Production proficiency prediction method and device, storage medium and program product
By fitting the growth curve of the production target product and building the function to be fitted, the problems of low accuracy and manual dependence of production proficiency prediction in the existing technology are solved, and automated prediction is achieved, which improves the comprehensiveness and accuracy of predictions. sex.
Patent Information
- Application Number
- CN202411503438.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-25
- Publication Date
- 2025-02-11
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
The prior art is low in accuracy and relies on manual labor when predicting product production proficiency on manufacturing production lines. The AI prediction model has defects in incomplete data coverage and abnormal data processing, resulting in serious resource consumption.
By obtaining the prediction request input by the user, obtaining the historical production data of the target product, determining the growth curve of the production target product, and constructing a function to be fitted including the offset, fitting the target function, and outputting the production based on the objective function and the target time Proficiency to adjust production tasks.
It realizes automated prediction of production proficiency, improves prediction accuracy and reliability, avoids the increase in manual dependence and resource consumption, and ensures full coverage of historical production data.
Smart Images
Figure CN119417301A_ABST
Abstract
Description
Technical Field
[0001] The present disclosure relates to the field of computer technology, and in particular to a method, device, storage medium and program product for predicting production proficiency. Background Art
[0002] With the automation and intelligence of product production, there are higher requirements for the prediction of production proficiency of products on manufacturing production lines. In the scenario of Advanced Planning and Scheduling (APS), if the production proficiency cannot be (accurately) determined, the feasibility of factory scheduling will be affected.
[0003] In the relevant technology, two methods are usually used to determine production proficiency. One method is average proficiency + manual correction, and the other is an artificial intelligence (AI) prediction model. Among them, the method of average proficiency + manual correction can be understood as obtaining production data within a preset time period, calculating the average proficiency based on the production data, and then manually correcting it based on experience, etc. to obtain the final production proficiency. The AI prediction model method can be understood as training prediction network models based on random forests, gradient boosting trees, k-nearest neighbors, etc., to predict production proficiency based on the prediction network model.
[0004] However, the average proficiency + manual correction method is based on the average value, which has relatively poor accuracy and is highly dependent on human factors, which is easily affected by human factors, resulting in low accuracy. The AI prediction model method is supervised learning during training, which cannot effectively predict the part not covered by the sample data, and the abnormal data in the sample data will also be trained into the model, so the data needs to be cleaned in advance, which leads to serious resource consumption.
[0005] The content of the background technology section is only the information known to the inventor personally, and does not mean that the above information has entered the public domain before the application date of this disclosure, nor does it mean that it can become the prior art of the present disclosure. Summary of the invention
[0006] The present disclosure provides a method, device, storage medium and program product for predicting production proficiency, so as to solve at least one of the above-mentioned technical problems.
[0007] In a first aspect, the present disclosure provides a method for predicting production proficiency, the method being applicable to product production on a manufacturing production line, the method comprising:
[0008] Obtaining a prediction request input by a user, wherein the prediction request is used to instruct to predict the production proficiency of a target product in a production task at a target time;
[0009] Obtaining historical production data corresponding to the target product, and determining a growth curve for producing the target product based on the historical production data, wherein the historical production data includes historical production time and historical production proficiency, and the growth curve is used to characterize the relationship between an increase in the time for producing the target product and an increase in proficiency in producing the target product;
[0010] Determine an initial function for characterizing the shape of the growth curve, and construct a function to be fitted including an offset based on the initial function, wherein the offset includes a time offset, or includes the time offset and a proficiency offset;
[0011] The function to be fitted is fitted according to the historical production data to obtain a target function, and the production proficiency corresponding to the prediction request is determined and output according to the target function and the target time, wherein the production proficiency corresponding to the prediction request is used to adjust the production task.
[0012] In some embodiments, fitting the function to be fitted according to the historical production data to obtain a target function includes:
[0013] From the historical production data, data whose historical production proficiency is less than a preset threshold is obtained, and an offset penalty weight is determined according to the obtained data less than the preset threshold, wherein the offset penalty weight is greater than 1;
[0014] The function to be fitted is fitted according to the historical production data and the offset penalty weight to obtain the objective function.
[0015] In some embodiments, fitting the to-be-fitted function according to the historical production data and the offset penalty weight to obtain the objective function includes:
[0016] Performing a first fitting on the function to be fitted according to the historical production data and the offset penalty weight to obtain a function after the first fitting;
[0017] The historical production data is filtered according to the first fitting function to obtain filtered data, and the function to be fitted is fitted for a second time according to the filtered data to obtain a second fitted function, wherein the target function is the second fitted function.
[0018] In some embodiments, filtering the historical production data according to the first fitting function to obtain filtered data includes:
[0019] Performing outlier detection on the historical production data according to the first post-fitting function to obtain the outlier;
[0020] The outliers in the historical production data are removed to filter the historical production data to obtain the filtered data.
[0021] In some embodiments, determining the offset penalty weight according to the obtained data less than a preset threshold includes:
[0022] Determining a ratio between the historical production data and the obtained data less than a preset threshold;
[0023] The offset penalty weight is determined according to the ratio, wherein the smaller the ratio is, the closer the offset penalty weight is to 1.
