Secret sharing data exchange for generating a data processing model

A non-transitory, computer-readable medium storing one or more instructions executable by a computer system to perform operations comprising:

• determining, by a first data party device, respective values of first coefficients based on a first share of service data, wherein the first coefficients are corresponding coefficients of respective target variables in different terms of a polynomial expression, and the target variables are variables that are in the polynomial expression and associated with the first share of the service data;
• determining, by a second data party device, respective values of second coefficients based on a second share of the service data, wherein the second coefficients comprise coefficients of the target variables other than the first coefficients in the different terms of the polynomial expression, wherein the first coefficients are expressed in terms of multiple orders of the second coefficients and the second coefficients are expressed in terms of multiple orders of the first coefficients;
• secretly sharing, by the first data party device, respective values of the different terms in the polynomial expression in parallel based on the respective values of the first coefficients, and secretly sharing, by the second data party, the respective values of the different terms in the polynomial expression in parallel based on the respective values of the second coefficients, so that the first data party obtains first shares of the respective values of the different terms, and the second data party obtains second shares of the respective values of the different terms;
• determining, by the first data party device a first share of a value of the polynomial expression based on the first shares of the respective values of the different terms;
• and
• determining, by the second data party device, a second share of the value of the polynomial expression based on the second shares of the respective values of the different terms
• determining by at least one of the first party device or the second party device, the value of the polynomial expression based on the first share of the value of the polynomial expression and the second share of the value of the polynomial expression;
• and
• constructing a machine learning model by fitting an activation function of the machine learning model using the value of the polynomial expression.

A computer-implemented system, comprising:

• one or more computers;
• and
• one or more computer memory devices interoperably coupled with the one or more computers and having tangible, non-transitory, machine-readable media storing one or more instructions that, when executed by the one or more computers, perform operations comprising:
• determining, by a first data party device, respective values of first coefficients based on a first share of service data, wherein the first coefficients are corresponding coefficients of respective target variables in different terms of a polynomial expression, and the target variables are variables that are in the polynomial expression and associated with the first share of the service data;
• determining, by a second data party device, respective values of second coefficients based on a second share of the service data, wherein the second coefficients comprise coefficients of the target variables other than the first coefficients in the different terms of the polynomial expression, wherein the first coefficients are expressed in terms of multiple orders of the second coefficients and the second coefficients are expressed in terms of multiple orders of the first coefficients;
• secretly sharing, by the first data party device, respective values of the different terms in the polynomial expression in parallel based on the respective values of the first coefficients, and secretly sharing, by the second data party, the respective values of the different terms in the polynomial expression in parallel based on the respective values of the second coefficients, so that the first data party obtains first shares of the respective values of the different terms, and the second data party obtains second shares of the respective values of the different terms;
• determining, by the first data party device a first share of a value of the polynomial expression based on the first shares of the respective values of the different terms;
• and
• determining, by the second data party device, a second share of the value of the polynomial expression based on the second shares of the respective values of the different terms
• determining by at least one of the first party device or the second party device, the value of the polynomial expression based on the first share of the value of the polynomial expression and the second share of the value of the polynomial expression;
• and
• constructing a machine learning model by fitting an activation function of the machine learning model using the value of the polynomial expression.