Data analysis task execution method, device and equipment of battery silicon wafer, storage medium and product

Abstract

The invention relates to a data analysis task execution method and device for a battery silicon wafer, equipment, a storage medium and a product. Comprising the steps that a to-be-executed data analysis task set for a target battery silicon wafer is determined, and the to-be-executed data analysis task carries identity identification information of the target battery silicon wafer; according to the identity identification information, matching a plurality of corresponding target analysis data for the to-be-executed data analysis task in a preset analysis data pool, the multiple pieces of target analysis data comprise first process data generated by a target battery silicon wafer in a target working procedure and first SPC data generated by the target battery silicon wafer in the target working procedure; at least two of second process data generated by the target battery silicon wafer under the associated process of the target process and second SPC data generated by the target battery silicon wafer under the associated process of the target process; and executing the to-be-executed data analysis task according to the multiple pieces of target analysis data. By adopting the method, the analysis effect of carrying out data analysis on the battery silicon wafer is improved.

Description

Technical Field

[0001] The present application relates to the technical field of photovoltaic cells, and particularly to a method, device, computer equipment, computer-readable storage medium, and computer program product for performing data analysis tasks on battery wafers. Background Art

[0002] With the continuous development of technology, photovoltaic cells have been widely used in people's lives. Considering aspects such as optimizing the quality of battery wafers, improving process parameters, and ensuring production stability, it is very necessary to perform data analysis on battery wafers during the manufacturing process of photovoltaic cells.

[0003] Currently, batch manufacturing process data of battery wafers is usually imported by means of big data analysis algorithms, and then data analysis tasks are executed to complete data correlation analysis. However, due to the large amount and complexity of batch manufacturing process data, it is still impossible to effectively analyze the data of battery wafers after executing the data analysis tasks, which may easily lead to situations such as low efficiency or errors in data analysis. Therefore, the current analysis effect of data analysis on battery wafers is poor. Summary of the Invention

[0004] Based on this, in view of the above technical problems, it is necessary to provide a method, device, computer equipment, computer-readable storage medium, and computer program product for performing data analysis tasks on battery wafers that can improve the analysis effect of data analysis on battery wafers.

[0005] In a first aspect, the present application provides a method for performing a data analysis task on a battery wafer, including:

[0006] Determine a data analysis task to be executed for a target battery wafer, where the data analysis task to be executed carries identity identification information of the target battery wafer;

[0007] According to the identity identification information, match a corresponding plurality of target analysis data in a preset analysis data pool for the data analysis task to be executed, where the plurality of target analysis data includes at least two of the first process data generated by the target battery wafer in a target process, the first SPC data generated by the target battery wafer in the target process, the second process data generated by the target battery wafer in an associated process of the target process, and the second SPC data generated by the target battery wafer in the associated process of the target process;

[0008] Execute the data analysis task to be executed according to the plurality of target analysis data.

[0009] In one embodiment, when the multiple target analysis data includes the first SPC data, the matching of the corresponding multiple target analysis data for the to-be-executed data analysis task in the preset analysis data pool according to the identity information includes:

[0010] Extract process-level identity information and wafer-level identity information from the identity information;

[0011] According to the process-level identity information, query multiple candidate SPC data generated under the target process where the target cell wafer is located;

[0012] According to the wafer-level identity information, query the first SPC data generated by the target cell wafer under the target process from the multiple candidate SPC data;

[0013] Use the first SPC data as the target analysis data matching the to-be-executed data analysis task.

[0014] In one embodiment, when the multiple target analysis data includes the first process data, the matching of the corresponding multiple target analysis data for the to-be-executed data analysis task in the preset analysis data pool according to the identity information includes:

[0015] Determine the in-process traceability information of the target cell wafer in the target process according to the identity information;

[0016] Query the first process data generated by the target cell wafer under the target process according to the in-process traceability information;

[0017] Use the first process data as the target analysis data matching the to-be-executed data analysis task.

[0018] In one embodiment, when the multiple target analysis data includes the second SPC data, the matching of the corresponding multiple target analysis data for the to-be-executed data analysis task in the preset analysis data pool according to the identity information includes:

[0019] Extract process-level identity information from the identity information;

[0020] Determine the first inter-process traceability information of the target cell wafer in the target process according to the process-level identity information;

[0021] Query the second SPC data generated by the target cell wafer under the associated process according to the first inter-process traceability information;

[0022] Use the second SPC data as the target analysis data that matches the data analysis task to be executed.

[0023] In one embodiment, when the multiple target analysis data includes the second process data, the step of matching multiple corresponding target analysis data for the data analysis task to be executed in the preset analysis data pool according to the identity information includes:

[0024] Extract the wafer-level identity information from the identity information;

[0025] Determine the second inter-process traceability information of the target cell wafer in the target process according to the wafer-level identity information;

[0026] Query the second process data generated by the target cell wafer in the target process according to the second inter-process traceability information;

[0027] Use the second process data as the target analysis data that matches the data analysis task to be executed.

[0028] In one embodiment, the step of executing the data analysis task to be executed according to the multiple target analysis data includes:

[0029] Determine the data difference characteristics of the multiple target analysis data;

[0030] Execute the data analysis task to be executed according to multiple data difference characteristics, where the multiple data difference characteristics include at least one of a data attribute difference characteristic and a data process difference characteristic. The data attribute difference characteristic is used to characterize the difference in data types of multiple target analysis data under the same process, and the data process difference characteristic is used to characterize the difference in multiple target analysis data of the same data type in different processes.

[0031] In one embodiment, the multiple data difference characteristics include the data attribute difference characteristic and the data process difference characteristic; the step of executing the data analysis task to be executed according to multiple data difference characteristics includes:

[0032] Divide multiple first target analysis data from the multiple target analysis data according to the data attribute difference characteristic, and divide multiple second target analysis data from the multiple target analysis data according to the data process difference characteristic;

[0033] Select the data to be compared and analyzed from the multiple first target analysis data and the multiple second target analysis data;

[0034] Execute the to-be-executed data analysis task by comparing the data to be analyzed with the standard analysis data.

[0035] In one embodiment, the to-be-executed data analysis task includes multiple to-be-executed analysis subtasks; executing the to-be-executed data analysis task includes:

[0036] According to the task type of the to-be-executed data analysis task, prioritize the multiple to-be-executed analysis subtasks to obtain a subtask ranking result;

[0037] Execute the multiple to-be-executed analysis subtasks in sequence according to the subtask ranking result.

[0038] In one embodiment, before matching the corresponding target analysis data for the to-be-executed data analysis task in the preset analysis data pool according to the identity identification information, the method further includes:

[0039] Obtain multiple original manufacturing process data generated by the target battery silicon wafer under different processes;

[0040] After all the original manufacturing process data is screened, perform format conversion on the screened multiple original manufacturing process data to obtain multiple to-be-processed manufacturing process data in a standard format;

[0041] Generate a preset analysis data pool according to the multiple to-be-processed manufacturing process data.

[0042] In one embodiment, generating the preset analysis data pool according to the multiple to-be-processed manufacturing process data includes:

[0043] According to the data attribute information of the multiple to-be-processed manufacturing process data, divide the multiple to-be-processed manufacturing process data into multiple first to-be-processed manufacturing process data and multiple second to-be-processed manufacturing process data;

[0044] Convert each of the multiple first to-be-processed manufacturing process data into first to-be-analyzed data, and perform data fusion on the multiple second to-be-processed manufacturing process data to obtain multiple second to-be-analyzed data; [[ID=3x1]]

[0045] Obtain a preset analysis data pool by integrating the multiple first to-be-analyzed data and the multiple second to-be-analyzed data.

[0046] [[ID=xx6]]Second aspect, the present application also provides a device for executing a data analysis task of a battery silicon wafer, including:

[0047] A determination module, configured to determine a to-be-executed data analysis task set for a target battery silicon wafer, where the to-be-executed data analysis task carries the identity identification information of the target battery silicon wafer; Note: There seems to be a minor error in the original text where '3x1' should likely be '31'. The translation has been adjusted accordingly.

