Destination verification method and system

Abstract

A destination verification method and system. A method for confirming arrival of a target location includes comparing, by one or more controllers, properties of a plurality of identifying features of the target location to properties of a corresponding plurality of corresponding features of a current location to result in a plurality of comparisons. The method additionally includes identifying, by the one or more controllers, the current location as the target location if the plurality of comparisons ascertain that the current location is the target location. The properties of the plurality of identifying features of the target location include at least one property of one or more wireless communication networks expected to be detectable at the target location.

Description

[0001] introduce

[0002] The present disclosure is in the field of routing and destination verification.

[0003] For various purposes, people periodically seek to travel to a desired destination location, such as a home or business. Such a purpose may be to deliver a package for a delivery service or for an online retailer. If the person is not familiar with the destination location, and furthermore, if the destination location is in a densely populated area, it may be difficult for the person to find the destination location and confirm that they are arriving there, rather than arriving at the wrong other location. Furthermore, similar street addresses for different buildings may cause a delivery person to inadvertently deliver a package to an incorrect location. Summary of the invention

[0004] A method for confirming arrival at a target location includes comparing, by one or more controllers, properties of a plurality of identification features of the target location with properties of a corresponding plurality of corresponding features of a current location to result in a plurality of comparisons. The method also includes identifying, by the one or more controllers, the current location as the target location if the plurality of comparisons conclude that the current location is the target location. The properties of the plurality of identification features of the target location include at least one property of one or more wireless communication networks that are expected to be detectable at the target location.

[0005] In a variation, the plurality of identifying features of the target location may include a visible street address number located at the target location. In an additional variation, the plurality of identifying features of the target location may include at least one visible external feature of a building at the target location. In yet another variation, the plurality of identifying features of the target location may include a walking profile of a route approaching the target location. The walking profile may include at least one of the number of stairs in the walking profile, the shape of the walking profile, the length of the walking profile, and the expected walking time to traverse the walking profile.

[0006] Alternatively, one or more wireless communication networks may be WiFi networks and the at least one identification feature may include an SSID or BSSID of the wireless communication network. Alternatively, at least one identification feature of the WiFi network may include the signal strength of the network. In addition, at least one identification feature of the WiFi network may include the radio frequency of the network.

[0007] The method may additionally include using geofencing to confirm proximity to the target location before comparing the properties of the plurality of identification features of the target location with the properties of the plurality of corresponding features of the current location.

[0008] The method may further include combining results of the plurality of comparisons to result in a confidence score, comparing the confidence score to a validation threshold, and identifying the current location as the target location if the confidence score is above the validation threshold.

[0009] Still additionally, the method may further include updating the database of properties of the identification feature of the target location with the property of the at least one identification feature of the current location if the current location has been identified as the target location.

[0010] Another method for confirming arrival at a target location includes retrieving properties of multiple identification features of the target location from a database populated based on previous observations made at the target location, comparing the properties of the multiple identification features of the target location with properties of a corresponding multiple corresponding features of the current location to result in multiple comparisons, and identifying the current location as the target location if the multiple comparisons conclude that the current location is the target location.

[0011] The plurality of identifying features of the target location may include at least one visible external feature of a building at the target location.Alternatively or additionally, the plurality of identifying features of the target location may include a walking profile of a route approaching the target location.

[0012] The method may further comprise updating the database of properties of the identification feature of the target location with the property of the at least one identification feature of the current location if the current location has been identified as the target location.

[0013] Additional methods for confirming arrival at a target location include comparing a profile of a wireless communication network that is expected to be detectable at the target location with a profile of a wireless communication network detected at a current location, and if the comparison determines that the current location is the target location, identifying the current location as the target location. The profile of the wireless communication network that is expected to be detectable at the target location may include one or more SSIDs or BSSIDs. The profile of the wireless communication network that is expected to be detectable at the target location may also include the signal strength of the wireless communication network at the target location. The profile of the wireless communication network that is expected to be detectable at the target location may additionally include the radio frequency of the wireless communication network. The profile of the wireless communication network that is expected to be detectable at the target location may include at least one vehicle-based WiFi network.

