Product yield prediction method, device, computer device and storage medium

Abstract

The present invention provides a product yield prediction method, a product yield prediction device, a computer device and a storage medium, the method comprising: obtaining quality data information of products in historical production records, calculating product yield data information according to the quality data information; inputting the yield data information of the product into at least one analysis model, calculating the influence ratio of the defective factor corresponding to each analysis model on the product yield; judging whether the influence ratio of at least one defective factor on the product yield can be reduced by a preset method according to set conditions; if it can be reduced, adjusting the influence ratio of the defective factor on the product yield according to the preset method, and then calculating the first predicted yield of the planned production of the product according to the adjusted influence ratio. The method can realize real-time tracking of production line yield, prediction of future yield, and propose improvement methods for improving future yield.

Description

Technical Field

[0001] The present invention relates to the field of product yield prediction, and in particular to a product yield prediction method, a product yield prediction device, a computer device and a storage medium. Background Art

[0002] During the production process of the product, the yield of each link in the production process will be statistically analyzed, such as the yield of each site, process, team, and production line. The existing statistical method for defective items is to obtain the data through manual swiping of data forms. Engineers analyze the causes of the yield and develop improvement measures. After the improvement measures are implemented, manual tracking and feedback on the improvement effects are required. The existing yield tracking and improvement methods are time-consuming and labor-intensive, and rely entirely on manpower to complete, and it is impossible to formulate response strategies in advance to prevent the production of defective products. Summary of the invention

[0003] In view of the above, it is necessary to propose a product yield prediction method and device, a computer device and a storage medium, which can realize real-time tracking of production line yield, predict future yield, propose improvement methods for improving future yield, and track the improvement effect of the improvement method.

[0004] A first aspect of the present application provides a product yield prediction method, the method comprising:

[0005] Obtaining product quality data information from historical production records, and calculating product yield data information based on the quality data information;

[0006] Inputting the yield data information of the product into at least one analysis model, and calculating the influence ratio of the defective factors corresponding to each analysis model on the yield of the product, wherein the at least one analysis model includes one or more of a personnel factor analysis model, a machine factor analysis model, an environmental factor analysis model, a production material factor analysis model, an operating method factor analysis model, and a software factor analysis model;

[0007] Determine, according to the set conditions, whether the influence ratio of at least one of the bad factors on the product yield can be reduced by a preset method;

[0008] If it can be reduced, the influence ratio of the defective factor on the product yield is adjusted according to the preset method, and then the first predicted yield of the planned production of the product is calculated according to the adjusted influence ratio.

[0009] Preferably, the method further comprises:

[0010] Sending the preset method to a preset person;

[0011] Receiving instructions from a preset person on whether to implement the preset method;

[0012] If the instruction is to implement the preset method, then the influence ratio of the defective factor on the product yield is adjusted according to the preset method, and then the first predicted yield of the planned production of the product is calculated according to the adjusted influence ratio;

[0013] If the instruction is not to implement the preset method, the defective rate of producing the product within a preset historical time period calculated based on the quality data information is used as the first predicted yield of the planned production of the product.

[0014] Preferably, the method of obtaining product quality data information in historical production records and calculating product yield data information based on the quality data information includes:

[0015] The historical quality data information of the product produced is obtained through the set selection conditions, and the product yield data information is generated by the obtained historical quality data information through a preset algorithm, wherein the selection conditions include: one or more of the product model to be produced, building, section, line, work order, capacity, color, time, work station, defective item, material, manufacturer, production team, and material manufacturer production date;

[0016] The quality data information includes: one or more of: product serial number, number of qualified tests at each site, number of unqualified tests at each site, assembly line, assembly time, test line, defective workstation, defective item, test time, functional material inventory and consumption information, functional material manufacturer and production date information, consumable material inventory and consumption information, consumable material manufacturer and production date information, and consumable material collection information;

[0017] The yield data information includes: one or more of: total yield target, site yield target, project yield target, total yield, segment yield, workstation yield, defective items, defective rate of defective items, material combination yield, and material manufacturer defective rate.

[0018] Preferably, the yield data information is output in the form of a yield report within a preset period according to the selection condition, wherein the form of the yield report includes one or more of a table, a graph, and text.

[0019] Preferably, the method of judging whether the influence ratio of the at least one defective factor on the product yield can be reduced by a preset method according to the set conditions comprises:

[0020] According to the defective factors affecting the production yield of the product, searching in a preset yield database whether there is a preset method corresponding to the defective factor to reduce the influence ratio of the at least one defective factor on the product yield;

[0021] If so, it is determined that the influence ratio of the at least one defective factor on the product yield can be reduced by a preset method.

[0022] Preferably, the method further comprises: obtaining a real-time yield of producing the product, and comparing the real-time yield with the first predicted yield;

[0023] If the real-time yield is less than the first predicted yield, query whether to execute the instruction of implementing the preset method to adjust the influence ratio of the defective factor on the product yield;

[0024] If the instruction for implementing the preset method is not executed, the preset method is implemented to adjust the influence ratio of the defective factor on the product yield;

[0025] If the instruction for implementing the preset method has been executed, a prompt message is issued, and the prompt message is used to remind the user to re-analyze the defective factors in producing the product.

[0026] Preferably, the product yield data information is input into the personnel factor analysis model, and the method for calculating the influence ratio of the personnel factor on the product yield is:

[0027] Calculating the relative yield of a first preset time period and the relative yield of a second preset time period within a set period, and determining the influence ratio of the personnel factor on the product yield through a mapping relationship between the preset relative yield and the influence ratio of the personnel factor, wherein the set period includes a plurality of first preset time lengths and a plurality of second preset time lengths, each of the first preset time lengths includes a plurality of first time periods, and each of the first preset time lengths includes a plurality of second time periods;

[0028] The relative yield of the first time period is equal to the maximum yield within the first preset time length of the time period minus the average yield of the corresponding time period in each first preset time length within the set period;

[0029] The relative yield of the second time period is equal to the average yield of multiple first preset time periods within the set period minus the yield of the second time period.

[0030] Preferably, the product yield data information is input into the machine factor analysis model, and the method for calculating the influence ratio of the machine factor on the product yield is:

[0031] Searching for yield data information of the product produced within a set historical time, wherein the yield data information includes the defective rate of defective items in the production of the product;

[0032] Searching the proportion of machine factors affecting product yield in a defective item database, wherein the defective item database stores the defective rate of defective items in producing the product and the name of the defective factor that produces the defective rate;

[0033] The proportion of the machine factor affecting the product yield is the product of the ratio of the machine factor affecting the product yield found and the defective rate of the defective item.

[0034] Preferably, the method of inputting the product yield data information into the environmental factor analysis model and calculating the influence ratio of the environmental factor on the product yield includes:

[0035] Searching for yield data information of the product produced within a set historical time, wherein the yield data information is the defective rate of defective items in the production of the product;

[0036] Searching for the proportion of environmental factors affecting product yield in a defective item database, wherein the defective item database stores the defective rate of defective items in producing the product and the names of defective factors that produce the defective rate;

[0037] The ratio of the environmental factors affecting the product yield is the product of the ratio of the environmental factors affecting the product yield found and the defective rate of the defective items.

[0038] Preferably, the method of inputting the product yield data information into a production material factor analysis model and calculating the influence ratio of the production material factor on the product yield includes:

[0039] Searching for yield data information of the product produced within a set historical time, wherein the yield data information includes defective item defective rate, incoming material defective rate of the product, and usage status information of consumables;

[0040] Searching the proportion of production material factors affecting product yield in a defective item database, wherein the defective item database stores the defective rate of defective items of the product and the names of defective factors that produce the defective rate, and the production materials include at least one of functional materials and consumables;

[0041] When the production material is a functional material, the ratio of the production material factor affecting the product yield is the product of the ratio of the functional material affecting the product yield and the defective rate of the incoming material of the product;

[0042] When the production material is a consumable, determine whether the consumable is used in the current product based on the usage status information of the consumable. If the consumable is used in the current product, search the quality data information for the historical defective item rate of the consumable according to the name of the consumable, and use the historical defective item rate of the consumable as the ratio of the production material factor affecting the product yield;

[0043] When the production materials include functional materials and consumables, the defective rate obtained by adding the proportion of the functional materials affecting the product yield and the proportion of the consumables affecting the product yield is used as the proportion of the production material factor affecting the product yield.

[0044] Preferably, the method of inputting the product yield data information into the operating method factor analysis model and calculating the influence ratio of the operating method factor on the product yield includes:

[0045] Searching for yield data information of the product produced within a set historical time, wherein the yield data information includes the defective rate of defective items in the production of the product;

[0046] Obtain a database of defective items affected by operating method factors, and find the proportion of the operating method factors affecting the product yield, wherein the defective item database stores the defective rate of the defective items in producing the product and the name of the defective factor that produces the defective rate;

[0047] The ratio of the operating technique factor affecting the product yield is the product of the ratio of the production operation affecting the product yield and the defective rate of the defective items of the product.

