Data processing method, device and equipment for dispensing, storage medium and product

Abstract

The invention discloses a data processing method, device and equipment for dispensing, a storage medium and a product, and relates to the technical field of dispensing. The method comprises the steps that expected glue weight data and a preset prediction model are obtained, predicted glue type category data corresponding to candidate glue dispensing parameter data are determined on the basis of the candidate glue dispensing parameter data and a preset glue type classification model in the preset prediction model, glue type categories comprise qualified glue type data and unqualified glue type data, and the predicted glue type category data correspond to the candidate glue dispensing parameter data. Based on the candidate dispensing parameter data and a preset glue weight regression model in a preset prediction model, determining predicted glue weight data corresponding to the candidate dispensing parameter data, and based on a first objective function determined according to the expected glue weight data, the predicted glue type category data and the predicted glue weight data, determining the predicted glue weight data corresponding to the candidate dispensing parameter data; and determining target dispensing parameter data corresponding to the expected glue weight data from the candidate dispensing parameter data. By adopting the technical scheme, the determination efficiency and accuracy of the dispensing process parameters can be improved.

Description

Technical Field

[0001] The present invention relates to the field of glue dispensing technology, and in particular to a data processing method, device, equipment, storage medium and product for glue dispensing. Background Art

[0002] The dispensing process is an industrial manufacturing technology that achieves functions such as bonding, sealing, insulation or thermal conductivity by precisely controlling the application, filling or dripping of glue or other fluids. It can be widely used in multiple fields and products.

[0003] The current dispensing control method relies on manual experience. According to the dispensing demand information, the process parameters such as glue heating temperature, dispensing height, valve opening time, rise time, delay time, fall time and striker stroke are manually combined and debugged. Since there are many types of the above parameters and each parameter is not independent for the dispensing effect, they will affect the width and height of the glue line and other shapes, and it is impossible to form a one-to-one linear function relationship. Therefore, it is very time-consuming and inefficient to debug qualified dispensing process parameters. Summary of the invention

[0004] The present invention provides a data processing method, device, equipment, storage medium and product for glue dispensing, which can realize automatic determination of accurate glue dispensing parameters.

[0005] According to one aspect of the present invention, a data processing method for dispensing is provided, comprising:

[0006] Acquire expected glue weight data and a preset prediction model, wherein the preset prediction model includes a preset glue type classification model and a preset glue weight regression model;

[0007] Based on the candidate dispensing parameter data and the preset glue type classification model, determining the predicted glue type category data corresponding to the candidate dispensing parameter data, wherein the glue type category includes qualified and unqualified;

[0008] Based on the candidate dispensing parameter data and the preset glue weight regression model, determining the predicted glue weight data corresponding to the candidate dispensing parameter data;

[0009] The target dispensing parameter data corresponding to the expected glue weight data is determined from the candidate dispensing parameter data based on a first objective function, wherein the first objective function is determined according to the expected glue weight data, the predicted glue type category data and the predicted glue weight data.

[0010] According to another aspect of the present invention, a data processing device for dispensing is provided. The device comprises:

[0011] An acquisition module, used for acquiring expected glue weight data and a preset prediction model, wherein the preset prediction model includes a preset glue type classification model and a preset glue weight regression model;

[0012] A category prediction module, used to determine predicted glue type category data corresponding to the candidate glue dispensing parameter data based on the candidate glue dispensing parameter data and the preset glue type classification model, wherein the glue type category includes qualified and unqualified;

[0013] A glue weight prediction module, used to determine predicted glue weight data corresponding to the candidate glue dispensing parameter data based on the candidate glue dispensing parameter data and the preset glue weight regression model;

[0014] A parameter data determination module is used to determine the target dispensing parameter data corresponding to the expected glue weight data from the candidate dispensing parameter data based on a first objective function, wherein the first objective function is determined according to the expected glue weight data, the predicted glue type category data and the predicted glue weight data.

[0015] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0016] At least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the data processing method for dispensing described in any embodiment of the present invention.

[0017] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the data processing method for dispensing described in any embodiment of the present invention when executed.

[0018] According to another aspect of the present invention, a computer program product is provided. The computer program product includes a computer program. When the computer program is executed by a processor, the data processing method for dispensing described in any embodiment of the present invention is implemented.

[0019] The technical solution of the embodiment of the present invention obtains expected glue weight data and a preset prediction model, determines the predicted glue type category data corresponding to the candidate glue dispensing parameter data based on the candidate glue dispensing parameter data and the preset glue type classification model in the preset prediction model, and the glue type categories include qualified and unqualified, determines the predicted glue weight data corresponding to the candidate glue dispensing parameter data based on the candidate glue dispensing parameter data and the preset glue weight regression model in the preset prediction model, and determines the target glue dispensing parameter data corresponding to the expected glue weight data from the candidate glue dispensing parameter data based on the first objective function determined according to the expected glue weight data, the predicted glue type category data and the predicted glue weight data. By adopting the above technical solution, the model is used to predict the candidate glue dispensing process parameters in terms of glue type and glue weight, and the objective function is used to automatically determine the target glue dispensing process parameters that meet the constraints of glue type and glue weight, thereby improving the efficiency and accuracy of determining the glue dispensing process parameters, reducing the cost of debugging the process parameters, and improving the debugging efficiency, thereby improving the production efficiency related to the glue dispensing process.