[0048] A matching module, configured to match, according to the identity identification information, a plurality of corresponding target analysis data for the to-be-executed data analysis task in a preset analysis data pool, where the plurality of target analysis data includes at least two of the following four: first process data generated by the target cell wafer in a target process, first SPC data generated by the target cell wafer in the target process, second process data generated by the target cell wafer in an associated process of the target process, and second SPC data generated by the target cell wafer in the associated process of the target process;

[0049] An execution module, configured to execute the to-be-executed data analysis task according to the plurality of target analysis data.

[0050] In a third aspect, the present application further provides a computer device, including a memory and a processor, where the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0051] Determine a to-be-executed data analysis task set for a target cell wafer, where the to-be-executed data analysis task carries the identity identification information of the target cell wafer; match, according to the identity identification information, a plurality of corresponding target analysis data for the to-be-executed data analysis task in a preset analysis data pool, where the plurality of target analysis data includes at least two of the following four: first process data generated by the target cell wafer in a target process, first SPC data generated by the target cell wafer in the target process, second process data generated by the target cell wafer in an associated process of the target process, and second SPC data generated by the target cell wafer in the associated process of the target process; execute the to-be-executed data analysis task according to the plurality of target analysis data.

[0052] In a fourth aspect, the present application further provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0053] Determine the data analysis task to be executed for the target battery silicon wafer, where the data analysis task to be executed carries the identity identification information of the target battery silicon wafer; according to the identity identification information, match a corresponding plurality of target analysis data for the data analysis task to be executed in a preset analysis data pool, where the plurality of target analysis data includes at least two of the first process data generated by the target battery silicon wafer under the target process, the first SPC data generated by the target battery silicon wafer under the target process, the second process data generated by the target battery silicon wafer under the associated process of the target process, and the second SPC data generated by the target battery silicon wafer under the associated process of the target process; execute the data analysis task to be executed according to the plurality of target analysis data.

[0054] In a fifth aspect, the present application further provides a computer program product, including a computer program, which when executed by a processor, implements the following steps:

[0055] Determine the data analysis task to be executed for the target battery silicon wafer, where the data analysis task to be executed carries the identity identification information of the target battery silicon wafer; according to the identity identification information, match a corresponding plurality of target analysis data for the data analysis task to be executed in a preset analysis data pool, where the plurality of target analysis data includes at least two of the first process data generated by the target battery silicon wafer under the target process, the first SPC data generated by the target battery silicon wafer under the target process, the second process data generated by the target battery silicon wafer under the associated process of the target process, and the second SPC data generated by the target battery silicon wafer under the associated process of the target process; execute the data analysis task to be executed according to the plurality of target analysis data.

[0056] The method, apparatus, computer device, computer-readable storage medium, and computer program product for performing data analysis tasks on the battery silicon wafers first determine the data analysis tasks to be performed for the target battery silicon wafers. Among them, the data analysis tasks to be performed carry the identity identification information of the target battery silicon wafers. Then, guided by the identity identification information, multiple target analysis data corresponding to the data analysis tasks to be performed are matched in the preset analysis data pool. The multiple target analysis data include at least two of the following four: the first process data generated by the target battery silicon wafers under the target process, the first SPC data generated by the target battery silicon wafers under the target process, the second process data generated by the target battery silicon wafers under the associated process of the target process, and the second SPC data generated by the target battery silicon wafers under the associated process of the target process. In this way, the purpose of capturing multiple target analysis data of the target battery silicon wafers in different dimensions for data analysis can be achieved. Finally, based on the multiple target analysis data, the data analysis tasks to be performed are executed. Since the multiple target analysis data are all matched guided by the identity identification information of the target battery silicon wafers, the orderly correlation of the target battery silicon wafers in the manufacturing process can be objectively reflected through the multiple target analysis data. Therefore, according to the different data analysis tasks to be performed, different multiple target analysis data can be specifically captured to complete the execution, rather than only relying on the data correlation given by the algorithm for data analysis of the target battery silicon wafers. Thus, the technical defect that due to the large amount and complexity of the batch manufacturing process data, the effective analysis of the battery silicon wafer data still cannot be achieved after performing the data analysis tasks, and thus the situations such as low efficiency or errors in data analysis are likely to occur is overcome. Therefore, the analysis effect of data analysis on the battery silicon wafers is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following will briefly introduce the drawings required for use in the description of the embodiments or related technologies. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0058] Figure 1 It is a schematic flowchart of the method for performing data analysis tasks on battery silicon wafers in an embodiment;

[0059] Figure 2 It is a schematic diagram of the data stored in the preset analysis data pool of the method for performing data analysis tasks on battery silicon wafers in an embodiment;

[0060] Figure 3 It is a schematic flowchart of the method for performing data analysis tasks on battery silicon wafers in another embodiment;

[0061] Figure 4Schematic diagram of data relationships stored in a data processing system for a method of performing data analysis tasks on battery wafers in another embodiment;

[0062] Figure 5 Block diagram of a device for performing a data analysis task on battery wafers in one embodiment;

[0063] Figure 6 Internal structure diagram of a computer device in one embodiment. Detailed implementation manners

[0064] In order to make the objectives, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0065] First of all, it should be understood that in the field of photovoltaic cells, it is very necessary to perform data analysis on battery wafers. At present, there is no fixed mode for analyzing battery wafer data. Usually, the method adopted is to perform correlation ranking on a large amount of data and multiple parameter factors to find key influencing factors for improvement, or directly apply other big data analysis algorithms such as regression algorithms or classification algorithms to analyze the batch manufacturing process data of battery wafers, and finally complete the execution of the data analysis task. However, the existing data analysis tasks for battery wafers face the following defects during the execution process: 1) The batch manufacturing process data imported is numerous and miscellaneous. Without effective extraction of influencing factors, only major abnormal problems can be solved, and production optimization cannot be effectively guided; 2) The relevant data from different modules cannot be effectively connected in series, and the data granularity of different modules is not the same. For example, during the analysis of the SPC (Statistical Process Control) data of battery wafers, the operation results of a whole boat or a whole tube are often represented by the SPC data of a single piece. When performing such data analysis tasks, it is often difficult to be effective. Therefore, when using the existing method for data analysis, even if certain analysis results can be obtained, it is easy to make the data analysis inefficient or error-prone. Therefore, there is an urgent need for a method for performing a data analysis task on battery wafers that can improve the data analysis effect on battery wafers.

[0066] In one embodiment, as Figure 1As shown, a method for executing a data analysis task of a battery silicon wafer is provided. In this embodiment, this method is exemplified by being applied to a terminal, which includes but is not limited to a personal computer, a laptop, a smart phone, a tablet computer, etc. The terminal includes a determination module, a matching module, and an execution module. Among them, the determination module is used to determine the data analysis task to be executed set for the target battery silicon wafer, where the data analysis task to be executed carries the identity identification information of the target battery silicon wafer; the matching module is used to match corresponding multiple target analysis data for the data analysis task to be executed in a preset analysis data pool according to the identity identification information, where the multiple target analysis data includes at least two of the first process data generated by the target battery silicon wafer under the target process, the first SPC data generated by the target battery silicon wafer under the target process, the second process data generated by the target battery silicon wafer under the associated process of the target process, and the second SPC data generated by the target battery silicon wafer under the associated process of the target process; the execution module is used to execute the data analysis task to be executed according to the multiple target analysis data; in the process of executing the data analysis task of the battery silicon wafer in this embodiment, first, the data analysis task to be executed set for the analysis object "target battery silicon wafer" is determined. Since the data analysis task to be executed carries the identity identification information of the target battery silicon wafer, then through the identity identification information, at least two of the first process data, the first SPC data, the second process data, and the second SPC data can be matched in the preset analysis data pool pre-constructed for the data analysis task to be executed as the multiple target analysis data corresponding to the data analysis task to be executed. Finally, the data analysis task to be executed is executed through the multiple target analysis tasks. Since the multiple target analysis data are all matched with the identity identification information of the target battery silicon wafer as the guide, then through the multiple target analysis data, the orderly correlation of the target battery silicon wafer in the manufacturing process can be objectively reflected. Therefore, different multiple target analysis data can be specifically captured and executed based on the difference of the data analysis task to be executed, rather than only relying on the data correlation given by the algorithm for the data analysis of the target battery silicon wafer. Therefore, the analysis effect of the data analysis of the battery silicon wafer can be improved; it can be understood that this method can also be applied to a server, and can also be applied to a system including a terminal and a server, and is realized through the interaction between the terminal and the server. In this embodiment, the method includes the following steps 202 to 206. Among them:

[0067] Step 202: Determine the data analysis task to be executed set for the target battery silicon wafer, where the data analysis task to be executed carries the identity identification information of the target battery silicon wafer.

