Method for manufacturing a semiconductor structure and semiconductor structure manufacturing system

Abstract

The present invention discloses a method for manufacturing a semiconductor structure and a semiconductor structure manufacturing system. The method for manufacturing a semiconductor structure includes the following processes. Input a plurality of product design parameters and a plurality of process control parameters into a semiconductor machine to form a test structure. Measure the experimental film thickness information of the test structure through a film thickness measurement unit. Transmit the product design parameters, the process control parameters, and the experimental film thickness information to a big data database of a server. Output a plurality of improved process control parameters based on the product design parameters according to the big data database through a data mining unit of the server. The semiconductor machine forms a semiconductor structure according to the product design parameters and the improved process control parameters. In this way, the automation of the process flow can be intelligently realized.

Description

Technical Field

[0001] The present invention relates to a method for manufacturing a semiconductor structure and a semiconductor structure manufacturing system. Background Art

[0002] In semiconductor processes, in the process of forming a thin film with a certain film thickness, due to different factors such as the type of product to be manufactured, the quantity of products to be manufactured, factors within the machine such as temperature and process time, and even the different positions of the wafers placed within the machine, the results of the products will be affected. In some actual operations, it often requires operators to adjust parameters according to different cases, thus wasting a lot of time.

[0003] Therefore, how to improve the above problems so as to save time and establish a standardized process is one of the problems to be solved by those skilled in the art. Summary of the Invention

[0004] An object of the present invention is to provide a method for manufacturing a semiconductor structure, which can achieve the automation and intelligence of the process flow.

[0005] According to an embodiment of the present invention, a method for manufacturing a semiconductor structure includes the following processes. Input a plurality of product design parameters and a plurality of process control parameters into a semiconductor machine to form a test structure. Measure the experimental film thickness information of the test structure through a film thickness measurement unit. Transmit the product design parameters, process control parameters, and experimental film thickness information to the big data database of the server. Output a plurality of improved process control parameters based on the product design parameters according to the big data database through the data mining unit of the server. The semiconductor machine forms a semiconductor structure according to the product design parameters and the improved process control parameters.

[0006] In one or more embodiments of the present invention, the product design parameters include the designed film thickness of the product type or the number of production wafers.

[0007] In some embodiments, the semiconductor machine has a processing area. The processing area is set to form a semiconductor structure. The number of production wafers corresponds to a local sub-processing area in the processing area.

[0008] In one or more embodiments of the present invention, the process control parameters include the temperature or processing time of the semiconductor machine.

[0009] In one or more embodiments of the present invention, the data mining unit includes a machine learning model. The machine learning model is set to output improved process control parameters according to the input product design parameters. The machine learning model is trained through the product design parameters, process control parameters, and experimental film thickness information.

[0010] Another object of the present invention relates to a semiconductor structure manufacturing system.

[0011] According to an embodiment of the present invention, a semiconductor structure manufacturing system includes a semiconductor machine tool, a film thickness measurement unit, and a server. The semiconductor machine tool is configured to form a test structure according to product design parameters and process control parameters. The film thickness measurement unit is connected to the semiconductor machine tool to obtain experimental film thickness information of the test structure. The server is connected to the semiconductor machine tool and the film thickness measurement unit. The server has a big data database and a data mining unit connected to each other. The server is configured to receive the product design parameters, the process control parameters, and the experimental film thickness information into the big data database. The data mining unit is configured to output a plurality of improved process control parameters to the semiconductor machine tool based on the experimental film thickness information according to the big data database. The semiconductor machine tool is configured to form a semiconductor structure according to the product design parameters and the improved process control parameters.

[0012] In one or more embodiments of the present invention, the product design parameters include the designed film thickness of the product type or the number of production wafers.

[0013] In some embodiments, the semiconductor machine tool has a processing area. The processing area is configured to form a semiconductor structure. The number of production wafers corresponds to a local sub-processing area in the processing area.

