Group identification and action

• US 10,244,355 B1
• Filed: 06/21/2018
• Issued: 03/26/2019
• Est. Priority Date: 06/21/2018
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: DeLuca, Lisa Seacat, Greenberger, Jeremy A.
• Primary Examiner(s): Ly, Nghi H
• Application Number:
  US16/014,344
• Time in Patent Office: 278 Days
• Field of Search: 4554563, 4554561, 4554042, 4554321, 4554221
• CPC Class Codes: G06Q 30/0641 Shopping interfaces
• CPC Class Codes: H04L 51/216 Handling conversation history, e.g. grouping of messages in sessions or threads
• CPC Class Codes: H04L 51/222 using geographical location information, e.g. messages transmitted or received in proximity of a certain spot or area
• CPC Class Codes: H04L 51/224 providing notification on incoming messages, e.g. pushed notifications of received messages
• CPC Class Codes: H04L 51/52 for supporting social networking services
• CPC Class Codes: H04W 4/023 using mutual or relative location information between multiple location based services [LBS] targets or of distance thresholds
• CPC Class Codes: H04W 4/14 Short messaging services, e.g. short message services [SMS] or unstructured supplementary service data [USSD]

Abstract

Methods, computer program products, and systems are presented. The method computer program products, and systems can include, for instance: examining data of a plurality of traveling users, wherein at least some of the plurality of traveling users have associated mobile client computer devices, and determining, by machine logic, based on the examining that certain traveling users of the plurality of traveling users are traveling in a group; deciding, by machine logic, based on the determining that one or more action is to be performed, wherein the deciding is in dependence on a processing of historical data, the historical data specifying activities of the certain traveling users when the certain traveling users travel in a group; and providing one or more output for performance of the one or more action.

Claims

1. A computer implemented method comprising:

examining data of a plurality of traveling users, wherein at least some of the plurality of traveling users have associated mobile client computer devices, and determining based on the examining that certain traveling users of the plurality of traveling users are traveling in a group;

deciding, based on the determining that one or more action is to be performed, wherein the deciding is in dependence on a processing of historical data, the historical data specifying activities of the certain traveling users when the certain traveling users travel in a group; and

providing one or more output for performance of the one or more action, wherein the examining data of a plurality of traveling users includes examining location data of users of the plurality of traveling users, wherein determining based on the examining that certain traveling users of the plurality of traveling users are traveling in a group includes examining a history of locations of the certain traveling users over time, wherein the determining includes classifying the group as belonging to a previously registered general group classification of traveling users, wherein the determining, based on the examining that certain traveling users of the plurality of traveling users are traveling in a group includes classifying the certain traveling users as belonging to a specific group of traveling users, wherein the deciding, based on the determining that one or more action is to be performed includes using a decision data structure that cognitively maps a group classifier to one or more action decision associated to the group classifier.

2. The computer implemented method of claim 1, wherein the processing of historical data includes processing of product purchase historical data of the certain traveling users when the certain traveling users travel in a group, and wherein the method includes classifying the certain traveling users as belonging to a previously registered specific group classification of traveling users having a previously recorded associated specific group ID, and wherein the deciding includes using a decision data structure that cognitively maps one or more action specifier to the specific group ID, wherein the one or more action specifier specifies an action to automatically order a favorite product of a user of the previously registered specific group classification.

3. The computer implemented method of claim 1, wherein the method includes classifying the certain traveling users as belonging to a previously registered specific group classification of traveling users having a previously recorded associated specific group ID, and wherein the deciding includes using a decision data structure that cognitively maps one or more action specifier to the specific group ID, wherein the one or more action specifier specifies an action to automatically order a favorite product of a user of the previously registered specific group classification, wherein the processing of historical data includes processing of product purchase historical data of the certain traveling users when the certain traveling users travel in a group, and wherein the one or more action includes automatically ordering for pickup a favorite product of one or more user of the certain traveling users as determined by the processing of product purchase historical data of the certain traveling users when the certain traveling users travel in a group.

4. The computer implemented method of claim 1, wherein the method includes recognizing that a certain user defining the certain traveling users traveling in a group has become separated from the certain traveling users traveling in a group, and accordingly further recognizing that there are particular traveling users of the plurality of traveling users traveling in a group, the particular traveling users having one or more user in common with the certain traveling users but being differentiated from the certain traveling users by being absent of the certain user, wherein the method includes further deciding, based on the recognizing that one or more changed action is to be performed, wherein the further deciding is in dependence on a processing of historical data, the historical data specifying activities of the particular traveling users when the particular traveling users travel in a group, wherein the one or more changed action includes at least one change relative to the one or more action, and wherein method includes providing one or more output for performance of the one or more changed action.

5. The computer implemented method of claim 1, wherein the method includes classifying the certain traveling users as belonging to a previously registered specific group of traveling users having a previously recorded associated specific group ID, wherein the deciding includes using a decision data structure that cognitively maps one or more action specifier to the specific group ID, and wherein the specified action is determined using a machine learning trained predictive model that is iteratively trained using training data, the predictive model predicting purchases made by respective first and second users associated to the specific group ID.

