Latest Contributions by JamesCrandall

Hi Aaron -- hope all is well. Is there any update regarding the documentation on this issue? We're now seeing a much larger lag/delay in some instances and trying to determine if this is an app setting, device/OS type, connectivity issue or if there's something on the ESRI side of things that may cause this?  Recently we noticed a specific instance with a 4 day delay between location_timestamp and created_date: ... View more

EDIT: would a single user logged into ESRI Tracker app across multiple devices simultaneously be a source to any of this?  I'm still skeptical even that would produce the same features with the exact same location_timestamp values but perhaps there's another process that is being affected by the simultaneous logins. Aaron, To reiterate, I'm not worried about the duplicates issue only because I'm handling them in an after-the-fact process that I can identify these instances.  But wanted to provide more info to you and your team.  Let me know if you'd like me to open a premium ticket to setup a more formal interaction outside of GeoNet, I would be able to remote session with you all if you need. I now see some triplicates.   [ { "attributes": { "objectid": 886296, "globalid": "cf208275-3d97-4f07-aa59-89dfe72d8f0a", "activity": 0, "altitude": -22, "app_id": "tracker", "battery_percentage": 87, "battery_state": 1, "course": 96.2351684570312, "device_id": "04ba83a0-09b0-4b4a-b87e-2be331924053", "floor": null, "horizontal_accuracy": 3.90000009536743, "location_source": "fused", "location_timestamp": 1592434582000, "session_id": "7aa745ba-42be-4b23-acc8-11a65d511740", "signal_strength": null, "speed": 26.8384494781494, "vertical_accuracy": 100, "created_user": "zzz", "created_date": 1592434625398, "last_edited_user": "zzz", "last_edited_date": 1592434625398 }, "geometry": { "x": -81.03567099999998, "y": 25.857096300000023 } }, { "attributes": { "objectid": 886297, "globalid": "dbabadd9-9d46-43eb-b42b-05836c94e46e", "activity": 0, "altitude": -22, "app_id": "tracker", "battery_percentage": 87, "battery_state": 1, "course": 96.2351684570312, "device_id": "04ba83a0-09b0-4b4a-b87e-2be331924053", "floor": null, "horizontal_accuracy": 3.90000009536743, "location_source": "fused", "location_timestamp": 1592434582000, "session_id": "7aa745ba-42be-4b23-acc8-11a65d511740", "signal_strength": null, "speed": 26.8384494781494, "vertical_accuracy": 100, "created_user": "zzz", "created_date": 1592434625398, "last_edited_user": "zzz", "last_edited_date": 1592434625398 }, "geometry": { "x": -81.03567099999998, "y": 25.857096300000023 } }, { "attributes": { "objectid": 886298, "globalid": "f7c56f5c-5d20-4772-9f28-2f5ba4e90640", "activity": 0, "altitude": -22, "app_id": "tracker", "battery_percentage": 87, "battery_state": 1, "course": 96.2351684570312, "device_id": "04ba83a0-09b0-4b4a-b87e-2be331924053", "floor": null, "horizontal_accuracy": 3.90000009536743, "location_source": "fused", "location_timestamp": 1592434582000, "session_id": "7aa745ba-42be-4b23-acc8-11a65d511740", "signal_strength": null, "speed": 26.8384494781494, "vertical_accuracy": 100, "created_user": "zzz", "created_date": 1592434625398, "last_edited_user": "zzz", "last_edited_date": 1592434625398 }, "geometry": { "x": -81.03567099999998, "y": 25.857096300000023 } } ]‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍ ... View more

