Patent Application
20140074610
Many techniques are employed to accurately identify a profile of the day-to-day activities of people, particularly consumers. Some systems rely upon how people use the internet, including sites most frequented, how much time and money is spent on those sites, as well as when such online activity occurs. Additionally, profile information may be obtained from publicly available census-type information, such as geo-political, occupational, gender or even marital profiling information. However, real profiles are based on more than just how people surf the web. Also, census-type information only reflects a general trend or stereotype and often does not accurately reflects the interests and past-times of numerous individuals that fall within the group associated with the stereotype. Thus, some profiling techniques use payment network activity to infer further profiling attributes. As someone travels outside their home and makes purchases, particularly using credit cards, such purchases provide indications of real world activity. However, such payment networks will not reflect when someone visits a location but does not spend their own money. For example, someone may visit a Chinese food restaurant they very much enjoy, but are often invited as guests and do not pay the bill themselves or perhaps pay cash, thus not being tracked by the payment network.
Additionally, individuals that carry smartphones or other electronic devices with GPS or the ability to accurately determine location may compile further profiling information. Such devices may be used to determine the location of a user, including the particular business, institution or property being visited. With such a device, over time information may be collected showing the locations most frequented by a particular user. Such most frequented locations are referred to herein as points of interest (POI's). Thus, when a user with a smartphone goes to a particular restaurant a lot, it can be inferred that individual likes eating out and likes the food at that restaurant. Alternatively, a user that frequents a gym may have exercise associated with a profile of their interests. However, many locations are multi-purposed and thus a visitor's interests are less clear. For example, it may be unclear whether someone who visits a beach likes to swim, exercise, tan themselves, surf or build sand castles. Also, a location like a restaurant may advertise the type of cuisine they prepare and the décor or ambiance they present, but this fails to indicate other profiling information like the age group that most frequents the locale or that book-clubs prefer meeting there.
The various embodiments include a method of generating a point of interest profile of a target user. The method may include querying a web site for at least one social comment associated with a point of interest visited by the target user. The at least one social comment may be posted to the web site by at least one third-party not affiliated with the point of interest. Also, the method may parse the at least one social comment for at least one keyword contained therein, the at least one keyword may be correlated to an attribute characterizing visitors of the point of interest, and a point of interest profile associating the attribute with the target user may be generated.
A further embodiment may include a method of generating a point of interest profile that may include receiving an identifier indicating a point of interest visited by a target user. A third-party attribute associated with at least one third-party and the point of interest may be determined, wherein the third-party is not affiliated with the point of interest. Additionally, a point of interest profile associating the attribute with the target user may be generated.
Further embodiments may include a method of generating a point of interest profile that may include receiving an identifier indicating a point of interest visited by a target user. An attribute associated with at least one third-party and the point of interest may be determined in which the third-party is not affiliated with the point of interest. Also, a point of interest profile may be generated associating the attribute with the target user.
Further embodiments may include a computing device having a processor configured with processor-executable instructions to perform various operations corresponding to the methods discussed above.
Further embodiments may include a computing device having various means for performing functions corresponding to the method operations discussed above.
Further embodiments may include a non-transitory processor-readable storage medium having stored thereon processor-executable instructions configured to cause a processor to perform various operations corresponding to the method operations discussed above.
The accompanying drawings, which are incorporated herein and constitute part of this specification, illustrate exemplary embodiments of the invention, and together with the general description given above and the detailed description given below, serve to explain the features of the invention.
The various embodiments will be described in detail with reference to the accompanying drawings. Wherever possible, the same reference numbers will be used throughout the drawings to refer to the same or like parts. References made to particular examples and implementations are for illustrative purposes, and are not intended to limit the scope of the claims.
The word “exemplary” is used herein to mean “serving as an example, instance, or illustration.” Any implementation described herein as “exemplary” is not necessarily to be construed as preferred or advantageous over other implementations.
As used herein, the terms “communication device,” “wireless device,” and “mobile device” refer to any one or all of cellular telephones, smart phones, personal or mobile multi-media players, personal data assistants (PDA's), laptop computers, tablet computers, desktop computers, smart books, palm-top computers, wireless electronic mail receivers, multimedia Internet enabled cellular telephones, wireless gaming controllers, and similar personal electronic devices which include a programmable processor and memory and circuitry for modifying search terms.
The systems, methods, and devices of the various embodiments use location data to determine where a mobile device is located, and thus the locations and points of interest frequently visited by the user in order to develop a more complete user profile. The location of a user at any given time can be determined by automated techniques or may be manually entered by the user by registering their location upon arrival. Alternatively, location information may be determined from one or more other entities indicated as being in close-proximity to the user and having their location information confirmed.