[0014] A method for confirming arrival at a target location, the method comprising: comparing, by one or more controllers, properties of a plurality of identification features of the target location with properties of a corresponding plurality of corresponding features of a current location to result in a plurality of comparisons; and if the plurality of comparisons conclude that the current location is the target location, identifying, by the one or more controllers, the current location as the target location; wherein the properties of the plurality of identification features of the target location include at least one property of one or more wireless communication networks that are expected to be detectable at the target location.

[0015] In the method, the plurality of identifying features of the target location includes a visible street address number located at the target location.

[0016] In the method, the plurality of identifying features of the target location includes at least one visible exterior feature of a building at the target location.

[0017] In the method, the one or more wireless communication networks are WiFi networks, and the at least one property of the one or more wireless communication networks includes an SSID or a BSSID of the wireless communication network.

[0018] In the method, the at least one property of the one or more wireless communication networks includes a signal strength of the one or more wireless communication networks.

[0019] In the method, at least one property of the one or more wireless communication networks includes a radio frequency of the one or more wireless communication networks.

[0020] In the method, the plurality of identifying features of the target location includes a travel profile of a route approaching the target location.

[0021] In the method, the walking profile includes at least one of a number of stairs in the walking profile, a shape of the walking profile, a length of the walking profile, and an expected walking time to traverse the walking profile.

[0022] The method further includes using geo-fencing to confirm proximity to the target location before comparing properties of the plurality of identification features of the target location with properties of the plurality of corresponding features of the current location.

[0023] The method further includes: combining results of the plurality of comparisons to result in a confidence score; comparing the confidence score to a validation threshold; and identifying the current location as a target location if the confidence score is above the validation threshold.

[0024] The method further includes updating a database record of properties of the identifying characteristic of the target location with a property of at least one identifying characteristic of the current location if the current location has been identified as the target location, wherein the database record is identified by a unique numeric identifier.

[0025] A method for confirming arrival at a target location, the method comprising: retrieving properties of a plurality of identification features of the target location from a database populated based on previous observations made at the target location; comparing the properties of the plurality of identification features of the target location with properties of a corresponding plurality of corresponding features of a current location to result in a plurality of comparisons; and identifying the current location as the target location if the plurality of comparisons conclude that the current location is the target location.

[0026] The method further includes updating a database record of properties of the identifying characteristic of the target location with a property of at least one identifying characteristic of the current location if the current location has been identified as the target location, wherein the database record is identified by a unique numeric identifier.

[0027] In the method, the plurality of identifying features of the target location includes at least one visible exterior feature of a building at the target location.

[0028] In the method, the plurality of identifying features of the target location includes a travel profile of a route approaching the target location.

[0029] A method for confirming arrival at a target location, the method comprising: generating a comparison of a profile of a wireless communication network expected to be detectable at the target location and a profile of a wireless communication network detected at a current location; and identifying the current location as the target location if the comparison concludes that the current location is the target location.

[0030] In the method, a profile of a wireless communication network that is expected to be detectable at a target location includes one or more SSIDs or BSSIDs.

[0031] In the method, a profile of a wireless communication network that is expected to be detectable at a target location includes a signal strength of the wireless communication network at the target location.

[0032] In the method, a profile of a wireless communication network that is expected to be detectable at a target location includes a radio frequency of the wireless communication network.

[0033] In the method, a profile of wireless communication networks detectable at a target location is expected to include at least one vehicle-based WiFi network.

[0034] The above summary of the invention does not represent every embodiment or every aspect of the present disclosure. When combined with the accompanying drawings and the appended claims, other possible features and advantages will be easily apparent from the following detailed description of the embodiments implementing the present disclosure. In addition, the combinations and sub-combinations of the elements described in the present disclosure are explicitly included in the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 A person is shown approaching the building.

[0036] Figure 2 It is a diagram for verification Figure 1 The building is a flow chart of part of the method of the personnel's intended target location.