[0024] In some embodiments, the historical production data is data on the historical production of the target product, or is data on the historical production of a similar product that is similar to the target product.
[0025] In some embodiments, the production task includes preset production scheduling information of the product to be produced, and the product to be produced includes the target product; the method further includes:
[0026] Determining forecast production scheduling information of the product to be produced according to the production proficiency of the target product;
[0027] Matching the predicted production scheduling information with the preset production scheduling information to obtain a matching result;
[0028] The preset production scheduling information is adjusted based on the matching result to adjust the production task.
[0029] In a second aspect, the present disclosure provides a production proficiency prediction device, which is applicable to product production in a manufacturing production line, and comprises:
[0030] An obtaining unit, configured to obtain a prediction request input by a user, wherein the prediction request is used to instruct to predict the production proficiency of a target product in a production task at a target time;
[0031] The obtaining unit is further used to obtain historical production data corresponding to the target product;
[0032] a determining unit, configured to determine a growth curve for producing the target product according to the historical production data, wherein the historical production data includes historical production time and historical production proficiency, and the growth curve is used to characterize the relationship between an increase in the time for producing the target product and an increase in proficiency in producing the target product;
[0033] The determination unit is further used to determine an initial function for characterizing the shape of the growth curve;
[0034] A construction unit, configured to construct a function to be fitted including an offset based on the initial function, wherein the offset includes a time offset, or includes the time offset and a proficiency offset;
[0035] A fitting unit, used for fitting the function to be fitted according to the historical production data to obtain a target function;
[0036] The determining unit is further configured to determine, according to the objective function and the target time, a production proficiency corresponding to the prediction request, wherein the production proficiency corresponding to the prediction request is used to adjust the production task;
[0037] The output unit is used to output the production proficiency corresponding to the prediction request.
[0038] In some embodiments, the fitting unit is specifically used for:
[0039] From the historical production data, data whose historical production proficiency is less than a preset threshold is obtained, and an offset penalty weight is determined according to the obtained data less than the preset threshold, wherein the offset penalty weight is greater than 1;
[0040] The function to be fitted is fitted according to the historical production data and the offset penalty weight to obtain the objective function.
[0041] In some embodiments, the fitting unit is specifically used for:
[0042] Performing a first fitting on the function to be fitted according to the historical production data and the offset penalty weight to obtain a function after the first fitting;
[0043] The historical production data is filtered according to the first fitting function to obtain filtered data, and the function to be fitted is fitted for a second time according to the filtered data to obtain a second fitted function, wherein the target function is the second fitted function.
[0044] In some embodiments, the fitting unit is specifically used for:
[0045] Performing outlier detection on the historical production data according to the first post-fitting function to obtain the outlier;
[0046] The outliers in the historical production data are removed to filter the historical production data to obtain the filtered data.
[0047] In some embodiments, the fitting unit is specifically used for:
[0048] Determining a ratio between the historical production data and the obtained data less than a preset threshold;
[0049] The offset penalty weight is determined according to the ratio, wherein the smaller the ratio is, the closer the offset penalty weight is to 1.
[0050] In some embodiments, the historical production data is data on the historical production of the target product, or is data on the historical production of a similar product that is similar to the target product.
[0051] In some embodiments, the production task includes preset production scheduling information for a product to be produced, and the product to be produced includes the target product;
[0052] The determining unit is further configured to determine the forecast production scheduling information of the product to be produced according to the production proficiency of the target product;
[0053] The device also includes:
[0054] A matching unit, used for matching the predicted production scheduling information with the preset production scheduling information to obtain a matching result;
[0055] An adjustment unit is used to adjust the preset production scheduling information based on the matching result to adjust the production task.
[0056] In a third aspect, the present disclosure provides a processor-readable storage medium, wherein the processor-readable storage medium stores a computer program, wherein the computer program is used to enable the processor to execute the method described in the first aspect above.
[0057] In a fourth aspect, the present disclosure provides a computer program product, including a computer program, which implements the method described in the first aspect when executed by a processor.
[0058] The present disclosure provides a method, device, storage medium and program product for predicting production proficiency, obtains a prediction request input by a user, wherein the prediction request is used to indicate a prediction of the production proficiency of a target product in a production task at a target time, obtains historical production data corresponding to the target product, and determines a growth curve for producing the target product based on the historical production data, wherein the historical production data includes historical production time and historical production proficiency, and the growth curve is used to characterize the relationship between an increase in the time for producing the target product and an increase in the proficiency of producing the target product, determines an initial function for characterizing the shape of the growth curve, and constructs a function to be fitted including an offset based on the initial function, wherein the offset includes a time offset, or includes a time offset and a proficiency offset, fits the function to be fitted according to the historical production data to obtain a target function, and determines and outputs a production proficiency corresponding to the prediction request based on the target function and the target time, wherein the production proficiency corresponding to the prediction request is used to adjust the production task. In the present disclosure, after determining the growth curve corresponding to the target product, the prediction device constructs a corresponding initial function, and adjusts the offset of the initial function from the dimension of time, or adjusts the offset from the two dimensions of time and proficiency, and fits the adjusted function to be fitted to obtain the target function, and determines and outputs the proficiency of producing the target product at the target time according to the target function. On the one hand, it can avoid the technical drawbacks of low accuracy and strong dependence on manual labor caused by the average proficiency + manual correction method in the above-mentioned related technologies, and can realize the automation of prediction and improve the accuracy and reliability of prediction. On the other hand, it can avoid the technical drawbacks of incomplete coverage of historical production data caused by the use of AI prediction models in the above-mentioned related technologies, and can achieve full coverage of historical production data, thereby improving the comprehensiveness and accuracy of prediction. BRIEF DESCRIPTION OF THE DRAWINGS
[0059] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.
