Patent Application
20140379521
Within the field of computing, many scenarios involve generation of an individual profile compiled from facts assembled from a set of data signals and sources. For example, an individual may input facts about the individual's life and preferences to a database. As a second example, a history of purchases through a commerce site may be examined to identify items that the individual owns. As a third example, a social profile of the individual provided by a social network may be examined to extract facts about the individual. The facts of the individual profile maybe inform various services, such as the recommendation of products that may be of interest to the individual.
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 factors or essential features of the claimed subject matter, nor is it intended to be used to limit the scope of the claimed subject matter.
While the assembly of an individual profile from a collected set of facts may provide useful information, additional information may be derived from inferences about activities of the individual. As a first such example, a device having a global positioning system (GPS) receiver that is configured to monitor the location of the individual over time may provide factual information about the individual's travel history, but may also enable inferences of individual details of the individual, the significance of the visited locations to the individual. For example, a location to which the individual often travels on weekday evenings and departs on weekday mornings may be inferred as the individual's residence, and a location where the individual regularly visits during consistent hours on weekdays may be inferred as the individual's workplace. As a second such example, a device having a physiological sensor may track the physical activities of the individual (e.g., detecting when the individual engages in bicycling), and depending on the contextual details of the bicycling activity, the device may infer various individual details of the individual, such as whether the individual is a bicycle enthusiast (e.g., choosing to bicycle long distances when other modes of transportation are available), a bicycle commuter (e.g., choosing to bicycle from home to a workplace and back), or utility bicyclist (e.g., bicycling for transportation only when other modes of transportation are unavailable, such as when the individual's automobile is unavailable).
In accordance with these observations, the present techniques enable the generation of an individual profile of an individual based on inferences derived from the activities of the individual. These techniques involve the generation of a behavioral rule set indicating, for one or more individual details, a set of activities that are correlated with the individual details. A device that is capable of monitoring the activities of the individual may compare such activities with the behavioral rule set, and may therefore infer individual details about the individual to be assembled into the individual profile of the individual. Additionally, the inferences may be identified according to a particular confidence (e.g., a certainty of the inference based on the number, frequency, and/or strength of correlation between the activities and the inference). The device may continue evaluating the confidence of the respective inferences over time in order to verify, maintain, update, and/or correct the individual profile of the individual over time (e.g., as new information becomes available, or as the individual's individual details change). The individual profile derived from such inferences may be used in many ways, such as recommending products to the individual based on the inferred individual details; initiates social connections between the individual and individuals having similar individual details; and updating a social profile of the individual in a social network.
To the accomplishment of the foregoing and related ends, the following description and annexed drawings set forth certain illustrative aspects and implementations. These are indicative of but a few of the various ways in which one or more aspects may be employed. Other aspects, advantages, and novel features of the disclosure will become apparent from the following detailed description when considered in conjunction with the annexed drawings.
The claimed subject matter is now described with reference to the drawings, wherein like reference numerals are used to refer to like elements throughout. In the following description, for purposes of explanation, numerous specific details are set forth in order to provide a thorough understanding of the claimed subject matter. It may be evident, however, that the claimed subject matter may be practiced without these specific details. In other instances, structures and devices are shown in block diagram form in order to facilitate describing the claimed subject matter.
While the assembly of individual profiles 106 of individuals 102 based on a collection of facts may inform various services and processes, the evaluation of the activities of the individual 102 may often enable the inference of individual details about the individual 102 that may significantly extend the individual profile 106.
In addition to tracking the travel history of the individual 102 through these four days, the device may also be able to perform a set of inferences 220 from the travel activities of the individual 102 to the individual details 222 of the individual 102. As a first example, the high frequency with which the individual 102 returns to the residence 204 each evening, and with which the individual 102 may support an inference 220 that the individual 102 lives in the residence 204. As a second example, the frequency with which the individual 102 visits the office 206 during the daytime (particularly if such days are coordinated with typical working hours, such as 9:00 am to 5:00 pm on weekdays) may enable an inference 220 that the individual 102 is employed, and that the office 206 is the workplace of the individual 102. As a third example, the visit of the individual 102 to the bowling alley 208 may enable an inference 220 that the individual 102 enjoys bowling. However, each inference 220 may be reached with a particular confidence 224; e.g., the confidence 224 in the inference 220 that the individual 102 lives in the residence 204 may be high, due to the regularity with which the individual 102 visits the residence 204, while the inference 220 that the individual 102 works in the office 206 may have a medium confidence 224 (due to the availability of other explanations, e.g., the individual 102 is visiting the office as a client of a professional service, and the divergence on the third day 214 to visit the bowling alley 208), and the inference 220 of the interest of the individual 102 in bowling may have a low confidence 224. In this manner, the use of the location data collected by the global positioning system (GPS) receiver may be used to infer about the individual 102 a significant number of individual details 222, and an estimation of the confidence 224 of such inferences.