[0037] Figure 3 It is further illustrated for verification Figure 1 The building is a flow chart of the personnel's approach to the intended target location.

[0038] Figure 4 is an image of the exterior features of the building as shown on the mobile phone.

[0039] Figure 5A is a table containing the properties of the WiFi networks expected at the target location.

[0040] Figure 5B is a table containing the characteristics of the WiFi networks detected at the current location.

[0041] Figure 6 It shows that it can be Figure 2 and Figure 3 An example of features used in the example destination verification method illustrated in FIG.

[0042] Figure 7 It shows that Figure 3 An enhanced flowchart of a portion of the flowchart illustrated at . DETAILED DESCRIPTION

[0043] First reference Figure 1 , a person 100, such as a delivery person, may be seeking to find a target location 102, such as a home or business. The target location 102 may have other structures adjacent to or attached to it. The person 100 may have arrived in a vehicle 104 and may now be walking to the target location 102 in order to deliver a package intended for an occupant of the target location 102. The person 100 may be carrying a smart phone 106. The person 100 may be following a path 108 from the vehicle 104 to the front door of the target location 102.

[0044] Personnel 100 may be someone who is not familiar with the neighborhood in which target location 102 is located, and / or person 100 may be a temporary worker or someone who is new to the job. Therefore, person 100 may not be sure which exact building is target location 102. This may be particularly problematic in areas where buildings are relatively densely laid out and where global positioning system (GPS) technology may not be reliably available. This may also be true in situations where delivery is intended for residents of multi-unit apartments or commercial buildings.

[0045] Methods and systems for helping personnel 100 reliably confirm arrival at target location 102 can be obtained from additional references Figure 2 Initially, start at box 200. At box 201, the geographic coordinates of the address of the target location 102 are retrieved from any of a number of databases where such information is available, which may include database 110. In addition, a margin of error ("geo delta") Δ may be retrieved (box 205). At box 202, the actual geographic coordinates ("AGC") of the vehicle 104 or smartphone 106 that the person 100 may be driving to the target location 102 are compared to the geographic coordinates ("TGC") of the target location 102. If the coordinates match within the error tolerance Δ, then it can be concluded that the person 100 is at the target location 102, as reflected in box 203. The error tolerance Δ may be retrieved from database 110. The error tolerance Δ may be fixed, or it may be variable, such as a function of the density of buildings near the target location 102; if the buildings in a given area are spaced farther apart than if the buildings are closer together, a larger error may be tolerated. If the geo-coordinates do not match within the error tolerance Δ, then at box 204 consider whether the person 100 is within a suitable geo-fence window of a location proximate to the target location 102 (box 206). The geo-fence window may also be variable, for example depending on the density of buildings near the target location 102. If the person 100 is not within the geo-fence boundary proximate to the target location, it may be concluded that the person 100 is not at the target location 102. The person 100 may then be notified on the smartphone 106 and the person 100 may be rerouted (box 208) or the person 100 may use an alternative method of finding his or her destination. However, if the person 100 is within the geo-fence boundary proximate to the target location 102, the verification method may continue at box 210, where a multimodal address verification may begin.

[0046] Reference Figure 3 Further describing the multi-mode address verification of block 210. There, one or more of the multiple address verification processes may occur. At block 212, optical address recognition may occur. Also referring to Figure 4, person 100 may use the camera of smartphone 106 to take an image of address plaque 300 at the building where person 100 is located and perform optical character recognition (OCR) on address plaque 300 to determine the numbers and / or letters contained thereon. (Alternatively, if target location 102 is a unit of an apartment or other multi-unit building, OCR may be performed on the numbers and / or letters identifying the unit within the building.) At block 214, a determination is made as to whether the address (LA) read by the optical address recognition of block 212 is the address (TA) of target location 102. If not, block 212 may be repeated with the possibility that repeated attempts to recognize the characters on address plaque 300 may produce a passing result. However, if the test result at block 214 is yes, the routine continues to block 216.