[0048] Preferably, the method of inputting the product yield data information into a software factor analysis model and calculating the influence ratio of the software factor on the product yield includes:

[0049] Searching for yield data information of the product produced within a set historical time, wherein the yield data information includes the defective rate of defective items in the production of the product;

[0050] Obtaining a database of defective items affected by software factors, and searching for the proportion of software factors affecting product yield, wherein the defective item database stores the defective rate of defective items in producing the product and the name of the defective factor that produces the defective rate;

[0051] The ratio of the software factor affecting the product yield is the product of the ratio of the software factor affecting the product yield and the defective rate of the defective items of the product.

[0052] A second aspect of the present application provides a product yield prediction device, the device comprising:

[0053] An acquisition module is used to acquire product quality data information in historical production records and calculate product yield data information based on the quality data information;

[0054] An analysis module, used to input the yield data information of the product into at least one analysis model, and calculate the influence ratio of the defective factor corresponding to each analysis model on the yield of the product, wherein the at least one analysis model includes one or more of a personnel factor analysis model, a machine factor analysis model, an environmental factor analysis model, a production material factor analysis model, an operating method factor analysis model, and a software factor analysis model;

[0055] A judgment module, used to judge whether the influence ratio of at least one of the bad factors on the product yield can be reduced by a preset method according to the set conditions;

[0056] The output module is used to adjust the influence ratio of the defective factor on the product yield according to the preset method if it can be reduced, and then calculate the first predicted yield of the planned production of the product according to the adjusted influence ratio.

[0057] A third aspect of the present application provides a computer device, the computer device comprising a processor, the processor being configured to implement the product yield prediction method as described above when executing a computer program stored in a memory.

[0058] A fourth aspect of the present application provides a storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the product yield prediction method as described above.

[0059] The product yield prediction method, product yield prediction device, computer device and storage medium of the present invention solve the problem that the current yield tracking and improvement method is time-consuming and labor-intensive, relies entirely on manpower, and cannot formulate response strategies in advance to prevent the generation of defective products. The present invention can obtain the production line yield in real time, estimate the adverse factors that affect the product yield and provide solutions, and track the accuracy of the solutions. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] Figure 1 It is a schematic diagram of the application environment architecture of the product yield prediction method provided by one embodiment of the present invention.

[0061] Figure 2 It is a flow chart of a product yield prediction method provided by an embodiment of the present invention.

[0062] Figure 3 It is a structural schematic diagram of a product yield prediction device provided by an embodiment of the present invention.

[0063] Figure 4 It is a schematic diagram of a computer device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0064] In order to more clearly understand the above-mentioned purpose, features and advantages of the present invention, the present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.

[0065] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. The embodiments described are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0066] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art of the present invention. The terms used in the specification of the present invention herein are only for the purpose of describing specific embodiments and are not intended to limit the present invention.

[0067] Embodiment 1

[0068] See also Figure 1 , which is a schematic diagram of an application environment architecture of a product yield prediction method provided by an embodiment of the present invention.

[0069] The product yield prediction method in the present invention is applied in a computer device 1, and the computer device 1 and at least one production equipment 2 establish a communication connection through a network. The production equipment 2 sends the product quality data acquired in real time to the computer device 1, and the product quality data includes the serial number of the product, the number of products that meet the quality requirements of each site test, the number of products that do not meet the quality requirements of each site test, the assembly line, the assembly time, the test line, the defective station, the defective item, the test time, the material manufacturer, the production date of the material manufacturer, the inventory status of the material manufacturer, etc. After analyzing and arranging the received quality data, the computer device 1 predicts the yield of the product, analyzes the cause of the defective rate and provides a solution, and tracks and feedbacks the improvement effect of the solution. The computer device 1 is also used to store a yield database and a defective item database. The yield database is used to store preset methods corresponding to defective factors to reduce the influence ratio of the at least one defective factor on the product yield. The defective item database is used to store the defective rate of defective items of the production product and the name of the defective factor that produces the defective rate. The network may be a wired network or a wireless network, such as radio, Wireless Fidelity (WIFI), cellular, satellite, broadcast, etc.

[0070] The computer device 1 may be a computer device installed with product yield prediction software, such as a personal computer, a server, etc., wherein the server may be a single server, a server cluster, a cloud server, etc.

[0071] The production equipment 2 can be a machine for producing products, or a testing equipment for testing product quality.

[0072] Embodiment 2

[0073] See also Figure 2 FIG. 1 is a flowchart of a product yield prediction method provided by an embodiment of the present invention. According to different requirements, the order of the steps in the flowchart can be changed, and some steps can be omitted.

[0074] Step S1, obtaining product quality data information from historical production records, and calculating product yield data information based on the quality data information.

[0075] In one embodiment of the present invention, the computer device 1 obtains product quality data information in historical production records by setting conditions, and generates product yield data information using a preset algorithm using the obtained quality data information.

[0076] The set conditions may include: product model to be produced, building, section, production line, production work order, capacity, color, time, work station, production team, defective items, materials, material manufacturer, and material production date.

[0077] The quality data information may include: product serial number, the number of products that have passed the test at each site, the number of products that have failed the test at each site, assembly line, assembly time, test line, defective workstation, defective item, test time, functional material inventory and consumption information, functional material manufacturer and production date information, consumable material inventory and consumption information, consumable material manufacturer and production date information, and consumable material collection information.

[0078] Methods for calculating the defect rate of each item, site yield, segment yield, total yield and major defect items according to the preset algorithm may include:

[0079] Project defect rate = number of unqualified projects / number of corresponding project site inputs;

[0080] Project yield rate = 1 - project defect rate;

[0081] Site yield = number of qualified sites / number of corresponding sites invested;

[0082] Segment yield = site 1 yield * ... * site N yield;

[0083] Total yield = segment 1 yield *… * segment N yield.

[0084] The yield data information may include: overall yield target, site yield target, project yield target, overall yield, segment yield, workstation yield, defective items, defective rate of defective items, material combination yield, and material manufacturer defective rate.

[0085] For example, the quality data information of the product to be produced is obtained according to different preset conditions selected by the user to calculate the product yield data.

[0086] The yield is calculated based on the selected basic information, the basic information includes one or more of the floor, section, line, work order, capacity, color, and product type. The calculation method includes screening the serial numbers of qualified products. The selected condition yield = the number of qualified machines tested / the total number of machines

[0087] The yield is calculated based on the selected defective item information, wherein the defective item information includes one or more of defective items and defective workstations. The calculation method includes screening the product serial numbers that meet the conditions. The selected condition yield = the number of qualified machine tests / the total number of machines

[0088] The yield is calculated based on the selected material matching information, the material matching information includes one or more of the material, manufacturer, and production date. The calculation method includes screening the serial numbers of qualified products, and the selected condition yield = the number of qualified machines tested / the total number of machines.

[0089] In another embodiment of the present invention, the yield data information may also include classified storage of historical defective items, wherein the stored content may include the categories of defective factors in historical defective items, the defective proportions of known defective factors in historical defective items, and the specific defective causes of defective factors in historical defective items.

[0090] In other embodiments of the present invention, the step may further include, according to the selection conditions, outputting the yield data information in the form of a yield report within a preset period, wherein the form of the yield report may include one or more of a table, a graph, and a text. For example, the computer device 1 organizes the quality data information of the product to be produced acquired according to the preset conditions to generate a visual quality data report. The visual quality data report may display the following information content: daily yield unit data, customized yield query unit. The content of the daily yield unit data includes: a machine model yield trend chart, a segment input and yield detail table, a defective item and defective rate detail table. The content of the customized yield query unit includes: a multiple selection column, a weekly yield trend chart of the selected conditions, a defective item and defective rate detail table, a segment input and yield detail table. In some embodiments, the step further includes sending the yield report to a designated contact person in a preset manner. Among them, the preset manner includes selectively sending the yield report to a designated contact person according to the content of the yield report, as well as information such as the frequency and time of sending the yield report. The contact person may be a designated person in charge, or the designated contact information may be input as needed.

[0091] Step S2: input the yield data information of the product into at least one analysis model, and calculate the influence ratio of the defective factor corresponding to each analysis model on the yield of the product.

[0092] In one embodiment of the present invention, the adverse factors may include personnel factors, machine factors, environmental factors, production material factors, operating method factors, and software factors.

[0093] The analysis model may include a personnel factor analysis model, a machine factor analysis model, an environmental factor analysis model, a production material factor analysis model, an operating method factor analysis model, and a software factor analysis model.