[0060] Figure 1 A schematic diagram of a process flow of a method for predicting production proficiency provided in an embodiment of the present disclosure;
[0061] Figure 2 When the production proficiency prediction device provided by the embodiment of the present disclosure is an electronic device, a schematic diagram of the structure of the electronic device;
[0062] Figure 3 A schematic diagram of a growth curve provided for one embodiment of the present disclosure;
[0063] Figure 4 A schematic diagram of a growth curve provided for another embodiment of the present disclosure;
[0064] Figure 5 A schematic diagram of a fitted curve provided for an embodiment of the present disclosure;
[0065] Figure 6 A schematic diagram of a fitted curve provided in another embodiment of the present disclosure;
[0066] Figure 7 A schematic diagram of a fitted curve provided in another embodiment of the present disclosure;
[0067] Figure 8 A schematic diagram of a fitted curve provided in another embodiment of the present disclosure;
[0068] Fig. 9 A schematic diagram of a module of a device for predicting production proficiency provided in an embodiment of the present disclosure.
[0069] The above drawings show clear embodiments of the present disclosure, which will be described in more detail below. These drawings and text descriptions are not intended to limit the scope of the present disclosure in any way, but to illustrate the concepts of the present disclosure to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION
[0070] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. Instead, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.
[0071] It should be understood that the terms "including" and "having" and any variations thereof in the embodiments of the present disclosure are intended to cover but not exclude inclusion. For example, a product or device comprising a series of components is not necessarily limited to those components explicitly listed, but may include other components not explicitly listed or inherent to these products or devices.
[0072] In the embodiments of the present disclosure, the term "and / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B may represent three situations: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the associated objects before and after are in an "or" relationship.
[0073] The term "plurality" in the embodiments of the present disclosure refers to two or more than two, and other quantifiers are similar thereto.
[0074] The terms "first", "second", "third", etc. in the present disclosure are used to distinguish similar or similar objects or entities, and are not necessarily meant to limit a specific order or sequence, unless otherwise indicated. It should be understood that the terms used in this way can be interchangeable under appropriate circumstances, for example, they can be implemented in an order other than those given in the diagrams or descriptions of the embodiments of the present disclosure.
[0075] The term "unit / module" as used in this disclosure refers to any known or later developed hardware, software, firmware, artificial intelligence, fuzzy logic or a combination of hardware and / or software code that is capable of performing the functions associated with that element.
[0076] The following will be combined with the drawings in the embodiments of the present disclosure to clearly and completely describe the technical solutions in the embodiments of the present disclosure. Obviously, the described embodiments are only part of the embodiments of the present disclosure, not all of the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present disclosure.
[0077] The present disclosure provides a method for predicting production proficiency (hereinafter referred to as the prediction method), which is applicable to the production of products in a manufacturing (manual) production line.
[0078] See also Figure 1 , Figure 1 The following is a flow chart of the prediction method provided by the embodiment of the present disclosure. Figure 1 As shown, the method includes the following S101 to S104:
[0079] S101: Obtaining a prediction request input by a user, wherein the prediction request is used to instruct to predict the production proficiency of a target product in a production task at a target time.
[0080] For example, the prediction method of this embodiment can be performed by a prediction device for production proficiency (hereinafter referred to as a prediction device). The prediction device can be a server (such as a local server or a cloud server), an electronic device, a processor, a chip, etc., which is not limited in this embodiment.
[0081] If the prediction device is an electronic device, then in some embodiments, the structure diagram of the electronic device can refer to Figure 2. Electronic devices are intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframes, and other suitable computers. Electronic devices may also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit implementations of the present disclosure described and / or claimed herein.
[0082] like Figure 2 As shown, the electronic device 200 includes a computing unit 201, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 202 or a computer program loaded from a storage unit 208 into a random access memory (RAM) 203. In the RAM 203, various programs and data required for the operation of the electronic device 200 can also be stored. The computing unit 201, the ROM 202, and the RAM 203 are connected to each other via a bus 204. An input / output (I / O) interface 205 is also connected to the bus 204.
[0083] A number of components in the electronic device 200 are connected to the I / O interface 205, including: an input unit 206, such as a keyboard, a mouse, etc.; an output unit 207, such as various types of displays, speakers, etc.; a storage unit 208, such as a disk, an optical disk, etc.; and a communication unit 209, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 209 allows the electronic device 200 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.