6. The computer implemented method of claim 1, wherein the method includes classifying the certain traveling users as belonging to a previously registered specific group of traveling users having a previously recorded associated specific group ID, wherein the deciding includes using a decision data structure that cognitively maps one or more action specifier to the specific group ID, and wherein the specified action is determined using a machine learning trained predictive model that is iteratively trained using training data, the predictive model predicting purchases made by respective first and second users associated to the specific group ID, wherein training data for training the predictive model includes purchase historical data of the certain traveling users when the certain traveling users travel in a group during a first instance of the certain traveling users traveling in a group, wherein training data for training the predictive model includes purchase historical data of the certain traveling users when the certain traveling users travel in a group during a second instance of the certain traveling users traveling in a group, the second instance being separated in time from the first instance.

7. The computer implemented method of claim 1, wherein the processing of historical data includes processing of product purchase historical data of the certain traveling users when the certain traveling users travel in a group, and wherein the one or more action includes automatically ordering for pickup a favorite product of one or more user of the certain traveling users as determined by the processing of product purchase historical data of the certain traveling users when the certain traveling users travel in a group.

8. The computer implemented method of claim 1, wherein the processing of historical data includes processing of product purchase historical data of the certain traveling users when the certain traveling users travel in a group, and wherein the one or more action includes (a) automatically ordering for pickup a favorite product of one or more user of the certain traveling users as determined by the processing of product purchase historical data of the certain traveling users when the certain traveling users travel in a group and (b) sending a notification to the one or more user of the certain traveling users as determined by the processing of product purchase historical data of the certain traveling users when the certain traveling users travel in a group, the notification including a text based notice that the favorite product for pickup has been order, and wherein the notification is accompanied by a user interface control that permits the one or more user to override the order for pickup.

9. The computer implemented method of claim 1, wherein the certain traveling users of the plurality of traveling determined to be traveling in a group have been previously recognized as a group of users traveling in a group during a first instance of the certain traveling users traveling in a group, and in a second instance of the certain traveling users traveling in a group, wherein the second instance is prior in time to a current instance of the certain traveling users traveling in a group in which the determining is performed, and wherein the first instance is prior in time to the second instance, wherein the processing of historical data includes processing of product purchase historical data of the certain traveling users when the certain traveling users travel in a group, and wherein the one or more action includes automatically ordering for pickup a favorite product of one or more user of the certain traveling users as determined by the processing of product purchase historical data of the certain traveling users when the certain traveling users travel in a group, wherein the processing of historical data includes processing of product purchase historical data of the certain traveling users when the certain traveling users travel in a group includes processing of historical data of each of the first instance and the second instance.

10. The computer implemented method of claim 1, wherein the method includes classifying the certain traveling users as belonging to a previously registered specific group classification of traveling users having a previously recorded associated specific group ID, and wherein the deciding includes using a decision data structure that cognitively maps one or more action specifier to the specific group ID, wherein the one or more action specifier specifies an action to automatically order a favorite product of a user of the previously registered specific group classification, wherein the examining data includes examining each of radio signal derived location data and video data obtained with use of a venue disposed camera system.

11. The computer implemented method of claim 1, wherein the method includes using image data processing to perform identification of users defining the certain traveling users.

12. The computer implemented method of claim 1, wherein the examining includes establishing a relationship graph that characterizes the certain group of traveling users, wherein the relationship graph includes nodes that specify users of the group of traveling users, wherein edges of the relationship graph specify relationships between users defining the group of traveling users, and wherein the method includes classifying the certain group of traveling users as belonging to a previously registered classification, the classifying including determining that the established relationship graph established by the establishing has characteristics in common with a previously registered relationship graph associated to the classification.

13. The computer implemented method of claim 1, wherein the deciding includes using a decision data structure that cognitively maps an action condition provided by an established relationship graph having a certain edge characteristic to an action decision specifier associated to the edge characteristic, wherein the certain traveling users include a first user, and wherein the method includes providing a user interface for use by the first user, wherein the method includes receiving entered data of the first user into the user interface specifying a second user who is remote from the first user, and in response to the receiving, logically associating the second user to the certain traveling users of the plurality of traveling users who are traveling in the group.

14. The computer implemented method of claim 1, wherein the one or more action is to perform automatically placing an order for a product for a particular user of the certain traveling users, wherein placing the order includes using a decision data structure that cognitively maps a classifier for the certain traveling users to an action specifier specifying product order placement, the product order placement specifying a favorite product and a second favorite product for the particular user, wherein the method includes examining an inventory of products at a venue, and wherein the automatically placing an order includes automatically placing an order to the second favorite product in response to the examining an inventory indicating that an inventory of the favorite product is below a threshold.