In view of these observations, a device may be configured to formulate inferences about the individual 102 according to the activities of the individual 102. In particular, the inferences 220 may be reached by comparing the activities of the individual 102 with a behavioral rule set indicating the correlation of activities with particular individual details 222. For example, the behavioral rule set may indicate that regular visits to the residence 204, particularly over weekday evenings, may indicate that the individual 102 resides in the residence. By storing a behavioral rule set specifying the correlation of activities and individual details 222, as well as the confidence 224 of such correlations, a device may utilize the behavioral rule set to achieve the inferences 220 of the individual details 222 of the individual 120 in accordance with the techniques presented herein.
The techniques discussed herein may be devised with variations in many aspects, and some variations may present additional advantages and/or reduce disadvantages with respect to other variations of these and other techniques. Moreover, some variations may be implemented in combination, and some combinations may feature additional advantages and/or reduced disadvantages through synergistic cooperation. The variations may be incorporated in various embodiments (e.g., the exemplary system 306 of
D1. Scenarios
A first aspect that may vary among embodiments of these techniques relates to the scenarios wherein such techniques may be utilized.
As a first variation of this first aspect, the techniques presented herein may be utilized to achieve the configuration of a variety of devices 104, such as workstations, servers, laptops, tablets, mobile phones, game consoles, portable gaming devices, portable or non-portable media players, media display devices such as televisions, appliances, home automation devices, and supervisory control and data acquisition (SCADA) devices. Part or all of the techniques may be implemented, e.g., on a personal device of the individual 102, and/or on a server, such as a cloud server providing data services to one or more individual 102. A collection of devices may also interoperate to achieve the completion of the techniques presented herein.
As a second variation of this first aspect, many techniques may be utilized to detect the activities 314 of the individual 102. As a first such example, a global positioning system (GPS) receiver may be configured to track the location of the individual 102 over time, which may enable inferences 220 based on the travel history of the individual 102. As a second such example, a physiological monitor may detect various physiological signals from the individual 102, such as heart rate, respiration, and body position and orientation, in order to identify physical activities 314 such as sitting, standing, walking, running, swimming, bicycling, and driving an automobile or boat. As a third such example, a portable device may comprise a set of sensors 308 measuring various properties of the environment while the individual 102 performs various activities 314 (such as accelerometers and gyroscopes measuring the orientation of the device 302; light sensors measuring the ambient light; temperature sensors detecting the ambient temperature; and microphones detecting an ambient noise level and possibly identifying the noise, e.g., as an automobile engine), and may therefore infer the activities 314 of the individual 102. As a fourth such example, a device 302 comprising a camera may utilize a variety of still and/or motion image processing techniques to infer the activities 314 from captured images of the individual 102. As a fifth such example, the device 302 may receive input from the individual 102 or a service (e.g., a calendar managed by the individual 102) indicating one or more activities 314 performed by the individual 102.
As a third variation of this first aspect, the individual profile 106 of the individual 102 may be generated in a general manner, e.g., a comprehensive description of the individual 102. Alternatively, the inferences 220 and selected individual details 222 may be oriented toward a particular type of individual profile 106, such as a demographic individual profile; an academic individual profile; a professional individual profile; a commercial individual profile; or a personality type individual profile. Those of ordinary skill in the art may devise a variety of such scenarios wherein the techniques presented herein may be utilized.
D2. Behavioral Rule Sets and Inferences
A second aspect that may vary among embodiments of the techniques presented herein involves the details of the behavioral rule set 316 and the inferences 220 derived therefrom.
