capable of executing software.) Illustrative embodiments may include microprocessor and/or digital signal processor (DSP) hardware, read-only memory (ROM) 140 for storing software performing the operations discussed below, and random access memory (RAM) 150 for storing results. Very large scale integration (VLSI) hardware embodiments, as well as custom VLSI circuitry in combination with a general purpose DSP circuit, may also be provided.

The logical operations of the various embodiments are implemented as: (1) a sequence of computer implemented steps, operations, or procedures running on a programmable circuit within a general use computer, (2) a sequence of computer implemented steps, operations, or procedures running on a specific-use programmable circuit; and/or (3) interconnected machine modules or program engines within the programmable circuits. The system 100 shown in FIG. 1 can practice all or part of the recited methods, can be a part of the recited systems, and/or can operate according to instructions in the recited non-transitory computer-readable storage media. Such logical operations can be implemented as modules configured to control the processor 120 to perform particular functions according to the programming of the module. For example, FIG. 1 illustrates three modules Mod1162, Mod2164 and Mod3166 which are modules configured to control the processor 120. These modules may be stored on the storage device 160 and loaded into RAM 150 or memory 130 at runtime or may be stored as would be known in the art in other computer-readable memory locations.

Having discussed some basic computing system components, the disclosure returns to a discussion of generating and presenting predictive contacts. This approach generates a predictive list of relevant contacts based on multiple sources of information, such as email history, IM history, call frequency, and so forth. A user services layer can mine information from many sources that a predictive contact widget can use to generate a list of contacts. In one aspect, the predictive contact component is a separate hardware and/or software widget that operates in conjunction with traditional communications equipment, but the predictive contact elements described herein can also be incorporated with communications equipment. The system uses that information and can add ‘user context’ at any given time to predict the contacts needed by the user. The system can use an algorithm to rank all or part of the contacts based on the above information. The system can display on a user interface a widget or other notification presenting a short history of a user's interactions with each predicted contact (i.e. a brief summary of recent communications with them). This solution presents a list of predicted people that the user may want to contact. The system can dynamically update the list based on a current communication, such as an email being received, or based on the user's activities or context.

This approach provides users with a dynamic contact list without manual contact management. This approach uses information gleaned from many different communications modalities (email, IM, voice calls, conference calls, text messages, etc.) to determine a predictive contact list. Further, a user of a predictive contact list can drill down to determine which communications or what pieces of information in a communications history led to a particular contact's placement in the predictive contact list.

This approach provides at least three benefits. First, this approach provides an optimal predictive list of people likely to be contacted by the user. Second, this approach provides the user access to the “why” behind the list of contacts and the order of the contacts. Third, this approach generates the list based on a variety of different communication paths (email, calls, IM, and so forth) and users' context at any given time.

FIG. 2 illustrates an exemplary communications environment 200 in which the predictive contacts system can operate. In this environment 200, a user 202 uses a computing device 204, such as a smart phone, desktop computer, laptop computer, tablet computing device, or smart television set-top box, to communicate via a communication network 206 with another user 208. Either as part of a periodic, continuous, or event-driven process, the device 204 and/or other system monitors the user's current communication context and compares that context with a communication history 212. Based on similarities in context, content, or other factors, the device 204 and/or other system selects and presents a list of predictive contacts from a list of contacts 210. In one aspect, the list of contacts 212 can be stored entirely or partially in a network-based database 214, as can the communication history 216.

For example, if the user 202 is talking to Bob via instant messaging and discussing Fred, the system can analyze the content of the instant messaging session (for example, the discussion of Fred) and the context of the instant messaging session (for example, a discussion with Bob at a particular time of day and day of the week). Based on the analysis, the system predicts that the user 202 and Bob are likely to want to talk with Fred. The system can assign Fred a higher ranking in the list of predictive contacts in real time to reflect that content and context. In this way, the user 202 can click on the list item for Fred and view current information for Fred based on Fred's presence and can also initiate a separate communication session with Fred or can request that Fred join the current communication session between the user 202 and Bob.