[0014] In one or more embodiments of the present invention, the process control parameters include the temperature or the processing time of the semiconductor machine tool.

[0015] In one or more embodiments of the present invention, the data mining unit includes a machine learning model. The machine learning model is configured to output improved process control parameters according to the input product design parameters. The machine learning model is trained by the product design parameters, the process control parameters, and the experimental film thickness information.

[0016] In summary, the semiconductor structure manufacturing method and the semiconductor structure manufacturing system provided by the present invention can automatically select the manufacturing parameters required for manufacturing a semiconductor structure according to big data, thereby intelligently realizing the automation of the process.

[0017] It should be understood that the above general description and the following detailed description are further illustrated by examples and are intended to provide a further explanation of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The advantages of the present invention and the drawings should be better understood from the following listed embodiments and with reference to the drawings. The descriptions of these drawings are only the listed embodiments, and thus should not be considered as limiting individual embodiments or the scope of the claims of the invention.

[0019] Figure 1 A block diagram of a semiconductor structure manufacturing system is shown according to an embodiment of the present invention;

[0020] Figure 2 Schematically illustrated is the film thickness of a manufactured semiconductor structure according to an embodiment of the present invention; and

[0021] Figure 3 Shown is a flowchart of a method for manufacturing a semiconductor structure according to an embodiment of the present invention.

[0022] Description of main reference numerals:

[0023] 100 - Semiconductor structure manufacturing system, 110 - Semiconductor machine, 115 - Control interface, 120 - Thin film forming unit, 125 - Temperature control unit, 130 - Time control unit, 135 - Processing area, 136 - Sub - processing area, 140 - Film thickness measurement unit, 150 - Server, 153 - Big data database, 156 - Data mining unit, 200 - Semiconductor wafer, 210 - Semiconductor pattern, 220 - Thin film, 300 - Semiconductor structure manufacturing method, 310 - 350 - Processes, h - Film thickness. Detailed description of specific embodiments

[0024] Examples are listed below and described in detail in conjunction with the accompanying drawings. However, the provided examples are not intended to limit the scope covered by the present invention, and the description of the structure and operation is not intended to limit the order of its execution. Any structure formed by recombining elements, which produces a device with equivalent functions, is within the scope covered by the present invention. Additionally, the drawings are for illustrative purposes only and are not drawn to the original scale. For ease of understanding, the same or similar elements will be denoted by the same reference numerals in the following description.

[0025] Unless otherwise defined, all terms (including technical and scientific terms) used herein have their ordinary meanings, which can be understood by those skilled in the art. Further, the definitions of the above - mentioned terms in commonly used dictionaries should be interpreted as having the same meaning as in the relevant fields of the present invention. Unless specifically defined otherwise, these terms will not be construed as idealized or overly formal meanings.

[0026] Regarding the use of "first", "second",... etc. in this article, it does not particularly refer to the order or sequence, nor is it intended to limit the present invention. It is merely used to distinguish elements or operations described with the same technical terms.

[0027] Secondly, the terms "comprising", "including", "having", "containing", etc. used herein are all open - ended terms, meaning including but not limited to.

[0028] Furthermore, in this document, unless otherwise specifically defined in the context for articles, "a" and "the" can refer to a single or multiple. It will be further understood that the terms "comprising", "including", "having", and similar terms used herein specify the features, regions, integers, steps, operations, elements, and / or components described therein, but do not exclude one or more other features, regions, integers, steps, operations, elements, components, and / or groups thereof described or additional thereto.

[0029] In semiconductor processes, operators operate semiconductor machines to form semiconductor structures. The formed semiconductor structures include various different semiconductor elements, transistors, or integrated integrated circuits.