[0068] It should be noted that the target cell wafer refers to the cell wafer that is the application target of data analysis. As a specific object in a specific data analysis task scenario, it can specifically be one or more cell wafers at any process during the manufacturing process of a photovoltaic cell. Among them, the process can specifically be crystal pulling, slicing, texturing, diffusion, etching, coating, etc. It can be understood that the cell wafer refers to a thin silicon material sheet used to manufacture a photovoltaic cell, and data such as its purity, thickness, and defect rate will determine the photoelectric conversion efficiency of the photovoltaic cell; the data analysis task to be executed refers to the data analysis task waiting to be executed. Among them, the data analysis task is set with the target cell wafer as the object. Therefore, the data analysis task to be executed can be either the data analysis performed on a certain cell wafer or the data analysis performed on multiple cell wafers. The data analysis task to be executed can delimit the scope of the target cell wafer based on dimensions such as time, space, or process parameters. For example, in an implementable manner, the data analysis task to be executed can specifically be the analysis of the sheet resistance value of all cell wafers undergoing the diffusion process during the time period from 10:00:00 to 15:00:00.

[0069] It should be noted that the data analysis task to be executed can be periodically generated by the terminal or configured through the interaction operation between the user and the terminal. The data analysis task to be executed carries identity identification information, and the identity identification information is used to characterize the identity information of the target cell wafer. Specifically, the identity identification information can be the ID of the cell wafer. For example, in an implementable manner, the ID of the cell wafer can be G1 - Axxx - a, G1 - Axxx - b, or G1 - Axxx - c, etc.; it can be understood that the identity identification information of different cell wafers is unique. Through the identity identification information, any cell wafer at any process can be locked. After clarifying the identity identification information of the target cell wafer in the data analysis task to be executed, the manufacturing process data corresponding to the identity identification information can be queried.

[0070] As an example, step 202 includes: obtaining the identity identification information of the target cell wafer, and generating a data analysis task to be executed set for the target cell wafer according to the identity identification information.

[0071] Step 204, according to the identity identification information, match corresponding multiple target analysis data for the data analysis task to be executed in the preset analysis data pool, where the multiple target analysis data includes at least two of the first process data generated by the target cell wafer in the target process, the first SPC data generated by the target cell wafer in the target process, the second process data generated by the target cell wafer in the associated process of the target process, and the second SPC data generated by the target cell wafer in the associated process of the target process.

[0072] It should be noted that the preset analysis data pool pre-stores relevant data generated by the target cell silicon wafer in the manufacturing process. The relevant data stored in the preset analysis data pool is unordered, and specifically may include first manufacturing data generated by the target cell silicon wafer in the target process, first SPC data generated by the target cell silicon wafer in the target process, second manufacturing data of the target cell silicon wafer in the associated process of the target process, and second SPC data generated by the cell silicon wafer in the associated process of the target process; the target process refers to the process where the data to be analyzed of the target cell silicon wafer is located, and specifically may be a boron diffusion process, a texturing process, an etching process, etc. The associated process may refer to a process having an associated relationship with the target process. Among them, the type of the associated relationship may specifically be resource association, information association, quality association, or logical association, etc. For example, in an implementable manner, assuming the target process is a boron diffusion process, the associated process of the target process may be an etching process; the target analysis data refers to the data that needs to be analyzed for the target cell silicon wafer.

[0073] It should be noted that the first manufacturing data is used to reflect the execution status of the target process, and specifically may be temperature, pressure, deposition rate, etc. The first SPC data is used to evaluate the process stability of the target process, and specifically may be film thickness, sheet resistance, etc. The second manufacturing data is used to reflect the execution status of the associated process, and specifically may be temperature, pressure, deposition rate, etc. The second SPC data is used to evaluate the process stability of the associated process, and specifically may be film thickness, sheet resistance, etc. The first manufacturing data, the first SPC data, the second manufacturing data, and the second SPC data may all be one or more; multiple data to be analyzed can be called in the preset analysis data pool through the identity identification information. The combination of multiple data to be analyzed can be "first manufacturing data + first SPC data", "first manufacturing data + second manufacturing data", "first manufacturing data + second SPC data", "first manufacturing data + second manufacturing data + first SPC data", "first manufacturing data + second manufacturing data + second SPC data", "first manufacturing data + first SPC data + second SPC data", or "first manufacturing data + second manufacturing data + first SPC data + second SPC data", etc. In some implementable manners, by comparing whether all the data to be analyzed have identity identification information, multiple target analysis data are screened out from all the data to be analyzed.

[0074] As an example, step 204 includes: querying multiple data to be analyzed in the preset analysis data pool according to the identity identification information, and taking the data to be analyzed with identity identification information among all the data to be analyzed as multiple target analysis data.

[0075] In an implementable manner, referring to Figure 2 , Figure 2To represent a schematic diagram of the data stored in the preset analysis data pool. Here, assume that the target battery silicon wafer undergoes "G1", "G2", "G3", "G4", and "G5" during the manufacturing process. "G1" represents the target process, "G2" and "G3" represent the associated processes of the target process, "G4" and "G5" represent the processes that have no associated relationship with the target process. "G1-Axxx-a" represents the first SPC data generated under the target process, "G1-Axxx-b" represents the first process data generated under the target process, "G2-Axxx-a" and "G3-Axxx-a" both represent the second SPC data generated under the associated processes of the target process, "G2-Axxx-b" and "G3-Axxx-b" both represent the second process data generated under the associated processes of the target process, and "G4-Axxx-a", "G4-Axxx-b", "G5-Axxx-a", and "G5-Axxx-b" are not used as the target analysis data.

[0076] Step 206: Execute the data analysis task to be executed based on multiple target analysis data.

[0077] It should be noted that after finding multiple target analysis data in the preset analysis data pool, it provides an analysis basis for the execution of the data analysis task to be executed. Furthermore, relying on multiple target analysis data, the execution of the data analysis task to be executed can be completed. The data analysis task to be executed can specifically be a query task or a call task. For example, in an implementable manner, assume that the data analysis task to be executed is a call task, and the multiple target analysis data matched in the preset analysis data pool are "G2-Axxx-a" and "G2-Axxx-b". Then the execution process of the data analysis task to be executed can be understood as calling "G2-Axxx-a" and "G2-Axxx-b" for application.

[0078] As an example, step 206 includes: Execute the data analysis task to be executed by calling multiple target analysis data in the preset analysis data pool.

[0079] As another example, step 206 includes: Execute the data analysis task to be executed by viewing multiple target analysis data in the preset analysis interface.