[0084] The computing unit 201 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 201 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 201 performs the prediction method and processing described in the present disclosure. For example, in some embodiments, the prediction method may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 208. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 200 via ROM 202 and / or communication unit 209. When the computer program is loaded into RAM 203 and executed by the computing unit 201, one or more steps of the prediction method of the present disclosure may be performed. Alternatively, in other embodiments, the computing unit 201 may be configured to perform the prediction method of the present disclosure in any other appropriate manner (e.g., by means of firmware).
[0085] It is worth noting that this embodiment does not limit the manner in which the prediction device obtains the prediction request. For example, the prediction device may include a display device, and may output an interactive interface through the display device, and the user may initiate a prediction request through the interactive interface.
[0086] The prediction device can display production tasks through an interactive interface, and the production tasks include products and production status, such as products that have been produced, products that are being produced, and products that have not been produced. The target product is an unproduced product, and specifically one or more products that need to be produced after the products that are being produced are completed.
[0087] Exemplarily, in some embodiments, the prediction device can interact with the user through an interactive interface, and obtain a prediction request based on the interaction information generated by the user's click operation on the interactive interface. For example, the interactive interface includes a production task and a virtual button for initiating a prediction request. The user can click on the target task in the production task and click on the virtual button for initiating a prediction request to initiate a prediction request to the prediction device.
[0088] The prediction request is used to instruct the prediction of the proficiency of producing the target product, and specifically to predict the production proficiency at the target time.
[0089] Accordingly, in some embodiments, the prediction device may also obtain the target time through an interactive interface. For example, the interactive interface includes a time input box. The user may input a time in the time input box, and the input time is the target time.
[0090] S102: Obtain historical production data corresponding to the target product, and determine a growth curve for producing the target product based on the historical production data, wherein the historical production data includes historical production time and historical production proficiency, and the growth curve is used to characterize the relationship between an increase in the time for producing the target product and an increase in the proficiency of producing the target product.
[0091] Combined with the above analysis, it can be seen that the prediction device includes a memory, which stores data, such as historical production data, that is, data generated by the production line during historical production, including the time corresponding to the historical production (i.e., historical production time) and proficiency (i.e., historical production proficiency).
[0092] When the prediction device obtains historical production data, it can determine a growth curve corresponding to the production of the target product based on the historical production data. Through the growth curve, the proficiency of producing the target product over time can be determined.
[0093] In some embodiments, the historical production data is data of historical production of the target product, or data of historical production of a similar product that is similar to the target product.
[0094] In combination with the above analysis, it can be known that the prediction device may include a memory, and the memory may store historical production-related data. It is understandable that the target product may or may not have been produced in the past.
[0095] In the case where the target product has been produced in history, the memory stores data of the target product produced in history, such as time and proficiency, etc. The historical production data may be data of the target product produced in history stored in the memory.
[0096] In the case where the target product has not been produced in history, the memory does not store data on the historical production of the target product. However, the memory may store data on products similar to the target product (i.e., similar products) produced in history. The historical production data may be data on the historical production of similar products stored in the memory.
[0097] Among them, similar products can be products that are very similar to the target product in production process, and can be specifically determined based on process similarity. For example, when there is no data of the target product produced in history stored in the memory, the prediction device can determine from the products that have been produced that the similarity with the target product in the production process dimension is less than a preset similarity threshold, and determine the product as a similar product.
[0098] In this embodiment, the prediction device determines the historical production data by combining the data of the historical production of the target product or the data of the historical production of similar products, so that the historical production data can have higher validity and reliability.
[0099] In some embodiments, the growth curve may be as follows Figure 3 The growth curve is shown. Figure 3 In the growth curve shown, the horizontal axis (or horizontal axis x) is time, and the vertical axis (or vertical axis y) is production proficiency. Figure 3 As shown in the figure, with the increase of production time, production proficiency increases from low to high, and the growth rate becomes slower and slower, and then gradually approaches a stable limit.
[0100] In other embodiments, the growth curve may be as follows: Figure 4 The growth curve is shown. Figure 4 In the growth curve shown, the horizontal axis is time and the vertical axis is production proficiency. Figure 4 As shown, with the increase of production time, production proficiency increases from low to high, and the growth rate is slow at first, then gradually increases, and then slows down again.
[0101] S103: Determine an initial function for characterizing the shape of the growth curve, and construct a function to be fitted including an offset based on the initial function, wherein the offset includes a time offset, or includes a time offset and a proficiency offset.
[0102] Exemplarily, the prediction device may obtain and construct a function (ie, an initial function) that can characterize the shape of the growth curve from various functions.
[0103] On this basis, the prediction device can adjust the initial function, and specifically adjust the initial function from the dimension of time, or adjust the initial function from the two dimensions of time and proficiency. Among them, the adjustment of the initial function from the time dimension is specifically reflected in the time offset; the adjustment of the initial function from the proficiency dimension is specifically reflected in the proficiency offset.