As used herein, the term “location” refers to either a physical or virtual place with an identifiable name. Such locations generally attract people to visit there, whether they are physical locations or virtual ones. As used herein, the term “visit,” “visited” and/or “visiting” refers to going to see, stay and/or spend time at or at least in close proximity to a location or even going to a website or web page. Additionally, visitor or visitors refers to one or more individuals that visit a location, including not only a physical location but also a website or web page. Also, locations will generally have owners or proprietors interested in running or maintaining those locations. Those owners or proprietors, as well as their employees and agents, are considered to be directly affiliated with their respective location(s). As used herein, the terms “point of interest” or “POI” refers to a location which a user visits more than others, spends more time at than others, meets the most acquaintances or at which the user spends substantial amounts of money. Similarly, as used herein the term “identifier” when referring to a location refers to at least one name, address or other code/symbol used to identify a unique location.
As used herein, the term “user” refers to a principal subject of the point of interest analysis for whom one or more attributes is being compiled and a user profile generated. Also, as used herein, the term “entity” refers to a person, partnership, organization or business that has an identifiable existence. Additionally, as used herein, the term “third-party” refers to an entity that is neither the user nor affiliated with a particular location. Thus, as relating to a location, a third-party is not officially attached or connected to the location or an entity that owns, operates or controls the location.
The various embodiments include methods, system and devices for building-on and/or enhancing a basic user profile in order to provide a more complete picture of a user's interests, habits and day-to-day activities based upon social comments associated with locations of interest to the user. Locations of interest may be chosen by the system based on various factors, including the duration/frequency of the user's visits or by the potential commercial or research interest in a location. In an embodiment relating identifying such points of interest frequented by the user, a point of interest may be a physical location, such a restaurant, tavern, theatre, park, etc. or a virtual location such as a web-site frequently visited by the user. Also, a point of interest may be a web-site, whether or not it is associated with a physical location, and thus may be an entirely virtual location.
Initially, the identification of points of interest may be accomplished by various means. In the case of physical locations, a user's visits to such locations must be tracked. Various embodiments take advantage of existing location awareness technologies, such as Gimbal™ (by Qualcomm Labs, Inc., San Diego, Calif.), which use an individual's smartphone to determine their physical location. In fact, such systems are able to detect and track the user's most frequently visited locations (such as home, the office, the gym, school, etc.) by clustering location fixes and mapping them to a list of points of interest in order to improve the identification of the real location of the user, as well as their POI's, based on the user's tracked travel habits. In the various embodiments, current state information, historical data, and expected location predictions may be used together to locate the user. Based on that determination of individual locations and times, a POI list may be determined and used for generating a user profile.
In the case of virtual locations that are points of interest to a user, the identification of that location is more easily obtained. Using tracking cookies or other web history tracking methods, a user's on-line points of interest may be identified along with the time and duration of visits to such sites. To the extent possible, both physical and virtual points of interest may be identified for a particular user. Also, sometimes virtual locations are in some way related to or affiliated with a physical location. For example, a restaurant or retail store may have its own official web site or a dedicated page/forum on a shared web site. Alternatively, the web site may provide information about one or more physical locations, and thus is considered for point of interest purposes to be related to each of those locations, but is not actually affiliated with those locations.
Another embodiment relates to obtaining social comments regarding the identified point of interest. Such social comments may be obtained from one or more existing feeds associated with a point of interest, such as on-line social networks. Any obtained social comment associated with the location of interest is scanned for keywords that may be correlated to one or more attributes associated with people who frequent that location. Once one or more such keywords are identified through the social comments related to the location, the attribute may be added to the user's profile to generate a point of interest profile pertinent to a target user.
The various embodiments use data, associated with locations, that is maintained on web sites in the form of social comments. As used herein, the terms “web site” refers to one or more pages on the Internet regarded as a single non-living entity, usually maintained to document information or the exchange thereof regarding one topic or closely related topics. In an embodiment, the social comments is collected from existing website feeds of such data obtained through social network web sites like Facebook®, Yelp®, Foursquare® and Twitter®. For example, an individual user may like a restaurant named Burlap, which is located in Del Mar, Calif. While the official restaurant web site for Burlap may describe its cuisine as Asian fusion and tout its accolades, it doesn't tell you much about the customers that frequent the establishment. In contrast, other web sites like Yelp maintain commentary about such places. Third-parties post comments like “ . . . great drinks and lots of good looking people, but . . . ,” “The atmosphere is like a trendy club,” or “Just another trendy restaurant where everyone comes ‘dressed to impress’.” These types of commentary contain various keywords that may be associated with “attributes” of people who frequent that location or attributes of the location itself. As used herein, the term “attribute” refers to a quality or feature regarded as a characteristic or inherent part of someone or something. Thus, words like “trendy,” “drinks” or “club” may reflect attributes of Burlap's customers. In the various embodiments, such attributes may be associated with a user identified as including Burlap as one of his points of interest. In this way, the user's profile is enhanced to reflect further attributes, which may be used by marketers and/or researchers. It should be noted that the date and/or time comments were made, as well as date or time indications in comments are also considered as being part of attributes (for example, a restaurant may receive different comments for Tuesdays than other days of the week because it hosts special events, like Salsa lessons).
