DESC:FIELD OF INVENTION

[001] The invention relates generally to local positioning systems and more specifically to a predictive modeling based approach for automatically determining user location with great accuracy.
BACKGROUND OF INVENTION

[002] Smartphones, smart watches and other smart devices have been widely embraced by people for personal and business needs alike. With the advent of technology, the users are witnessing more powerful smartphones with faster processors and feature rich operating systemseveryday. With more and more smartphone manufacturers joining the race, millions of new users are able to afford these devices and take advantage of the innumerable features and functionality they offer. In parallel, there has been great advancement in the mobile network and connectivity space as well. With 2G paving way for 3G and 4G connectivity and Wi-Fi technology becoming commonplace, smartphone users are connected to the Internet wherever they go.
[003] Availability of constant connectivity through GPRS, Wi-Fi hotspots and other means when coupled with Global Positioning System (GPS) has made it possible to determine the location and position of a user carrying a smart phone. With the determination of user location within the grasp of businesses and network providers, there is a seemingly huge potential of utilizing such location determination in various walks of life. A lot of research and development has taken place in trying to predict user location with greater accuracy. GPS is the most common method used for determining user location. GPS technology uses a network of satellites that determine the position of a smartphone. The smartphones carry a GPS receiver that interacts with the satellites to determine the position of the user based on time deviation calculation. Other methods and systems involving cell tower, Bluetooth and Wi-Fi signals have also been attempted to determine user location but neither GPS nor these other methodologies can pin point the exact location of the user. At best these can determine the approximate geographical area within which the user may be present. For example, studies have shown that GPS and Assisted GPS (A-GPS) used in smartphones and similar devices can determine user location with at best an accuracy in the range of 8 - 10 meters. Though this may be sufficient for some basic applications, for other advanced applications such a wide area may not be good enough. As a practical example, a GPS may be good enough to determine the locality in which the user is present, but my not be good enough to determine or predict the specific aisle of a store or specific area within a restaurant where the user is actually present within the locality. Further, most often than not GPS does not work indoors and the signals are not available indoors. As a result, if specific targeted advertisements have to be pushed on the user smartphone or similar device, all advertisements related to multiple stores and restaurants in the area will all have to be pushed. However, if the exact location of the user can be pinpointed, the targeted advertising can become highly effective as only that specific stores or restaurant’s deals and advertisements may be pushed to the user device or smartphone.
[004] Another problem that smartphone users face today is that the available systems of checking in a particular place or claiming rewards are dependent on the user being connected to the Internet or the user actively checking in manually on the smartphone.This is quite cumbersome and requires considerable time and effort on part of the user. It is highly desirable to have a system that automatically checks in the user based on user location and functions even in the absence of Internet connectivity.
[005] Not only is this, a highly accurate prediction and determination of user location desirable in areas other than targeted advertising. Another effective and highly desirous usage of such accurate user location determination can be in location determination accessories for children and other individuals, such as bags, belts, badges or safety accessories for women.
[006] Therefore, in light of the aforementioned points, there is a need for an automated means for prediction and determination of user location accurately without involving any change in the current infrastructure or without requiring additional effort from the users.

OBJECT OF INVENTION

[007] The object of this invention is to provide a system and method for predicting user location with great accuracy utilizing existing smartphone features and without any change in existing infrastructure.

STATEMENT OF THE INVENTION
[008] The invention is a system and method of determining accurate user location, the method involves mapping, using a mapping device, of a target area by recording the signal strength of multiple access points, the signal strength alongwitha database and other attributes build a mapping model.

