Logging information describing a type of event occurring in a mobile application received via an SDK incorporated into mobile application code of the mobile application

Patent metadata

Field	Value
Publication number	US-11853371-B1
Application number	US-201816050951-A
Country	US
Kind code	B1
Filing date	Jul 31, 2018
Priority date	Jul 31, 2018
Publication date	Dec 26, 2023
Grant date	Dec 26, 2023

Abstract

An online system receives information including a description of an event occurring in a mobile application and user identifying information associated with a user of the mobile application associated with the event via an SDK incorporated into the mobile application code of the mobile application. The online system determines whether the description corresponds to information maintained in the online system describing types of events capable of occurring in the mobile application. If the description corresponds to information describing a type of event capable of occurring in the mobile application, the online system logs the type of event in association with the user identifying information. Otherwise, the online system predicts a type of event corresponding to the event occurring in the mobile application based at least in part on the information received at the online system and logs the predicted type of event in association with the user identifying information.

First claim

What is claimed is:

1. A method comprising:
accessing, at an online system, an event datastore describing one or more types of events occurring in one or more mobile applications, the event datastore including at least first text describing a first type of event in the one or more types of events;
receiving, at the online system, a set of information comprising a description of an event occurring in a mobile application and user identifying information associated with a user of the mobile application associated with the event, the set of information received via a software development kit (SDK) incorporated into mobile application code of the mobile application, wherein the description of the event occurring in the mobile application includes second text describing a type of the event that is different from the first text;
extracting a set of keywords from the set of information for the event, the set of keywords including at least keywords extracted from the second text;
determining whether the description of the event corresponds to information maintained in the online system describing the one or more types of events;
responsive to determining that the description of the event does not correspond to information maintained in the online system describing any of the one or more types of events, predicting an event type corresponding to the event occurring in the mobile application by applying a machine-learning model or a set of rules to at least the extracted set of keywords for the event, the predicted event type indicating that the event is of the first type; and
logging, in the event datastore, the event as the first type of event in association with the user identifying information associated with the user of the mobile application.

2. The method of claim 1 , wherein the set of information includes one or more of metadata and contextual information associated with the event occurring in the mobile application, wherein the event is logged in conjunction with the one or more of the metadata and the contextual information associated with the event occurring in the mobile application.

3. The method of claim 2 , wherein the contextual information comprises one or more selected from a group consisting of: a time at which the event occurred, an identifier associated with the mobile application, information describing a geographic location of a client device used by the user to access the mobile application at the time that the event occurred, a deep link used by the user to launch the mobile application, and any combination thereof.

4. The method of claim 1 , further comprising:
training the machine-learning model based at least in part on a set of training data comprising information describing a plurality of events that previously occurred in one or more mobile applications, metadata associated with the plurality of events, contextual information associated with the plurality of events, and a label identifying a type of event associated with each of the plurality of events.

5. The method of claim 4 , wherein the set of training data comprises a training set of keywords extracted from one or more of: the information describing the plurality of events that previously occurred in the one or more mobile applications, the metadata associated with the plurality of events, and the contextual information associated with the plurality of events.

6. The method of claim 5 , wherein the training set of keywords are extracted based at least in part on a term frequency-inverse document frequency weighting scheme applied to one or more of: the information describing the plurality of events that previously occurred in the one or more mobile applications, the metadata associated with the plurality of events, and the contextual information associated with the plurality of events.

7. The method of claim 1 , further comprising:
extracting a second set of keywords from data associated with a plurality of events that previously occurred in one or more mobile applications based at least in part on a term frequency-inverse document frequency weighting scheme; and
generating the set of rules mapping one or more subsets of the set of keywords to the one or more types of events.

8. The method of claim 7 , wherein predicting the type of event corresponding to the event occurring in the mobile application is further based at least in part on the set of rules.

9. The method of claim 1 , wherein the second text in the set of information received at the online system comprises natural language text.

10. The method of claim 9 , further comprising:
processing the set of information received at the online system using a natural language processing technique.

11. The method of claim 1 , wherein the one or more types of events capable of occurring in the mobile application are selected from the group consisting of: completing a registration process, subscribing to a membership, subscribing to a service, purchasing a good, purchasing a service, adding payment information, initiating a checkout, using a credit, reserving a good, reserving a service, and any combination thereof.

12. A computer program product comprising a computer readable storage medium having instructions encoded thereon that, when executed by a processor, cause the processor to:
access, at an online system, an event datastore describing one or more types of events occurring in one or more mobile applications, the event datastore including at least first text describing a first type of event in the one or more types of events;
receive, at the online system, a set of information comprising a description of an event occurring in a mobile application and user identifying information associated with a user of the mobile application associated with the event, the set of information received via software development kit (SDK) incorporated into mobile application code of the mobile application, wherein the description of the event occurring in the mobile application includes second text describing a type of the event that is different from the first text;
extract a set of keywords from the set of information for the event, the set of keywords including at least keywords extracted from the second text;
determine whether the description of the event corresponds to information maintained in the online system describing one or more types of events;
responsive to determining that the description of the event does not correspond to information maintained in the online system describing any of the one or more types of events, predict an event type corresponding to the event occurring in the mobile application by applying a machine-learning model or a set of rules to at least the extracted set of keywords for the event, the predicted event type indicating that the event is of the first type; and
log, in the event datastore, the event as the first type of event in association with the user identifying information associated with the user of the mobile application.

13. The computer program product of claim 12 , wherein the set of information includes one or more of metadata and contextual information associated with the event occurring in the mobile application, wherein the event is logged in conjunction with the one or more of the metadata and the contextual information associated with the event occurring in the mobile application.

14. The computer program product of claim 13 , wherein the contextual information comprises one or more selected from a group consisting of: a time at which the event occurred, an identifier associated with the mobile application, information describing a geographic location of a client de

Assignees

• Meta Platforms Inc

Inventors

• Zhou Li
• Xu Liang

Classifications

• G06F16/9535 Primary

  Search customisation based on user profiles and personalisation · CPC title

• G06F16/907

  Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually · CPC title

• G06F16/90332

  Natural language query formulation or dialogue systems · CPC title

• G06F16/9558

  Details of hyperlinks; Management of linked annotations · CPC title

• G06F40/20

  Natural language analysis (semantic analysis of natural language G06F40/30) · CPC title