As a first variation of this second aspect, the behavior rule set 316 may be specified as an administrator as a set of logical conditions representing each inference 220, such as an algorithm provided to determine whether a set of location coordinates detected by a location-aware device are likely to support an inference 220 of the residence of the individual 102. Alternatively, the rules of the behavioral rule set 316 may be specified by an administrator as natural-language expression, and one or more natural-language parsing techniques may be applied to derive from the natural-language expression one or more logical conditions enabling the determination of an inference 220 from a set of inputs. For example, a user such as an administrator may provide a natural-language statement specifying an association, such as “if the individual frequently spends weekday evenings at a location, then the location is likely the home of the individual,” and the device 302 may translate this association into logical constraints encoding the inference 220 expressed by the user. Alternatively or additionally, the behavioral rule set 316 may be automatically generated, e.g., by a behavioral rule set evaluator that evaluates a set of individual profiles 106 to identify correlations 318 of individual details 222 with activities 314. Various machine-learning techniques may be utilized for this automated generation of the behavioral rule set 316, including Bayesian classifiers, artificial neural networks, and/or genetic algorithms that are configured to identify statistically consistent patterns in data sets, including the automated generation of inferences 220 of correlations 317 between the activities 314 and individual details 222.
As a second variation of this second aspect, respective rules of the behavioral rule set 316 may specify additional information additional to an activity 314 upon which an inference 220 of an individual detail 222 may be based. Accordingly, a sensor 308 of a device 302 may detect at least one contextual descriptor of a context in which the individual 102 performed at least one activity 314, and compare the activities 314 of the individual 102 with the behavioral rule set 316 particularly in the context associated with the at least one contextual descriptor. As a first such example, if an individual 102 is detected as bicycling to work for several days in a row, some inferences 220 may be applied to determine that the individual 102 has an individual detail 222 involving a bicycling enthusiast. However, detected contextual factors may alter this inference 220, such as a detection of car repairs performed upon an automobile of the individual 102; a closure of a driving road between the home of the individual 102 and the workplace of the individual 102 while a bicycle path remains available; and/or the suspension or termination of a public transportation service utilized by the individual 102, such as the cancellation of a bus or train route. These contextual descriptors may alter the selection of an inference 220, and/or may enable the selection of substitute inferences 220. As a second such example, the determination that the individual 102 is visiting particular locations may be informed with contextual descriptors involving details of the locations retrieved from a location database. For example, if the individual 102 is determined to frequent a particular restaurant, a location data set may provide contextual descriptors indicating a type of cuisine served by the restaurant, thus enabling an inference 220 of the dietary tastes of the individual 102.
As a third variation of this second aspect, the behavioral rule set 316 may specify one or more levels of confidence 224 in respective inferences 220. As a first such example, the confidence 224 may be related to the frequency of the performance of the activity 314; e.g., an activity 314 that is performed occasionally by an individual 102 may be less indicative of an individual detail 222 than an activity 314 that is frequently performed by the individual 102. As a second such example, the confidence 224 may be related to the strength of the correlation 318 between the activity 314 and the individual detail 222. For example, frequently spent weekend evenings in a residence may provide a lower-confidence inference 220 that the residence is the home of the individual 102 than an inference 220 based on frequently spent weekday evenings in a residence (e.g., the residence may be the home of a family member or friend whom the individual 102 frequently visits on weekends). Additionally, some behavioral rule sets 316 may specify several different confidences 224 based on the performance of an activity 314 and the correlation 318 with an individual detail 222. As a first such example, a behavioral rule set 316 may specify, for an activity 314, a first confidence threshold comprising an individual detail likelihood (e.g., an indication that an individual 102 performing the activity 314 at a certain level, such as a first instance count or a first instance frequency, is likely to exhibit the individual detail 222), and also a second confidence threshold comprising an individual detail assurance (e.g., an indication that an individual 102 performing the activity 314 at a higher level, such as a second instance count that is higher than the first instance count or a second instance frequency that is higher than the first instance frequency, is assured to exhibit the individual detail 222).
As a fourth variation of this second aspect, the individual profile 106 of the individual 102 may include additional sources of information that may supplement the inferences 220 of individual details 222. As a first such example, the individual profile 106 may be supplemented with user input 108; e.g., the device 302 may request the individual 102 to verify an individual detail 222 selected as a result of an inference 220, and may generate the individual profile 106 of the individual 102 including only the individual details 222 that have been verified by the individual 102. As a second such example, the individual profile 106 may include information retrieved from a social profile 118 of the individual 102 provided by a social network 116.
As a fifth variation of this second aspect, the individual profile 106 of the individual 102 may be conditionally updated with some individual details 222 selected by inference 220 from the activities 314 of the individual 102. For example, some inferences 220 may seem likely but not assured. Additional information may later raise the confidence in the inference 220 to a certainty, and the inference 220 may then be added as an individual detail 222 to the individual profile 106.