[0030] One of the processes in semiconductor processes is to form thin films of different materials on a semiconductor wafer, and form semiconductor elements or integrated integrated circuits through the stacking and electrical connection of different thin films. In this regard, operators usually have to set the parameters of the semiconductor machine according to different products, working conditions, and environments. The present invention provides a method for manufacturing a semiconductor structure and a device for manufacturing a semiconductor structure, which can systematically provide input parameters to the operator with the assistance of big data. The provided parameters can also be instantaneously corrected according to the current working conditions with the assistance of big data.

[0031] Figure 1 A block diagram of a semiconductor structure manufacturing system 100 is shown according to an embodiment of the present invention.

[0032] As Figure 1 shown, in this embodiment, the semiconductor structure manufacturing system 100 includes a semiconductor machine 110, a film thickness measurement unit 140, and a server 150.

[0033] In this embodiment, the semiconductor machine 110 includes a control interface 115, a thin film forming unit 120, a temperature control unit 125, a time control unit 130, and a processing area 135. The processing area 135 includes a plurality of sub-processing areas 136. The control interface 115 is connected to the processing area 135 through the thin film forming unit 120, the temperature control unit 125, and the time control unit 130.

[0034] In the semiconductor machine 110, the semiconductor wafers to be processed are placed in different sub-processing areas 136 in the processing area 135. In the semiconductor machine 110, the processing area 135 is, for example, a batch furnace, and the different sub-processing areas 136 are, for example, different zones in the furnace. According to different production product conditions, the semiconductor wafers to be processed are selected to be placed in different sub-processing areas 136.

[0035] Figure 1Only a processing area 135 is schematically illustrated, but this does not limit the number of processing areas 135 in the semiconductor machine 110. In some embodiments, the number of processing areas 135 may be one or more. It should be understood that Figure 1 The illustrated sub-processing areas 136 are only schematic, and do not limit the size of each sub-processing area 136, nor do they limit that the sub-processing areas 136 must be side by side.

[0036] In some embodiments, the semiconductor machine may also have multiple different furnace tubes as processing areas, and each furnace tube further includes one or more sub-processing areas.

[0037] In some embodiments, the volume sizes of different sub-processing areas 136 are different to accommodate different numbers of semiconductor wafers. For example, in some embodiments, when the number of semiconductor wafers required for the production product conditions is different, different-sized sub-processing areas 136 are selected to accommodate different numbers of semiconductor wafers.

[0038] When the semiconductor wafers to be processed are disposed in the respective sub-processing areas 136 of the semiconductor machine 110, different process control parameters can be implemented through the film forming unit 120, the temperature control unit 125, and the time control unit 130, so as to regulate the environment of the sub-processing areas 136. The process control parameters can be input through the control interface 115.

[0039] In some embodiments, the film forming unit 120 can form a film on the semiconductor wafer. For example, the film forming unit 120 can form a film by, for example, physical vapor deposition (PVD), chemical vapor deposition (CVD), or atomic layer deposition (ALD). The process conditions for the film forming unit 120 to form a film can be controlled by the temperature control unit 125 and the time control unit 130. The temperature control unit 125 can be used to control the temperature within the sub-processing area 136, and the time control unit 130 can be set to control the overall processing time of the film forming process. Through the control interface 115, different process control parameters can be input to the film forming unit 120, the temperature control unit 125, and the time control unit 130 respectively to control the overall film forming process.

[0040] Figure 1 The illustrated architecture of the semiconductor machine 110 is only schematic, and does not limit the aspect of the semiconductor machine of the present invention in this regard. In some embodiments, the semiconductor machine may be composed of different functional elements, but can also control the ambient temperature and the overall processing time when forming a film on the semiconductor wafer, which are also included in the present invention.

[0041] Such as Figure 1As shown, in the present embodiment, the semiconductor structure manufacturing system 100 is further provided with a film thickness measurement unit 140. After the semiconductor machine 110 forms a thin film on the semiconductor wafer, the film thickness of the thin film can be confirmed by the film thickness measurement unit 140.