[0080] The method for executing the data analysis task of the above-mentioned battery silicon wafer first determines the data analysis task to be executed set for the target battery silicon wafer. Among them, the data analysis task to be executed carries the identity identification information of the target battery silicon wafer. Then, guided by the identity identification information, multiple target analysis data corresponding to the data analysis task to be executed are matched in the preset analysis data pool. Among them, the multiple target analysis data includes at least two of the first process data generated by the target battery silicon wafer under the target process, the first SPC data generated by the target battery silicon wafer under the target process, the second process data generated by the target battery silicon wafer under the associated process of the target process, and the second SPC data generated by the target battery silicon wafer under the associated process of the target process. That is, it can achieve the purpose of capturing multiple target analysis data of the target battery silicon wafer in different dimensions for data analysis. Finally, based on the multiple target analysis data, the data analysis task to be executed is executed. Since the multiple target analysis data are all matched guided by the identity identification information of the target battery silicon wafer, the orderly correlation of the target battery silicon wafer in the manufacturing process can be objectively reflected through the multiple target analysis data. Therefore, according to the difference of the data analysis task to be executed, different multiple target analysis data can be targeted to be captured to complete the execution, rather than only relying on the data correlation given by the algorithm for the data analysis of the target battery silicon wafer, thus overcoming the technical defect that due to the large amount and complexity of the batch manufacturing process data, the effective analysis of the battery silicon wafer data still cannot be achieved after executing the data analysis task, and thus the situations such as low efficiency or error in data analysis are likely to occur. Therefore, the analysis effect of data analysis on the battery silicon wafer is improved.

[0081] In one embodiment, as Figure 3 shown, when the multiple target analysis data includes the first SPC data, according to the identity identification information, matching the corresponding multiple target analysis data for the data analysis task to be executed in the preset analysis data pool includes:

[0082] Step 302, extract the process-level identity identification information and the wafer-level identity identification information from the identity identification information.

[0083] It should be noted that due to the large amount and complexity of the batch manufacturing process data, in order to improve the matching efficiency of the first SPC data, different dimensions of data can be marked and associated in the data collection stage, that is, various different types of identity identifications are set for the data of the battery silicon wafer in the data collection stage; the process-level identity identification information is used to identify the production process where the target battery silicon wafer is located, which can specifically be the process name, process number, or process sequence, etc.; the wafer-level identity identification information is used to distinguish and identify different battery silicon wafers, which can specifically be the batch number of the battery silicon wafer or the serial number of the battery silicon wafer, etc.; in some feasible embodiments, assuming the identity identification information is "G1-Axxx-b", then "G1" is the process-level identity identification information, and "Axxx-b" is the wafer-level identity identification information.

[0084] As an example, step 302 includes: extracting process-level identity information from the identity information, and extracting wafer-level identity information from the identity information.

[0085] Step 304, according to the process-level identity information, query a plurality of candidate SPC data generated under the target process in which the target cell wafer is located.

[0086] It should be noted that during the execution of the data analysis task to be executed, since the data analysis task to be executed carries identity information, and then through the process-level identity information in the identity information, the target process in which the target cell wafer is located is locked, so that there is no need to screen multiple target analysis data from all the data to be analyzed. For example, in an implementable manner, assume that the preset analysis data pool includes 50 SPC data generated under process A, 50 SPC data generated under process B, and 50 SPC data generated under process C. Then, after a preliminary query through the process-level identity information, it is possible to limit the matching of the first SPC data among the 50 candidate SPC data generated under a certain process. Among them, the 50 SPC data generated under a certain process can be understood as the SPC data corresponding to 50 cell wafers respectively.

[0087] As an example, step 304 includes: among all the data to be analyzed, taking the data to be analyzed carrying the process-level identity information as a plurality of candidate SPC data generated under the target process in which the target cell wafer is located.

[0088] Step 306, according to the wafer-level identity information, query the first SPC data generated by the target cell wafer under the target process from among the plurality of candidate SPC data.

[0089] As an example, step 306 includes: using the wafer-level identity information as an index, querying the first SPC data from among the plurality of candidate SPC data generated under the target process.

[0090] Step 308, taking the first SPC data as the target analysis data that matches the data analysis task to be executed.

[0091] It should be noted that if the plurality of target analysis data includes the first SPC data, then the first SPC data can be quickly queried through the process-level identity information and the wafer-level identity information, and will be used as part of the plurality of target analysis data.

[0092] As an example, step 308 includes: taking the first SPC data as the target analysis data that matches the data analysis task to be executed.

[0093] In this embodiment, when the data to be analyzed in the data analysis task to be executed includes first SPC data, multiple candidate SPC data generated under the target process where the target cell wafer is located can be first screened out from all the data to be analyzed through the process-level identity identification information in the identity identification information. Then, through the wafer-level identity identification information in the identity identification information, the first SPC data generated by the target cell wafer under the target process can be screened out from the multiple candidate SPC data. Therefore, the first SPC data can be quickly matched as part of the multiple target analysis data in the preset analysis data pool through the multi-dimensional identification information in the identity identification information. Therefore, while laying a foundation for improving the analysis effect of data analysis on cell wafers, the matching efficiency of the first SPC data is improved.

[0094] In one embodiment, when the multiple target analysis data includes first process data, according to the identity identification information, matching the corresponding multiple target analysis data for the data analysis task to be executed in the preset analysis data pool includes:

[0095] Determine the in-process traceability information of the target cell wafer in the target process according to the identity identification information; query the first process data generated by the target cell wafer under the target process according to the in-process traceability information; use the first process data as the target analysis data matched to the data analysis task to be executed.

[0096] It should be noted that to improve the collection efficiency of the process data of cell wafers, a mapping relationship between the identity identification information of cell wafers and the in-process traceability information can be established during the data collection stage to facilitate subsequent rapid data matching in different dimensions within the process based on the identity identification information. For example, in an implementable manner, assuming that "G1-Axxx-a" is the identity identification information, "G1-Axxx-b" can be set as the in-process traceability information. Then, with "G1-Axxx-b" as the index, the first process data generated by the target cell wafer under the target process can be traced within the process.

[0097] As an example, using the identity identification information as the index, query the in-process traceability information of the target cell wafer in the target process in the first preset mapping table, where the first preset mapping table is used to store the mapping relationship between the identity identification information of cell wafers and the in-process traceability information; use the in-process traceability information as the index, query the first process data generated by the target cell wafer under the target process from all the data to be analyzed; use the first process data as the target analysis data matched to the analysis task to be executed.

[0098] In this embodiment, when the data to be analyzed in the data analysis task to be executed includes first SPC data, the in-process traceability information of the target battery wafer in the target process can be first queried through the identity identification information. Furthermore, through the in-process traceability information, the first process data generated by the target battery wafer in the target process can be quickly queried. Therefore, the in-process traceability information within the target process can be determined through the identity identification information, and the first process data generated by the target battery wafer in the target process can be quickly traced through the in-process traceability information. Therefore, while laying a foundation for improving the analysis effect of data analysis on battery wafers, the matching efficiency of matching the first process data is improved.

[0099] In one embodiment, when multiple target analysis data include second SPC data, according to the identity identification information, matching corresponding multiple target analysis data for the data analysis task to be executed in a preset analysis data pool includes:

[0100] Extracting process-level identity identification information from the identity identification information; determining the first inter-process traceability information of the target battery wafer in the target process according to the process-level identity identification information; querying the second SPC data generated by the target battery wafer in the associated process according to the first inter-process traceability information; and using the second SPC data as the target analysis data matched to the data analysis task to be executed.

[0101] It should be noted that to improve the collection efficiency of the process data of the battery wafer, a mapping relationship between the identity identification information of the battery wafer and the first inter-process traceability information can be established during the data collection stage, so as to facilitate subsequent rapid data matching between different dimensions among processes based on the identity identification information. Among them, the first inter-process traceability information is used to trace the same type of manufacturing process data generated in the associated process associated with the target process. For example, in an implementable manner, assuming that "G1-Axxx-a" is the identity identification information, then "G2-Axxx-a" or "G3-Axxx-a" can be set as the first inter-process traceability information. Furthermore, taking "G2-Axxx-a" or "G3-Axxx-a" as the index, the first process data generated by the target battery wafer in the target process can be traced among processes.

[0102] As an example, extracting process-level identity identification information from the identity identification information; using the process-level identity identification information as the index to query the first inter-process traceability information of the target battery wafer in the target process in a second preset mapping table, where the first preset mapping table is used to store the mapping relationship between the identity identification information of the battery wafer and the first inter-process traceability information; using the first inter-process traceability information as the index to query the second SPC data generated by the target battery wafer in the associated process from all the data to be analyzed; and using the second SPC data as the target analysis data matched to the analysis task to be executed.

