Using hardware profiles of hardware components to determine performance issues of user devices
Systems and methods are described for providing recommendations for a user experience in online meetings. A recommendation engine can aggregate data from user devices to make recommendations before, during and after online meetings. Before a meeting, the recommendation engine can recommend which of a user's devices to use for the meeting. During the meeting, the recommendation engine can identify current or anticipated issues and recommend changes the user can make to correct or prevent the issue. After meetings, the recommendation engine can aggregate data and identify an ongoing issue for one or multiple users. The recommendation engine can identify the cause of the issue and make recommendations to the user or an administrator accordingly.
1. A method for providing organizational hardware and software recommendations, comprising:
aggregating performance data from a plurality of user devices associated with an organization;
identifying, based on the performance data, an issue experienced by a portion of user devices in the plurality of user devices at a rate above a threshold rate;
identifying a hardware component associated with a percentage of the plurality of user devices above a threshold percentage;
extracting data points from the performance data related to the hardware component;
inputting the extracted data points into a first machine learning (“ML”) model;
receiving, as output from the first ML model, a hardware profile of the hardware component in relation to the issue, the hardware profile indicating measured performance levels of the hardware component in comparison to expected performance levels;
determining, based on the hardware profile, that the hardware component is the cause of the issue;
identifying, from a list of approved hardware, a hardware option that may fix the issue; and
providing a recommendation identifying the hardware option as a potential fix to the issue, wherein:
the issue is identified by inputting the performance data into a second ML model that learns issue trends and outputs an issue profile of the issue,
the issue profile is inputted into the first ML model with the extracted data points, and
the hardware option is identified by inputting the hardware profile into a third ML model that outputs the recommendation.
2. The method of claim 1 , further comprising automatically purchasing the hardware component from a third party based on a set of rules.
3. The method of claim 1 , wherein the hardware component is a first user device model, and wherein the identifying the hardware option that can fix the issue includes identifying a second user device model.
4. The method of claim 1 , wherein the first ML model cross-references the issue profile and extracted data points with third-party data to identify known issues with the hardware component related to the cause.
5. The method of claim 1 , wherein the hardware component is a component of a network, and the recommended hardware option is a replacement network component.
6. The method of claim 1 , wherein the recommended hardware option includes a peripheral device that can be connected to the portion of user devices in the plurality of user devices.
7. A non-transitory, computer-readable medium containing instructions that, when executed by a hardware-based processor, cause the processor to perform stages for providing organizational hardware and software recommendations, the stages comprising:
aggregating performance data from a plurality of user devices associated with an organization;
identifying, based on the performance data, an issue experienced by a portion of user devices in the plurality of user devices at a rate above a threshold rate;
identifying a hardware component associated with a percentage of the plurality of user devices above a threshold percentage;
extracting data points from the performance data related to the hardware component;
inputting the extracted data points into a first machine learning (“ML”) model;
receiving, as output from the first ML model, a hardware profile of the hardware component in relation to the issue, the hardware profile indicating measured performance levels of the hardware component in comparison to expected performance levels;
determining, based on the hardware profile, that the hardware component is the cause of the issue;
identifying, from a list of approved hardware, a hardware option that may fix the issue; and
providing a recommendation identifying the hardware option as a potential fix to the issue, wherein:
the issue is identified by inputting the performance data into a second ML model that learns issue trends and outputs an issue profile of the issue,
the issue profile is inputted into the first ML model with the extracted data points, and
the hardware option is identified by inputting the hardware profile into a third ML model that outputs the recommendation.
8. The non-transitory, computer-readable medium of claim 7 , the stages further comprising automatically purchasing the hardware component from a third party based on a set of rules.
9. The non-transitory, computer-readable medium of claim 7 , wherein the hardware component is a first user device model, and wherein the identifying the hardware option that can fix the issue includes identifying a second user device model.
10. The non-transitory, computer-readable medium of claim 7 , wherein the first ML model cross-references the issue profile and extracted data points with third-party data to identify known issues with the hardware component related to the cause.
11. The non-transitory, computer-readable medium of claim 7 , wherein the hardware component is a component of a network, and the hardware option is a replacement network component.
12. The non-transitory, computer-readable medium of claim 7 , wherein the recommended hardware option includes a peripheral device that can be connected to the portion of user devices in the plurality of user devices.
13. A system for providing organizational hardware and software recommendations, comprising:
a memory storage including a non-transitory, computer-readable medium comprising instructions; and
a hardware-based processor that executes the instructions to carry out stages comprising:
aggregating performance data from a plurality of user devices associated with an organization;
aggregating performance data from a plurality of user devices associated with an organization;
identifying, based on the performance data, an issue experienced by a portion of user devices in the plurality of user devices at a rate above a threshold rate;
identifying a hardware component associated with a percentage of the plurality of user devices above a threshold percentage;
extracting data points from the performance data related to the hardware component;
inputting the extracted data points into a first machine learning (“ML”) model;
receiving, as output from the first ML model, a hardware profile of the hardware component in relation to the issue, the hardware profile indicating measured performance levels of the hardware component in comparison to expected performance levels;
determining, based on the hardware profile, that the hardware component is the cause of the issue;
identifying, from a list of approved hardware, a hardware option that may fix the issue; and
providing a recommendation identifying the hardware option as a potential fix to the issue, wherein:
the issue is identified by inputting the performance data into a second ML model that learns issue trends and outputs an issue profile of the issue,
the issue profile is inputted into the first ML model with the extracted data points, and
the hardware option is identified by inputting the hardware profile into a third ML model that outputs the recommendation.
14. The system of claim 13 , the stages further comprising automatically purchasing the hardware component from a third party based on a set of rules.
15. The system of claim 13 , wherein the hardware component is a first user device model, and wherein the identifying the hardware option that can fix the issue includes identifying a second user device model.
16. The system of claim 13 , wherein the first ML model cross-references the issue profile and extracted data points with third-party data to identify known issues with the hardware component related to the cause.
17. The system of claim 13 , wherein the hardware component is a component of a network, and the hardware option is a replacement network component.