[0042] In the present embodiment, the film thickness measurement unit 140 is connected to the semiconductor machine 110. In some embodiments, the film thickness measurement unit 140 can be directly disposed within the semiconductor machine 110.

[0043] Please refer to Figure 1 and Figure 2 . Figure 2 A film thickness h of a semiconductor structure fabricated on a semiconductor wafer 200 is schematically illustrated according to an embodiment of the present invention. In the sub-processing region 136 of the semiconductor machine 110, the semiconductor structure formed on the semiconductor wafer 200 is as Figure 2 schematically illustrated.

[0044] As Figure 2 illustrated, a semiconductor pattern 210 is formed on the semiconductor wafer 200. Figure 2 The illustrated semiconductor pattern 210 is only schematic and does not limit the aspect of the semiconductor pattern on the semiconductor structure of the present invention.

[0045] After the semiconductor pattern 210 is formed on the semiconductor wafer 200 in the previous process, the semiconductor wafer 200 is placed in the sub-processing region 136 of the semiconductor machine 110 to form a thin film 220 on the semiconductor pattern 210 of the semiconductor wafer 200. In some embodiments, the semiconductor wafer 200 also includes other formed transistors, integrated integrated circuits, memory or memory cell arrays, or stacked redistribution layers or interconnect structures. In order to form a further structure in the subsequent process, a thin film 220 is formed in the sub-processing region 136 of the semiconductor machine 110.

[0046] Through the film thickness measurement unit 140, the film thickness h of the thin film 220 on the semiconductor pattern 210 can be measured. The film thickness measurement unit 140 can measure the film thickness h when the thin film 220 is formed, ensuring that the thin film formation and the film thickness measurement do not interfere with each other. In some embodiments, the film thickness measurement unit 140 can be directly integrated into the semiconductor machine 110 as a stage in the semiconductor machine 110 to measure the film thickness h with better efficiency when the thin film 220 is formed. In some embodiments, the film thickness measurement unit 140 can measure the film thickness h of the thin film 220 by an optical method.

[0047] It should be noted that Figure 2 the illustrated semiconductor wafer 200 can schematically represent a test structure for pre-production to collect relevant experimental data, or can schematically represent a formed semiconductor product.

[0048] Please return to Figure 1 In this embodiment, the semiconductor structure manufacturing system 100 includes a server 150. The server 150 is remotely connected to the semiconductor processing tool 110 and the film thickness measurement unit 140, which are shown by dashed lines in Figure 1 Thus, both the process parameters input through the control interface 115 of the semiconductor processing tool 110 and the film thickness h measured by the film thickness measurement unit 140 can be received by the server 150.

[0049] As Figure 1 shown, in this embodiment, the server 150 includes a big data database 153 and a data mining unit 156. The process parameters input through the control interface 115 and the film thickness h measured by the film thickness measurement unit 140 can both be stored in the big data database 153. Thus, the required process parameters can be obtained from the big data database 153 through the data mining unit 156.

[0050] Specifically, for the process of forming the thin film 220 on the semiconductor wafer 200 by the semiconductor processing tool 110, the operator needs to set the corresponding process parameters according to the product design parameters. For example, for the product to be produced, the product design parameters include the product type, the designed film thickness, or the number of wafers to be produced, so as to respectively pre-control the type of the semiconductor wafer 200, the desired ideal film thickness, or the number of semiconductor wafers 200 that must be processed at one time in the sub-processing area. For different product types, the operator needs to input the environmental temperature and processing time in the sub-processing area 136 through the control interface 115. However, depending on the semiconductor processing tool 110, the process parameters are not fixed and often need to be set by the operator according to the current situation. By collecting the input product design parameters and process parameters to the big data database 153 through the server 150, the process parameters to be input can be systematically obtained through the data mining unit 156.