[0047] At block 220, and with continued reference to Figure 4 , the image of the building in which the person 100 is located, captured by the smart phone 106, can be compared with the visually observable characteristics (VS) of the target location 102 stored in the database. Such characteristics can include the color, texture, and / or composition (e.g., brick, wood, vinyl) of the exterior siding 302 of the building. Characteristics can also include the presence, color, size, shape, and / or texture of door frames 304 and doors 308, as well as the presence, color, size, shape, and / or texture of other identification elements such as exterior coach lamps 306. Several of the aforementioned factors (e.g., color match, texture match, key points of the structure) can be evaluated for sufficient matching and the results of such evaluations can be combined in a majority-rule or other combination scheme to determine whether the test at box 222 results in a sufficient match overall. If so, the routine continues to box 216. If not, box 220 can be repeated by instructing the person 100 to capture another visual signature using the camera on the smart phone 106.

[0048] At box 230, it may be considered whether the profile of the wireless communication (e.g., WiFi) network near the person 100 is a sufficient match to the WiFi profile expected at the target location 102. The WiFi profile expected at the target location 102 may be stored in a database, as will be discussed further below. The WiFi profile expected at the target location 102 may include WiFi networks of homes, commercial buildings, vehicles, and Internet service provider "hotspots" near the target location 102. It is particularly advantageous that providers of WiFi services to a large number of vehicles (such as vehicle manufacturers) may have considerable knowledge about the WiFi networks of the owners' vehicles living near the target location 102. It may be expected that such a network is detectable for a person who has arrived at the target location 102. At box 232, it is considered whether the WiFi profile at the current location of the person 100 implies that the person 100 is at the target location 102. At box 232, various properties of the WiFi profile near the person 100 may be considered. For example, the presence of an SSID (Service Set Identifier) ​​or BSSID (Basic Service Set Identifier) ​​of a WiFi network that is expected to be near the target location 102 may be considered. Additionally, the signal strength of the WiFi network near the person 100 may be compared to the signal strength of the WiFi network that is expected at the target location 102. Furthermore, the radio frequency of the WiFi network near the person 100 may then be compared to the radio frequency of the WiFi network that is expected to be near the target location 102. If the WiFi profile near the person 100 is sufficiently close to the WiFi profile that is expected at the target location 102 to indicate that the person 100 may be at the target location 102, the routine may continue at block 216. However, if the WiFi profile near the person 100 is not sufficiently close to the WiFi profile that is expected near the target location 102 to indicate that the person 100 may be at the target location 102, the routine may return to block 230.

[0049] Figure 5A is an illustration of how a WiFi profile may be expected to view a target location 102, including one or more of a BSSID 350, SSID 352, signal strength 354, and radio frequency 356 of a corresponding WiFi network. Figure 5B 350', SSID 352', signal strength 354', and radio frequency 356' for each WiFi network detectable at the actual location of the person 100. As a method for comparing the two to determine if they are close enough to indicate that the person 100 is at the target location 102, the Hamming distance between the data in the two tables can be calculated.

[0050] At box 240, a motion matching routine may be entered. There, characteristics of the path 108 approaching the target location 102 stored in the database may be accessed. Such characteristics may include the distance from, for example, a street walk to the front porch or front door of the target location 102. The characteristics may also include the time required to walk from, for example, a street walk to the front porch or front door of the target location 102. The characteristics may additionally include the number of steps leading up or down from the front walk to the front porch of the target location 102. The characteristics may further include the shape of the walking route from, for example, a street to the target location 102. The characteristics may also include the change in height from the ground floor of a multi-dwelling building such as an apartment house or a commercial building to the floor where the target location 102 is located. Several of the aforementioned factors may be evaluated for sufficient matching, and the results of such evaluations may be combined in a majority-rule or other combination scheme to determine whether the test at box 242 results in a sufficiently sufficient match as a positive indicator that the person 100 is at the target location 102.