As used herein, the term “social comment” refers to one or more web postings intended as an explanation, illustration, criticism or praise on a subject. The social comment may include annotations, explanations, statements of fact or opinion and/or remarks that express a personal reaction or attitude. Also, as used herein the term “posting” or “posted” refers to an electronic message that is conveyed, transmitted or sent to a web site for others to view.
In an embodiment, the user's smart phone may be configured to determine the smart phone's current location using a navigation system receiver, such as a Global Positioning System (“GPS”) receiver. The GPS receiver can determine or assist in determining a current location by using geographic coordinates, such as a latitude and longitude. Those geographic coordinates may be compared to point of interest information available either to the smart phone processor, to a connected server 124 or elsewhere on the internet 122. In this way, the user's smart phone is employed to identify the location a user is visiting. The server 124 may maintain user profile data that is enhanced by the embodiments. A user may be provided an option whether to authorize the system to generate or enhance user profiles and particularly the point of interest profile described herein.
Alternatively, the smart phone might determine its location through proximity to a cellular tower 118 and its cellular connection 116 therewith. The cellular tower 118 may included a wired connection 114 to a server 124 or other computer network, or communicate to other cellular towers or communications stations that themselves have connections to the Internet 122. As a further alternative, the smart phone may determine its location through a wireless connection, such as Wi-Fi, provided at the location 111, which in-turn has its own wired connection 114 to a server 124 and/or the Internet 122. In these localized ways the mobile communication device communicates with a local communication device in the neighborhood of or associated with the point of interest, when the mobile communication device comes in proximity with the local communication device.
A point of interest for a particular user may be distinguished from just any location visited by the user in that the points of interest correspond to those locations identified as being most pertinent to the user. This determination of pertinence may be made based on various factors, such as how often and when the user visits the location, how long the user visits the location, how many other people the user meets at the location, how much commercial value the location has to vendors or proprietors of the location and other factors. In this way, the points of interest for a user may be limited to a certain quantity of locations with the highest determination of pertinence or simply most visited by the user. For example, the top 10 or 20 most frequented locations for a user may be designated as her points of interest. Alternatively, a threshold number of visits to a location may define whether it is a point of interest or not. Thus, the system need not consider associating attributes from a particular location to a user unless they visit the location a plurality of times greater than that preselected threshold number of visits.
Once an identifier is received or obtained for a location 111 determined to be a point of interest for the user, the system will query a web site for social comments regarding the location 111. Querying a web site is a mechanism for retrieving information from one or more databases maintained in connection with that web site. A query includes questions presented to the web site and/or directly to the one or more databases in a predefined format. One example of such format is the Structured Query Language (SQL). Such a query may be initiated from a server 124 or related equipment. The server 124, having a wired connection 114 or other connection to the Internet 122 may either transmit the request to a social networking web site 50 or access the social networking web site 50 for obtaining the requested social comments. The social networking web site 50 should include social comments, particularly social comments regarding the identified location 111. The requested social comments are ones previously posted to the web site 50 by third-party individuals 21, 23, 25, not affiliated with the point of interest and preferably not comments posted by the user 10, herself. If no social comments or insufficient social comments are available from the web site 50, then the user profile may remain unchanged or other methods used to enhance the profile. However, if social comments are received or otherwise obtained from the web site, the system may parse the social comments for keywords that may be correlated to a user attribute. Alternatively, in order to ensure the social comments more accurately reflect attributes of visitors to that location, the system need not associate attributes with a particular user unless a threshold quantity of third-parties have posted social comments about the location or a threshold number of common keywords are found among the social comments.
Keyword extraction may use NLP, Stochastic and Bayesian models of language such as Alchemy, GNU Libextractor, TerMine, TrM Extractor, etc. Also, keywords may be grouped by synonyms and/or manually associated to attributes.