[009] Theses access points on a target area are scanned using a user device and the signal strength of the access points are compared with the mapping model, a probability score is calculated based on the comparison, which helps in determining the position of the user.
BRIEF DESCRIPTION OF FIGURES

[0010] This invention is illustrated in the accompanying drawings, throughout which, like reference letters indicate corresponding parts in the various figures. The embodiments herein will be better understood from the following description with reference to the drawings, in which:
[0011] Fig. 1 illustrates a flow diagram for mapping a target area.
[0012] Fig. 2 illustrates a flow diagram for user location determination.
[0013] Fig. 3 depictsthe network architecture configured to predict user location.
[0014] Fig. 4 illustrates a specific implementation of user location prediction for automated checking in and targeted advertising system.
DETAILED DESCRIPTION OF INVENTION

[0015] The embodiments herein and the various features and advantageous details thereof are explained more fully with reference to the non-limiting embodiments that are illustrated in the accompanying drawings and / or detailed in the following description. Descriptions of well-known components and processing techniques are omitted so as to not unnecessarily obscure the embodiments herein. The examples used herein are intended merely to facilitate an understanding of ways in which the embodiments herein may be practiced and to further enable those of skill in the art to practice the embodiments herein. Accordingly, the examples should not be construed as limiting the scope of the embodiments herein.
[0016] The embodiments herein below provide a system and method for determination of user location with great accuracy using signal strength of various Access Points (APs) including but not limited to Wi-Fi Access Points (WAPs), Bluetooth Access Points and Cellular Signal Access Pointsin a target area.Thetarget area is first mapped based on signal strength of various APs at different points in the target area and the mapped data is stored in a database. Thereafter, when a user carrying a device such as a smartphone, which is configured to run an application that periodically scans for AP signal strength, gets into the vicinity of the target area, the device sends information regarding received signal strength from APs to the server and based on a comparison with earlier mapped data the user location is determined. In the embodiments described herein WAPs are usedfor describing the method and system as WAPs provide better accuracy for local positioning. However, Bluetooth or cellular tower signal strength may be used instead of or in conjunction with WAPs to achieve the desired result of user location determination.
[0017] Referring now to the drawings, where similar reference characters denote corresponding features consistently throughout the figures, there are shown preferred embodiments.
[0018] Fig. 1 illustrates the flow diagram for a method of mapping a target area for the purposes of determining user location. A mapping device, which may be a smartphone or any other device with WAP scan and signal strength recording functions, configured to run a mapping application, is taken to a target area that needs to be mapped 102. The mapping application is an application that is configured to capture and record signal strength of various WAPs in any given area unit. For detailed mapping, the target area is divided into multiple smaller area units 104. In an illustrative embodiment, these smaller area units may be standardized as one-foot by one-foot (1ft *1ft) area units for a uniform mapping. The mapping device records the signal strengths from various Wi-Fi Access Points (WAPs) within the area unit 106 at different times and collates such data. During the mapping, the inside and outside of the target area are demarcated 108 for more accurate location determinationlater. At the end of the mapping activity, each area unit is represented in terms of signal strength from various access points 110. For example the mapping of a specific restaurant is to be carried out. The mapping device is taken to the restaurant and the restaurant is divided into one-foot by one-foot (1ft *1ft) area units.Let’s assume that the restaurant receives signals from ‘n’ WAPs. In an illustrative embodiment the restaurant is mapped in the following manner-
Area Unit Time Interval SS WAP1 SS WAP2 SS WAPn