[0104] In some embodiments, different growth curves correspond to different initial functions. For example, in combination with the above example, if the growth curve is as follows Figure 3 If the growth curve is as shown, the initial function may be a logarithmic function y=a*ln(x)+b, a power law function y=a*x^(-b), an exponential decay function y=L*(1-e^(-k*x)), etc. Figure 4 If it is the growth curve shown, the initial function may be the Logistic function y=L / (1+e^(-k(x-x0)), the Gompertz function y=a*e^(-b*e&(-c*x)), the cumulative normal distribution function, and so on.
[0105] Correspondingly, the time offset is the offset on x, and the proficiency offset is the offset on y. On y, the offset can be represented by b. On x, the offset can be represented by x0, so the initial function is actually x+x0. In this way, the initial function is offset in two directions. For example, if the initial function is an exponential decay function y=L*(1-e^(-k*x)), the function to be fitted becomes y=L*(1-e^(-k*(x+x0)))+b.
[0106] In some embodiments, in order to avoid overfitting, the prediction device may only construct a function to be fitted including a time offset. For example, the function to be fitted obtained by constructing the initial y=L*(1-e^(-k*x)) is y=L*(1-e^(-k*(x+x0))).
[0107] S104: Fit the function to be fitted according to historical production data to obtain the target function, and determine and output the production proficiency corresponding to the prediction request according to the target function and the target time, wherein the production proficiency corresponding to the prediction request is used to adjust the production task.
[0108] In this embodiment, fitting can be understood as finding a function that can best describe or predict the pattern or trend in the data. This embodiment does not limit the fitting method. For example, the prediction device can use the BOBYQA method to fit to obtain the objective function. Accordingly, combined with the above analysis, the objective function can be a curve relationship between the characterization time and production proficiency.
[0109] On this basis, the prediction device can input the target time as a parameter of the objective function, and obtain the production proficiency corresponding to the target time (i.e., the production proficiency corresponding to the prediction request). In addition, the prediction device can adjust the production task based on the production proficiency corresponding to the prediction request, such as adjusting the start production time of a product in the production task.
[0110] In some embodiments, based on the above examples, it can be known that the prediction device can output an interactive interface. Accordingly, when the prediction device determines the production proficiency corresponding to the prediction request, the production proficiency corresponding to the prediction request can be output through the interactive interface.
[0111] Combined with the above analysis of S101 to S104, it can be known that in this embodiment, after determining the growth curve corresponding to the target product, the prediction device constructs a corresponding initial function, and adjusts the offset of the initial function from the dimension of time, or adjusts the offset from the two dimensions of time and proficiency, and fits the adjusted function to be fitted to obtain the target function, and determines and outputs the proficiency of producing the target product at the target time based on the target function. On the one hand, it can avoid the technical drawbacks of low accuracy and strong dependence on manual labor caused by the average proficiency + manual correction method in the above-mentioned related technologies, and can realize the automation of prediction and improve the accuracy and reliability of prediction. On the other hand, it can avoid the technical drawbacks of incomplete coverage of historical production data caused by the use of AI prediction models in the above-mentioned related technologies, and can achieve full coverage of historical production data, thereby improving the comprehensiveness and accuracy of prediction.
[0112] In some embodiments, the “fitting the function to be fitted according to the historical production data to obtain the target function” in the above S104 includes the following steps 1 and 2:
[0113] Step 1: From the historical production data, obtain data whose historical production proficiency is less than a preset threshold, and determine the offset penalty weight based on the obtained data less than the preset threshold, wherein the offset penalty weight is greater than 1.
[0114] Step 2: Fit the function to be fitted according to the historical production data and the offset penalty weight to obtain the target function.
[0115] This embodiment does not limit the preset threshold value, which can be determined by the prediction device based on demand, historical records, experiments, etc.
[0116] That is to say, in this embodiment, the prediction device can adjust the weight of the penalty in the fitting process to avoid the fitting process being affected by abnormal data.
[0117] For example, Figure 5 As shown in the figure, the red points are historical production data, and some of them are much lower than normal, which makes the fitted curve (blue curve) lower than the actual situation. Combined with the above description of related technologies, it can be seen that if the historical production data is cleaned manually, the workload of manual cleaning is not small due to the large amount of data, and it is also difficult to ensure the quality.
[0118] Therefore, in this embodiment, the prediction device can increase the penalty of historical production data on the growth curve. Generally speaking, the proficiency corresponding to abnormal data is low, such as the maintenance of production tools, resulting in low production proficiency; workers are temporarily arranged to do other production work, resulting in a decrease in the production proficiency of the production line itself; some workers take vacations, resulting in a decrease in the overall production proficiency of the production line, etc.
[0119] Accordingly, in some embodiments, in the above step 1, "determining the offset penalty weight based on the data obtained that is less than a preset threshold value" may include: determining the ratio between the historical production data and the data obtained that is less than a preset threshold value, and determining the offset penalty weight based on the ratio, wherein the smaller the ratio, the closer the offset penalty weight is to 1.