A list of keywords may be maintained in a database, along with the one or more attributes correlated to each of those keywords. Correlating a keyword to an attribute, as used herein, refers to establishing a mutual relationship or connection between a keyword and an attribute. The correlation between keywords and attributes may be maintained in a database or performed at any time in accordance with the various embodiments herein. In this way, identified keywords will have a direct association with one or more attributes. Also, each attribute may have a direct association to one or more keywords. Thus, a target user's profile may be enhanced by adding attributes correlated to keywords to generate a point of interest profile. Examples of categories of point of interest attributes associated with a user may include age, sex, income, marital status, sexual preference, parental status, hobbies, entertainment interests and other interests. Additionally, within each category a set of attributes may be defined. For example, the age category may include attributes defined by words like “seniors,” “thirty-somethings,” “teens,” or even particular age ranges. Also, a particular attributes may fall into more than one category. Further, a group of keywords may be correlated to just one attribute. For example, “lively,” “wild” and “exciting” may be commonly associated and thus correlated to “partier.” Moreover, the at least one keyword may include more than one keyword. Additionally, one or more keywords may be given a higher level of significance than other keywords. The higher level of significance may represents input being received from a greater number of third-parties.
In an embodiment, a temporal indicator may be received along with the identifier indicating the point of interest. The temporal indicator represents a time of day and/or duration the user visited the point of interest. In this way, keywords may be correlated to the temporal indicator, so if many keywords found in social comments refer to the night time, but the user mainly visits the point of interest during the day, the system will know not to associate the related attribute(s) from those social comments.
Some points of interest will naturally emerge for the majority of users as their home and work. These specific locations may be excluded from profiling, particularly in cases when the individual works at a location about which people post comments. For example, if someone works at Burlap, the system need not associate the attributes inferred about Burlap from retail customers to that person. However, if other employees post social comments, the system may want to associate attributes correlated from keywords parsed from those social comments.
In another embodiment, a point of interest profile may be generated by determining one or more attributes from a second user whose user profile is associated with the subject point of interest. This alternative may be used separately, in combination with the social comment derived attributes described above or as an alternative when no social comments are received containing the at least one keyword.
The additional smart phones 126, 128 and a cellular tower or base station 118 may exchange data via a cellular connections 130, 132, respectively, including CDMA, TDMA, GSM, PCS, 3G, 4G, LTE, or any other type connection. In this manner via the connections to the cellular tower or base station 118 and/or the Internet 122, data may be exchanged between the smart phones 126, 128 and the laptop computer 104, server 124, and/or smart phone 102.
In an embodiment, the smart phone 102 and laptop computer 104 may be devices owned/operated by the same user, while smart phones 126, 128 may be owned/operated by different users. In an embodiment, smart phones 102, 126, 128 may be configured to determine their respective locations, for example using GPS receivers or potentially WiFi location services if available. Similarly, the laptop computer 104 may not be configured with GPS or cellular service and may need to rely upon an Ethernet connection, either wired or wireless.
In an alternative embodiment a point of interest profile may be generated using attributes of other users who frequent the same location. This alternative may be used when social comments are not available for a particular location, used in conjunction with social comment attributes or as a stand-alone technique. Consider, for example, 100 people recorded in a user database as having visited a beach. As part of maintaining that user database, profiles of those 100 people may be scanned for attributes. As with the earlier embodiment, such attributes may be derived from keywords identified in the user profiles. For example, that user profile database may include the attribute “has-kids” common to all or a significant number of those people. Using this commonality, the attribute “has-kids” may be added to a target user. In this example, the attribute may refer to a characteristic other than being a parent or guardian, such as someone who frequents that particular location or that type of location with children. This may identify the user as a parent or guardian, but also may identify them as a user that likes to visit that type of location bringing children along with them. Information of this type may be helpful to identify a more accurate profile of a target user's regular activity. Thus, this alternative method may be initiated to generate a point of interest profile by receiving an identifier indicating a point of interest visited by a user. The system may also determine an attribute associated with at least one other user (i.e., third party user) in connection with the point of interest who has visited the same point of interest. Additionally, a significant number of other users may be used to more accurately correlate the attribute with the target user. A point of interest profile may thus be generated associating the attribute determined in this way with the target user.
In the various embodiments, the point of interest profile may include an accuracy rating associated with the location attribute based on a frequency the attribute is associated with third-parties that visit the location. Thus, the point of interest profile may include an accuracy level indicator for the attribute. The accuracy level indicator may represent a statistical likelihood that the attribute is correctly associated with the user. Such a statistical likelihood may be determined based on the frequency that an attribute is used in association with a location, the number of third-parties that have that attribute associated with them or similar indicators of accuracy.