[0094] The product yield data information is input into the personnel factor analysis model, and the method for calculating the influence ratio of the personnel factor on the product yield is:

[0095] Calculating the relative yield of a first preset time period and the relative yield of a second preset time period within a set period, and determining the influence ratio of the personnel factor on the product yield through a mapping relationship between the preset relative yield and the influence ratio of the personnel factor, wherein the set period includes a plurality of first preset time lengths and a plurality of second preset time lengths, each of the first preset time lengths includes a plurality of first time periods, and each of the first preset time lengths includes a plurality of second time periods;

[0096] The relative yield of the first time period is equal to the maximum yield within the first preset time length of the time period minus the average yield of the corresponding time period in each first preset time length within the set period;

[0097] The relative yield of the second time period is equal to the average yield of multiple first preset time periods within the set period minus the yield of the second time period.

[0098] In one embodiment, the set period is one month, the first preset time length is a weekday, and the second preset time length is a holiday time, and the holidays include New Year's Day, Spring Festival, May Day, Qingming Festival, Dragon Boat Festival, Mid-Autumn Festival, National Day, Sunday and other statutory holidays;

[0099] Calculate the total yield rate and daily yield rate within the set period, and mark the maximum yield rate per week;

[0100] Calculate the average yield rate for all dates except holidays within the set period;

[0101] Calculate the yield rate during holidays within the set period;

[0102] Calculate the average yield from Monday to Saturday excluding holidays during the time period;

[0103] Calculate the average yield on Monday = (yield on Monday of the first week + ... yield on Monday of the Nth week) / N;

[0104] …

[0105] Calculate the average yield rate on Saturday = (yield rate on Saturday of the first week + ... yield rate on Saturday of the Nth week) / N;

[0106] Thus, the relative yield from Monday to Saturday is calculated:

[0107] Relative yield on Monday = maximum yield of the week - average yield on Monday;

[0108] …

[0109] Relative yield on Saturday = maximum yield in a week - average yield on Saturday;

[0110] Calculate the relative yield rate during holidays: relative yield rate during holidays = average yield rate within the set period excluding holidays - holiday yield rate;

[0111] The influence ratio of the personnel factor on the product yield is determined by the preset mapping relationship between the relative yield and the influence ratio of the personnel factor. For example, if the relative yield on Monday is 1.5%, and the preset mapping relationship between the relative yield and the influence ratio of the personnel factor is 1:1, then the calculation results show that the influence ratio of the personnel factor on the product yield on Monday is 1.5%, and so on, the influence ratio of the personnel factor on the product yield on different working days is calculated. The ratio changes in real time according to the different time periods.

[0112] The product yield data information is input into the machine factor analysis model, and the method for calculating the influence ratio of the machine factor on the product yield is:

[0113] Searching for yield data information of the product produced within a set historical time, wherein the yield data information includes the defective rate of defective items in the production of the product;

[0114] Searching the proportion of machine factors affecting product yield in a defective item database, wherein the defective item database stores the defective rate of defective items in producing the product and the name of the defective factor that produces the defective rate;

[0115] The proportion of the machine factor affecting the product yield is the product of the ratio of the machine factor affecting the product yield found and the defective rate of the defective item.

[0116] The method of inputting the product yield data information into an environmental factor analysis model and calculating the influence ratio of environmental factors on the product yield includes:

[0117] Searching for yield data information of the product produced within a set historical time, wherein the yield data information is the defective rate of defective items in the production of the product;

[0118] Searching for the proportion of environmental factors affecting product yield in a defective item database, wherein the defective item database stores the defective rate of defective items in producing the product and the names of defective factors that produce the defective rate;

[0119] The ratio of the environmental factors affecting the product yield is the product of the ratio of the environmental factors affecting the product yield found and the defective rate of the defective items.

[0120] The method of inputting the product yield data information into a production material factor analysis model and calculating the influence ratio of the production material factor on the product yield includes:

[0121] Searching for yield data information of the product produced within a set historical time, wherein the yield data information includes defective item defective rate, incoming material defective rate of the product, usage status information of consumables, and inventory status information of consumables;

[0122] Searching the proportion of production material factors affecting product yield in a defective item database, wherein the defective item database stores the defective rate of defective items of the product and the names of defective factors that produce the defective rate, and the production materials include at least one of functional materials and consumables;

[0123] When the production material is a functional material, the ratio of the production material factor affecting the product yield is the product of the ratio of the functional material affecting the product yield and the defective rate of the incoming material of the product;

[0124] When the production material is a consumable, determine whether the consumable is used in the current product based on the usage status information of the consumable. If the consumable is used in the current product, search the quality data information for the historical defective item rate of the consumable according to the name of the consumable, and use the historical defective item rate of the consumable as the ratio of the production material factor affecting the product yield;

[0125] When the production materials include functional materials and consumables, the defective rate obtained by adding the proportion of the functional materials affecting the product yield and the proportion of the consumables affecting the product yield is used as the proportion of the production material factor affecting the product yield.

[0126] The method of inputting the product yield data information into the operating method factor analysis model and calculating the influence ratio of the operating method factor on the product yield includes:

[0127] Searching for yield data information of the product produced within a set historical time, wherein the yield data information includes the defective rate of defective items in the production of the product;

[0128] Obtain a database of defective items affected by operating method factors, and find the proportion of the operating method factors affecting the product yield, wherein the defective item database stores the defective rate of the defective items in producing the product and the name of the defective factor that produces the defective rate;

[0129] The ratio of the operating technique factor affecting the product yield is the product of the ratio of the production operation affecting the product yield and the defective rate of the defective items of the product.

[0130] The method of inputting the product yield data information into a software factor analysis model and calculating the influence ratio of the software factor on the product yield includes:

[0131] Searching for yield data information of the product produced within a set historical time, wherein the yield data information includes the defective rate of defective items in the production of the product;

[0132] Obtaining a database of defective items affected by software factors, and searching for the proportion of software factors affecting product yield, wherein the defective item database stores the defective rate of defective items in producing the product and the name of the defective factor that produces the defective rate;

[0133] The ratio of the software factor affecting the product yield is the product of the ratio of the software factor affecting the product yield and the defective rate of the defective items of the product.

[0134] The influence ratio of the bad factors that affect the product production yield analyzed by the personnel factor analysis model, the machine factor analysis model, the environmental factor analysis model, the production material factor analysis model, the operation method factor analysis model, and the software factor analysis model are used to search for the causes of the bad factors in the bad project database, and to search for the preset method corresponding to the bad factors in the yield database to reduce the influence ratio of at least one bad factor on the product yield; if it exists, it is determined that the influence ratio of at least one bad factor on the product yield can be reduced by the preset method. In another embodiment of the present invention, the method also includes sending the preset method to the preset personnel; receiving the instruction of the preset personnel whether to implement the preset method; if the instruction is to implement the preset method, adjusting the influence ratio of the bad factors on the product yield according to the preset method.

[0135] For example, the model of the product to be generated is A-001, and the product is generated by three production lines A, B, and C. The production quality data of the online products of the three production lines are captured within a preset historical time. The preset historical time can be one day, one week, one month, or one year. The length of the preset historical time depends on the life cycle of the product. If it is a product in the trial production period, the preset historical time is set to be shorter, which can be one day or one week. If it is a product in the mass production period, the preset historical time can be set to four weeks, eight weeks, ten weeks, etc. In one embodiment, between October 6, 2019 and October 12, 2019, production line A put into production 1000 pieces, 990 pieces passed the test, and 10 pieces failed the test; production line B put into production 1000 pieces, 980 pieces passed the test, and 20 pieces failed the test; production line C put into production 1000 pieces, 990 pieces passed the test, and 10 pieces failed the test; production line D put into production 1000 pieces, 990 pieces passed the test, and 10 pieces failed the test. From the above data, the yield of production line A is 99%, the yield of production line B is 98%, the yield of production line C is 99%, the yield of production line D is 99%, the defective rate of production line A is 1%, the defective rate of production line B is 2%, the defective rate of production line C is 1%, and the defective rate of production line D is 1%. From this, it can be obtained that the yield of the product with product model A-001 is 1-1%-2%-1%-1%=95%.

[0136] The product yield of 95% of product model A-001 between October 6, 2019 and October 12, 2019 was brought into multiple defect factor analysis models for analysis. The analysis showed that the proportion of the impact of personnel factors on the yield of production line A was 0.1%, the proportion of the impact of machine factors on the yield of production line A was 0.02%, the proportion of the impact of production material factors on the yield of production line A was 0.02%, the proportion of the impact of operating method factors and machine factors on the yield of production line A was 0, and the proportion of the impact of software factors on the yield of production line A was 0. Through the influence ratio of personnel factors, machine factors, environmental factors, production material factors, operating method factors and software factors, the defective items related to the personnel factors, machine factors, environmental factors, production material factors, operating method factors and software factors and the causes of the defective items are searched in the defective item database to determine whether there is a preset method corresponding to the defective factor in the yield database to reduce the influence ratio of the at least one defective factor on the product yield; if so, it is determined that the influence ratio of the at least one defective factor on the product yield can be reduced by the preset method.