[0051] If the path followed by person 100 sufficiently matches the expected path to target location 102, the routine may continue at block 216. If not, motion matching may be attempted again at block 240.

[0052] At box 216, inputs from any of the tests 214, 222, 232, and 242 that may have been performed and further considered to have been successfully passed can be combined. The combination can be based on several methods. For example, a weighted scheme can be adopted, in which the factors that are considered most reliable in determining whether the person 100 has arrived at the target location 102 can be given the most weight. Alternatively, a majority voting scheme can be used, in which it can be determined whether there are more successful tests than unsuccessful tests. Additional schemes may include Bayesian information fusion and Dempster-Shafer weighted evidence combination rules. The analysis result at box 216 can be a conclusion about whether the person 100 has arrived at the target location 102. The analysis result at box 216 can also be a confidence score CS, which reflects the confidence level that the person 100 has successfully arrived at the target location 102.

[0053] Then, at block 218, the verification threshold V TThe confidence score CS is tested (block 217). If the confidence score is sufficiently high, the routine proceeds to block 219 where the person 100 is notified that she or he is at the target location 102, such as by an app on the person's 100 smartphone 106 or via text. If the confidence score is not sufficiently high, the person 100 may be given an alert that the person 100 is not at the target location 102, such as by calling for help, or the routing system that brought the person 100 to her / his current location may make another attempt to route the person 100 to the target location 102.

[0054] The database 110 can be adopted to store multiple identification characteristics of each potential target location in a digital profile (i.e., database record), which has a unique digital identifier for each potential target location. Those stored identification characteristics can be used at least in part as the basis for various comparisons performed at frames 214, 222, 232 and 242. In addition, then, once personnel 100 has successfully arrived at a target location such as target location 102, the result of the travel from personnel 100 to target location 102 can be used to update and enrich the digital profile for target location 102. For example, the number of steps required for personnel 100 to arrive at the front door of target location 102 can be recorded in the database 110 by the automatic feedback of the small application running on smart phone 106, and smart phone 106 can be equipped with a step counting function. In addition, the external visual characteristics of target location 102 can be recorded in the database to update and enrich the digital profile for target location 102. The presence and visual characteristics of other visual landmarks captured during the person 100's travel to the target location 102 (e.g., fire hydrants, basketball hoops, makes and models of vehicles in the driveway) may also be recorded in the digital record and used for subsequent visual comparisons (e.g., at block 232) for people seeking to travel to the target location 102. As a result of the database update, when the person 100 or another person makes a future trip to the target location 102, the record in the database 110 for the target location 102 may be more reliable as a basis for future comparisons. Furthermore, the result of such future comparisons may be a conclusion with a higher degree of confidence as to whether the person seeking to reach the target location 102 has actually successfully done so.

[0055] The presence of hazards, such as unfriendly dogs, may also be uploaded by person 100 into a digital profile of target location 102 so that future persons seeking to travel to target location 102 may be warned of such hazards.

[0056] The database 110 may be a cloud-based database that communicates with the smartphone 106 via wireless communications. The database 110 may reside in the "back office" of a telecommunications-based service provider, such as an automobile manufacturer. A telecommunications service provider affiliated with General Motors is one such provider. Database 110 may alternatively reside in a "backstage" associated with a delivery service or online retailer associated with person 100. The various calculations, comparisons, and other operations described herein may be run by small applications in smartphone 106, remotely via cloud computing, or in a corresponding "backstage," or they may be distributed among any combination of the foregoing. In each case, the corresponding controllers contain sufficient electronic resources (including, but not limited to, microprocessors, memory, inputs, outputs, and software) to perform the functions assigned to them herein.

[0057] Further references Figure 6 The data that may be stored in a database 110 is illustrated, where location-specific attributes 112 for possible target locations may be stored. For the purposes of this example disclosure, the data is categorized as "crowd-sourced attributes" 114 and "auto-sourced attributes" 116, and some may be sourced in both ways or the other.

