Classifying real-world points of interest in a parallel virtual world
A machine learning model classifies points of interest in a parallel reality game hosted by a server. The server generates training data sets that include verified properties for points of interest. The machine learning model may predict unverified properties for points of interest. Players in the parallel reality game may input properties for the points of interest. The machine learning model use the received properties from players as inputs to the machine learning model to verify unverified properties or generate new properties for the points of interest. The server may classify the points of interest as suitable for particular activities, and the server may use the classifications for future activities within the parallel reality game.
1. A non-transitory computer readable storage medium comprising stored instructions for classifying a point of interest that, when executed, cause a computing system to perform operations comprising:
receiving an identification of a point of interest from a client device;
retrieving properties for the point of interest, the properties including a verified property and an unverified property, wherein the properties were generated by a process including:
obtaining training data sets for classifying points of interest;
training a machine-learning point of interest classification model, using the training data sets, to generate properties for points of interest; and
using the machine-learning point of interest classification model to generate the properties;
generating a properties input interface to be displayed on the client device, wherein the properties input interface comprises displaying a prompt requesting a user to verify the unverified property;
receiving a verification of the unverified property from the client device, the verification having been provided via the properties input interface in response to the prompt; and
updating the properties for the point of interest based on receiving the verification of the unverified property.
2. The non-transitory computer readable storage medium of claim 1 , wherein the training data sets comprise a plurality of points of interest and a plurality of verified properties for the plurality of points of interest.
3. The non-transitory computer readable storage medium of claim 1 , wherein the identification of a point of interest is determined based on a geographic location of the client device.
4. The non-transitory computer readable storage medium of claim 1 , wherein the properties for the point of interest comprise at least one verified property and at least one unverified property.
5. The non-transitory computer readable storage medium of claim 1 , wherein the properties input interface comprises at least one unverified property.
6. The non-transitory computer readable storage medium of claim 1 , wherein the instructions further cause the computing system to input the received selection of properties to the machine-learning point of interest classification model.
7. The non-transitory computer readable storage medium of claim 1 , wherein the instructions further cause the computing system to place a virtual object at the point of interest based on the updated properties for the point of interest.
8. A method for classifying a point of interest comprising:
receiving an identification of a point of interest from a client device;
retrieving properties for the point of interest, the properties including a verified property and an unverified property, wherein the properties were generated by a process including:
obtaining training data sets for classifying points of interest;
training a machine-learning point of interest classification model, using the training data sets, to generate properties for points on interest; and
using the machine-learning point of interest classification model to generate the properties;
generating a properties input interface to be displayed on the client device, wherein the properties input interface comprises displaying a prompt requesting a user to verify the unverified property;
receiving a verification of the unverified property from the client device the verification having been provided via the properties input interface in response to the prompt; and
updating the properties for the point of interest based on receiving the verification of the unverified property.
9. The method of claim 8 , wherein the training data sets comprise a plurality of points of interest and a plurality of verified properties for the plurality of points of interest.
10. The method of claim 8 , wherein the identification of a point of interest is determined based on a geographic location of the client device.
11. The method of claim 8 , wherein the properties for the point of interest comprise at least one verified property and at least one unverified property.
12. The method of claim 8 , wherein the properties input interface comprises at least one unverified property.
13. The method of claim 8 , further comprising inputting the received selection of properties to the machine-learning point of interest classification model.
14. The method of claim 8 , further comprising placing a virtual object at the point of interest based on the updated properties for the point of interest.
15. A system comprising:
memory with instructions encoded thereon; and
one or more processors that, when executing the instructions, are caused to perform operations comprising:
receiving an identification of a point of interest from a client device;
retrieving properties for the point of interest, the properties including a verified property and an unverified property, wherein the properties were generated by a process including:
obtaining training data sets for classifying points of interest;
training a machine-learning point of interest classification model, using the training data sets, to generate properties for points on interest; and
using the machine-learning point of interest classification model to generate the properties;
generating a properties input interface to be displayed on the client device, wherein the properties input interface comprises displaying a prompt requesting a user to verify the unverified property;
receiving a verification of the unverified property from the client device the verification having been provided via the properties input interface in response to the prompt; and
updating the properties for the point of interest based on receiving the verification of the unverified property.
16. The system of claim 15 , wherein the training data sets comprise a plurality of points of interest and a plurality of verified properties for the plurality of points of interest.
17. The system of claim 15 , wherein the identification of a point of interest is determined based on a geographic location of the client device.
18. The system of claim 15 , wherein the properties for the point of interest comprise at least one verified property and at least one unverified property.
19. The system of claim 15 , wherein the properties input interface comprises at least one unverified property.
20. The system of claim 15 , further comprising inputting the received selection of properties to the machine-learning point of interest classification model.