A1 T1 SSA1 SSB1 SSn1
T2 SSA11 SSB11 SSn11
T3 SSA111 SSB111 SSn111

A2 T1 SSA2 SSB2 SSn2
T2 SSA22 SSB22 SSn22
T3 SSA222 SSB222 SSn222

A3 T1 SSA3 SSB3 SSn3
T2 SSA33 SSB33 SSn33
T3 SSA333 SSB333 SSn333

AZ T1 SSAZ SSBZ SSnz
T2 SSAZZ SSBZZ SSnzz
T3 SSAZZZ SSBZZZ SSnzzz

Herein the place of interest say a retail store or a restaurant is divided into area units A1, A2, A3….AZ and the Signal Strength (SS) of each WAP (WAP1 to WAPn) is recorded at three different time intervals i.e. T1, T2 and T3. For area unit A1 the SS recorded from WAP1 at time T1 is SSA1, that recorded from WAP2 is SSB1and for WAPn it is SSn1. Similarly for area unit A1 at time T2 the SS recorded from WAP1 is SSA11,that recorded from WAP2 is SSB11 and for WAPn is SSn11. Continuing the mapping in similar fashion, for area unit AZ the SS recorded in time interval T1 for WAP1 is SSAZ,that for WAP2 is SSBZ and for WAPn it is SSnzIn this manner each area unit in the restaurant is represented in terms of signal strength from various access points. This data is curated and stored in a database 112. In case there are other Access Points such as Bluetooth Access Point or Cellular Signal Access Point then they are also recorded in the same manner and become an additional entry that is utilized for position identification.This curated data along with user behavior characteristics and other attributesare used to build a mapping model 114 that is used to predict user location in a pre-mapped place in accordance with the method provided herein.
[0019] Fig. 2 illustrates the flow diagram for the method of user location determination once the user visits an already mapped area 210. The user smartphone is configured to execute and run a scanning application that periodically checks for signal strength from available WAPs. When the user gets into the vicinity of an already mapped area, the user smartphone configured with the scanning application automatically scans for WAPs 212 and sends the recorded signal strength to the server for comparison with the mapping model 214. The user position is determined based on a probability score computed by mapping model 216. To continue the previously discussed example, when the user walks into the mapped place say a restaurant, the user smartphone scans for available WAPs and records the signal strength from WAP1 to WAPn at the point where the user is sitting in the restaurant.The recorded set of signal strengths at the various time intervals T1, T2…Tnare fed to the database and a probability score is computed based on a mapping model 216. The mapping model is a machine learning model created based on recorded signal strengths and user behavior characteristics which continuously evolves through the input of feedback from user devices, heuristic data, device attributes, user behavior etc.Based on the probability score calculated by the mapping model and a predetermined threshold corresponding to whether the user is in a particular area or not the user location is predicted 218. In case the probability score indicates the presence of the user a check in alert is triggered and the user is alerted 220. The user device sends feedback in the form of updated signal strength data to the mapping model 222 to help the mapping model predict user location more accurately.
[0020] Fig. 3 illustrates anetwork architecture of the system configured to utilize the method provided herein for user location determination. A mapping device 310 is configured to map a target area in accordance with the mapping method provided herein and explained in Fig. 1. The mapping device 310 may be a smart phone or any device with Access Point scan and data recording capability. Once the mapping device 310 maps a target area and represents the area units within the target area in the form of Signal Strength (SS) received from various WAPs in a given time interval, this mapped data is then sent to the Web Server 312 wherein it is stored in a database 314. The database may be any known Database Management System (DBMS) such as MySQL, Oracle, IBM DB2 etc or any other form of organized collection of data Such as Nosql databases like hadoop,hive etc. In an alternate embodiment, the data captured by the mapping device may be directly sent to the web server 312 in real time and be automatically saved in the database 314.This database 314 along with other attributes such as device attributes (device position, device hardware, available sensors etc) heuristic data, user behavior (user habits, regular user actions etc), user device data (sensor data, unique identification data etc)etc may be used to build a Mapping Model 318 which is a machine learning model that calculates a probability score for predicting user location. Based on the probability score being above a certain threshold, the user location is determined.The Mapping Model 318 may be based on a computational cluster model such as a Hadoop cluster to accommodate and analyze large amounts of unstructured data. For example, with time the System Admin 316 may feed data in the data model regarding a specific user who goes to watch a movie every Wednesday evening. This data will be available to the System Admin 316 over a period of time. The Mapping Model 318 will evolve, as it will automatically configure the scanning app on such user’s device to be activated on a Wednesday evening to scan and check if the user is in the movie theatre.
[0021] The user device 320 is configured to execute and run an application that periodically scans for available WAPs and records their signal strength. As soon as the user reaches into the vicinity of an already mapped area, the application sends the recorded signal strength to the web server 312, which then based on a comparison with the already mapped data is easily able to determine if the user is inside or outside the mapped area and in case the user is inside the mapped area then the exact location of the user. The user device may be a smart phone, smartwatch, tablet, laptop or any device that has scanning capability (Wi-Fi, Bluetooth etc) to check for Access Points along with an ability to communicate with the server at any point currently or in the future. The application is designed in a manner that it utilizes the scanning capability of the user device in the background without triggering any alerts or without waiting for any prompts from the user. The application is configured to work even if the device is not connected to the Internet and is designed to consume minimal battery of the user device.The application comprises of an intelligent assist feature that automatically recognizes user location based on indoor positioning, behavioral and temporal attributes and alerts the user.
[0022] The user device 320 is also configured to send feedback to the web server 312 in case a new WAP is added or if the position on an existing WAP is changed thereby causing a change in the signal received at different points within the area. Once the web server is alerted through the feedback mechanism, the area may be remapped in the same manner as discussed earlier to ensure that the changed signal strength is used to accurately predict user location. This feedback data is also fed to the mapping model 318 to ensure that the model is up-to-date and is capable of intelligently predicting user location.
[0023] In an alternate embodiment, user behavior such as carrying out a transaction at a specific store or a restaurant may result in the user receiving an SMS or other type of message on the device. This SMS or other message type triggers the scanning of the available access points in the store or restaurant (target area) and such access point data including signal strength of various access points is sent to the server. The server verifies such data and updates the database with the most current access point data. This SMS or other message based trigger of access point data collection is capable of working independently even if the user is not connected to the internet and may be used by the server to initiate a check in for the user.
[0024]