[0020] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0022] Figure 1 is a flow chart of a data processing method for dispensing provided according to an embodiment of the present invention;

[0023] Figure 2 is a schematic diagram of a process of generating a glue-weighted regression model according to an embodiment of the present invention;

[0024] Figure 3 is a schematic diagram of a model updating process provided according to an embodiment of the present invention;

[0025] Figure 4 is a flow chart of a data processing method for dispensing provided according to an embodiment of the present invention;

[0026] Figure 5 is a schematic diagram of a framework of a data processing solution for dispensing provided according to an embodiment of the present invention;

[0027] Figure 6is a structural schematic diagram of a data processing device for dispensing provided according to an embodiment of the present invention;

[0028] Figure 7 It is a structural schematic diagram of an electronic device for implementing the data processing method for dispensing according to an embodiment of the present invention. DETAILED DESCRIPTION

[0029] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0030] It should be noted that the terms "first", "second", "initial" and "target" in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0031] Figure 1 This is a flow chart of a data processing method for dispensing according to an embodiment of the present invention. This embodiment is applicable to the case of automatically determining dispensing process parameters. The method can be executed by a data processing device for dispensing. The data processing device for dispensing can be implemented in the form of hardware and / or software. The data processing device for dispensing can be configured in an electronic device, which can be a computer device or an industrial production device. Figure 1 As shown, the method includes:

[0032] Step 101: Obtain expected glue weight data and a preset prediction model, wherein the preset prediction model includes a preset glue type classification model and a preset glue weight regression model.

[0033] Glue weight generally refers to the actual weight of glue or other fluid (hereinafter referred to as glue for ease of description) on the product during the dispensing process. It is an important parameter used to ensure that the amount of glue dispensed each time is consistent, thereby ensuring product quality. In the embodiment of the present invention, the expected glue weight data can be understood as the data of the glue weight that needs to be achieved after dispensing determined according to actual production needs, and can also be called target glue weight data, which can specifically be a weight value.

[0034] In an embodiment of the present invention, the preset prediction model may be a machine learning model that has been trained in advance, and may be trained based on the collected sample data. The sample data may include sample dispensing parameter data, sample glue type data, and sample glue weight data. The preset prediction model may be a dynamically updated model to improve the prediction accuracy. The preset prediction model includes a preset glue type classification model and a preset glue weight regression model, which may be used to make predictions for glue type and glue weight, respectively, wherein the glue type categories may include qualified and unqualified. Optionally, the preset glue type classification model may include a classification model based on extreme gradient boosting (eXtreme Gradient Boosting, XGBoost), and may also include a logistic regression model for classification tasks; the preset glue weight regression model may include a regression model based on XGBoost, and may also include a linear regression model for regression tasks.

[0035] Step 102: Based on the candidate dispensing parameter data and the preset glue type classification model, determine the predicted glue type category data corresponding to the candidate dispensing parameter data, wherein the glue type category includes qualified and unqualified.

[0036] Exemplarily, the dispensing parameter data may be the parameter value of the dispensing process parameter. The candidate dispensing parameter data may include the parameter value of any dispensing process parameter supported by the dispensing process equipment or the parameter value of the preset dispensing process parameter. The specific type of the dispensing process parameter involved is not limited, and may include glue-related control parameters or spray valve-related control parameters, etc. For example, it may include at least one of the following: glue heating temperature, dispensing height, glue valve opening time, rise time, delay time, fall time, and striker stroke. There are generally multiple groups of candidate dispensing parameter data, and each group of dispensing parameter data usually includes parameter values ​​of multiple dispensing process parameters. A preset search algorithm (such as a heuristic search algorithm) may be used to sequentially determine the candidate dispensing parameter data currently involved in the calculation until the candidate dispensing parameter data that meets the requirements corresponding to the expected glue weight data is searched, which is the dispensing parameter data obtained after prediction using a preset prediction model, and can also be recorded as the target dispensing parameter data.

[0037] Exemplarily, glue type classification can be regarded as a binary classification task, which is used to predict whether the glue type dispensed under specified dispensing process parameters is qualified. The preset glue type classification model can be trained using the training set.

[0038] Optionally, the preset glue type classification model includes a first glue type classification model, and the first glue type classification model is trained using a local training set, and specifically may be a classification model based on XGBoost.