[0051] In some embodiments, one or more semiconductor structures can be successively formed on the test semiconductor wafer. The same or different product design parameters are input into the semiconductor processing tool 110, and the process control parameters are manually input for test purposes to form the thin film through the operation of the semiconductor processing tool 110. The product design parameters, the process control parameters, and the film thickness h of the thin film 220 are all received by the server 150 and stored in the big data database 153. Through the data mining unit 156, the required process control parameters can be automatically obtained according to the input product design parameters.

[0052] In some embodiments, the data mining unit 156 obtains process control parameters, for example, by machine learning. For example, after a complete thin film formation process is completed, the film thickness of the formed thin film can be obtained. Thus, the input process control parameters (including the selected sub-processing area 136, temperature, and processing time) and the obtained film thickness can be collected. Accordingly, the data mining unit 156 obtains a learning model through machine learning. Thus, when the required film thickness is input into the learning model, the learning model can correspondingly output the process control parameters that should be input into the semiconductor machine 110.

[0053] Figure 3 A flowchart of a semiconductor structure manufacturing method 300 is illustrated according to an embodiment of the present invention. The semiconductor structure manufacturing system 100 can implement the semiconductor structure manufacturing method 300 to systematically and automatically obtain the required process control parameters. In this embodiment, the semiconductor structure manufacturing method 300 includes processes 310 to 350. The semiconductor structure manufacturing method 300 first provides data to the big data database 153 of the server 150 through a test structure, and then obtains the required process control parameters through the data mining unit 156 of the server 150.

[0054] In process 310, product design parameters and process control parameters are input into the semiconductor machine 110 to form a test structure.

[0055] In some embodiments, the product design parameters include product type, design film thickness, or production quantity. The product type includes aspects of the semiconductor pattern 210 to be formed on the semiconductor wafer 200, the shape of the formed thin film 220, and so on. The design film thickness is the ideal film thickness of the thin film 220 determined according to requirements. However, due to different environments, the film thickness h of the formed thin film 220 is not necessarily the ideal film thickness. The production quantity corresponds to the number of semiconductor wafers 200 processed in a thin film formation process.

[0056] In some embodiments, the process control parameters include the selected sub-processing area 136, ambient temperature, and processing time. For example, for different production quantities, different sizes of sub-processing areas 136 in the processing area 135 are correspondingly selected. The ambient temperature corresponds to the temperature set in the selected sub-processing area 136. The processing time corresponds to the total duration of the thin film formation process.

[0057] After setting the product design parameters and process control parameters of the semiconductor machine 110 through the control interface 115, the semiconductor wafer 200 is placed in the selected sub-processing area 136 to form a test structure. Forming the test structure will include a predetermined semiconductor pattern 210 and a thin film 220, and the thin film 220 has a film thickness h, and the film thickness h may not be the ideal film thickness required by the product setting parameters.

[0058] In this way, a semiconductor test structure for testing can be formed, such as Figure 2 shown, having a semiconductor pattern 210, on which a thin film 220 is disposed.

[0059] Following process 310, in process 320, after the test structure is formed, the experimental film thickness information of the thin film 220 of the test structure is measured by the film thickness measurement unit 140. In this embodiment, the experimental film thickness information includes the film thickness h of the thin film 220 of the test structure.

[0060] In process 330, the input product design parameters, process control parameters, and film thickness control information are transmitted to the big data database 153 of the server 150. In some embodiments, the big data stored in the big data database 153 can establish a learning model through the data mining unit 156 to respond to the requests input by subsequent operators.

[0061] After collecting big data through the test structure, the operator can request the server 150 based on the required product design parameters to obtain the corresponding required process control parameters.

[0062] In some embodiments, processes 310 to 330 can be repeated multiple times to obtain multiple sets of experimental data for storage as big data. In some embodiments, the experimental film thickness information can also be obtained in the manner of processes 310 to 330 through the film thickness measurement unit 140 for general production processes and stored as big data.