Like I mentioned, I don't have a sense of frequency just yet but I do have some monitoring tools setup.  This duplicate issue has only happened about 7 or so times since I started monitoring about 50 ESRI Tracker users collecting roughly 30,000 tracks each 24hrs. I have a daily summary metrics that I am querying against the ESRI Tracker Service and the Hosted service I have moved points into from the tracker service.  In the instances where there's both a "actualDiscrepancies" and "possibleDiscrepancies" values then these are cases where valid ESRI Tracker features were created much later after the copy process ran and these are true discrepancies that I recover those points. Whenever "actualDiscrepancies" = 0 and "possibleDiscrepancies" > 0 these are all instances where the ESRI track points were created later but already had created a point at the earlier time, hence it's a duplicate feature. I'm only interested in the actualDiscrepancies and have a process in place to move these into the destination feature service after-the-fact. (the -1 values are likely due to a missing ">=" somewhere in my programming that queries the feature services but I consider this quite minor and I simply ignore at the moment until I can find time to remedy it). ... View more

Edit: I will have to determine OS.  Also, I cannot find any significant pattern on when this occurs but it can be as much as a few hundred points. They do look like true duplicates but created at different datetime values, same location_timestamp values in milliseconds.  This is from a different instance than in my screenshots above but all the same example in every way, "features" : [ { "attributes" : { "objectid" : 780399, "location_timestamp" : 1592092364993, "created_user" : "x", "created_date" : 1592092528672, "globalid" : "e8344433-d21e-469e-aa92-59c99df1ae56" }, "geometry" : { "x" : -80.821906594999973, "y" : 25.762405908000066 } }, { "attributes" : { "objectid" : 781743, "location_timestamp" : 1592092364993, "created_user" : "x", "created_date" : 1592093778509, "globalid" : "e0e22585-ae08-4406-81cb-243e36fcb829" }, "geometry" : { "x" : -80.821906594999973, "y" : 25.762405908000066 } } ]‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍‍ I also have a post-processing step that identifies discrepancies after I have moved points from the ESRI tracker service to another hosted feature service that creates local feature classes from the json result of queries against both services.  Once they are FC's I run a selectByLocation for identical features as well as using Find Identical GP tool. When I run the Find Identical GP tool on the ESRI Tracker service results, they are definitely identical in every way except for the Created_date values. ... View more

Hopefully this will do, I can get you the globalid's and service url if needed too.  Bascially, you see there are 2 tracks on top of each other, identical location_timestamp and username, all of the same attributes altogether (except for OID and GlobalID).  The difference is the created_date, which seems to show that they were created at later datetimes. The takeaway is that location_timestamp and username is exactly the same.  I couldn't fit the full popup so just pay attention to the (1 of 2).  Here are 2 images of point 1: Here's the second point: ... View more

Yep, will find some of those instances for asap. Thanks again! j ... View more

There is one other item that I cannot understand: Why are there some duplicate ESRI Track points? I can see that in those after-the-fact times created_date is after the location_timestamp, there may be instances of the same point even though it was created around the location_timestamp.  The location_timestamp values are exactly the same. (edit: it's not a huge issue and I can identify/account for these pretty easily in my post processing tools, but would be good to fully understand.) j ... View more

Good stuff  Thanks a bunch! ... View more

Aaron -- one last question on this as I've got it worked out to post-process tracks that are created after the location_timestamp that my initial processing misses.... How much later in the future could a Created_date value actually be? I guess I really just need to know if that is more than a 24 hours / 1 calendar day.  This would really help me to solidify recapturing those missed points. Thanks for any info! Take care, j ... View more

Thank you for the quick reply Aaron! It does sound like my assessment is somewhat correct and point features can be uploaded/added at a much later (hours) time, not necessarily in succession.   We are processing the tracks each hour, enriching them with some other attributes and copying them into another destination feature service that has a similar schema to the tracker service.  This is essentially what occurs at the top of each hour: To identify "new" track features, query the destination feature service to get the most recent feature location_timestamp value for a particular username. Query parameters include: orderByFields': 'location_timestamp DESC',  'resultRecordCount' : '1' With that location_timestamp value, query the ESRI Tracker service to see if there are any feature >= that value, if so then execute the process on those features. As you can see, if new point features were created in the ESRI tracker service after the process had executed then subsequent executions would not pickup those in the past. I'll have to implement a secondary post-processing that identifies these "missed" tracks that were created after the location_timestamp values and pull them into the destination feature service. Take care, j ... View more