15. The computer implemented method of claim 1, wherein the examining is performed in response to a particular user of the certain traveling users breaching a geofence of a venue, and wherein the one or more action is to perform automatically placing an order for a product available from within the venue.

16. The computer implemented method of claim 1, wherein the processing historical data includes applying purchase historical data of the traveling group of users as training data by machine learning to a predictive model so that when the predictive model is trained, the predictive model predicts a favorite product of the group of traveling users.

17. A computer program product comprising:

a computer readable storage device readable by one or more processing circuit and storing instructions for execution by one or more processor for performing a method comprising;

examining data of a plurality of traveling users, wherein at least some of the plurality of traveling users have associated mobile client computer devices, and determining, based on the examining that certain traveling users of the plurality of traveling users are traveling in a group;

deciding, based on the determining that one or more action is to be performed, wherein the deciding is in dependence on a processing of historical data, the historical data specifying activities of the certain traveling users when the certain traveling users travel in a group; and

providing one or more output for performance of the one or more action, wherein the method includes recognizing that a certain user defining the certain traveling users traveling in a group has become separated from the certain traveling users traveling in a group, and accordingly further recognizing that there are particular traveling users of the plurality of traveling users traveling in a group, the particular traveling users having one or more user in common with the certain traveling users but being differentiated from the certain traveling users by being absent of the certain user, wherein the method includes further deciding, based on the recognizing that one or more changed action is to be performed, wherein the further deciding is in dependence on a processing of historical data, the historical data specifying activities of the particular traveling users when the particular traveling users travel in a group, wherein the one or more changed action includes at least one change relative to the one or more action, and wherein method includes providing one or more output for performance of the one or more changed action.

18. The computer program product of claim 17, wherein the examining data of a plurality of traveling users includes examining location data of users of the plurality of traveling users, wherein determining based on the examining that certain traveling users of the plurality of traveling users are traveling in a group includes examining a history of locations of the certain traveling users over time, wherein the determining includes classifying the group as belonging to a previously registered general group classification of traveling users, wherein the determining, based on the examining that certain traveling users of the plurality of traveling users are traveling in a group includes classifying the certain traveling users as belonging to a specific group of traveling users, wherein the deciding, based on the determining that one or more action is to be performed includes using a decision data structure that cognitively maps a group classifier to one or more action decision associated to the group classifier.

19. The computer program product of claim 17, wherein the certain traveling users of the plurality of traveling determined to be traveling in a group have been previously recognized as a group of users traveling in a group during a first instance of the certain traveling users traveling in a group, and in a second instance of the certain traveling users traveling in a group, wherein the second instance is prior in time to a current instance of the certain traveling users traveling in a group in which the determining is performed, and wherein the first instance is prior in time to the second instance, wherein the processing of historical data includes processing of product purchase historical data of the certain traveling users when the certain traveling users travel in a group, and wherein the one or more action includes automatically ordering for pickup a favorite product of one or more user of the certain traveling users as determined by the processing of product purchase historical data of the certain traveling users when the certain traveling users travel in a group, wherein the processing of historical data includes processing of product purchase historical data of the certain traveling users when the certain traveling users travel in a group includes processing of historical data of each of the first instance and the second instance, wherein the method includes classifying the certain traveling users as belonging to a previously registered specific group of traveling users having a previously recorded associated specific group ID, wherein the deciding includes using a decision data structure that cognitively maps one or more action specifier to the specific group ID, and wherein the specified action is determined using a machine learning trained predictive model that is iteratively trained using training data, the predictive model predicting purchases made by respective first and second users associated to the specific group ID, wherein training data for training the predictive model includes purchase historical data of the certain traveling users when the certain traveling users travel in a group during a first instance of the certain traveling users traveling in a group, wherein training data for training the predictive model includes purchase historical data of the certain traveling users when the certain traveling users travel in a group during a second instance of the certain traveling users traveling in a group, the second instance being separated in time from the first instance.

20. A system comprising:

a memory;

at least one processor in communication with memory; and

program instructions executable by one or more processor via the memory to perform a method comprising;

examining data of a plurality of traveling users, wherein at least some of the plurality of traveling users have associated mobile client computer devices, and determining, based on the examining that certain traveling users of the plurality of traveling users are traveling in a group;

deciding, based on the determining that one or more action is to be performed, wherein the deciding is in dependence on a processing of historical data, the historical data specifying activities of the certain traveling users when the certain traveling users travel in a group; and

providing one or more output for performance of the one or more action, wherein the processing of historical data includes processing of product purchase historical data of the certain traveling users when the certain traveling users travel in a group, and wherein the method includes classifying the certain traveling users as belonging to a previously registered specific group classification of traveling users having a previously recorded associated specific group ID, and wherein the deciding includes using a decision data structure that cognitively maps one or more action specifier to the specific group ID, wherein the one or more action specifier specifies an action to automatically order a favorite product of a user of the previously registered specific group classification.