[0137] In another embodiment of the present invention, it also includes analyzing the concentration status of the defective items of the first preset yield, and the concentration status includes whether there is test line concentration, test fixture concentration, assembly line concentration, assembly shift concentration, material manufacturer concentration, and material production date concentration.

[0138] The method for determining the concentration status may include searching for the defective cause of the defective item in a defective item database according to the name of the defective item, searching for a solution to the defective item in a yield database, and analyzing the concentration status in the solution to determine whether there is test line concentration, test fixture concentration, assembly line concentration, assembly shift concentration, material manufacturer concentration, and material production date concentration in the solution.

[0139] For example, if the name of the defective item is a bright line on the display screen, the causes of the bright line on the display screen are searched in the defective item database according to the defective name, which are respectively personnel factors, machine factors, and production material factors, and the solution to the defect is searched in the yield database. The solution to the personnel factor is to strengthen the training of the operator, the solution to the machine factor is to perform regular maintenance on the machine, and the solution to the production material factor is to require the supplier to control the quality of the incoming materials. The three solutions are compared with the centralized conditions that have appeared in history to determine whether the three solutions have centralized problems. After comparison, it is found that the corresponding solutions of the production material factor are all for the materials of the same production date, so the production material factor has a centralized problem. The defective items, the causes of the defective items, and the centralized conditions of the production material factors are sent to the designated staff, and the staff determines whether the solution to the centralized condition in history is applicable to the current defective item. If the solution is applicable to the current defective item, the staff sends an instruction to agree to execute the solution to the computer device 1. If the solution is not applicable to the current defective item, the second staff formulates a new solution and sends the solution to the computer device 1, and the computer device 1 stores the solution in the yield database.

[0140] In other embodiments of the present invention, the step further includes that the computer device 1 displays the first predicted yield in the form of a visual chart. Among them, the content of the visual chart may include: a set cycle yield prediction chart, a man-machine-material-method-environment-soft analysis chart (personnel factor, machine factor, environmental factor, production material factor, operation method factor, software factor analysis chart), a concentration analysis chart (test line concentration, test fixture concentration, assembly line concentration, assembly shift concentration, material manufacturer concentration, material production date concentration, box and whisker chart, production process capability control chart), a system recommended yield adjustment data chart, and a material input ratio control detail pop-up window.

[0141] Step S3: judging whether the influence ratio of at least one of the defective factors on the product yield can be reduced by a preset method according to the set conditions.

[0142] The method of judging whether the influence ratio of the at least one defective factor on the product yield can be reduced by a preset method according to the set conditions comprises:

[0143] According to the defective factors affecting the production yield of the product, searching in a preset yield database whether there is a preset method corresponding to the defective factor to reduce the influence ratio of the at least one defective factor on the product yield;

[0144] If so, it is determined that the influence ratio of the at least one defective factor on the product yield can be reduced by a preset method.

[0145] In another embodiment of the present invention, if there is a preset method corresponding to the production material factor in the preset yield database to reduce the impact ratio of the production material factor on the product yield, it is also necessary to find the inventory data information of the corresponding material in the preset method to determine whether the inventory quantity of the corresponding material in the preset method meets the production requirements of the product to be produced. If the inventory quantity of the corresponding material in the preset method can meet the production requirements of the product to be produced, then the preset method is determined to be an available method for reducing the impact ratio of the production material factor on the product yield. If the inventory quantity of the corresponding material in the preset method is not enough to meet the production requirements of the product to be produced, then the name of the alternative material of the material and the inventory information of the alternative material are searched. If the inventory information of the alternative material can meet the production requirements of the product to be produced, then the alternative material is used as an available method to solve the impact ratio of the production material factor on the product yield.

[0146] Step S4: If it can be reduced, then adjust the influence ratio of the defective factor on the product yield according to the preset method, and then calculate the first predicted yield of the planned production of the product according to the adjusted influence ratio.

[0147] The calculation method of the first predicted yield may be:

[0148] Adjusted product defect rate = product defect rate - (adjusted ratio of personnel factors affecting product yield + adjusted ratio of machine factors affecting product yield + adjusted ratio of environmental factors affecting product yield + adjusted ratio of production material factors affecting product yield + adjusted ratio of operating method factors affecting product yield + adjusted ratio of software factors affecting product yield)

[0149] The first predicted yield rate = 1-adjusted product defect rate.

[0150] In another embodiment of the present invention, the steps further include: the computer device 1 sends the improvement plan for the defective project to the user terminal in a preset manner; the user terminal can selectively receive the improvement plan as needed, and send the selection result to the computer device 1; the computer device 1 receives the operation instruction of the improvement plan to be executed sent by the user terminal, and calculates the first predicted yield according to the received improvement plan. For example, the computer device 1 sends the user terminal an improvement plan to reduce the impact of personnel factors, machine factors, environmental factors, production materials, operating method factors, and software factors on production yield, but the user terminal only accepts the improvement plan for the impact of personnel factors, machine factors, and environmental factors on production yield, and does not accept the improvement plan for the impact of production materials, operating method factors, and software factors on production yield.

[0151] Therefore, the calculation method of the first predicted yield is:

[0152] Adjusted product defect rate = product defect rate - (the proportion of the adjusted personnel factor affecting the product yield rate + the proportion of the adjusted machine factor affecting the product yield rate + the proportion of the adjusted environmental factor affecting the product yield rate)

[0153] The first predicted yield rate = 1-adjusted product defect rate.

[0154] For example, the product model A-001 between October 6, 2019 and October 12, 2019, the product yield of 95% is brought into the multidimensional model for analysis, and the analysis shows that the impact ratio of personnel factors on the yield of production line A is 0.1%, the impact ratio of machine factors on the yield of production line A is 0.02%, the impact ratio of production material factors on the yield of production line A is 0.02%, and the impact ratio of operation method factors, software factors and environmental factors on the yield of production line A is 0. The impact ratio of personnel factors and machine factors on production line A in the defective items can be reduced from 0.1% to 0, and the impact ratio of machine factors on production line A can be reduced from 0.02% to 0 by applying the improvement method found in the yield database. Therefore, the estimated yield of production line A changes from 99% to 99%+0.1%+0.02%=99.12%. Production lines B, C and D have not improved the yield in this embodiment, so the yields of production lines B, C and D are still 98%, 99% and 99%, respectively. The defective rate of production line A is 1-99.12%=0.88%, the defective rate of production line B is 2%, the defective rate of production line C is 1%, the defective rate of production line D is 1%, and the yield of the product with product signal A-001 is 1-0.88%-2%-1%-1%=95.12%. The yield of the product is 95.12% as the first predicted yield.

[0155] In another embodiment of the present invention, the step further includes obtaining a real-time yield rate of producing the product, and comparing the real-time yield rate with the first predicted yield rate;

[0156] If the real-time yield is less than the first predicted yield, query whether to execute the instruction of implementing the preset method to adjust the influence ratio of the defective factor on the product yield;

[0157] If the instruction for implementing the preset method is not executed, the preset method is implemented to adjust the influence ratio of the defective factor on the product yield;

[0158] If the instruction for implementing the preset method has been executed, a prompt message is issued, and the prompt message is used to remind the user to re-analyze the defective factors in producing the product.

[0159] The real-time yield of the product produced after the improvement plan is applied is obtained, and the real-time yield is compared with the second predicted yield of 95.12%. If the real-time yield is greater than the second predicted yield, it is verified that the improvement plan meets the requirements for improving the production yield of the product. If the real-time yield is less than the second predicted yield, it is queried whether the preset method is implemented to adjust the influence ratio of the bad factor on the product yield. If it is not implemented, the preset method is implemented to adjust the influence ratio of the bad factor on the product yield. If it has been implemented, it is necessary to send a prompt message to the preset staff. The prompt message can be prompted by a signal display light, email, text message, or instant message. After the staff re-analyzes the personnel factors, machine factors, production material factors, operating method factors, environmental factors, and software factors that affect the product yield according to the prompt message, a new improvement plan is obtained, and the improvement plan is sent to the computer device 1. After the computer device 1 stores the improvement plan in correspondence with the bad items and the bad item bad rate, the improvement plan is sent to the corresponding production equipment.

[0160] In other embodiments of the present invention, the step further includes that the computer device 1 displays the improvement plan in the form of a visual chart. The contents displayed in the visual chart may include: a prescription and countermeasures detailed selection table, an improvement effect tracking detailed table, and an adverse warning detailed table.

[0161] In another embodiment of the present invention, the influence ratio of the personnel factor, machine factor, environmental factor analysis model, production material factor, operation method factor, and software factor on the first predicted yield is displayed in a yield bridge information table, and the yield bridge information table displays the influence ratio of the various undesirable factors on the first predicted yield, and dynamically adjusts according to the influence ratio of different undesirable factors. The yield bridge information table can make operators more clearly understand the influence of different yield information on product yield.