[0120] Exemplarily, the smaller the ratio, the less abnormal data there are, and therefore, the offset penalty weight can be set to a smaller value that is relatively close to 1. Conversely, the larger the ratio, the more abnormal data there are, and therefore, the offset penalty weight can be set to a relatively larger value greater than 1.
[0121] like Figure 6 , if for Figure 5 The curve shown sets the offset penalty weight to 5 (ie, 5:1), and the accuracy of the objective function is relatively higher.
[0122] That is, in this embodiment, the prediction device determines the offset penalty weight, and specifically can determine the offset penalty weight for the combination ratio to improve the validity and reliability of the fitting, thereby improving the accuracy of the prediction.
[0123] In some embodiments, the above step 2 may include the following sub-steps 1 and 2:
[0124] Sub-step 1: Perform the first fitting on the function to be fitted according to the historical production data and the offset penalty weight to obtain the function after the first fitting.
[0125] Exemplarily, the prediction device may perform two fittings on the function to be fitted, and the first fitting is performed based on the historical production data and the offset penalty weight. For example, based on the above example, the result of the first fitting can be found in Figure 6 .
[0126] Sub-step 2: Filter the historical production data according to the first fitting function to obtain filtered data, and perform a second fitting on the function to be fitted according to the filtered data to obtain the second fitted function, wherein the target function is the second fitted function.
[0127] Accordingly, after the first fitting, the prediction device can filter the historical production data based on the result of the first fitting. In combination with the above example, it can be seen that there are abnormal data in the historical production data. Through filtering, the abnormal data in the historical production data can be filtered so that the filtered data is data with at least some abnormal data removed. On this basis, the prediction device fits the data without abnormal data in the historical production data (i.e., filtered data) again (i.e., the second fitting) to obtain the function after the second fitting, that is, the target function. For example, Figure 7 As shown, Figure 7 The black points in the figure are the abnormal data after filtering. Figure 7 The red points in the figure are the data used for the second fitting, and the blue curve is the objective function.
[0128] Combined with the above analysis of sub-step 1 and sub-step 2, it can be seen that in this embodiment, the prediction device performs two fittings on the function to be fitted, and the result of the first fitting is used to filter the abnormal data in the historical production data, so that the second fitting is performed on the filtered data. The accuracy and effectiveness of the fitting can be improved, thereby improving the reliability of the prediction.
[0129] In some embodiments, the "filtering the historical production data according to the first fitting function to obtain filtered data" in the above sub-step 2 may include: performing outlier detection on the historical production data according to the first fitted function to obtain outliers, and removing outliers in the historical production data to filter the historical production data to obtain filtered data.
[0130] Exemplarily, in combination with the above analysis, the prediction device first performs a first fitting, then removes outliers based on residual outlier detection, and then performs a second fitting.
[0131] Combining the above examples with Figure 7 It can be seen that Figure 7 The black points are abnormal data, which are relatively outlier data. In this embodiment, the prediction device can use outlier detection to obtain outliers from each point, and remove the detected outliers to eliminate abnormal data from historical production data, so that the filtered data has higher validity and reliability, thereby improving the validity and reliability of fitting, and further improving the validity and accuracy of prediction.
[0132] It is worth noting that the two fittings in the above example can be used separately or in combination. The above example is an example of combined use for exemplary explanation and cannot be understood as a limitation between the two fittings.
[0133] For example, the prediction device may fit the to-be-fitted function according to historical production data and offset penalty weights to obtain a target function.
[0134] For another example, the prediction device can remove outliers based on outlier detection of residual errors, and perform fitting on this basis to obtain the target function.
[0135] For another example, the prediction device can perform a first fit based on historical production data (without using an offset penalty weight), then remove outliers based on residual outlier detection, and then perform a second fit. The objective function obtained by the prediction device in this way can be found in Figure 8 .
[0136] Comparison Figure 6 , Figure 7 , Figure 8 It can be seen that, relatively speaking, Figure 7 The objective function shown has a better effect. In actual application scenarios, the prediction device can select different ways from the above methods to fit the objective function based on pre-set prediction configuration information, such as pre-configured prediction accuracy, so as to achieve flexibility and diversity in prediction and meet different prediction needs of different users.
[0137] In some embodiments, the production task includes preset production scheduling information for the product to be produced, and the product to be produced includes the target product. Accordingly, the prediction method provided by the present disclosure may also include: determining the predicted production scheduling information of the product to be produced according to the production proficiency of the target product, matching the predicted production scheduling information with the preset production scheduling information to obtain a matching result, and adjusting the preset production scheduling information based on the matching result to adjust the production task.
[0138] For example, the preset production scheduling information can be understood as pre-determined production scheduling information, which can represent information such as the start time of production, production duration, and end time of production for each product in the production task.
[0139] When the production proficiency of the target product is obtained, the prediction device can obtain information such as the production duration and the end production time of the target product under the production proficiency. Accordingly, the prediction device can match the information such as the production duration and the end production time with the relevant information in the preset production scheduling information, and adjust the relevant information in the preset production scheduling information based on the matching result.