[0103] In this embodiment, when the data to be analyzed for the data analysis task includes the second SPC data, the first inter-process traceability information between the target battery wafer in the target process and the associated process can be first queried through the identity identification information. Then, through the first inter-process traceability information, the second SPC data generated by the target battery wafer in the associated process can be quickly queried. Therefore, the first inter-process traceability information between the target process and the associated process can be determined through the identity identification information, and the second SPC data generated by the target battery wafer in the associated process can be quickly traced through the first inter-process traceability information. Therefore, while laying a foundation for improving the analysis effect of data analysis on the battery wafer, the matching efficiency of the second SPC data is improved.

[0104] In one embodiment, when multiple target analysis data include the second process data, according to the identity identification information, matching the corresponding multiple target analysis data for the data analysis task to be executed in the preset analysis data pool includes:

[0105] Extracting the wafer-level identity identification information from the identity identification information; determining the second inter-process traceability information of the target battery wafer in the target process according to the wafer-level identity identification information; querying the second process data generated by the target battery wafer in the target process according to the second inter-process traceability information; and using the second process data as the target analysis data matched to the data analysis task to be executed.

[0106] It should be noted that to improve the collection efficiency of the process data of the battery wafer, a mapping relationship between the identity identification information of the battery wafer and the second inter-process traceability information can be established during the data collection stage, so as to facilitate subsequent rapid data matching between different dimensions between processes based on the identity identification information. Among them, the second inter-process traceability information is used to trace different types of manufacturing process data generated in the associated process associated with the target process; for example, in an implementable manner, assuming that "G1-Axxx-a" is the identity identification information, then "G2-Axxx-b" or "G3-Axxx-b" can be set as the second inter-process traceability information. Then, using "G2-Axxx-b" or "G3-Axxx-b" as the index, the second process data generated by the target battery wafer in the target process can be traced between processes.

[0107] As an example, extract the wafer-level identity identification information from the identity identification information; use the wafer-level identity identification information as an index to query the second inter-process traceability information of the target cell wafer in the target process in the third preset mapping table, where the third preset mapping table is used to store the mapping relationship between the identity identification information of the cell wafer and the second inter-process traceability information; use the second inter-process traceability information as an index to query the second process data generated by the target cell wafer in the associated process from all the data to be analyzed; and use the second process data as the target analysis data matching the analysis task to be executed.

[0108] In this embodiment, when the data to be analyzed in the analysis task to be executed includes the second process data, the second inter-process traceability information of the target cell wafer between the target process and the associated process can be first queried through the identity identification information, and then, through the second inter-process traceability information, the second process data generated by the target cell wafer in the associated process can be quickly queried. Therefore, the second inter-process traceability information between the target process and the associated process can be determined through the identity identification information, and the second process data generated by the target cell wafer in the associated process can be quickly traced through the second inter-process traceability information. Therefore, while laying a foundation for improving the analysis effect of data analysis on cell wafers, the matching efficiency of the second process data is improved.

[0109] In an implementable manner, before determining the data analysis task to be executed, the terminal can collect data in different dimensions through the deployed data collection system. It can be understood that this embodiment is oriented towards data analysis. In the data collection link of the data collection system, requirements for the collection granularity and collection logic of data in different dimensions are put forward: 1) The granularity of the first SPC data, the second SPC data, the in-process traceability information, the first inter-process traceability information, and the second inter-process traceability information is all at the single-wafer level, and the granularity of the first process data and the second process data is the smallest collection unit in a single operation process. For example, in an implementable manner, the collection requirement for temperature data in a tube equipment is refined to the change data of a single temperature zone and a single temperature sensor during the entire operation process, and the acquisition frequency of each point is less than or equal to 5 s; 2) Requirements for the quality of the collected data are also put forward. Among them, the data accuracy rate of the entire production line in a single shift should be greater than 99%, and the traceability rate should be greater than 90%; 3) To improve the accuracy of long-term data collection and synchronously improve the data call speed, data in different dimensions are marked and associated during the collection stage. Specifically, taking the in-process traceability information and inter-process traceability information (the first inter-process traceability information and the second inter-process traceability information) of the automated equipment as the main line, for the battery wafer ID involved in a single operation within a single process, a group is formed and marked (for example, in a tube equipment, the unique IDs of all battery wafers in the same boat are packed and marked as data group Axxx, that is, G1-Axxx). The data group number is always a unique number. Then, the SPC data generated by all battery wafers in this wafer group under the current process and the corresponding unique wafer ID are packed and marked as "G1-Axxx-a", and the process data generated by this operation is packed and marked as "G1-Axxx-b". Similarly, data of other demand modules can be packed and marked in a corresponding manner, such as c or d, etc. For example, the next process of the current process can be marked as G2-Bxxx-a, and so on; It can be understood that within a process, the smallest collection unit corresponding to a single battery wafer can be located through the in-process traceability information and inter-process traceability information, and multi-process data packets can be connected in series between the front and back processes through the in-process traceability information and inter-process traceability information. Thus, based on the above collection logic, the process data and SPC data generated under different processes are marked and then uploaded to the data processing system, referring to Figure 4 , Figure 4To represent a schematic diagram of the data relationships stored in a data processing system, during the data processing process, relevant data can be quickly called through the unique ID of the battery silicon wafer. Alternatively, the job data group number of a certain process can be first queried through the unique ID of the battery silicon wafer, and then the corresponding module data packet can be retrieved through the job data group number. In addition, the corresponding SPC data within the data packet can be called through the unique ID of the silicon wafer. Through the traceability information within the process, the first process data generated by the target battery silicon wafer under the target process can be located. Through the first inter-process traceability information, the second SPC data generated by the target battery silicon wafer under the associated process can be located, and through the second inter-process traceability information, the second process data generated by the target battery silicon wafer under the associated process can be located.

[0110] In one embodiment, according to multiple target analysis data, perform a data analysis task to be executed, including:

[0111] Determine the data difference characteristics of the multiple target analysis data; according to the multiple data difference characteristics, perform the data analysis task to be executed, where the multiple data difference characteristics include at least one of a data attribute difference characteristic and a data process difference characteristic. The data attribute difference characteristic is used to characterize the difference in data types of multiple target analysis data under the same process, and the data process difference characteristic is used to characterize the difference in multiple target analysis data of the same data type in different processes.

[0112] It should be noted that during the execution of the data analysis task to be executed, different types of tasks can be set based on the different analysis perspectives, with the data difference characteristics of the multiple target analysis data as the benchmark. The data difference characteristics are used to characterize the differences between different target analysis data, including the data attribute difference characteristic and the data process difference characteristic. The data attribute difference characteristic is used to characterize the difference in data types of multiple target analysis data under the same process, and the data process difference characteristic is used to characterize the difference in multiple target analysis data of the same data type in different processes. In some implementable ways, the first SPC data and the first process data reflect the data attribute difference characteristic, the second SPC data and the second process data reflect the data attribute difference characteristic, the first SPC data and the second SPC data reflect the data process difference characteristic, and the first process data and the second process data reflect the data process difference characteristic.