[0162] Above Figure 2 The product yield prediction method of the present invention is introduced in detail. In conjunction with Figures 3-4, the functional modules of the software device that implements the product yield prediction method and the hardware device architecture that implements the product yield prediction method are introduced below.

[0163] It should be understood that the embodiment is for illustration only and the scope of the patent application is not limited by this structure.

[0164] Embodiment 3

[0165] Figure 3 It is a structural diagram of a preferred embodiment of the product yield prediction device of the present invention.

[0166] In some embodiments, the product yield prediction device 10 runs in a computer device. The computer device is connected to multiple user terminals via a network. The product yield prediction device 10 may include multiple functional modules composed of program code segments. The program code of each program segment in the product yield prediction device 10 may be stored in the memory of the computer device and executed by the at least one processor to implement the product yield prediction function.

[0167] In this embodiment, the product yield prediction device 10 can be divided into multiple functional modules according to the functions it performs. Figure 3 As shown, the functional modules may include: an acquisition module 101, an analysis module 102, a judgment module 103, and an output module 104. The module referred to in the present invention refers to a series of computer program segments that can be executed by at least one processor and can complete fixed functions, which are stored in a memory. In this embodiment, the functions of each module will be described in detail in subsequent embodiments.

[0168] The acquisition module 101 is used to acquire product quality data information in historical production records, and calculate product yield data information based on the quality data information.

[0169] In one embodiment of the present invention, the acquisition module 101 acquires product quality data information in historical production records by setting conditions, and generates product yield data information using a preset algorithm using the acquired quality data information.

[0170] The set conditions may include: product model to be produced, building, section, production line, production work order, capacity, color, time, work station, production team, defective items, materials, material manufacturer, and material production date.

[0171] The quality data information may include: product serial number, the number of products that have passed the test at each site, the number of products that have failed the test at each site, assembly line, assembly time, test line, defective workstation, defective item, test time, functional material inventory and consumption information, functional material manufacturer and production date information, consumable material inventory and consumption information, consumable material manufacturer and production date information, and consumable material collection information.

[0172] Methods for calculating the defect rate of each item, site yield, segment yield, total yield and major defect items according to the preset algorithm may include:

[0173] Project defect rate = number of unqualified projects / number of corresponding project site inputs;

[0174] Project yield rate = 1 - project defect rate;

[0175] Site yield = number of qualified sites / number of corresponding sites invested;

[0176] Segment yield = site 1 yield * ... * site N yield;

[0177] Total yield = segment 1 yield *… * segment N yield.

[0178] The yield data information may include: overall yield target, site yield target, project yield target, overall yield, segment yield, workstation yield, defective items, defective rate of defective items, material combination yield, and material manufacturer defective rate.

[0179] For example, the quality data information of the product to be produced is obtained according to different preset conditions selected by the user to calculate the product yield data.

[0180] The yield is calculated based on selected basic information, the basic information including one or more of floor, section, line, work order, capacity, color, and product type. The calculation method includes screening the serial numbers of qualified products. The selected condition yield = the number of qualified machines tested / the total number of machines.

[0181] The yield is calculated based on the selected defective item information, wherein the defective item information includes one or more of defective items and defective workstations. The calculation method includes screening the serial numbers of products that meet the conditions, and the selected condition yield = the number of qualified machine tests / the total number of machines.

[0182] The yield is calculated based on the selected material matching information, the material matching information includes one or more of the material, manufacturer, and production date. The calculation method includes screening the serial numbers of qualified products, and the selected condition yield = the number of qualified machines tested / the total number of machines.

[0183] In another embodiment of the present invention, the yield data information also includes classified storage of historical defective items, wherein the stored content may include the categories of defective factors in historical defective items, the defective proportions of known defective factors in historical defective items, and the specific defective causes of defective factors in historical defective items.

[0184] In other embodiments of the present invention, the step may further include, according to the selection conditions, outputting the yield data information in the form of a yield report within a preset period, wherein the form of the yield report may include one or more of a table, a graph, and a text. For example, the computer device 1 organizes the quality data information of the product to be produced acquired according to the preset conditions to generate a visual quality data report. The visual quality data report may display the following information content: daily yield unit data, customized yield query unit. The content of the daily yield unit data includes: a machine model yield trend chart, a segment input and yield detail table, a defective item and defective rate detail table. The content of the customized yield query unit includes: a multiple selection column, a weekly yield trend chart of the selected conditions, a defective item and defective rate detail table, a segment input and yield detail table. In some embodiments, the step further includes sending the yield report to a designated contact person in a preset manner. Among them, the preset manner includes selectively sending the yield report to a designated contact person according to the content of the yield report, as well as information such as the frequency and time of sending the yield report. The contact person may be a designated person in charge, or the designated contact information may be input as needed.

[0185] The analysis module 102 is used to input the yield data information of the product into at least one analysis model, and calculate the influence ratio of the defective factor corresponding to each analysis model on the yield of the product.

[0186] In one embodiment of the present invention, the adverse factors may include personnel factors, machine factors, environmental factors, production material factors, operating method factors, and software factors.

[0187] The analysis model may include a personnel factor analysis model, a machine factor analysis model, an environmental factor analysis model, a production material factor analysis model, an operating method factor analysis model, and a software factor analysis model.

[0188] The product yield data information is input into the personnel factor analysis model, and the method for calculating the influence ratio of the personnel factor on the product yield is:

[0189] Calculating the relative yield of a first preset time period and the relative yield of a second preset time period within a set period, and determining the influence ratio of the personnel factor on the product yield through a mapping relationship between the preset relative yield and the influence ratio of the personnel factor, wherein the set period includes a plurality of first preset time lengths and a plurality of second preset time lengths, each of the first preset time lengths includes a plurality of first time periods, and each of the first preset time lengths includes a plurality of second time periods;

[0190] The relative yield of the first time period is equal to the maximum yield within the first preset time length of the time period minus the average yield of the corresponding time period in each first preset time length within the set period;

[0191] The relative yield of the second time period is equal to the average yield of multiple first preset time periods within the set period minus the yield of the second time period.

[0192] In one embodiment, the set period is one month, the first preset time length is a weekday, and the second preset time length is a holiday time, and the holidays include New Year's Day, Spring Festival, May Day, Qingming Festival, Dragon Boat Festival, Mid-Autumn Festival, National Day, Sunday and other statutory holidays;

[0193] Calculate the total yield rate and daily yield rate within the set period, and mark the maximum yield rate per week;

[0194] Calculate the average yield rate for all dates except holidays within the set period;

[0195] Calculate the yield rate during holidays within the set period;

[0196] Calculate the average yield from Monday to Saturday excluding holidays during the time period;

[0197] Calculate the average yield on Monday = (yield on Monday of the first week + ... yield on Monday of the Nth week) / N;

[0198] …

[0199] Calculate the average yield rate on Saturday = (yield rate on Saturday of the first week + ... yield rate on Saturday of the Nth week) / N;

[0200] Thus, the relative yield from Monday to Saturday is calculated:

[0201] Relative yield on Monday = maximum yield of the week - average yield on Monday;

[0202] …

[0203] Relative yield on Saturday = maximum yield in a week - average yield on Saturday;

[0204] Calculate the relative yield rate during holidays: relative yield rate during holidays = average yield rate within the set period excluding holidays - holiday yield rate;

[0205] The influence ratio of the personnel factor on the product yield is determined by the preset mapping relationship between the relative yield and the influence ratio of the personnel factor. For example, if the relative yield on Monday is 1.5%, and the preset mapping relationship between the relative yield and the influence ratio of the personnel factor is 1:1, then the calculation results show that the influence ratio of the personnel factor on the product yield on Monday is 1.5%, and so on, the influence ratio of the personnel factor on the product yield on different working days is calculated. The ratio changes in real time according to the different time periods.

[0206] The product yield data information is input into the machine factor analysis model, and the method for calculating the influence ratio of the machine factor on the product yield is:

[0207] Searching for yield data information of the product produced within a set historical time, wherein the yield data information includes the defective rate of defective items in the production of the product;

[0208] Searching the proportion of machine factors affecting product yield in a defective item database, wherein the defective item database stores the defective rate of defective items in producing the product and the name of the defective factor that produces the defective rate;

[0209] The proportion of the machine factor affecting the product yield is the product of the ratio of the machine factor affecting the product yield found and the defective rate of the defective item.

[0210] The method of inputting the product yield data information into an environmental factor analysis model and calculating the influence ratio of environmental factors on the product yield includes:

[0211] Searching for yield data information of the product produced within a set historical time, wherein the yield data information is the defective rate of defective items in the production of the product;

[0212] Searching for the proportion of environmental factors affecting product yield in a defective item database, wherein the defective item database stores the defective rate of defective items in producing the product and the names of defective factors that produce the defective rate;

[0213] The ratio of the environmental factors affecting the product yield is the product of the ratio of the environmental factors affecting the product yield found and the defective rate of the defective items.

