CN-121985787-A - Electrical parameter value determining method, device, equipment, medium and product
Abstract
The application provides a method, a device, equipment, a medium and a product for determining an electrical parameter value. The method comprises the steps of obtaining manufacturing related data of a semiconductor device and a pre-trained prediction model, inputting the manufacturing related data into the prediction model, wherein the prediction model comprises a conversion unit and a processing unit, the conversion unit is used for converting the manufacturing related data into a target vector, the processing unit is used for obtaining the target vector, extracting electrical parameter characteristics according to the target vector and mapping the electrical parameter characteristics to a spatial domain to obtain an electrical parameter image, and decoding the electrical parameter image to obtain the electrical parameter value. The efficiency of determining the value of the electrical parameter is improved, thereby improving the efficiency of measuring the quality of the product.
Inventors
- XIA MINGYANG
- ZHOU TAO
- LI CHEN
Assignees
- 上海集成电路装备材料产业创新中心有限公司
Dates
- Publication Date
- 20260505
- Application Date
- 20241030
Claims (10)
- 1. A method of determining an electrical parameter value, the method comprising: Acquiring manufacturing related data of a semiconductor device and a pre-trained prediction model; inputting the manufacturing-related data into the prediction model, wherein the prediction model comprises a conversion unit and a processing unit; the conversion unit is used for converting the manufacturing-related data into a target vector; The processing unit is used for acquiring the target vector, extracting electrical parameter characteristics according to the target vector, mapping the electrical parameter characteristics to a spatial domain to obtain an electrical parameter image, and decoding the electrical parameter image to obtain the electrical parameter value.
- 2. The method of claim 1, wherein the types of manufacturing-related data include a string type and a discrete point type, wherein the discrete point type of data has a spatial relationship; The conversion unit is specifically configured to: encoding the data of the character string type into a numerical vector; encoding the data of the discrete point location type into a complete two-dimensional image, and carrying out convolution processing on the two-dimensional image so as to flatten the two-dimensional image into a one-dimensional vector; And connecting the numerical vector and the one-dimensional vector to obtain a target vector.
- 3. The method of claim 2, wherein the discrete point type data comprises on-line manufacturing metrology data.
- 4. The method of claim 2, wherein the string-type data comprises at least one of: process recipe data, machine operation data for manufacturing the semiconductor device, and shipment record data.
- 5. The method according to claim 4, wherein the conversion unit is specifically configured to: when the data of the character string type comprises process recipe data, coding the corresponding identifier of the semiconductor device and the corresponding process recipe into a numerical vector based on the mapping relation between the semiconductor device and the corresponding process recipe of the semiconductor device; When the data of the character string type comprises machine operation data for manufacturing the semiconductor device, carrying out aggregation processing on the machine operation data according to the sensor type, and encoding the identification of the sensor type and the aggregated machine operation data into a numerical vector; when the data of the character string type comprises the goods passing record data, determining the correlation among the machine stations according to the manufacturing flow of the semiconductor device, and encoding the identification of each machine station into a numerical vector according to the correlation.
- 6. The method of claim 2, wherein the target vector comprises a plurality of channels, the channels mapped with corresponding parameter characteristics; the processing unit is specifically configured to: Determining the weight value of each channel; masking the channel with the weight value of zero, and extracting parameter characteristics based on the channel with the weight value of non-zero to obtain electrical parameter characteristics; and performing deconvolution processing based on the electrical parameter characteristics so that the electrical parameter characteristics are mapped to a spatial domain to obtain an electrical parameter image.
- 7. An electrical parameter value determining apparatus includes an acquisition module for acquiring manufacturing-related data of a semiconductor device and a pre-trained prediction model; the input module is used for inputting the manufacturing related data into the prediction model, wherein the prediction model comprises a conversion unit and a processing unit; The processing unit is used for acquiring the target vector, extracting electrical parameter characteristics according to the target vector, mapping the electrical parameter characteristics to a space domain to obtain an electrical parameter image, and decoding the electrical parameter image to obtain the electrical parameter value.