As a sixth variation of this second aspect, a device 302 may be configured to, after selecting an inference 2220 of an individual detail 222 for an individual 102, continue monitoring the activities 314 of the individual 102 to verify and update the individual profile 106 in view of additional and changing information. As a first such example, an individual 102 may discover a new individual detail 222, such as a new pastime, and the device 302 may detect the new individual detail 222 based on the detection of new activities 314 and new inferences 220 related thereto. As a second such example, an individual detail 222 of an individual 102 may lapse due to changing interests or circumstances, and the device 302 may detect a lapsing by the individual 102 of an activity 314 associated with an individual detail 222 and accordingly reduce the confidence 224 of the individual detail 222 in the individual profile 106 of the individual 102 (e.g., if the individual 102 stops commuting to a workplace via bicycle, the confidence 224 in the inference 220 of the individual 102 as a bicycle commuter may steadily diminish until falling below a threshold, and may then be removed from the individual details 222 of the individual profile 106 of the individual 102 and/or marked as a past individual detail 222). Those of ordinary skill in the art may devise many such inferences 220 and behavioral rule sets 316 in accordance with the techniques presented herein.
D3. Uses of Inferences and Individual Profiles
A third aspect that may vary among embodiments of the techniques presented herein involves various uses of the individual profiles 106 generated through inferences 220 of individual details 222.
As a first variation of this third aspect, an exemplary system 306 may include a product recommendation module that recommends at least one product to the individual 102, where such products are associated with the at least one individual detail 222. For example, the inference 220 that the individual 102 is a bicycle enthusiast may inform the recommendation of products such as bicycling clothing and equipment.
As a second variation of this third aspect, an exemplary system 306 may be utilized in the context of social relationships. For example, a social network may infer that the individual 102 has some hobbies that are similar to those of a second individual, such as inferences that the individuals have an overlapping set of close friends, and may initiate an introduction between the individual 102 and the second individual as members of the same social circle.
Although not required, embodiments are described in the general context of “computer-readable instructions” being executed by one or more computing devices. Computer-readable instructions may be distributed via computer-readable media (discussed below). Computer-readable instructions may be implemented as program modules, such as functions, objects, Application Programming Interfaces (APIs), data structures, and the like, that perform particular tasks or implement particular abstract data types. Typically, the functionality of the computer-readable instructions may be combined or distributed as desired in various environments.
In other embodiments, device 802 may include additional features and/or functionality. For example, device 802 may also include additional storage (e.g., removable and/or non-removable) including, but not limited to, magnetic storage, optical storage, and the like. Such additional storage is illustrated in
The term “computer-readable media” as used herein includes memory devices that, as a class of technology, categorically excludes electromagnetic signals and non-statutory embodiments. Such memory devices may be volatile and/or nonvolatile, removable and/or non-removable, and may involve various types of physical devices storing computer-readable instructions or other data. Examples of such memory devices include RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, Digital Versatile Disks (DVDs) or other optical storage, magnetic cassettes, magnetic tape, and magnetic disk storage or other magnetic storage devices.
Device 802 may also include communication connection(s) 816 that allows device 802 to communicate with other devices. Communication connection(s) 816 may include, but is not limited to, a modem, a Network Interface Card (NIC), an integrated network interface, a radio frequency transmitter/receiver, an infrared port, a USB connection, or other interfaces for connecting computing device 802 to other computing devices. Communication connection(s) 816 may include a wired connection or a wireless connection. Communication connection(s) 816 may transmit and/or receive communication media.
The term “computer-readable media” also includes communication media, as a distinct and mutually exclusive category of computer-readable media than memory devices. Communication media typically embodies computer-readable instructions or other data in a “modulated data signal” such as a carrier wave or other transport mechanism and includes any information delivery media. The term “modulated data signal” may include an electromagnetic signal that has one or more of its characteristics set or changed in such a manner as to encode information in the signal.
Device 802 may include input device(s) 814 such as keyboard, mouse, pen, voice input device, touch input device, infrared cameras, video input devices, and/or any other input device. Output device(s) 812 such as one or more displays, speakers, printers, and/or any other output device may also be included in device 802. Input device(s) 814 and output device(s) 812 may be connected to device 802 via a wired connection, wireless connection, or any combination thereof. In one embodiment, an input device or an output device from another computing device may be used as input device(s) 814 or output device(s) 812 for computing device 802.