[0214] The method of inputting the product yield data information into a production material factor analysis model and calculating the influence ratio of the production material factor on the product yield includes:

[0215] Searching for yield data information of the product produced within a set historical time, wherein the yield data information includes defective item defective rate, incoming material defective rate of the product, usage status information of consumables, and inventory status information of consumables;

[0216] The proportion of production material factors affecting product yield is searched in the defective item database, wherein the defective item database stores the defective rate of defective items in producing the product and the names of defective factors that produce the defective rate, and the production materials include one or more functional materials and consumables.

[0217] When the production material is a functional material, the ratio of the production material factor affecting the product yield is the product of the ratio of the functional material affecting the product yield and the defective rate of the incoming material of the product;

[0218] When the production material is a consumable, determine whether the consumable is used in the current product based on the usage status information of the consumable. If the consumable is used in the current product, search the quality data information for the historical defective item rate of the consumable according to the name of the consumable, and use the historical defective item rate of the consumable as the ratio of the production material factor affecting the product yield;

[0219] When the production materials include functional materials and consumables, the defective rate obtained by adding the proportion of the functional materials affecting the product yield and the proportion of the consumables affecting the product yield is used as the proportion of the production material factor affecting the product yield.

[0220] The method of inputting the product yield data information into the operating method factor analysis model and calculating the influence ratio of the operating method factor on the product yield includes:

[0221] Searching for yield data information of the product produced within a set historical time, wherein the yield data information includes the defective rate of defective items in the production of the product;

[0222] Obtain a database of defective items affected by operating method factors, and find the proportion of the operating method factors affecting the product yield, wherein the defective item database stores the defective rate of the defective items in producing the product and the name of the defective factor that produces the defective rate;

[0223] The ratio of the operating technique factor affecting the product yield is the product of the ratio of the production operation affecting the product yield and the defective rate of the defective items of the product.

[0224] The method of inputting the product yield data information into a software factor analysis model and calculating the influence ratio of the software factor on the product yield includes:

[0225] Searching for yield data information of the product produced within a set historical time, wherein the yield data information includes the defective rate of defective items in the production of the product;

[0226] Obtaining a database of defective items affected by software factors, and searching for the proportion of software factors affecting product yield, wherein the defective item database stores the defective rate of defective items in producing the product and the name of the defective factor that produces the defective rate;

[0227] The ratio of the software factor affecting the product yield is the product of the ratio of the software factor affecting the product yield and the defective rate of the defective items of the product.

[0228] The influence ratio of the bad factors that affect the product production yield analyzed by the personnel factor analysis model, the machine factor analysis model, the environmental factor analysis model, the production material factor analysis model, the operation method factor analysis model, and the software factor analysis model are used to search for the causes of the bad factors in the bad project database, and to search for the preset method corresponding to the bad factors in the yield database to reduce the influence ratio of at least one bad factor on the product yield; if it exists, it is determined that the influence ratio of at least one bad factor on the product yield can be reduced by the preset method. In another embodiment of the present invention, the method also includes sending the preset method to the preset personnel; receiving the instruction of the preset personnel whether to implement the preset method; if the instruction is to implement the preset method, adjusting the influence ratio of the bad factors on the product yield according to the preset method.

[0229] For example, the model of the product to be generated is A-001, and the product is generated by three production lines A, B, and C. The production quality data of the online products of the three production lines are captured within a preset historical time. The preset historical time can be one day, one week, one month, or one year. The length of the preset historical time depends on the life cycle of the product. If it is a product in the trial production period, the preset historical time is set to be shorter, which can be one day or one week. If it is a product in the mass production period, the preset historical time can be set to four weeks, eight weeks, etc. In one embodiment, between October 6, 2019 and October 12, 2019, production line A put into production 1000 pieces, 990 pieces passed the test, and 10 pieces failed the test; production line B put into production 1000 pieces, 980 pieces passed the test, and 20 pieces failed the test; production line C put into production 1000 pieces, 990 pieces passed the test, and 10 pieces failed the test; production line D put into production 1000 pieces, 990 pieces passed the test, and 10 pieces failed the test. From the above data, the yield of production line A is 99%, the yield of production line B is 98%, the yield of production line C is 99%, the yield of production line D is 99%, the defective rate of production line A is 1%, the defective rate of production line B is 2%, the defective rate of production line C is 1%, and the defective rate of production line D is 1%. From this, it can be obtained that the yield of the product with product model A-001 is 1-1%-2%-1%-1%=95%.

[0230] The product yield of 95% of the product model A-001 between October 6, 2019 and October 12, 2019 is brought into multiple analysis models for analysis. The analysis shows that the impact ratio of personnel factors on the yield of production line A is 0.1%, the impact ratio of machine factors on the yield of production line A is 0.02%, the impact ratio of production material factors on the yield of production line A is 0.02%, the impact ratio of operation method factors and machine factors on the yield of production line A is 0, and the impact ratio of software factors on the yield of production line A is 0. According to the impact ratio of personnel factors, machine factors, environmental factors, production material factors, operation method factors, and software factors, the defective items related to the personnel factors, machine factors, environmental factors, production material factors, operation method factors, and software factors, as well as the causes of the defective items, are searched in the defective item database to determine whether there is a preset method corresponding to the defective factor in the yield database to reduce the impact ratio of the at least one defective factor on the product yield; if so, it is determined that the impact ratio of the at least one defective factor on the product yield can be reduced by the preset method.

[0231] In another embodiment of the present invention, it also includes analyzing the concentration status of the defective items of the first preset yield, and the concentration status includes whether there is test line concentration, test fixture concentration, assembly line concentration, assembly shift concentration, material manufacturer concentration, and material production date concentration.

[0232] The method for determining the concentration status may include searching for the defective cause of the defective item in a defective item database according to the name of the defective item, searching for a solution to the defective item in a yield database, and analyzing the concentration status in the solution to determine whether there is test line concentration, test fixture concentration, assembly line concentration, assembly shift concentration, material manufacturer concentration, and material production date concentration in the solution.

[0233] For example, if the name of the defective item is a bright line on the display screen, the causes of the bright line on the display screen are searched in the defective item database according to the defective name, which are respectively personnel factors, machine factors, and production material factors, and the solution to the defect is searched in the yield database. The solution to the personnel factor is to strengthen the training of the operator, the solution to the machine factor is to perform regular maintenance on the machine, and the solution to the production material factor is to require the supplier to control the quality of the incoming materials. The three solutions are compared with the centralized conditions that have appeared in history to determine whether the three solutions have centralized problems. After comparison, it is found that the corresponding solutions of the production material factor are all for the materials of the same production date, so the production material factor has a centralized problem. The defective items, the causes of the defective items, and the centralized conditions of the production material factors are sent to the designated staff, and the staff determines whether the solution to the centralized conditions in history is applicable to the current defective items. If the solution is applicable to the current defective item, the staff sends an instruction to agree to execute the solution to the computer device 1. If the solution is not applicable to the current defective item, the second staff formulates a new solution and sends the solution to the analysis module 102, and the analysis module 102 stores the solution in the yield database.

[0234] In other embodiments of the present invention, the step may also include that the analysis module 102 outputs and displays the first predicted yield in the form of a visual chart. The contents of the visual chart may include: a set cycle yield prediction chart, a man-machine-material-method-environment-soft analysis chart (personnel factor, machine factor, environmental factor, production material factor, operation method factor, software factor analysis chart), a concentration analysis chart (test line concentration, test fixture concentration, assembly line concentration, assembly shift concentration, material manufacturer concentration, material production date concentration, box plot, production process capability control chart), a system recommended yield adjustment data chart, and a material input ratio control detail pop-up window.

[0235] The judgment module 103 is used to judge whether the influence ratio of at least one of the defective factors on the product yield can be reduced by a preset method according to the set conditions.

[0236] The method of judging whether the influence ratio of the at least one defective factor on the product yield can be reduced by a preset method according to the set conditions comprises:

[0237] According to the defective factors affecting the production yield of the product, searching in a preset yield database whether there is a preset method corresponding to the defective factor to reduce the influence ratio of the at least one defective factor on the product yield;

[0238] If so, it is determined that the influence ratio of the at least one defective factor on the product yield can be reduced by a preset method.

[0239] In another embodiment of the present invention, if there is a preset method corresponding to the production material factor in the preset yield database to reduce the impact ratio of the production material factor on the product yield, it is also necessary to find the inventory data information of the corresponding material in the preset method to determine whether the inventory quantity of the corresponding material in the preset method meets the production requirements of the product to be produced. If the inventory quantity of the corresponding material in the preset method can meet the production requirements of the product to be produced, then the preset method is determined to be an available method for reducing the impact ratio of the production material factor on the product yield. If the inventory quantity of the corresponding material in the preset method is not enough to meet the production requirements of the product to be produced, then the name of the alternative material of the material and the inventory information of the alternative material are searched. If the inventory information of the alternative material can meet the production requirements of the product to be produced, then the alternative material is used as an available method to solve the impact ratio of the production material factor on the product yield.

