3D printer device management using machine learning
Systems and methods for 3D printer management can allow or reject printing of an object based on a model that is trained with machine learning. In one example, the model classifies the object according to object type. The object type can be compared against a list, such as a whitelist or blacklist, to determine whether to block the object from printing. The lists can be specific to users, such as based on an organizational group to which the user belongs. A print server can apply the model prior to forwarding the object to a 3D printer for printing. Both the models and the lists can evolve based on machine learning, such as based on which print decisions receive override from administrators.
1. A method for 3D printer management, comprising:
receiving, at a print server from a user device, a request to print an object at a 3D printer;
applying a model to the object to determine a classification, wherein the model is trained by machine learning and the classification is based on shape information of the object;
determining whether to allow the request by comparing the classification against a list,
wherein the list is one of multiple lists received at the print server from a management server, the multiple lists corresponding to different enterprise groups;
wherein the list is automatically selected for comparison based on the user device belonging to a first group of the different enterprise groups;
wherein the list is a whitelist or a blacklist; and
in an instance where the request is allowed, printing the object at the 3D printer,
wherein the classification represents an object type, wherein the whitelist includes allowed object types, and wherein the blacklist includes disallowed object types.
2. The method of claim 1 , wherein the list is the whitelist and corresponds to an organizational group of an enterprise, the user device being associated with that organizational group, wherein different organizational groups have different whitelists.
3. The method of claim 1 , wherein the list is the blacklist and is received at the print server from the management server.
4. The method of claim 1 , wherein the model identifies similarity to a design patent, and wherein the list is the blacklist that disallows matching design patents.
5. The method of claim 1 , wherein the model includes a first model for identifying object types and a second model for identifying similarity to design patents.
6. The method of claim 1 , further comprising, in an instance where the request is denied, sending an alert to an administrator that identifies the classification of the object.
7. A non-transitory, computer-readable medium comprising instructions that are executed by a processor to perform stages for 3D printer management, the stages comprising:
receiving, at a print server from a user device, a request to print an object at a 3D printer;
applying a model to the object to determine a classification, wherein the model is trained by machine learning and the classification is based on shape information of the object;
determining whether to allow the request by comparing the classification against a list, wherein the list is one of multiple lists received at the print server from a management server, the multiple lists corresponding to different enterprise groups;
wherein the list is automatically selected for comparison based on the user device belonging to a first group of the different enterprise groups;
wherein the list is a whitelist or a blacklist; and
in an instance where the request is allowed, printing the object at the 3D printer,
wherein the classification represents an object type, wherein the whitelist includes allowed object types, and wherein the blacklist includes disallowed object types.
8. The non-transitory, computer-readable medium of claim 7 , wherein the list is the whitelist and corresponds to an organizational group of an enterprise, the user device being associated with that organizational group, wherein different organizational groups have different whitelists.
9. The non-transitory, computer-readable medium of claim 7 , wherein the list is the blacklist and is received at the print server from the management server.
10. The non-transitory, computer-readable medium of claim 7 , wherein the model identifies similarity to a design patent, and wherein the list is the blacklist and disallows matching design patents.
11. The non-transitory, computer-readable medium of claim 7 , wherein the model includes a first model for identifying object types and a second model for identifying similarity to design patents.
12. The non-transitory, computer-readable medium of claim 7 , the stages further comprising, in an instance where the request is denied, sending an alert to an administrator that identifies the classification of the object.
13. A system for 3D printer management, comprising:
a non-transitory, computer-readable medium containing instructions; and
a processor that executes the instructions to perform stages comprising:
receiving, at a print server from a user device, a request to print an object at a 3D printer;
applying a model to the object to determine a classification, wherein the model is trained by machine learning and the classification is based on shape information of the object;
determining whether to allow the request by comparing the classification against a list, wherein the list is one of multiple lists received at the print server from a management server, the multiple lists corresponding to different enterprise groups;
wherein the list is automatically selected for comparison based on the user device belonging to a first group of the different enterprise groups;
wherein the list is a whitelist or a blacklist; and
in an instance where the request is allowed, printing the object at the 3D printer,
wherein the classification represents an object type, wherein the whitelist includes allowed object types, and wherein the blacklist includes disallowed object types.
14. The system of claim 13 , wherein the list is the whitelist and corresponds to an organizational group of an enterprise, the user device being associated with that organizational group, wherein different organizational groups have different whitelists.
15. The system of claim 13 , wherein the list is the blacklist and is received at the print server from the management server.
16. The system of claim 13 , wherein the model identifies similarity to a design patent, and wherein the list is the blacklist and disallows matching design patents.
17. The system of claim 13 , wherein the model includes a first model for identifying object types and a second model for identifying similarity to design patents.