[0113] It should be noted that based on different types of data difference characteristics, multiple target analysis data can be analyzed from different perspectives. For example, in an implementable manner, process analysis can be performed within the target process based on data attribute difference characteristics. Among them, process analysis is a forward analysis, and process analysis relies on five commonly used analysis perspectives in the photovoltaic industry, namely people (responsible person information), machine (equipment machine information), material (material information), method (preparation method process information), and environment (environment information) for numerical monitoring. The above-mentioned multiple target analysis data can be recorded in the process data packet and uploaded to the system. Among them, the analysis methods include: horizontally comparing the differences between SPC data and process data in the same process link within the same period of time to identify problem points, comparing the changes in each monitoring parameter during different operations in the same process and the same operating environment (pipe or tank) to monitor and identify problem points. Further, finding the characteristic values where problems occur can prevent problems from occurring, and matching SPC data or electrical performance data to extract the change trend can find the optimal interval and optimization trend; based on the data process difference characteristics, root cause analysis can be performed between the target process and the associated process. Among them, root cause analysis is a reverse analysis. This method relies on the first process traceability information and the second process traceability information (all collectable data within the single silicon wafer life cycle), and it is necessary to concatenate the data of the front and back processes and combine the process analysis method for analysis. It can be used to identify the characteristic causes of characteristic solar cell products and to identify the abnormal root causes of finished products. For example, for the problem that the film color of some finished product silicon wafers is reddish, the unique ID of these defective wafers can be extracted, and the machine, carrier, and SPC data information can be traced back through the traceability data to check the concentration. If they are all produced by the same machine or carrier, it can be determined as an equipment problem and further investigated. If a certain SPC data deviates significantly from that of normal finished products, it is determined as a process problem and the process information of this process is further traced back for process analysis. It can also be used for the optimization path analysis of finished products. For example, if the electrical performance of some finished products is excellent, after finding the unique ID of the silicon wafers of these products, the SPC data of each process segment can be traced back to analyze the concentration. After finding the key SPC data, the key influencing parameters can be found through process analysis and finally the optimization path can be located.

[0114] As an example, extract the data attribute difference characteristics of multiple target analysis data; analyze the multiple target analysis data according to the data attribute difference characteristics under the data analysis task to be executed.

[0115] As another example, extract the data process difference characteristics of multiple target analysis data; analyze the multiple target analysis data according to the data process difference characteristics under the data analysis task to be executed.

[0116] In this embodiment, during the execution of the data analysis task to be executed, qualitative analysis can be performed on multiple target analysis data based on the data difference characteristics of the multiple target analysis data. Thus, the combination of the multiple target analysis data can be flexibly designed according to the actual analysis requirements of the operator, and relying on the data difference characteristics that can reflect the difference situation between data, the effectiveness of data analysis is ensured. Therefore, from the aspects of the effectiveness and flexibility of data analysis, the analysis effect of data analysis on battery wafers is improved.

[0117] In one embodiment, the multiple data difference characteristics include data attribute difference characteristics and data process difference characteristics; according to the multiple data difference characteristics, performing the data analysis task to be executed includes:

[0118] Dividing multiple first target analysis data from multiple target analysis data according to the data attribute difference characteristics, and dividing multiple second target analysis data from multiple target analysis data according to the data process difference characteristics; selecting the data to be compared and analyzed from the multiple first target analysis data and the multiple second target analysis data; performing the data analysis task to be executed by comparing the data to be compared and analyzed with the standard analysis data.

[0119] It should be noted that in addition to process analysis and root cause analysis, experimental analysis can also be performed on multiple target analysis data. For example, in an implementable manner, if experimental analysis is to be performed, then during the data collection process, the battery wafers in the experimental group and the target battery wafers with unique ID identifiers in the control group are separately grouped and the data is independently stored. When performing experimental analysis, the SPC data of the experimental group and the control group is compared according to certain rules, and after identifying the key SPC data, volume verification is carried out to eliminate contingency; it can be understood that in the processes of process analysis, root cause analysis, and experimental analysis, relevant data in each dimension may be involved. Among them, the standard analysis data can be pre-stored standard SPC data or standard process data, etc.

[0120] As an example, randomly extracting multiple first target analysis data from multiple target analysis data according to the data attribute difference characteristics, and randomly extracting multiple second target analysis data from multiple target analysis data according to the data attribute difference characteristics; randomly selecting a preset number of target analysis data from the multiple first target analysis data and the multiple second target analysis data respectively as the data to be compared and analyzed; performing the data analysis task to be executed by comparing the data to be compared and analyzed with the standard analysis data.

[0121] In this embodiment, during the execution of the data analysis task to be executed, the data analysis task to be executed can be executed based on the comparison result between the standard analysis data and the analysis data to be compared. Thus, the comparative experiment analysis can be flexibly designed based on the actual analysis requirements of the operator, and relying on the data difference characteristics that can reflect the differences between data, the effectiveness of data analysis is ensured. Therefore, from the aspects of the effectiveness and flexibility of data analysis, the analysis effect of data analysis on battery wafers is improved.

[0122] In one embodiment, the data analysis task to be executed includes multiple sub-tasks to be executed for analysis; executing the data analysis task to be executed includes:

[0123] According to the task type of the data analysis task to be executed, prioritize multiple sub-tasks to be executed for analysis to obtain a sub-task ranking result; execute multiple sub-tasks to be executed for analysis in sequence according to the sub-task ranking result.

[0124] It should be noted that during the execution of data analysis by the execution module deployed on the terminal, different task types of the data analysis task to be executed will result in different priorities of target analysis data in different dimensions during the analysis process. For example, in one implementable manner, assuming that multiple target analysis tasks include first SPC data, second SPC data, first process data, and second process data, when the data analysis task to be executed is a process analysis task, the priorities of different target analysis data are first SPC data > second SPC data > first process data > second process data. Assuming that the data analysis task to be executed is a root cause analysis task, then first SPC data < second SPC data < first process data < second process data; the sub-task ranking result is used to represent the analysis order of different sub-tasks to be executed for analysis, where the sub-task to be executed for analysis is used to analyze some of the target analysis data among all the target analysis data.

[0125] As an example, according to the task type of the data analysis task to be executed, determine the target execution order of multiple sub-tasks to be executed for analysis, prioritize multiple sub-tasks to be executed for analysis according to the target execution order to obtain a sub-task ranking result; execute multiple sub-tasks to be executed for analysis in sequence according to the sub-task ranking result.

[0126] In this embodiment, during the process of performing data analysis on multiple target analysis data, different priorities are used to complete the data analysis according to different types of the data analysis task to be executed, which can make the analysis of different target analysis data more flexible. Therefore, the analysis effect of performing data analysis on battery wafers is improved.

[0127] In one embodiment, before matching corresponding target analysis data for a data analysis task to be executed in a preset analysis data pool according to identity identification information, the method further includes:

[0128] Obtain a plurality of original manufacturing process data generated by a target battery wafer under different processes; after all the original manufacturing process data is screened, perform format conversion on the screened plurality of original manufacturing process data to obtain a plurality of manufacturing process data to be processed in a standard format; generate a preset analysis data pool according to the plurality of manufacturing process data to be processed.

[0129] It should be noted that since the batch manufacturing process data is numerous and miscellaneous, for the convenience of executing the data analysis task, data processing needs to be synchronized during the data collection process to construct a preset analysis data pool; for example, in an implementable manner, the data processing flow is as follows: 1) Clean the original data; 2) Convert the data format; 3) Concatenate the single-chip data; 4) Integrate the data. It can be understood that after obtaining a plurality of original manufacturing process data, by preliminarily screening the plurality of original manufacturing process data, problematic data can be eliminated, such as eliminating a small amount of problematic data caused by network or hardware problems, etc. Then, the data format conversion operation is to unify the data with different formats collected from different devices into data in a standard format convenient for subsequent data processing, so as to improve the analysis efficiency and accuracy in the data analysis process. Among them, concatenating the single-chip data means integrating and storing the data of a single battery wafer throughout the manufacturing life cycle for convenient calling during data analysis, and the data integration operation is to construct a preset analysis data pool.

[0130] As an example, collect a plurality of original manufacturing process data generated by a target battery wafer under different processes; screen all the original process data according to a preset data screening rule, and after all the original manufacturing process data is screened, convert the screened plurality of original manufacturing process data into a plurality of manufacturing process data to be processed in a standard format; integrate the plurality of manufacturing process data to be processed into a preset analysis data pool.

[0131] In this embodiment, before matching a plurality of target analysis data for a data analysis task to be executed in a preset analysis data pool, by performing data integration and data format conversion, normal data in different dimensions in a standard format is obtained, and then a preset analysis data pool is integrated through the data integration operation, providing a basis for the matching of a plurality of target analysis data. Therefore, it lays a foundation for improving the analysis effect of performing data analysis on battery wafers.