[0240] The output module 104 is used to adjust the influence ratio of the defective factor on the product yield according to the preset method if it can be reduced, and then calculate the first predicted yield of the planned production of the product according to the adjusted influence ratio.

[0241] The calculation method of the first predicted yield may be:

[0242] Adjusted product defect rate = product defect rate - (adjusted ratio of personnel factors affecting product yield + adjusted ratio of machine factors affecting product yield + adjusted ratio of environmental factors affecting product yield + adjusted ratio of production material factors affecting product yield + adjusted ratio of operating method factors affecting product yield + adjusted ratio of software factors affecting product yield)

[0243] The first predicted yield rate = 1-adjusted product defect rate.

[0244] In another embodiment of the present invention, the step further includes that the output module 104 sends the defective project improvement plan to the user terminal in a preset manner, the user terminal can selectively receive the improvement plan as needed, and send the selection result to the output module 104, the output module 104 receives the operation instruction of the improvement plan to be executed sent by the user terminal, and calculates the first predicted yield according to the received improvement plan. For example, the output module 104 sends the user terminal an improvement plan to reduce the impact of personnel factors, machine factors, environmental factors, production materials, operating method factors, and software factors on production yield, but the user terminal only accepts the improvement plan for the impact of personnel factors, machine factors, and environmental factors on production yield, and does not accept the improvement plan for the impact of production materials, operating method factors, and software factors on production yield.

[0245] Therefore, the calculation method of the first predicted yield is:

[0246] Adjusted product defect rate = product defect rate - (the proportion of the adjusted personnel factor affecting the product yield rate + the proportion of the adjusted machine factor affecting the product yield rate + the proportion of the adjusted environmental factor affecting the product yield rate)

[0247] The first predicted yield rate = 1-adjusted product defect rate.

[0248] For example, the product model A-001 between October 6, 2019 and October 12, 2019, the product yield of 95% is brought into the multidimensional model for analysis, and the analysis shows that the impact ratio of personnel factors on the yield of production line A is 0.1%, the impact ratio of machine factors on the yield of production line A is 0.02%, the impact ratio of production material factors on the yield of production line A is 0.02%, and the impact ratio of operation method factors, software factors and environmental factors on the yield of production line A is 0. The impact ratio of personnel factors and machine factors on production line A in the defective items can be reduced from 0.1% to 0, and the impact ratio of machine factors on production line A can be reduced from 0.02% to 0 by applying the improvement method found in the yield database. Therefore, the estimated yield of production line A changes from 99% to 99%+0.1%+0.02%=99.12%. Production lines B, C and D have not improved the yield in this embodiment, so the yields of production lines B, C and D are still 98%, 99% and 99%, respectively. The defective rate of production line A is 1-99.12%=0.88%, the defective rate of production line B is 2%, the defective rate of production line C is 1%, the defective rate of production line D is 1%, and the yield of the product with product signal A-001 is 1-0.88%-2%-1%-1%=95.12%. The yield of the product is 95.12% as the first predicted yield.

[0249] In another embodiment of the present invention, the step further includes obtaining a real-time yield rate of producing the product, and comparing the real-time yield rate with the first predicted yield rate;

[0250] If the real-time yield is less than the first predicted yield, query whether to implement the preset method for adjusting the influence ratio of the defective factor on the product yield;

[0251] If not implemented, then implementing the preset method to adjust the impact ratio of the defective factor on the product yield;

[0252] If it has been implemented, a prompt message is issued, and the prompt message is used to remind the user to re-analyze the defective factors in producing the product.

[0253] The real-time yield of the product produced after the improvement plan is applied is obtained, and the real-time yield is compared with the second predicted yield of 95.12%. If the real-time yield is greater than the second predicted yield, it is verified that the improvement plan meets the requirements for improving the production yield of the product. If the real-time yield is less than the second predicted yield, it is queried whether the preset method is implemented to adjust the influence ratio of the defective factor on the product yield. If not implemented, the preset method is implemented to adjust the influence ratio of the defective factor on the product yield. If it has been implemented, it is necessary to send a prompt message to the preset staff. The prompt message can be prompted by a signal display light, email, text message, or instant message. After the staff re-analyzes the personnel factors, machine factors, production material factors, operating method factors, environmental factors, and software factors that affect the product yield according to the prompt message, a new yield improvement plan is obtained, and the improvement plan is sent to the output module 104. After the output module 104 stores the improvement plan in correspondence with the defective items and the defective rate of the defective items, the improvement plan is sent to the corresponding production equipment.

[0254] In other embodiments of the present invention, the step may further include that the output module 104 displays the improvement plan in a visual chart. The contents displayed in the visual chart may include: a prescription and countermeasures selection list, an improvement effect tracking list, and an adverse warning list.

[0255] In another embodiment of the present invention, the influence ratio of the personnel factor, machine factor, environmental factor analysis model, production material factor, operation method factor, and software factor on the first predicted yield is displayed in a yield bridge information table, and the yield bridge information table displays the influence ratio of the various undesirable factors on the first predicted yield, and dynamically adjusts according to the influence ratio of different undesirable factors. The yield bridge information table can make operators more clearly understand the influence of different yield information on product yield.

[0256] Embodiment 4

[0257] Figure 4 FIG. 4 is a schematic diagram of a preferred embodiment of a computer device of the present invention.

[0258] The computer device 1 includes a memory 20, a processor 30, and a computer program 40 stored in the memory 20 and executable on the processor 30, such as a product yield prediction program. When the processor 30 executes the computer program 40, the steps in the above-mentioned product yield prediction method embodiment are implemented, such as Figure 2 Alternatively, when the processor 30 executes the computer program 40, the functions of each module / unit in the above-mentioned product yield prediction device embodiment are realized, for example Figure 3 Units 101-104 in.

[0259] Exemplarily, the computer program 40 may be divided into one or more modules / units, which are stored in the memory 20 and executed by the processor 30 to implement the present invention. The one or more modules / units may be a series of computer program instruction segments capable of implementing specific functions, and the instruction segments are used to describe the execution process of the computer program 40 in the computer device 1. For example, the computer program 40 may be divided into Figure 3 The acquisition module 101, the analysis module 102, the judgment module 103, and the output module 104 are included in the embodiment.

[0260] The computer device 1 may be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. Those skilled in the art will appreciate that the schematic diagram is merely an example of the computer device 1 and does not limit the computer device 1. The computer device 1 may include more or fewer components than shown in the diagram, or may combine certain components, or may include different components. For example, the computer device 1 may also include input and output devices, network access devices, buses, etc.

[0261] The processor 30 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor 30 may be any conventional processor, etc. The processor 30 is the control center of the computer device 1, and uses various interfaces and lines to connect various parts of the entire computer device 1.

[0262] The memory 20 can be used to store the computer program 40 and / or modules / units. The processor 30 implements various functions of the computer device 1 by running or executing the computer program and / or modules / units stored in the memory 20 and calling the data stored in the memory 20. The memory 20 can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data created according to the use of the computer device 1 (such as audio data, a phone book, etc.), etc. In addition, the memory 20 can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0263] If the module / unit integrated in the computer device 1 is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the above-mentioned various method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0264] In the several embodiments provided by the present invention, it should be understood that the disclosed computer device and method can be implemented in other ways. For example, the computer device embodiment described above is only illustrative, for example, the division of the unit is only a logical function division, and there may be other division methods in actual implementation.

[0265] In addition, each functional unit in each embodiment of the present invention may be integrated into the same processing unit, each unit may exist physically separately, or two or more units may be integrated into the same unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of hardware plus software functional modules.

[0266] It is obvious to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential features of the present invention. Therefore, from any point of view, the embodiments should be regarded as exemplary and non-restrictive, and the scope of the present invention is defined by the appended claims rather than the above description, and it is intended that all changes falling within the meaning and scope of the equivalent elements of the claims are included in the present invention. Any figure mark in the claims should not be regarded as limiting the claims involved. In addition, it is obvious that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or computer devices stated in the computer device claim can also be implemented by the same unit or computer device through software or hardware. The words first, second, etc. are used to indicate names, and do not indicate any particular order.

[0267] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention.