[0063] In process 340, the operator requests the server 150 based on the product design parameters, and the data mining unit 156 of the server 150 outputs improved process control parameters according to the big data database 153 and based on the product design parameters. As described above, in some embodiments, the data mining unit 156 can establish a learning model according to the big data, so that when the operator makes a request, the product design parameters are input into the learning model to output improved process control parameters.

[0064] After the operator obtains the improved process control parameters, it enters process 350. The operator inputs the improved process control parameters through the control interface 115, and the semiconductor machine 110 will form a semiconductor structure according to the product design parameters and the improved process control parameters as the actual product to be produced. In this way, the film thickness h of the thin film 220 should be able to be closer to the set ideal film thickness.

[0065] To further illustrate the semiconductor structure manufacturing method 300 in detail, an embodiment is provided below, but the present invention is not limited thereto.

[0066] In process 310, the product design parameter settings include the product type, the designed film thickness, and the number of production pieces. The product type is related to the process selection of the film forming unit 120. The designed film thickness is recorded by the server 150. The number of production pieces is selected for the sub-processing area 136. The process control parameters are set to include the ambient temperature and the processing time of the selected sub-processing area 136. In a practical example, the product type of the product design parameters is product A, and the code of the selected sub-processing area 136 is BA; the ambient temperature of the process control parameters is T1 degrees Celsius, and the processing time is H1 hours. In this way, the first test structure is formed. In process 320, through the film thickness measurement unit 140, the film thickness hA of the first test structure is obtained. In process 330, the product type of product A, the code BA of the sub-processing area 136, the ambient temperature of TA degrees Celsius, the processing time of HA hours, and the film thickness hA are uploaded to the big data database 153 of the server 150.

[0067] As described above, processes 310 to 330 can be repeated one or more times to accumulate the big data stored in the big data database 153. For example, by repeating process 310, the product type of the product design parameters is product B, and the code of the selected sub-processing area 136 is BB; the ambient temperature of the process control parameters is TB degrees Celsius, and the processing time is HB hours. In this way, the second test structure is formed. In process 320, through the film thickness measurement unit 140, the film thickness hB of the second test structure is obtained. In process 330, the product type of product B, the code BB of the sub-processing area 136, the ambient temperature of TB degrees Celsius, the processing time of HB hours, and the film thickness hB are uploaded to the big data database 153 of the server 150.

[0068] Taking the implementation method where the data mining unit 156 mines big data through machine learning as an example, the data mining unit 156 trains a learning model based on the big data stored in the big data database 153. One piece of data in the big data includes: the product type of product A, the code BA of the sub-processing area 136, the ambient temperature of TA degrees Celsius, the processing time of HA hours, and the film thickness hA. Another piece of data in the big data includes: the product type of product B, the code BB of the sub-processing area 136, the ambient temperature of TB degrees Celsius, the processing time of HB hours, and the film thickness hB.

[0069] In this way, the data mining unit 156 establishes a learning model. After inputting the product type, designed film thickness, and selected sub - processing area 136 of the product design parameters, the data mining unit 156 outputs improved process control parameters according to the learning model, including the environmental temperature and processing time to be set. Thus, process 340 can be realized, and then process 350 is executed to form the required semiconductor structure. For example, when the input product type is product A, the code of the sub - processing area 136 is BA (corresponding to the number of wafers placed), and the designed film is input, the data mining unit 156 outputs that the processing time should be HA + C hours, with a correction of C hours; the output environmental temperature is TA + D degrees Celsius, with a correction of D degrees Celsius.

[0070] In summary, the semiconductor structure manufacturing method and the semiconductor structure manufacturing system provided by the present invention can automatically select the manufacturing parameters required for a semiconductor structure during manufacturing according to big data, thereby intelligently realizing the automation of the process, reducing the time for operators to fine - tune the parameters of semiconductor machines, and improving the overall production efficiency. The pattern density caused by different product types, the number of wafers and the placement positions (loading effect) in different sub - working areas (such as different areas in a furnace tube), and the film thickness value measured on the wafer after film formation can all be transmitted back to the big data database of the server for rapid calculation to determine the optimal execution conditions for the next execution, without manual calculation or fine - tuning, which is conducive to moving towards the direction of an automated factory.