Specific Application for Automatic Check in and Targeted Advertising
[0025] Fig.4 illustrates a specific application of the user location determination described herein for the purposes of automatic user check in and forwarding targeted advertisements to the user. A partner place is first mapped 410 in accordance with the mapping process provided herein. The partner place can be a restaurant, shop, store, movie theatre or any other business outlet desirous of participating in an automated check in and/or targeted advertising campaign. The mapping data is then sent to a web server 312 which may be any known server including but not limited to Linux, Apache, Nginx or PHP based server. The mapping data is stored in a database that may be any known Database Management System (DBMS) such as MySQL,NoSQL, Oracle, IBM DB2 etc or any other form of organized collection of data. A mapping model 318 may be built upon the mapping data in the database and additional attributes such as device attributes, heuristic data, user behavior attributes etc may be used to make the model more intelligent. This mapping model may continuously evolve in order to predict user location with greater accuracy. Once the mapping data is fed into the database, the system admin 316 also feeds into the web server corresponding information that may be useful for the consumer such as menu items, coupons, offers, advertisements and other related data of the partner place.
[0026] When the user carrying a device that is configured to run the scanning application 412 visits the partner place that is already mapped 414, the user device configured to run the application scans for available WAPs and records their signal strength at the place where the user is present. If the user device is online (connected to the Internet) 416 then the recorded signal strength is sent to the web server 312 where it is compared against mapping data for the partner place already stored in the database 314. The mapping model 318 predicts the user location using signal strength data sent by user device and other attributes such as device attributes, user behavior, user device data etc. Based on a match between the signal strength sent by the user and the mapping data of the partner place, a model response and check in alert is sent to the user. Thereafter, specific coupons, offers, advertisements etc. may be pushed to user device based on user actions and behavior as the position and behavior of the user can be automatically tracked. This system enables highly localized targeted advertisements due to its capability to predict user location accurately. For example if the user walks into a partner apparel store, the check in is triggered and an alert is sent to the user. The user location is further identified as the children apparel section in the store based on signal strength match and coupons and offers with respect to children apparel are pushed to the user device thereby prompting user to buy more or buy specific products. In case the user device is offline 416 then the recorded signal strength data is processed locally by comparison against a data file of mapping data stored on the user device that is automatically stored in user device at the time of installation of the application. Based on signal strength match, the check in response is triggered and sent to the user.The system may optionally have a new user registration based on an SMS OTP (One Time Password) verification, which involves interaction of the system with any SMS gateway 418 and for the purpose of this verification an SMS API runs on the server.
[0027] The foregoing description of the specific embodiments will so fully reveal the general nature of the embodiments herein that others can, by applying current knowledge, readily modify and/or adapt for various applications such specific embodiments without departing from the generic concept, and, therefore, such adaptations and modifications should and are intended to be comprehended within the meaning and range of equivalents of the disclosed embodiments. It is to be understood that the phraseology or terminology employed herein is for the purpose of description and not of limitation. Therefore, while the embodiments herein have been described in terms of preferred embodiments, those skilled in the art will recognize that the embodiments herein can be practiced with modification within the spirit and scope of the embodiments as described herein. ,CLAIMS:What is claimed:
1. A method of automated user presence detection, said method comprising:
mapping a target area based on signal strength of multiple access points in said target area;
creating a mapping model comprising of said signal strength mapping of said target area;
scanning said multiple access points of said target area via a user device when a user reaches in vicinity of said target area;
comparing signal strength received on said user device with said mapping model; and
determining user location based on said comparison.