Claims

1. A product yield prediction method, characterized in that: The method comprises: Obtaining product quality data information from historical production records, and calculating product yield data information based on the quality data information; Inputting the yield data information of the product into at least one analysis model, and calculating the influence ratio of the defective factors corresponding to each analysis model on the yield of the product, wherein the at least one analysis model includes one or more of a personnel factor analysis model, a machine factor analysis model, an environmental factor analysis model, a production material factor analysis model, an operating method factor analysis model, and a software factor analysis model; Judging whether the influence ratio of at least one of the bad factors on the product yield can be reduced by a preset method according to the set conditions, including: searching in a preset yield database whether there is a preset method corresponding to the bad factor to reduce the influence ratio of the at least one bad factor on the product yield according to the bad factor affecting the production yield of the product; if there is, determining that the influence ratio of the at least one bad factor on the product yield can be reduced by the preset method; If it can be reduced, adjusting the influence ratio of the defective factor on the product yield according to the preset method, and then calculating the first predicted yield of the planned production of the product according to the adjusted influence ratio; Obtain the real-time yield of producing the product, and compare the real-time yield with the first predicted yield; if the real-time yield is less than the first predicted yield, query whether to run the instruction for implementing the preset method to adjust the proportion of influence of the defective factor on the product yield; if the instruction for implementing the preset method has not been run, implement the preset method to adjust the proportion of influence of the defective factor on the product yield; if the instruction for implementing the preset method has been run, issue a prompt message, and the prompt message is used to remind the user to re-analyze the defective factors for producing the product.

2. The product yield prediction method according to claim 1, characterized in that: The method further comprises: Sending the preset method to a preset person; Receiving instructions from a preset person on whether to implement the preset method; If the instruction is to implement the preset method, then the influence ratio of the defective factor on the product yield is adjusted according to the preset method, and then the first predicted yield of the planned production of the product is calculated according to the adjusted influence ratio; If the instruction is not to implement the preset method, the defective rate of producing the product within a preset historical time period calculated based on the quality data information is used as the first predicted yield of the planned production of the product.

3. The product yield prediction method according to claim 1, characterized in that: The method of obtaining product quality data information in historical production records and calculating product yield data information based on the quality data information includes: The historical quality data information of the product produced is obtained through the set selection conditions, and the product yield data information is generated by the obtained historical quality data information through a preset algorithm, wherein the selection conditions include: one or more of the product model to be produced, building, section, line, work order, capacity, color, time, work station, defective item, material, manufacturer, production team, and material manufacturer production date; The quality data information includes: one or more of: product serial number, number of qualified tests at each site, number of unqualified tests at each site, assembly line, assembly time, test line, defective workstation, defective item, test time, functional material inventory and consumption information, functional material manufacturer and production date information, consumable material inventory and consumption information, consumable material manufacturer and production date information, and consumable material collection information; The yield data information includes: one or more of: total yield target, site yield target, project yield target, total yield, segment yield, workstation yield, defective items, defective rate of defective items, material combination yield, and material manufacturer defective rate.

4. The product yield prediction method according to claim 3, characterized in that: The method further comprises: The yield data information is output in the form of a yield report within a preset period according to the selection condition, wherein the form of the yield report includes one or more of a table, a graph, and text.

5. The product yield prediction method according to claim 1, characterized in that: The product yield data information is input into the personnel factor analysis model, and the method for calculating the influence ratio of the personnel factor on the product yield is: Calculating the relative yield of a first preset time period and the relative yield of a second preset time period within a set period, and determining the influence ratio of the personnel factor on the product yield through a mapping relationship between the preset relative yield and the influence ratio of the personnel factor, wherein the set period includes a plurality of first preset time lengths and a plurality of second preset time lengths, each of the first preset time lengths includes a plurality of first time periods, and each of the first preset time lengths includes a plurality of second time periods; The relative yield of the first time period is equal to the maximum yield within the first preset time length of the time period minus the average yield of the corresponding time period in each first preset time length within the set period; The relative yield of the second time period is equal to the average yield of multiple first preset time periods within the set period minus the yield of the second time period.

6. The product yield prediction method according to claim 1, characterized in that: The product yield data information is input into the machine factor analysis model, and the method for calculating the influence ratio of the machine factor on the product yield is: Searching for yield data information of the product produced within a set historical time, wherein the yield data information includes the defective rate of defective items in the production of the product; Searching the proportion of machine factors affecting product yield in a defective item database, wherein the defective item database stores the defective rate of defective items in producing the product and the name of the defective factor that produces the defective rate; The proportion of the machine factor affecting the product yield is the product of the ratio of the machine factor affecting the product yield found and the defective rate of the defective item.

7. The product yield prediction method according to claim 1, characterized in that: The method of inputting the product yield data information into an environmental factor analysis model and calculating the influence ratio of environmental factors on the product yield includes: Searching for yield data information of the product produced within a set historical time, wherein the yield data information is the defective rate of defective items in the production of the product; Searching for the proportion of environmental factors affecting product yield in a defective item database, wherein the defective item database stores the defective rate of defective items in producing the product and the names of defective factors that produce the defective rate; The ratio of the environmental factors affecting the product yield is the product of the ratio of the environmental factors affecting the product yield found and the defective rate of the defective items.

8. The product yield prediction method according to claim 1, characterized in that: The method of inputting the product yield data information into a production material factor analysis model and calculating the influence ratio of the production material factor on the product yield includes: Searching for yield data information of the product produced within a set historical time, wherein the yield data information includes defective item defective rate, incoming material defective rate of the product, and usage status information of consumables; Searching the proportion of production material factors affecting product yield in a defective item database, wherein the defective item database stores the defective rate of defective items of the product and the names of defective factors that produce the defective rate, and the production materials include at least one of functional materials and consumables; When the production material is a functional material, the ratio of the production material factor affecting the product yield is the product of the ratio of the functional material affecting the product yield and the defective rate of the incoming material of the product; When the production material is a consumable, determine whether the consumable is used in the current product based on the usage status information of the consumable. If the consumable is used in the current product, search the quality data information for the historical defective item rate of the consumable according to the name of the consumable, and use the historical defective item rate of the consumable as the ratio of the production material factor affecting the product yield; When the production materials include functional materials and consumables, the defective rate obtained by adding the proportion of the functional materials affecting the product yield and the proportion of the consumables affecting the product yield is used as the proportion of the production material factor affecting the product yield.

9. The product yield prediction method according to claim 1, characterized in that: The method of inputting the product yield data information into the operating method factor analysis model and calculating the influence ratio of the operating method factor on the product yield includes: Searching for yield data information of the product produced within a set historical time, wherein the yield data information includes the defective rate of defective items in the production of the product; Obtain a database of defective items affected by operating method factors, and find the proportion of the operating method factors affecting the product yield, wherein the defective item database stores the defective rate of the defective items in producing the product and the name of the defective factor that produces the defective rate; The ratio of the operating technique factor affecting the product yield is the product of the ratio of the production operation affecting the product yield and the defective rate of the defective items of the product.

10. The product yield prediction method according to claim 1, characterized in that: The method of inputting the product yield data information into a software factor analysis model and calculating the influence ratio of the software factor on the product yield includes: Searching for yield data information of the product produced within a set historical time, wherein the yield data information includes the defective rate of defective items in the production of the product; Obtaining a database of defective items affected by software factors, and searching for the proportion of software factors affecting product yield, wherein the defective item database stores the defective rate of defective items in producing the product and the name of the defective factor that produces the defective rate; The ratio of the software factor affecting the product yield is the product of the ratio of the software factor affecting the product yield and the defective rate of the defective items of the product.

11. A product yield prediction device, characterized in that: The device comprises: An acquisition module is used to acquire product quality data information in historical production records and calculate product yield data information based on the quality data information; An analysis module, used to input the yield data information of the product into at least one analysis model, and calculate the influence ratio of the defective factor corresponding to each analysis model on the yield of the product, wherein the at least one analysis model includes one or more of a personnel factor analysis model, a machine factor analysis model, an environmental factor analysis model, a production material factor analysis model, an operating method factor analysis model, and a software factor analysis model; A judgment module, used to judge whether the influence ratio of at least one bad factor on the product yield can be reduced by a preset method according to the set conditions, including: according to the bad factor affecting the production yield of the product, searching in a preset yield database whether there is a preset method corresponding to the bad factor to reduce the influence ratio of the at least one bad factor on the product yield; if there is, determining that the influence ratio of the at least one bad factor on the product yield can be reduced by the preset method; An output module, configured to adjust the influence ratio of the defective factor on the product yield according to the preset method if it can be reduced, and then calculate a first predicted yield of the planned production of the product according to the adjusted influence ratio; The output module is also used to obtain the real-time yield of the production of the product and compare the real-time yield with the first predicted yield; if the real-time yield is less than the first predicted yield, query whether to run the instruction to implement the preset method to adjust the proportion of the impact of the defective factor on the product yield; if the instruction to implement the preset method has not been run, implement the preset method to adjust the proportion of the impact of the defective factor on the product yield; if the instruction to implement the preset method has been run, issue a prompt message, and the prompt message is used to remind the user to re-analyze the defective factors for producing the product.

12. A computer device, characterized in that: The computer device comprises a processor, and the processor is used to implement the product yield prediction method according to any one of claims 1 to 10 when executing a computer program stored in a memory.

13. A storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the product yield prediction method according to any one of claims 1 to 10 is implemented.

Images