The various embodiments may be implemented in any of a variety of mobile communication devices, an example of which is illustrated in
The various embodiments may be implemented in any of a variety of communication devices, an example of which is illustrated in
The various embodiments described above may also be implemented within a variety of personal communication devices, such as a laptop computer 1210 as illustrated in
The various embodiments may also be implemented on any of a variety of commercially available server devices, such as the server 1300 illustrated in
The processors 1002, 1102, 1202 and 1301 may be any programmable microprocessor, microcomputer or multiple processor chip or chips that can be configured by software instructions (applications) to perform a variety of functions, including the functions of the various embodiments described above. In some devices, multiple processors may be provided, such as one processor dedicated to wireless communication functions and one processor dedicated to running other applications. Typically, software applications may be stored in the internal memory 1004, 1104, 1106, 1212, and 1302 before they are accessed and loaded into the processors 1002, 1111, and 1201. The processors 1002, 1102, 1202 and 1301 may include internal memory sufficient to store the application software instructions. In many devices the internal memory may be a volatile or nonvolatile memory, such as flash memory, or a mixture of both. For the purposes of this description, a general reference to memory refers to memory accessible by the processors 1002, 1102, 1202 and 1301 including internal memory or removable memory plugged into the device and memory within the processor 1002, 1102, 1202 and 1301 themselves.
The foregoing method descriptions and the process flow diagrams are provided merely as illustrative examples and are not intended to require or imply that the steps of the various embodiments must be performed in the order presented. As will be appreciated by one of skill in the art the order of steps in the foregoing embodiments may be performed in any order. Words such as “thereafter,” “then,” “next,” etc. are not intended to limit the order of the steps; these words are simply used to guide the reader through the description of the methods. Further, any reference to claim elements in the singular, for example, using the articles “a,” “an” or “the” is not to be construed as limiting the element to the singular.
The various illustrative logical blocks, modules, circuits, and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both. To clearly illustrate this interchangeability of hardware and software, various illustrative components, blocks, modules, circuits, and steps have been described above generally in terms of their functionality. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the overall system. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
The hardware used to implement the various illustrative logics, logical blocks, modules, and circuits described in connection with various embodiments may be implemented or performed with a general purpose processor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or any combination thereof designed to perform the functions described herein. A general-purpose processor may be a microprocessor, but, in the alternative, the processor may be any conventional processor, controller, microcontroller, or state machine. A processor may also be implemented as a combination of communication devices, e.g., a combination of a DSP and a microprocessor, a plurality of microprocessors, one or more microprocessors in conjunction with a DSP core, or any other such configuration. Alternatively, some steps or methods may be performed by circuitry that is specific to a given function.
In one or more exemplary embodiments, the functions described may be implemented in hardware, software, firmware, or any combination thereof. If implemented in software, the functions may be stored as one or more instructions or code on a non-transitory computer-readable medium or non-transitory processor-readable medium. The operations of a method or algorithm embodiment disclosed herein may be embodied in a processor-executable software module which may reside on a non-transitory computer-readable or processor-readable storage medium. Non-transitory computer-readable or processor-readable storage media may be any storage media that may be accessed by a computer or a processor. By way of example but not limitation, such non-transitory computer-readable or processor-readable media may include RAM, ROM, EEPROM, FLASH memory, CD-ROM or other optical disk storage, magnetic disk storage or other magnetic storage devices, or any other medium that may be used to store desired program code in the form of instructions or data structures and that may be accessed by a computer. Disk and disc, as used herein, includes compact disc (CD), laser disc, optical disc, digital versatile disc (DVD), floppy disk, and blu-ray disc where disks usually reproduce data magnetically, while discs reproduce data optically with lasers. Combinations of the above are also included within the scope of non-transitory computer-readable and processor-readable media. Additionally, the operations of a method or algorithm may reside as one or any combination or set of codes and/or instructions on a non-transitory processor-readable medium and/or computer-readable medium, which may be incorporated into a computer program product.
The preceding description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the aspects and/or embodiments shown herein but is to be accorded the widest scope consistent with the following claims and the principles and novel features disclosed herein.
This application claims the benefit of priority to U.S. Provisional Application No. 61/700,670 entitled “Deriving Profile Attribute From Real World Activity Using Social Qualification of Points of Interest,” filed Sep. 13, 2012, the entire contents of which are hereby incorporated by reference.
| Number | Date | Country | |
|---|---|---|---|
| 61700670 | Sep 2012 | US |