FIG. 3 illustrates an exemplary list of predictive contacts 300, such as the device 204 would display as part of a graphical user interface to the user 202. This exemplary list of predictive contacts 300 includes three entries: Mary 302, Joe 304, and Nick 306. The list of predictive contacts can be pure text or can include multimedia content. For example, each predictive contact in the list includes a profile image, a name, a telephone number, and an email. Each contact can include more or less information. For example, the contact listing can include presence information, available communication modalities, social network information, notes, memos, and other information describing the contact or the contact's relationship to the user. In addition, each contact can include at least part of the motivation 308, 310, 312 for their appearance and placement in the predictive list of contacts. In one motivation 308, the list includes an excerpt of a communication log between the user and Mary from which the system deduced that the user is very likely to contact Mary at this time. In another motivation 310, the list includes an explanation of the high ranking of Joe based on a pattern of calling Joe on Fridays. In yet another motivation 312, the list bases the ranking on a somewhat frequent and loosely connected pattern of communication sessions. For example, the system tracks that after the user speaks with his manager, the user sometimes calls Nick. Thus, after the user speaks with his manager, the system can bump the ranking of Nick so Nick moves up the list. As time passes after the user's conversation with the manager, the system can apply a decay rate to Nick's ranking so he is gradually ranked lower. For example, if, when the user calls Nick after speaking to his manager, the user typically calls within three minutes of speaking with his manager, the system can rank Nick in a high position for three minutes and then rapidly decrease Nick's ranking thereafter.

Having disclosed some basic system components and concepts, the disclosure now turns to the exemplary method embodiment for providing predictive contacts as shown in FIG. 4. For the sake of clarity, the method is discussed in terms of an exemplary system 100 as shown in FIG. 1 configured to practice the method. The system 100 first analyzes a communication history and a current usage context of a user to yield an analysis (402). The communication history can include, for example, an email history, an instant messaging history, a call history, a video conference history, and a past calendar event. Different portions of the communication history can be stored on different communications devices, such as users' cell phones, a network-based communication server, a web calendar, and so forth. In one aspect, the system operates in real time and constantly compares the current usage context to the communication history. In another aspect, the system is triggered by a discrete event, such as receiving an incoming instant message or the user picking up a telephone receiver to make a call. The current usage context can include data such as time of day, day of the week, previous communications (including the timing, content, participants, and metadata of previous communications), location, a user identity, a calendar of past, current, and/or future events, and so forth.

Based on the analysis, the system 100 ranks contacts that the user is likely to communicate with from a list of contacts to yield ranked contacts (404). In one aspect, the system assigns each contact a probability score. In another aspect, the system only processes a subset of the entire list of contacts. In a blended approach, the system performs a very speed efficient, perhaps not as accurate, initial ranking, and then uses the initial ranking to cull less likely candidates from a more comprehensive, and perhaps more time intensive, ranking process. The system can also sort or filter ranked contacts using different sets of criteria, such as phone calls, instant messages, contacts with whom the user has communicated in the last 30 days, and so forth.

The system 100 identifies a respective motive for ranking each contact (406). The system can identify the motive for ranking each contact as the system ranks the contacts. The motive can include, for example, a history of interactions between the user and a respective contact. In this case, the system can highly rank a first contact in touch with the user on a daily basis. The motivation for the first contact's high rank is the consistent communication history. The system can highly rank a second contact because the user left a message on the answering machine of the second contact and indicated in the message that the user would call again soon. In this case, the motivation for the second contact's high rank is that the user said he would call again soon despite not having the lengthy communication history like the first contact. The motivation can include multiple factors. The user can filter and sort predictive contacts based on one or more factor. For example, the system can receive from the user a request to ignore one respective motive, rerank the contacts based on the request to ignore the one respective motive, and present an updated predictive list of contacts based at least in part on the reranked contacts.

Further, the system 100 can base the motive at least partially on how sent communications are viewed with respect to received communications. This portion of the motive reflects how a user's interest in incoming messages based on the user's responses and corresponding actions with respect to the incoming messages. For example, if Amy receives hourly emails from Fred, the system 100 might be inclined to assign Fred a higher ranking However, if Amy has no interest in Fred or what Fred has to say, she may delete Fred's emails without reading them or after having the email open for only a few moments. Such interactions are not indicative of a strong connection between Amy and Fred. The system 100 can analyze such interactions and assign Fred a lower ranking Alternatively, if Amy opens each of Fred's emails and replies in an average of 2 minutes or less, the system 100 can assign Fred a higher ranking. The system 100 can consider several factors for sent messages. One exemplary factor is the mean arrival time of received messages versus mean sent time for sent messages. This factor can predict whom the user is likely to contact at any given time and/or after receiving a message from a person. Another exemplary factor is the time difference between received messages and sent messages. A low value can indicate to the system 100 that a contact is of high importance to the user. A high value can indicate to the system 100 that the user either never responds to certain messages or takes a long time to respond. Thus, if the user never responds to a message from a certain contact, then the mean sent time is very high and the system does not rank that contact very highly regardless of how many times that contact sends (or attempts to send) the user messages. These and similar factors can influence how the system 100 ranks contacts.

