Location-aware query transformation using weighted temporal models to derive user and region context
A system and method for transforming location-based data queries into temporal domain by leveraging a location-to-time knowledge conversion graph. In some systems which contain diverse sets of data objects, only certain objects may contain explicit location data, while others may not. Therefore, queriability of this diverse data by location properties would likely yield incomplete results. In some embodiments, this method allows for the transformation and augmentation of a given data query containing location-based filtering properties into a time-region-based lookup, wherein a given location has been assigned to a time region in the given data graph and all data events within that time region may be augmented with location metadata automatically in the knowledge graph. Over time, a system utilizing these embodiments can offer comprehensive location-based data services and insights with a diverse set of data objects that exists and not all objects contain explicit location information.
1 . A method comprising:
receiving, from a user via a user device, a first query associated with a first region;
determining a time-based query parameter associated with the first query, wherein the time-based query parameter is associated with data items generated within a first time window in which the user was located in a first location within the first region;
determining a first time model associated with the user and the first region, wherein the first time model indicates the data items that are associated with the user during the first time window, and wherein the data items include metadata indicating a corresponding time of a creation or a use of each of the data items during the first time window;
determining a priority of each of the first location and a second location within the first region, wherein the second location is associated with a second time window in which the user was located in the second location;
updating the first time model based on the first and second time windows and the priority;
determining a second time model associated with a second region and having second metadata indicating the data items further associated with the second region;
converting the first query to a second query having a location-based query parameter based on the first time model and the second time model, wherein the location-based query parameter is associated with the data item generated in association with the second region;
determining time-based metadata associated with the data items based on one of a device or a sensor associated with detecting the data items in association with the first region;
determining one of the data items that is responsive to the second query based on the location-based query parameter and the item-based metadata;
predicting the data item should be a response to the first query based on the determining the one of the data items; and
communicating the data item to the user via the user device.
2 . The method of claim 1 , wherein the data items are associated with at least one of an electronic communication, an audio content, a visual content, or a purchase of the user, and wherein the metadata comprises at least one of a timestamp or a geolocation.
3 . The method of claim 1 , further comprising:
determining an activity engaged in by the user in association with the first region,
wherein the converting is further based on the activity.
4 . The method of claim 3 , further comprising:
predicting an amount of time that the user was engaged in the activity in association with the first region based on the first time model and the second time model,
wherein the converting is further based on the amount of time.
5 . The method of claim 1 , wherein, prior to the converting the first query to the second query, the method further comprises:
resolving a conflicting portion of the first time window and a second time window.
6 . The method of claim 5 , wherein the resolving the conflicting portion comprises:
merging the first time window and the second time window during the conflicting portion based on the priority and location-based data used by the first time model and the second time model; and
removing the conflicting portion from one of the first time window or the second time window.
7 . The method of claim 5 , further comprising:
updating at least one of the first time model or the second time model based on the resolving.
8 . A system comprising:
a non-transitory memory; and
one or more hardware processors coupled to the non-transitory memory and configured to read instructions from the non-transitory memory to cause the system to perform operations comprising:
receiving, from a user via a user device, a first query associated with a first region;
determining a time-based query parameter associated with the first query, wherein the time-based query parameter is associated with data items generated within a first time window in which the user was located in a first location within the first region;
accessing a first time model associated with the user and the first region, wherein the first time model indicates the data items that are associated with the user during the first time window, and wherein the data items include metadata indicating a corresponding time of a creation or a use of each of the data items during the first time window;
determining a priority of each of the first location and a second location within the first region, wherein the second location is associated with a second time window in which the user was located in the second location;
updating the first time model based on the first and second time windows and the priority;
determining a second time model associated with a second region and having second metadata indicating the data items further associated with the second region;
converting the first query to a second query having a location-based query parameter based on the first time model and the second time model, wherein the location-based query parameter is associated with the data item generated in association with the second region;
determining time-based metadata associated with the data items based on one of a device or a sensor associated with detecting the data items in association with the first region;
determining one of the data items that is responsive to the second query based on the location-based query parameter and the item-based metadata;
predicting the data item is responsive to the first query based on the determining the one of the data items; and
communicating the data item to the user via the user device.
9 . The system of claim 8 , wherein the data items are associated with at least one of an electronic communication, an audio content, a visual content, or a purchase of the user, and wherein the metadata comprises at least one of a timestamp or a geolocation.
10 . The system of claim 8 , wherein the operations further comprise:
determining an activity engaged in by the user in association with the first region,
wherein the converting is further based on the activity.
11 . The system of claim 10 , wherein the operations further comprise:
predicting an amount of time that the user was engaged in the activity in association with the first region based on the first time model and the second time model,
wherein the converting is further based on the amount of time.
12 . The system of claim 8 , wherein, prior to the converting the first query to the second query, the operations further comprise:
resolving a conflicting portion of the first time window and the second time window.
13 . The system of claim 12 , wherein the resolving the conflicting portion comprises:
merging the first time window and the second time window during the conflicting portion based on the priority and location-based data used by the first time model and the second time model; and
removing the conflicting portion from one of the first time window or the second time window.
14 . The system of claim 12 , wherein the operations further comprise:
updating at least one of the first time model or the second time model based on the resolving.
15 . A non-transitory computer-readable medium having stored thereon instructions executable by a computer system to cause the computer system to perform operations comprising:
receiving, from a user via a user device, a first query associated with a first region;
determining a time-based query parameter associated with the first query, wherein the time-based query parameter is associated with data items generated within a first time window in which the user was located in a first location within the first region;
accessing a first time model associated with the user and the first region, wherein the first time model indicates the data items that are associated with the user during the first time window, and wherein the data items include metadata indicating a corresponding time of a creation or a use of each of the data items during the first time window;
determining a priority of each of the first location and a second location within the first region, wherein the second location is associated with a second time window in which the user was located in the second location;
updating the first time model based on the first and second time windows and the priority;
determining a second time model associated with a second region and having second metadata indicating the data items further associated with the second region;
converting the first query to a second query having a location-based query parameter based on the first time model and the second time model, wherein the location-based query parameter is associated with the data item generated in association with the second region;
determining time-based metadata associated with the data items based on one of a device or a sensor associated with detecting the data items in association with the first region;
determining one of the data items that is responsive to the second query based on the location-based query parameter and the item-based metadata;
predicting the data item is a response to the first query based on the determining the one of the data items; and
communicating the data item to the user via the user device.
16 . The non-transitory computer-readable medium of claim 15 , wherein the data items are associated with at least one of an electronic communication, an audio content, a visual content, or a purchase of the user, and wherein the metadata comprises at least one of a timestamp or a geolocation.
17 . The non-transitory computer-readable medium of claim 15 , wherein the operations further comprise:
determining an activity engaged in by the user in association with the first region,
wherein the converting is further based on the activity.
18 . The non-transitory computer-readable medium of claim 17 , wherein the operations further comprise:
predicting an amount of time that the user was engaged in the activity in association with the first region based on the first time model and the second time model,
wherein the converting is further based on the amount of time.
19 . The non-transitory computer-readable medium of claim 15 , wherein, prior to the converting the first query to the second query, the operations further comprise:
resolving a conflicting portion of the first time window and the second time window.
20 . The non-transitory computer-readable medium of claim 19 , wherein the resolving the conflicting portion comprises:
merging the first time window and the second time window during the conflicting portion based on the priority and location-based data used by the first time model and the second time model; and
removing the conflicting portion from one of the first time window or the second time window.