[0132] In one embodiment, generating a preset analysis data pool according to a plurality of manufacturing process data to be processed includes:

[0133] According to the data attribute information of multiple manufacturing process data to be processed, multiple first manufacturing process data to be processed and multiple second manufacturing process data to be processed are obtained by partitioning the multiple manufacturing process data to be processed; each of the multiple first manufacturing process data to be processed is converted into first data to be analyzed, and data fusion is performed on the multiple second manufacturing process data to be processed to obtain multiple second data to be analyzed; a preset analysis data pool is obtained by integrating the multiple first data to be analyzed and the multiple second data to be analyzed.

[0134] It should be noted that the data processing operation is to calculate and process the data according to a fixed calculation processing logic immediately after the data is collected and store the calculated data, so that the calculated data can be directly called during later calls, thereby saving the time for calling the original manufacturing process data and calculating during data analysis; for example, in an implementable manner, assuming that the film thickness uniformity after single-tube operation needs to be analyzed in the coating process, before integrating the data to construct a preset analysis data pool, a data fusion operation is performed, that is, by setting the film thickness data of each operation data group in the data processing operation, and immediately calculating the average value and standard deviation data of the film thickness of the data group after collection, storing the calculated module data and marking it, and directly calling the module data for display during subsequent data analysis.

[0135] As an example, according to the data attribute information of multiple manufacturing process data to be processed, the multiple manufacturing process data to be processed are partitioned to obtain multiple first manufacturing process data to be processed without data fusion attributes and multiple second manufacturing process data to be processed with data fusion attributes; each of the multiple first manufacturing process data to be processed is converted into first data to be analyzed, and data fusion is performed on the multiple second manufacturing process data to be processed to obtain multiple second data to be analyzed; the multiple first data to be analyzed and the multiple data to be analyzed are jointly integrated into a preset analysis data pool.

[0136] In this embodiment, in the process of constructing a preset analysis data pool, based on the user's data analysis requirements, data fusion is performed on the data with data fusion attributes, so as to obtain second data to be analyzed, so that the second data to be analyzed can be directly extracted as the target analysis data and the to-be-executed data analysis task can be executed in the future. Therefore, it lays a foundation for improving the analysis efficiency of battery silicon wafer data analysis.

[0137] It should be understood that although the steps in the flowcharts involved in the above embodiments are shown in sequence according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise clearly stated in this article, there is no strict order limit for the execution of these steps, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be executed alternately or in turn with at least a part of other steps or steps or stages in other steps.

[0138] Based on the same inventive concept, an embodiment of the present application further provides a device for executing a data analysis task of a battery silicon wafer for implementing the above-mentioned data analysis task execution method of the battery silicon wafer. The solution provided by this device to solve the problem is similar to the solution described in the above method. Therefore, the specific limitations in one or more embodiments of the device for executing a data analysis task of a battery silicon wafer provided below can refer to the limitations on the data analysis task execution method of the battery silicon wafer in the above text, and will not be repeated here.

[0139] In an exemplary embodiment, as Figure 5 shown, a device for executing a data analysis task of a battery silicon wafer is provided, including: a determination module 401, an allocation module 402, and an execution module 403, where:

[0140] The determination module 401 is configured to determine a data analysis task to be executed set for a target battery silicon wafer, where the data analysis task to be executed carries identity identification information of the target battery silicon wafer;

[0141] The matching module 402 is configured to match a corresponding plurality of target analysis data for the data analysis task to be executed in a preset analysis data pool according to the identity identification information, where the plurality of target analysis data includes at least two of the first process data generated by the target battery silicon wafer in the target process, the first SPC data generated by the target battery silicon wafer in the target process, the second process data generated by the target battery silicon wafer in the associated process of the target process, and the second SPC data generated by the target battery silicon wafer in the associated process of the target process;

[0142] The execution module 403 is configured to execute the data analysis task to be executed according to the plurality of target analysis data.

[0143] In one of the embodiments, when the plurality of target analysis data includes the first SPC data, the matching module 402 is further configured to:

[0144] Extract process-level identity identification information and wafer-level identity identification information from the identity identification information;

[0145] According to the process-level identity identification information, query a plurality of candidate SPC data generated under the target process where the target cell wafer is located; according to the wafer-level identity identification information, query the first SPC data generated by the target cell wafer under the target process from the plurality of candidate SPC data; use the first SPC data as the target analysis data matching the data analysis task to be executed.

[0146] In one embodiment, when the plurality of target analysis data includes first process data, the matching module 402 is further configured to:

[0147] Determine the in-process traceability information of the target cell wafer in the target process according to the identity identification information; query the first process data generated by the target cell wafer under the target process according to the in-process traceability information; use the first process data as the target analysis data matching the data analysis task to be executed.

[0148] In one embodiment, when the plurality of target analysis data includes second SPC data, the matching module 402 is further configured to:

[0149] Extract process-level identity identification information from the identity identification information; determine the first inter-process traceability information of the target cell wafer in the target process according to the process-level identity identification information; query the second SPC data generated by the target cell wafer under the associated process according to the first inter-process traceability information; use the second SPC data as the target analysis data matching the data analysis task to be executed.

[0150] In one embodiment, when the plurality of target analysis data includes second process data, the matching module 402 is further configured to:

[0151] Extract wafer-level identity identification information from the identity identification information; determine the second inter-process traceability information of the target cell wafer in the target process according to the wafer-level identity identification information; query the second process data generated by the target cell wafer under the target process according to the second inter-process traceability information; use the second process data as the target analysis data matching the data analysis task to be executed.

[0152] In one embodiment, the execution module 403 is further configured to:

[0153] Determine the data difference characteristics of multiple target analysis data; according to the multiple data difference characteristics, perform the data analysis task to be executed, where the multiple data difference characteristics include at least one of data attribute difference characteristics and data process difference characteristics. The data attribute difference characteristics are used to characterize the differences in data types of multiple target analysis data under the same process, and the data process difference characteristics are used to characterize the differences in multiple target analysis data of the same data type in different processes.

[0154] In one embodiment, the multiple data difference characteristics include data attribute difference characteristics and data process difference characteristics; the execution module 403 is further configured to:

[0155] According to the data attribute difference characteristics, divide multiple target analysis data into multiple first target analysis data, and according to the data process difference characteristics, divide multiple target analysis data into multiple second target analysis data; select the data to be compared and analyzed from the multiple first target analysis data and the multiple second target analysis data; perform the data analysis task to be executed by comparing the data to be compared and analyzed with the standard analysis data.

[0156] In one embodiment, the data analysis task to be executed includes multiple sub-tasks to be executed; the execution module 403 is further configured to:

[0157] According to the task type of the data analysis task to be executed, perform priority sorting on the multiple sub-tasks to be executed to obtain a sub-task sorting result; sequentially execute the multiple sub-tasks to be executed according to the sub-task sorting result.

[0158] In one embodiment, the device is further configured to:

[0159] Obtain multiple original manufacturing process data generated by the target battery silicon wafer under different processes; after all the original manufacturing process data are screened, perform format conversion on the screened multiple original manufacturing process data to obtain multiple manufacturing process data to be processed in a standard format; generate a preset analysis data pool according to the multiple manufacturing process data to be processed.

[0160] In one embodiment, the device is further configured to:

[0161] According to the data attribute information of the multiple manufacturing process data to be processed, divide the multiple manufacturing process data to be processed into multiple first manufacturing process data to be processed and multiple second manufacturing process data to be processed; convert each of the multiple first manufacturing process data to be processed into first data to be analyzed, and perform data fusion on the multiple second manufacturing process data to be processed to obtain multiple second data to be analyzed; obtain a preset analysis data pool by integrating the multiple first data to be analyzed and the multiple second data to be analyzed.