- 8. An electronic device comprising a processor and a memory communicatively coupled to the processor; the memory stores computer-executable instructions; The processor executes computer-executable instructions stored in the memory to implement the electrical parameter value determination method of any one of claims 1-6.
- 9. A computer readable storage medium, wherein computer executable instructions are stored in the computer readable storage medium, which when executed by a processor are adapted to implement the electrical parameter value determination method according to any one of claims 1-6.
- 10. A computer program product comprising a computer program which, when executed by a processor, implements the electrical parameter value determination method as claimed in any one of claims 1 to 6.
Description
Electrical parameter value determining method, device, equipment, medium and product Technical Field The present application relates to the field of semiconductor manufacturing technologies, and in particular, to a method, an apparatus, a device, a medium, and a product for determining an electrical parameter value. Background With the continuous development of semiconductor manufacturing technology and application fields, higher requirements are put on the quality of semiconductor products, and the electrical parameter value of the semiconductor product material, i.e. the wafer, needs to be determined, so that the yield and reliability of the semiconductor product can be measured according to the parameter value. Currently, when determining an electrical parameter value of a wafer, it is generally based on a semiconductor manufacturing process, and at a final stage of the wafer manufacturing, the wafer is manually tested, for example, WAT (WAFER ACCEPTANCE TEST ), and the electrical parameter value of the wafer is determined according to the test result. However, the cycle time of the semiconductor manufacturing process is generally long, and the test itself may also have a certain influence on the wafer, so that multiple tests cannot be performed on the same wafer, and the efficiency of determining the electrical parameter value is reduced, thereby reducing the efficiency of measuring the product quality. Disclosure of Invention The application provides a method, a device, equipment, a medium and a product for determining an electrical parameter value, which are used for solving the technical problem that the efficiency of determining the electrical parameter value is reduced in the prior art, so that the efficiency of measuring the quality of the product is reduced. In a first aspect, the present application provides a method for determining an electrical parameter value, comprising obtaining manufacturing-related data of a semiconductor device and a pre-trained predictive model; inputting the manufacturing-related data into the prediction model, wherein the prediction model comprises a conversion unit and a processing unit; the conversion unit is used for converting the manufacturing-related data into a target vector; The processing unit is used for acquiring the target vector, extracting electrical parameter characteristics according to the target vector, mapping the electrical parameter characteristics to a spatial domain to obtain an electrical parameter image, and decoding the electrical parameter image to obtain the electrical parameter value. In a second aspect, the present application provides an electrical parameter value determining apparatus, comprising an acquisition module for acquiring manufacturing-related data and a pre-trained prediction model of a semiconductor device; the input module is used for inputting the manufacturing related data into the prediction model, wherein the prediction model comprises a conversion unit and a processing unit; The processing unit is used for acquiring the target vector, extracting electrical parameter characteristics according to the target vector, mapping the electrical parameter characteristics to a space domain to obtain an electrical parameter image, and decoding the electrical parameter image to obtain the electrical parameter value. In a third aspect, the present application provides an electronic device comprising a processor, and a memory communicatively coupled to the processor; the memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory to implement the method for determining an electrical parameter value according to the first aspect of the present application. In a fourth aspect, the present application provides a computer readable storage medium having stored therein computer executable instructions for implementing the method for determining an electrical parameter value according to the first aspect of the present application when executed by a processor. In a fifth aspect, the present application provides a computer program product comprising a computer program which, when executed by a processor, implements the method for determining an electrical parameter value according to the first aspect of the present application. The application provides an electrical parameter value determining method, device, equipment, medium and product, which are used for acquiring manufacturing related data of a semiconductor device and a pre-trained prediction model, inputting the manufacturing related data into the prediction model, wherein the prediction model comprises a conversion unit and a processing unit, the conversion unit is used for converting the manufacturing related data into a target vector, the processing unit is used for acquiring the target vector, extracting electrical parameter characteristics according to the target vector and mapping the electrical parameter chara