[0058] The crowdsourced attributes 114 may include attributes that may be input by a user, such as a street address number 114a, a street name 114b, a street type (e.g., paved / unpaved, number of lanes) 114c, a direction 114d, a unit or suite number 114e, a postal (or ZIP) code 114f, a city 114g, a state or province 114h, a country 114i, a front photo 114j, and a buzzer number 114k (in the event that the target location 102 is a multi-unit building).

[0059] Automatic source attributes 116 may be attributes that are automatically updated in database 110 and may include GPS coordinates (latitude, longitude) 116a, GEO tags (e.g., What Three Words (“W3W”) and / or Google Plus codes) 116b, visual tags 116c, motion tags 116d, WiFi network lists (SSID, BSSID, network radio frequency, and signal strength) 116e, Geo deltas 116f (see box 205, Figure 2), Building Information Modeling (“BIM”) information 116g, location type (e.g., single family home, multi-unit home, commercial, industrial) 116h, metadata associated with the location (e.g., open and closed times and dates) 116i, human-friendly direction descriptions 116j, and nearby parking lots 116k.

[0060] Further references Figure 7 , illustrates a method for verifying an image captured by a smart phone 106 prior to processing at blocks 212 and 220. Here, the quality of the image captured by the smart phone 106 is characterized at block 402 by a blind / referenceless spatial quality assessor 404. At block 406, the resulting assessed quality QI of the image is compared to the quality threshold QT from block 408. If the quality QI of the image is better than the quality threshold QT, processing may continue at blocks 212, 214, 220, 222, and 216, as previously described with reference to FIG. Figure 3 (Note that for clarity, Figure 7 The block 216 shown in the figure is intentionally omitted for reference Figure 3 However, if the image quality QI is not better than the quality threshold QT, the person 100 may be instructed at block 410 to take another photo with the smartphone 106 with the intent of capturing a better image. Figure 3 As discussed, if the test results at blocks 214 and 222 are positive, then at block 216 they are fed to the combining rule.

[0061] The specific implementation and the accompanying drawings or each figure are support and description of this teaching, but the scope of this teaching is limited only by the claims. Although some best modes and other embodiments for implementing this teaching have been described in detail, there are various alternative designs and embodiments to practice this teaching defined in the appended claims.

Claims

1. A method for confirming arrival at a target location, the method comprising: comparing, by the one or more controllers, properties of a plurality of identification features of the target location with properties of a corresponding plurality of corresponding features of the current location to result in a plurality of comparisons; and If the plurality of comparisons conclude that the current location is the target location, then identifying the current location as the target location by one or more controllers; The properties of the plurality of identification features of the target location include at least one property of one or more wireless communication networks that are expected to be detectable at the target location.

2. The method according to claim 1, wherein: The plurality of identifying features of the target location includes a visible street address number located at the target location.

3. The method according to claim 1, wherein: The plurality of identifying features of the target location include at least one visible exterior feature of a structure at the target location.

4. The method according to claim 1, wherein: The one or more wireless communication networks are WiFi networks, and the at least one property of the one or more wireless communication networks includes an SSID or a BSSID of the wireless communication network.

5. The method according to claim 4, wherein: The at least one property of the one or more wireless communication networks includes a signal strength of the one or more wireless communication networks.

6. The method according to claim 4, wherein: The at least one property of the one or more wireless communication networks includes a radio frequency of the one or more wireless communication networks.

7. The method according to claim 1, wherein: The plurality of identifying features of the target location includes a travel profile of a route approaching the target location.

8. The method according to claim 7, wherein: The walking profile includes at least one of a number of stairs in the walking profile, a shape of the walking profile, a length of the walking profile, and an expected walking time to traverse the walking profile.

9. The method according to claim 1, further comprising: Geofencing is used to confirm proximity to a target location before comparing properties of a plurality of identifying features of the target location to properties of a plurality of corresponding features of the current location.

10. The method according to claim 1, further comprising: combining the results of multiple comparisons to result in a confidence score; Compare the confidence score to a validation threshold; and If the confidence score is above the validation threshold, the current location is identified as the target location.

Images