[0140] For example, if the production time of the product after the production transfer in the preset production scheduling information is XX hours, and based on the predicted production proficiency of the target product, it is known that the production proficiency of the target product is relatively high, which may shorten the production time of the target product, then the prediction device can adjust the production time of the target product in the predicted production scheduling information, so that after the target product is produced, it can quickly enter the production of the product after the target product in the production generation task, thereby reducing time consumption and improving the overall production progress.
[0141] In other embodiments, if the matching result indicates that the production proficiency of the target product obtained based on the prediction cannot meet the production schedule of the target product in the preset production scheduling information, the prediction device can generate and output prompt information so that the management personnel can take corresponding measures according to the prompt information to avoid delaying the execution of the production task.
[0142] According to an embodiment of the present disclosure, the present disclosure also provides a device for predicting production proficiency, which is suitable for product production in a manufacturing production line.
[0143] See also Fig. 9 , Fig. 9 Schematic diagram of a module of a prediction device provided by an embodiment of the present disclosure. Fig. 9 As shown, the prediction device 900 includes:
[0144] An obtaining unit 901 is used to obtain a prediction request input by a user, wherein the prediction request is used to indicate a prediction of a production proficiency of a target product in a production task at a target time;
[0145] The obtaining unit 901 is also used to obtain historical production data corresponding to the target product;
[0146] A determining unit 902 is configured to determine a growth curve for producing the target product according to the historical production data, wherein the historical production data includes historical production time and historical production proficiency, and the growth curve is used to characterize the relationship between an increase in the time for producing the target product and an increase in proficiency in producing the target product;
[0147] The determining unit 902 is further used to determine an initial function for characterizing the shape of the growth curve;
[0148] A construction unit 903 is used to construct a function to be fitted including an offset based on the initial function, wherein the offset includes a time offset, or includes the time offset and a proficiency offset;
[0149] A fitting unit 904 is used to fit the function to be fitted according to the historical production data to obtain a target function;
[0150] The determining unit 902 is further configured to determine, according to the objective function and the target time, a production proficiency corresponding to the prediction request, wherein the production proficiency corresponding to the prediction request is used to adjust the production task;
[0151] The output unit 905 is used to output the production proficiency corresponding to the prediction request.
[0152] In some embodiments, the fitting unit 904 is specifically used for:
[0153] From the historical production data, data whose historical production proficiency is less than a preset threshold is obtained, and an offset penalty weight is determined according to the obtained data less than the preset threshold, wherein the offset penalty weight is greater than 1;
[0154] The function to be fitted is fitted according to the historical production data and the offset penalty weight to obtain the objective function.
[0155] In some embodiments, the fitting unit 904 is specifically used for:
[0156] Performing a first fitting on the function to be fitted according to the historical production data and the offset penalty weight to obtain a function after the first fitting;
[0157] The historical production data is filtered according to the first fitting function to obtain filtered data, and the function to be fitted is fitted for a second time according to the filtered data to obtain a second fitted function, wherein the target function is the second fitted function.
[0158] In some embodiments, the fitting unit 904 is specifically used for:
[0159] Performing outlier detection on the historical production data according to the first post-fitting function to obtain the outlier;
[0160] The outliers in the historical production data are removed to filter the historical production data to obtain the filtered data.
[0161] In some embodiments, the fitting unit 904 is specifically used for:
[0162] Determining a ratio between the historical production data and the obtained data less than a preset threshold;
[0163] The offset penalty weight is determined according to the ratio, wherein the smaller the ratio is, the closer the offset penalty weight is to 1.
[0164] In some embodiments, the historical production data is data on the historical production of the target product, or is data on the historical production of a similar product that is similar to the target product.
[0165] In some embodiments, the production task includes preset production scheduling information for a product to be produced, and the product to be produced includes the target product;
[0166] The determining unit 902 is further configured to determine the forecast production scheduling information of the product to be produced according to the production proficiency of the target product;
[0167] The device also includes:
[0168] A matching unit 906, configured to match the predicted production scheduling information with the preset production scheduling information to obtain a matching result;
[0169] The adjusting unit 907 is used to adjust the preset production scheduling information based on the matching result to adjust the production task.
[0170] According to an embodiment of the present disclosure, the present disclosure further provides a processor-readable storage medium, wherein the processor-readable storage medium stores a computer program, and the computer program is used to enable the processor to execute the method described in the above embodiment.
[0171] According to an embodiment of the present disclosure, the present disclosure further provides a computer program product, including a computer program, which implements the steps of the method described in the above embodiment when executed by a processor.
[0172] Exemplarily, a computer program product includes: a computer program, the computer program is stored in a readable storage medium, at least one processor of an electronic device can read the computer program from the readable storage medium, and at least one processor executes the computer program so that the prediction device (the electronic device as described above) executes the solution provided by any of the above embodiments.
[0173] Various embodiments of the devices and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.
[0174] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.
[0175] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
[0176] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).
[0177] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.
[0178] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship between the client and the server is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services ("Virtual Private Server", or "VPS" for short). The server may also be a server of a distributed system, or a server combined with a blockchain.