[0071] Although the present invention has been disclosed as above by way of embodiments, it is not intended to limit the present invention. Any person skilled in the art can make various changes and modifications without departing from the spirit and scope of the present invention. Therefore, the protection scope of the present invention shall be determined by the scope defined by the claims.

[0072] It will be apparent to those skilled in the art that various modifications and changes can be made to the structure of the embodiments of the present invention without departing from the scope or spirit of the present disclosure. In view of the foregoing, the present invention is intended to cover various modifications and variations as long as they fall within the scope of the claims.

Claims

1. A method for manufacturing a semiconductor structure, characterized in that, Including: Inputting a plurality of product design parameters and a plurality of process control parameters into a semiconductor machine to form a test structure; Measuring experimental film thickness information of the test structure by a film thickness measurement unit; Transmitting the plurality of product design parameters, the plurality of process control parameters, and the experimental film thickness information to a big data database of a server; Outputting a plurality of improved process control parameters by a data mining unit of the server according to the big data database and based on the plurality of product design parameters; The semiconductor machine forming a semiconductor structure according to the plurality of product design parameters and the plurality of improved process control parameters, wherein the plurality of product design parameters include product type, designed film thickness, and number of production wafers, the semiconductor machine has a processing area, the processing area is set to form the semiconductor structure of the product type, and the number of production wafers of the semiconductor structure corresponds to a local sub-processing area in the processing area, wherein the processing area is a furnace tube of the semiconductor machine, and the sub-processing area is one of a plurality of local areas of the semiconductor machine.

2. The method for manufacturing a semiconductor structure according to claim 1, wherein, The plurality of process control parameters include the temperature or processing time of the semiconductor machine.

3. The method for manufacturing a semiconductor structure according to claim 1, wherein, The data mining unit includes a machine learning model, the machine learning model is set to output the plurality of improved process control parameters according to the input plurality of product design parameters, and the machine learning model is trained by the plurality of product design parameters, the plurality of process control parameters, and the experimental film thickness information.

4. A semiconductor structure manufacturing system, characterized in that, Including: A semiconductor machine, configured to form a test structure according to a plurality of product design parameters and a plurality of process control parameters; A film thickness measurement unit, connected to the semiconductor machine to obtain experimental film thickness information of the test structure; And A server, connected to the semiconductor machine and the film thickness measurement unit, wherein the server has a big data database and a data mining unit connected to each other, the server is configured to receive the plurality of product design parameters, the plurality of process control parameters, and the experimental film thickness information to the big data database, the data mining unit is configured to output a plurality of improved process control parameters to the semiconductor machine according to the big data database based on the experimental film thickness information, and the semiconductor machine is configured to form a semiconductor structure according to the plurality of product design parameters and the plurality of improved process control parameters, wherein the plurality of product design parameters include product type, designed film thickness, and number of production wafers, the semiconductor machine has a processing area, the processing area is set to form the semiconductor structure of the product type, and the number of production wafers of the semiconductor structure corresponds to a local sub-processing area in the processing area, wherein the processing area is a furnace tube of the semiconductor machine, and the sub-processing area is one of a plurality of local areas of the semiconductor machine.

5. The semiconductor structure manufacturing system according to claim 4, wherein, The plurality of process control parameters include the temperature or processing time of the semiconductor machine.

6. The semiconductor structure manufacturing system according to claim 4, wherein, The data mining unit includes a machine learning model, which is configured to output the multiple improved process control parameters according to the input multiple product design parameters, and the machine learning model is trained by the multiple product design parameters, the multiple process control parameters, and the experimental film thickness information.

Images