MULTI-CLIENT SERVICE SYSTEM PLATFORM
A modular machine learning-as-a-service (MLAAS) system uses machine learning to respond to tasks without requiring machine learning modeling or design knowledge by its users. The MLAAS system receives an inference request including a model identifier and a target defining features for use in processing the inference request. The features correspond to a task for evaluation using a machine learning model associated with the model identifier. An inference outcome is generated by processing the inference request using the target as input to the model. Feedback indicating an accuracy of the inference outcome with respect to the task is later received and used to generate a training data set, which the MLAAS can use to further train model used to generate the inference outcome. As a result, the training of a machine learning model by the MLAAS system is limited to using data resulting from an inference performed using that model.
1 . A method, comprising:
receiving an inference request from a client, wherein the inference request specifies a task to be performed by a machine learning model associated with the task;
identifying features to input into the machine learning model based upon based upon the inference request;
generating an inference outcome by executing the machine learning model to process the features; and
constructing an inference response to the inference request based upon the inference outcome; and
providing the inference response to the client as a response to the inference request.
2 . The method of claim 1 , comprising:
determining that the task relates to an email task to be performed by the client, wherein the inference response includes a suggested instruction for performing the email task.
3 . The method of claim 1 , wherein the inference request comprises a question asked by the client through the inference request, and wherein the inference response comprises an answer generated by the machine learning model to the question.
4 . The method of claim 1 , wherein the client comprises a client system, and wherein the inference request is received as an application programming interface (API) call through an API framework of a machine learning-as-a-service system hosting the machine learning model.
5 . The method of claim 1 , comprising:
generating a set of candidate inference outcomes using a plurality of machine learning models including the machine learning model, wherein a candidate inference outcome is selected from the set of candidate inference outcomes as the inference outcome for constructing the inference response.
6 . The method of claim 1 , wherein the inference response includes a suggested instruction comprising information of a contact stored within a database.
7 . The method of claim 1 , comprising:
constructing the inference response to include a marketing decision suggestion for the client to use in making a marketing decision.
8 . The method of claim 1 , comprising:
extracting a model identifier and a target feature from the inference request for use in processing the inference request.
9 . The method of claim 1 , wherein the client is a service provider hosting a software product accessible to users.
10 . The method of claim 1 , wherein the client is a service provider of a customer relationship management system.
11 . A non-transitory machine readable medium comprising instructions, which when executed by a machine, causes the machine to perform operations including:
receiving an inference request from a client, wherein the inference request specifies a task to be performed by a machine learning model associated with the task;
identifying features to input into the machine learning model based upon based upon the inference request;
generating an inference outcome by executing the machine learning model to process the features; and
constructing an inference response to the inference request based upon the inference outcome; and
providing the inference response to the client as a response to the inference request.
12 . The non-transitory machine readable medium of claim 11 , wherein the inference response includes a prediction provided to the client.
13 . The non-transitory machine readable medium of claim 11 , wherein the inference response includes a classification provided to the client.
14 . The non-transitory machine readable medium of claim 11 , wherein the inference response includes a recommendation provided to the client.
15 . The non-transitory machine readable medium of claim 11 , wherein the inference request comprises a version identifier indicating a version of the machine learning model to utilize.
16 . A computing device comprising:
a memory comprising instructions; and
a processor coupled to the memory, the processor configured to execute the instructions to perform operations including:
receiving an inference request from a client, wherein the inference request specifies a task to be performed by a machine learning model associated with the task;
identifying features to input into the machine learning model based upon based upon the inference request;
generating an inference outcome by executing the machine learning model to process the features; and
constructing an inference response to the inference request based upon the inference outcome; and
providing the inference response to the client as a response to the inference request.
17 . The computing device of claim 16 , the operations including:
determining that the task relates to an email task to be performed by the client, wherein the inference response includes a suggested instruction for performing the email task.
18 . The computing device of claim 16 , wherein the inference request comprises a question, and wherein the inference response comprises an answer to the question.
19 . The computing device of claim 16 , wherein the client comprises a client system, and wherein the inference request is received as an application programming interface (API) call through an API framework of a machine learning-as-a-service system hosting the machine learning model.
20 . The computing device of claim 16 , the operations including:
generating a set of candidate inference outcomes using a plurality of machine learning models including the machine learning model, wherein a candidate inference outcome is selected from the set of candidate inference outcomes as the inference outcome for constructing the inference response.