2. The method as claimed in claim 1, wherein said access points are Wi-Fi access points (WAP’s).

3. The method as claimed in claim 1, wherein said access points are Bluetooth access points.

4. The method as claimed in claim 1, wherein said access points are Cellular signal access points.

5. The method as claimed in claim 1 wherein said mapping further comprising:
dividingsaid target area into multiple smaller area units; and
recording signal strength of said access points for each said smaller area unit.

6. The method as claimed in claim 1 further comprising of curating and storing of said mapping ofsignal strength data corresponding to saidmapped target area in a database.
7. The method as claimed in claim 1 wherein said mapping model further comprising user behavior attributes.
8. The method as claimed in claim 1 wherein said mapping model further comprising heuristic data.
9. The method as claimed in claim 1 wherein said mapping model further comprising device attributes.
10. The method as claimed in claim 1, wherein said mapping model is a machine learning model configured to receive continuous feedback from user devices and evolve based on said feedback.
11. The method as claimed in claim 1, further comprising triggering user device based scanning of said target area based on an SMS or other message type received on said user device and sending said scanned data to said Server.
12. The method as claimed in claim 1 further comprising computing a probability score for predicting user location based on said mapping model.
13. The method as claimed in claim 1 further comprising providing said user with automatic check in when said userenters said target area.
14. The method as claimed in claim 12 further comprising triggering automatic check in even if the user is offline.
15. The method as claimed in claim 1 further comprising providing said user targeted advertisements based on said user location or behavior.
16. A systemof automated user presence detection, said system comprising:
a mapping device, configured to map signal strengths of multiple access points in a target area;
a server configured to create a mapping model comprising of said signal strength data from said mapping device;
a user device configured to periodically scan for signal strength from available access points in said target area and send said signal strength data to said server; and
a processor within said server configured to receive said signal strength data and compare against said database to determine said user location.

17. The system as claimed in claim 16, wherein said mapping device is a smart device enabled with Access Point scan and data recording capability.
18. The system as claimed in claim 16, further comprising a database configured to store mapping data received from said mapping device.
19. The system as claimed in claim 16, wherein said access points are Wi-Fi access points (WAP’s).

20. The system as claimed in claim 16, wherein said access points are Bluetooth access points.

21. The system as claimed in claim 16, wherein said access points are Cellular signal access points.
22. The system as claimed in claim 16 wherein said mapping model further comprising user behavior attributes.
23. The system as claimed in claim 16 wherein said mapping model further comprising user device data.
24. The system as claimed in claim 16 wherein said mapping model further comprising device attributes.

25. The system as claimed in claim 16 wherein said mapping model further comprising heuristic data.

26. The system as claimed in claim 16 further comprising said user device is configured to trigger scanning of access points of said target area based on an SMS or other message type received on said user device and said user device configured to send said scanned data to said Server.

27. The system as claimed in claim 26 further comprising said Server configured to update said mapping model based on said scanned data received from said device.