[0162] Each module in the above-described apparatus for performing data analysis tasks on battery silicon wafers can be implemented in whole or in part by software, hardware, or a combination thereof. Each of the above modules can be embedded in the processor of a computer device in hardware form or be independent of it, or can be stored in the memory of the computer device in software form, so that the processor can call and execute the operations corresponding to each of the above modules.

[0163] In an exemplary embodiment, a computer device is provided. The computer device can be a terminal, and its internal structural diagram can be as Figure 6 shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit, and an input device. Among them, the processor, the memory, and the input / output interface are connected through a system bus, and the communication interface, the display unit, and the input device are connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with external terminals in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a mobile cellular network, NFC (Near Field Communication), or other technologies. When the computer program is executed by the processor, it implements a method for performing data analysis tasks on battery silicon wafers. Those skilled in the art can understand that Figure 6 the structure shown in

[0164] is only a block diagram of some structures related to the solution of this application, and does not constitute a limitation on the computer device to which the solution of this application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0165] In an embodiment, a computer device is further provided, including a memory and a processor. A computer program is stored in the memory, and when the processor executes the computer program, it implements the steps in the above method embodiments.

[0166] In an embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by the processor, it implements the steps in the above method embodiments.

[0167] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, database, or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memories. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The databases involved in the embodiments provided in the present application can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., and are not limited thereto. The processors involved in the embodiments provided in the present application can be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, data processing logics based on quantum computing, etc., and are not limited thereto.

[0168] The technical features of the above embodiments can be combined arbitrarily. For the sake of concise description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope recorded in this specification.

[0169] The above embodiments only represent several implementation manners of the present application, and the description is relatively specific and detailed, but it should not be understood as a limitation on the patent scope of the present application by this. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the appended claims.

Claims

1. A method for executing a data analysis task of a battery silicon wafer, characterized in that, The method includes: Determine a data analysis task to be executed for a target battery wafer, where the data analysis task to be executed carries identity identification information of the target battery wafer; According to the identity identification information, match a corresponding plurality of target analysis data for the data analysis task to be executed in a preset analysis data pool, where the plurality of target analysis data includes at least two of the first process data generated by the target battery wafer in a target process, the first SPC data generated by the target battery wafer in the target process, the second process data generated by the target battery wafer in an associated process of the target process, and the second SPC data generated by the target battery wafer in the associated process of the target process; Execute the data analysis task to be executed according to the plurality of target analysis data.

2. The method according to claim 1, characterized in that, When the plurality of target analysis data includes the first SPC data, the step of matching a corresponding plurality of target analysis data for the data analysis task to be executed in a preset analysis data pool according to the identity identification information includes: Extract process-level identity identification information and wafer-level identity identification information from the identity identification information; Query a plurality of candidate SPC data generated by the target battery wafer in the target process according to the process-level identity identification information; Query the first SPC data generated by the target battery wafer in the target process from the plurality of candidate SPC data according to the wafer-level identity identification information; Use the first SPC data as the target analysis data matched to the data analysis task to be executed.

3. The method according to claim 1, characterized in that, When the plurality of target analysis data includes the first process data, the step of matching a corresponding plurality of target analysis data for the data analysis task to be executed in a preset analysis data pool according to the identity identification information includes: Determine in-process traceability information of the target battery wafer in the target process according to the identity identification information; Query the first process data generated by the target battery wafer in the target process according to the in-process traceability information; Use the first process data as the target analysis data matched to the data analysis task to be executed.

4. The method according to claim 1, wherein When the plurality of target analysis data includes the second SPC data, the step of matching a corresponding plurality of target analysis data for the data analysis task to be executed in a preset analysis data pool according to the identity identification information includes: Extract process-level identity identification information from the identity identification information; Determine first inter-process traceability information of the target battery wafer in the target process according to the process-level identity identification information; Query the second SPC data generated by the target battery wafer in the associated process according to the first inter-process traceability information; Use the second SPC data as the target analysis data matched to the data analysis task to be executed.

5. The method according to claim 1, characterized in that When the plurality of target analysis data includes the second process data, the step of matching a corresponding plurality of target analysis data for the data analysis task to be executed in a preset analysis data pool according to the identity identification information includes: Extract the wafer-level identity information from the identity information; Determine the second in-process traceability information of the target cell wafer in the target process according to the wafer-level identity information; Query the second process data generated by the target cell wafer in the target process according to the second in-process traceability information; Use the second process data as the target analysis data matching the to-be-executed data analysis task.

6. The method according to claim 1, characterized in that The executing the to-be-executed data analysis task according to the multiple target analysis data includes; Determine the data difference characteristics of the multiple target analysis data; Execute the to-be-executed data analysis task according to multiple data difference characteristics, where the multiple data difference characteristics include at least one of a data attribute difference characteristic and a data process difference characteristic, the data attribute difference characteristic is used to characterize the difference in data types of multiple target analysis data under the same process, and the data process difference characteristic is used to characterize the difference in multiple target analysis data of the same data type in different processes.

7. The method according to claim 6, characterized in that The multiple data difference characteristics include the data attribute difference characteristic and the data process difference characteristic; the executing the to-be-executed data analysis task according to multiple data difference characteristics includes: Divide multiple first target analysis data from the multiple target analysis data according to the data attribute difference characteristic, and divide multiple second target analysis data from the multiple target analysis data according to the data process difference characteristic; Select the to-be-compared analysis data from the multiple first target analysis data and the multiple second target analysis data; Execute the to-be-executed data analysis task by comparing the to-be-compared analysis data and the standard analysis data.

8. The method according to claim 1, wherein The to-be-executed data analysis task includes multiple to-be-executed analysis subtasks; The executing the to-be-executed data analysis task includes: Rank the multiple to-be-executed analysis subtasks according to the task type of the to-be-executed data analysis task to obtain a subtask ranking result; Execute the multiple to-be-executed analysis subtasks in sequence according to the subtask ranking result.

9. The method according to claim 1, wherein Before matching the corresponding target analysis data for the to-be-executed data analysis task in the preset analysis data pool according to the identity information, the method further includes: Obtain multiple original manufacturing process data generated by the target cell wafer under different processes; After all the original manufacturing process data is screened, perform format conversion on the screened multiple original manufacturing process data to obtain multiple to-be-processed manufacturing process data in a standard format; Generate a preset analysis data pool according to the multiple to-be-processed manufacturing process data.

10. The method according to claim 9, wherein The generating a preset analysis data pool according to the multiple to-be-processed manufacturing process data includes: Divide multiple first to-be-processed manufacturing process data and multiple second to-be-processed manufacturing process data from the multiple to-be-processed manufacturing process data according to the data attribute information of the multiple to-be-processed manufacturing process data; Convert each of the multiple pieces of first manufacturing process data to be processed into first data to be analyzed, and perform data fusion on the multiple pieces of second manufacturing process data to be processed to obtain multiple pieces of second data to be analyzed; Obtain a preset analysis data pool by integrating the multiple pieces of first data to be analyzed and the multiple pieces of second data to be analyzed.

11. An apparatus for executing a data analysis task of a battery silicon wafer, characterized in that, The device includes: A determination module, configured to determine a data analysis task to be executed for a target battery silicon wafer, where the data analysis task to be executed carries identity identification information of the target battery silicon wafer; A matching module, configured to match corresponding multiple target analysis data for the data analysis task to be executed in the preset analysis data pool according to the identity identification information, where the multiple target analysis data includes at least two of the first process data generated by the target battery silicon wafer in a target process, the first SPC data generated by the target battery silicon wafer in the target process, the second process data generated by the target battery silicon wafer in an associated process of the target process, and the second SPC data generated by the target battery silicon wafer in the associated process of the target process; An execution module, configured to execute the data analysis task to be executed according to the multiple target analysis data.

12. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, the steps of the method according to any one of claims 1 to 10 are implemented.

13. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, the steps of the method according to any one of claims 1 to 10 are implemented.

14. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, the steps of the method according to any one of claims 1 to 10 are implemented.

Images