Components of computing device 802 may be connected by various interconnects, such as a bus. Such interconnects may include a Peripheral Component Interconnect (PCI), such as PCI Express, a Universal Serial Bus (USB), Firewire (IEEE 1394), an optical bus structure, and the like. In another embodiment, components of computing device 802 may be interconnected by a network. For example, memory 808 may be comprised of multiple physical memory units located in different physical locations interconnected by a network.
Those skilled in the art will realize that storage devices utilized to store computer-readable instructions may be distributed across a network. For example, a computing device 820 accessible via network 818 may store computer-readable instructions to implement one or more embodiments provided herein. Computing device 802 may access computing device 820 and download a part or all of the computer-readable instructions for execution. Alternatively, computing device 802 may download pieces of the computer-readable instructions, as needed, or some instructions may be executed at computing device 802 and some at computing device 820.
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.
As used in this application, the terms “component,” “module,” “system”, “interface”, and the like are generally intended to refer to a computer-related entity, either hardware, a combination of hardware and software, software, or software in execution. For example, a component may be, but is not limited to being, a process running on a processor, a processor, an object, an executable, a thread of execution, a program, and/or a computer. By way of illustration, both an application running on a controller and the controller can be a component. One or more components may reside within a process and/or thread of execution and a component may be localized on one computer and/or distributed between two or more computers.
Furthermore, the claimed subject matter may be implemented as a method, apparatus, or article of manufacture using standard programming and/or engineering techniques to produce software, firmware, hardware, or any combination thereof to control a computer to implement the disclosed subject matter. The term “article of manufacture” as used herein is intended to encompass a computer program accessible from any computer-readable device, carrier, or media. Of course, those skilled in the art will recognize many modifications may be made to this configuration without departing from the scope or spirit of the claimed subject matter.
Various operations of embodiments are provided herein. In one embodiment, one or more of the operations described may constitute computer-readable instructions stored on one or more memory devices, where the execution of such instructions by a computing device causes the computing device to perform the operations described. The order in which some or all of the operations are described should not be construed as to imply that these operations are necessarily order dependent. Alternative ordering will be appreciated by one skilled in the art having the benefit of this description. Further, it will be understood that not all operations are necessarily present in each embodiment provided herein.
Moreover, the word “exemplary” is used herein to mean serving as an example, instance, or illustration. Any aspect or design described herein as “exemplary” is not necessarily to be construed as advantageous over other aspects or designs. Rather, use of the word exemplary is intended to present concepts in a concrete fashion. As used in this application, the term “or” is intended to mean an inclusive “or” rather than an exclusive “or”. That is, unless specified otherwise, or clear from context, “X employs A or B” is intended to mean any of the natural inclusive permutations. That is, if X employs A; X employs B; or X employs both A and B, then “X employs A or B” is satisfied under any of the foregoing instances. In addition, the articles “a” and “an” as used in this application and the appended claims may generally be construed to mean “one or more” unless specified otherwise or clear from context to be directed to a singular form.
Also, although the disclosure has been shown and described with respect to one or more implementations, equivalent alterations and modifications will occur to others skilled in the art based upon a reading and understanding of this specification and the annexed drawings. The disclosure includes all such modifications and alterations and is limited only by the scope of the following claims. In particular regard to the various functions performed by the above described components (e.g., elements, resources, etc.), the terms used to describe such components are intended to correspond, unless otherwise indicated, to any component which performs the specified function of the described component (e.g., that is functionally equivalent), even though not structurally equivalent to the disclosed structure which performs the function in the herein illustrated exemplary implementations of the disclosure. In addition, while a particular feature of the disclosure may have been disclosed with respect to only one of several implementations, such feature may be combined with one or more other features of the other implementations as may be desired and advantageous for any given or particular application. Furthermore, to the extent that the terms “includes”, “having”, “has”, “with”, or variants thereof are used in either the detailed description or the claims, such terms are intended to be inclusive in a manner similar to the term “comprising.”
The present application is a continuation of and claims priority to U.S. patent application Ser. No. 13/924,052, filed Jun. 21, 2013 and titled “ACTIVITY-BASED PERSONAL PROFILE INFERENCE,” the entirety of which is incorporated by reference as if fully rewritten herein.
| Number | Date | Country | |
|---|---|---|---|
| Parent | 13924052 | Jun 2013 | US |
| Child | 14467638 | US |