In another aspect, the system 100 is tied into social media, such as Facebook or Twitter. If the user is friends with a contact on Facebook, the system can boost the ranking for that contact. The system can also adjust the ranking based on a number of other social network elements, such as a number of shared contacts, how often the user has viewed that contact's profile page or feed, total time the user has spent interacting with the contact via social media, and so forth. On the other hand, if a user has removed a contact as a friend on Facebook or has recently denied a friend request from the contact, the system 100 can rank that contact lower.

The system 100 can determine the motive and/or rankings based on other extra-system factors. For example, during working hours, a user's immediate supervisor is ranked highly and the motivation can be based on the fact that the time of day indicates that the user is at work. After working hours, the system 100 can rank the supervisor much lower based on the motivation that the user is not ‘on the clock’. Similarly, user location can influence motive. For example, if the user is in New York City, the system 100 can boost the ranking of contacts residing or working in and around New York City. The system 100 can apply an algorithm to modify rankings, such as an inverse square algorithm where a small distance between a contact and the user corresponds to a large increase to that contact's ranking and a large distance corresponds accordingly to a small increase in the ranking, no change in the ranking, or a reduction of the ranking.

The system 100 can assemble a composite of multiple factors and/or motivations, including the ones described above and others, to arrive at a particular ranking value for a contact.

The system 100 presents a predictive list of contacts based at least in part on the ranked contacts, wherein each ranked contact in the predictive list of contacts includes at least part of the respective motive (408). The system can present the predictive list of contacts with real time updates as the current usage context changes. In another aspect, the system presents the predictive list of contacts in response to a discrete event that triggers the system to generate a predictive list of contacts. In one modification, the system identifies a likely communication modality for each ranked contact and presents, as part of the predictive list of contacts, the likely communication modality.

Embodiments within the scope of the present disclosure may also include tangible and/or non-transitory computer-readable storage media for carrying or having computer-executable instructions or data structures stored thereon. Such non-transitory computer-readable storage media can be any available media that can be accessed by a general purpose or special purpose computer, including the functional design of any special purpose processor as discussed above. By way of example, and not limitation, such non-transitory computer-readable media can include RAM, ROM, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage or other magnetic storage devices, or any other medium which can be used to carry or store desired program code means in the form of computer-executable instructions, data structures, or processor chip design. When information is transferred or provided over a network or another communications connection (either hardwired, wireless, or combination thereof) to a computer, the computer properly views the connection as a computer-readable medium. Thus, any such connection is properly termed a computer-readable medium. Combinations of the above should also be included within the scope of the computer-readable media.

Computer-executable instructions include, for example, instructions and data which cause a general purpose computer, special purpose computer, or special purpose processing device to perform a certain function or group of functions. Computer-executable instructions also include program modules that are executed by computers in stand-alone or network environments. Generally, program modules include routines, programs, components, data structures, objects, and the functions inherent in the design of special-purpose processors, etc. that perform particular tasks or implement particular abstract data types. Computer-executable instructions, associated data structures, and program modules represent examples of the program code means for executing steps of the methods disclosed herein. The particular sequence of such executable instructions or associated data structures represents examples of corresponding acts for implementing the functions described in such steps.

Those of skill in the art will appreciate that other embodiments of the disclosure may be practiced in network computing environments with many types of computer system configurations, including personal computers, hand-held devices, multi-processor systems, microprocessor-based or programmable consumer electronics, network PCs, minicomputers, mainframe computers, and the like. Embodiments may also be practiced in distributed computing environments where tasks are performed by local and remote processing devices that are linked (either by hardwired links, wireless links, or by a combination thereof) through a communications network. In a distributed computing environment, program modules may be located in both local and remote memory storage devices.