[0179] Those skilled in the art will appreciate that the embodiments of the present disclosure may be provided as methods, devices, or computer program products. Therefore, the present disclosure may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present disclosure may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage and optical storage, etc.) containing computer-usable program code.
[0180] The present disclosure is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present disclosure. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer executable instructions. These computer executable instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0181] These processor executable instructions may also be stored in a processor readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the processor readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.
[0182] These processor-executable instructions may also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for executing on the computer or other programmable device to implement the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.
[0183] Obviously, those skilled in the art can make various changes and modifications to the present disclosure without departing from the spirit and scope of the present disclosure. Thus, if these modifications and variations of the present disclosure fall within the scope of the claims of the present disclosure and their equivalents, the present disclosure is also intended to include these modifications and variations.
Claims
1. A method for predicting production proficiency, characterized in that: The method is applicable to the production of products on a manufacturing production line, and comprises: Obtaining a prediction request input by a user, wherein the prediction request is used to instruct to predict the production proficiency of a target product in a production task at a target time; Obtaining historical production data corresponding to the target product, and determining a growth curve for producing the target product based on the historical production data, wherein the historical production data includes historical production time and historical production proficiency, and the growth curve is used to characterize the relationship between an increase in the time for producing the target product and an increase in proficiency in producing the target product; Determine an initial function for characterizing the shape of the growth curve, and construct a function to be fitted including an offset based on the initial function, wherein the offset includes a time offset, or includes the time offset and a proficiency offset; The function to be fitted is fitted according to the historical production data to obtain a target function, and the production proficiency corresponding to the prediction request is determined and output according to the target function and the target time, wherein the production proficiency corresponding to the prediction request is used to adjust the production task.
2. The method according to claim 1, characterized in that The step of fitting the function to be fitted according to the historical production data to obtain a target function includes: From the historical production data, data whose historical production proficiency is less than a preset threshold is obtained, and an offset penalty weight is determined according to the obtained data less than the preset threshold, wherein the offset penalty weight is greater than 1; The function to be fitted is fitted according to the historical production data and the offset penalty weight to obtain the objective function.
3. The method according to claim 2, characterized in that The step of fitting the function to be fitted according to the historical production data and the offset penalty weight to obtain the objective function includes: Performing a first fitting on the function to be fitted according to the historical production data and the offset penalty weight to obtain a function after the first fitting; The historical production data is filtered according to the first fitting function to obtain filtered data, and the function to be fitted is fitted for a second time according to the filtered data to obtain a second fitted function, wherein the target function is the second fitted function.
4. The method according to claim 3, characterized in that The filtering process of the historical production data according to the first fitting function to obtain filtered data includes: Performing outlier detection on the historical production data according to the first post-fitting function to obtain the outlier; The outliers in the historical production data are removed to filter the historical production data to obtain the filtered data.
5. The method according to claim 2, characterized in that: The step of determining the offset penalty weight according to the obtained data that is less than a preset threshold value includes: Determining a ratio between the historical production data and the obtained data less than a preset threshold; The offset penalty weight is determined according to the ratio, wherein the smaller the ratio is, the closer the offset penalty weight is to 1.
6. The method according to claim 1, characterized in that The historical production data is data of the historical production of the target product, or data of the historical production of a similar product that is similar to the target product.
7. The method according to claim 1, characterized in that The production task includes preset production scheduling information of the product to be produced, and the product to be produced includes the target product; the method further includes: Determining forecast production scheduling information of the product to be produced according to the production proficiency of the target product; Matching the predicted production scheduling information with the preset production scheduling information to obtain a matching result; The preset production scheduling information is adjusted based on the matching result to adjust the production task.
8. A production proficiency prediction device, characterized in that: The device is suitable for the production of products on a manufacturing production line, and comprises: An obtaining unit, configured to obtain a prediction request input by a user, wherein the prediction request is used to instruct to predict the production proficiency of a target product in a production task at a target time; The obtaining unit is further used to obtain historical production data corresponding to the target product; a determining unit, configured to determine a growth curve for producing the target product according to the historical production data, wherein the historical production data includes historical production time and historical production proficiency, and the growth curve is used to characterize the relationship between an increase in the time for producing the target product and an increase in proficiency in producing the target product; The determination unit is further used to determine an initial function for characterizing the shape of the growth curve; A construction unit, configured to construct a function to be fitted including an offset based on the initial function, wherein the offset includes a time offset, or includes the time offset and a proficiency offset; A fitting unit, used for fitting the function to be fitted according to the historical production data to obtain a target function; The determining unit is further configured to determine, according to the objective function and the target time, a production proficiency corresponding to the prediction request, wherein the production proficiency corresponding to the prediction request is used to adjust the production task; The output unit is used to output the production proficiency corresponding to the prediction request.
9. A processor-readable storage medium, characterized in that: The processor-readable storage medium stores a computer program, and the computer program is used to cause the processor to execute the method according to any one of claims 1 to 8.
10. A computer program product, comprising a computer program, which implements the steps of the method according to any one of claims 1 to 8 when executed by a processor.