The various embodiments described above are provided by way of illustration only and should not be construed to limit the scope of the disclosure. For example, the principles herein can be applied to set-top phones, mobile phones, or other mobile communications devices. The predictive contact system components can reside on a communications device and/or in a communication network. Those skilled in the art will readily recognize various modifications and changes that may be made to the principles described herein without following the example embodiments and applications illustrated and described herein, and without departing from the spirit and scope of the disclosure.

Claims

1. A method of providing predictive contacts, the method comprising: analyzing a communication history and a current usage context of a user to yield an analysis;based on the analysis, ranking contacts that the user is likely to communicate with from a list of contacts to yield ranked contacts;identifying a respective motive for ranking each contact; andpresenting a predictive list of contacts based at least in part on the ranked contacts, wherein each ranked contact in the predictive list of contacts includes at least part of the respective motive.

2. The method of claim 1, wherein the predictive list of contacts is updated in real time as the current usage context changes.

3. The method of claim 1, wherein the communication history includes at least one of an email history, an instant messaging history, a call history, a video conference history, and a past calendar event.

4. The method of claim 1, wherein the respective motive comprises a history of interactions between the user and a respective contact.

5. The method of claim 1, further comprising: identifying a likely communication modality for each ranked contact; andpresenting, as part of the predictive list of contacts, the likely communication modality.

6. The method of claim 1, further comprising: receiving from the user a request to ignore one respective motive;reranking the contacts based on the request to ignore the one respective motive to yield reranked contacts; andpresenting an updated predictive list of contacts based at least in part on the reranked contacts.

7. The method of claim 1, wherein the communication history is stored on a plurality of communications devices.

8. A system for providing predictive contacts, the method comprising: a processor;a first module configured to control the processor to analyze a communication history and a current usage context of a user to yield an analysis;a second module configured to control the processor, based on the analysis, to rank contacts that the user is likely to communicate with from a list of contacts to yield ranked contacts;a fourth module configured to control the processor to identify a respective motive for ranking each contact; anda fifth module configured to control the processor to present a predictive list of contacts based at least in part on the ranked contacts, wherein each ranked contact in the predictive list of contacts includes at least part of the respective motive.

9. The system of claim 8, wherein the predictive list of contacts is updated in real time as the current usage context changes.

10. The system of claim 8, wherein the communication history includes at least one of an email history, an instant messaging history, a call history, a video conference history, and a past calendar event.

11. The system of claim 8, wherein the respective motive comprises a history of interactions between the user and a respective contact.

12. The system of claim 8, further comprising: a sixth module configured to control the processor to identify a likely communication modality for each ranked contact; anda seventh module configured to control the processor to present, as part of the predictive list of contacts, the likely communication modality.

13. The system of claim 8, further comprising: a sixth module configured to control the processor to receive from the user a request to ignore one respective motive;a seventh module configured to control the processor to rerank the contacts based on the request to ignore the one respective motive to yield reranked contacts; andan eighth module configured to control the processor to present an updated predictive list of contacts based at least in part on the reranked contacts.

14. The system of claim 8, wherein the communication history is stored on a plurality of communications devices.

15. A non-transitory computer-readable storage medium storing instructions which, when executed by a computing device, cause the computing device to provide predictive contacts, the instructions comprising: analyzing a communication history and a current usage context of a user to yield an analysis;based on the analysis, ranking contacts that the user is likely to communicate with from a list of contacts to yield ranked contacts;identifying a respective motive for ranking each contact; andpresenting a predictive list of contacts based at least in part on the ranked contacts, wherein each ranked contact in the predictive list of contacts includes at least part of the respective motive.

16. The non-transitory computer-readable storage medium of claim 15, wherein the predictive list of contacts is updated in real time as the current usage context changes.

17. The non-transitory computer-readable storage medium of claim 15, wherein the communication history includes at least one of an email history, an instant messaging history, a call history, a video conference history, and a past calendar event.

18. The non-transitory computer-readable storage medium of claim 15, wherein the respective motive comprises a history of interactions between the user and a respective contact.

19. The non-transitory computer-readable storage medium of claim 15, the instructions further comprising: identifying a likely communication modality for each ranked contact; andpresenting, as part of the predictive list of contacts, the likely communication modality.

20. The non-transitory computer-readable storage medium of claim 15, the instructions further comprising: receiving from the user a request to ignore one respective motive;reranking the contacts based on the request to ignore the one respective motive to yield reranked contacts; andpresenting an updated predictive list of contacts based at least in part on the reranked contacts.