[0039] For example, a sampling set of dispensing process parameters is pre-set, and data on glue type and glue weight under different dispensing parameter data are collected through dispensing experiments, and data preprocessing is performed to obtain a local data set. , also known as the local training set, can be expressed as .in, Indicates The feature vector of samples (the feature dimension is , i.e., the dimension of adjustable dispensing process parameters), R represents the real number set, i.e., the set of all real numbers; Indicates The glue weight value corresponding to each sample; , indicating the The glue type label corresponding to each sample, Represents unqualified, Representatives are qualified; Represents the total number of samples in the local training set.

[0040] Exemplarily, the collected data is preprocessed and converted into binary classification labels (qualified and unqualified), and then trained using a machine learning model (such as XGBoost) to obtain a first type classification model.

[0041] For example, in the glue type data collection, for each set of dispensing parameters, the data of a first number (recorded as m, for example, m=3) of glue lines can be sampled, and each glue line records the number of scattered points, the number of bubbles, and the glue width value at a second number (recorded as n, for example, n=40). For each set of parameter value records, those that meet the preset qualified conditions are recorded as qualified (category ), otherwise it is unqualified (category ). The preset qualified conditions may include conditions of multiple dimensions. If the conditions of the multiple dimensions are met at the same time, it is considered that the preset qualified conditions are met. Multiple dimensions may include, for example, glue breaking dimension, bubble dimension, scatter point dimension and glue width dimension. For the glue breaking dimension, all glue width values ​​of the m groups of glue lines are not 0; for the bubble dimension, the mean number of bubbles of the m groups of glue lines is less than the bubble threshold (such as 3); for the scatter point dimension, the mean number of scatter points of the m groups of glue lines is less than the scatter point threshold (such as 3); for the glue width dimension, at least p groups (for example, 2) of the m groups of glue lines have uniform glue width. Uniform glue width means that after deleting the maximum and minimum values ​​of the glue width values ​​at n locations, the standard deviation of the remaining glue width values ​​divided by the mean of the remaining glue width values ​​is less than the first proportion value (such as 5%), and the range divided by the mean is less than the second proportion value (such as 10%).

[0042] The first glue type classification model is a two-class model , which can be expressed as . , is the probability of the glue type being qualified predicted by the classification model, is the optimal parameter of the model. The model output is that the sample belongs to the category Probability: ,in, Indicates The predicted probability that a sample is a qualified glue type, Indicates The predicted probability that a sample is an unqualified glue type, is the parameter of the classification model. The glue type category predicted by the model is .

[0043] The training goal of the first type of classification model is to optimize the parameters of the classification model by minimizing the binary cross entropy loss function:

[0044] .

[0045] in, Indicates The real glue type labels of the samples; Indicates The predicted probability of a sample.

[0046] XGBoost is a machine learning algorithm based on gradient boosting. It improves the prediction accuracy of the model by building and combining multiple weak classifiers (usually decision trees). The working principle of XGBoost's binary classification can be simply summarized into the following steps:

[0047] (1) Initialize the model: XGBoost starts with a simple model, such as one where all samples have the same predicted value. For binary classification problems, it is usually initialized to predict all samples as a constant value (for example, the initial probability of all samples is 0.5).

[0048] (2) Calculating the error (residual): XGBoost calculates the error of the current prediction of the model. For binary classification problems, the loss function used is the logarithmic loss function (log-loss). This error represents the degree of error of the current model in predicting the positive and negative categories.

[0049] (3) Build a new decision tree: Based on the error of the current model, XGBoost builds a new decision tree to correct the error. Each node of the decision tree represents the division of a certain feature, and the leaves store the predicted correction value of the residual (that is, the direction and magnitude of the model that needs to be adjusted).

[0050] (4) Update the model: The newly constructed decision tree will fine-tune the predicted value of each sample. The output of each new tree is an adjustment to the previous model. XGBoost will add new trees to the existing model so that the prediction results gradually approach a more accurate direction.

[0051] (5) Repeated iteration: XGBoost repeats the above steps to gradually build new trees, and each iteration will make corrections based on the error information of the previous iteration. This process usually lasts for multiple rounds until the model reaches the predetermined number of trees or the error drops to a certain threshold.

[0052] (6) Output the final prediction: For a binary classification problem, the final output is the probability that the sample belongs to a certain category. XGBoost performs a weighted summation of the prediction results of all trees and then uses the logarithmic probability function (LogisticFunction, ), convert the result into a probability value between 0 and 1. Set the classification threshold, which is usually set to 0.5. If the probability is greater than the classification threshold, the prediction is class, otherwise the prediction is category (i.e. unqualified).

[0053] Exemplarily, in this step, the candidate dispensing parameter data currently required to participate in the calculation is input into the preset glue type classification model, and the predicted glue type category data corresponding to the currently input candidate dispensing parameter data is determined according to the data output by the preset glue type classification model. The predicted glue type category data can be, for example, a probability value, and the specific glue type category can be determined according to the comparison result between the probability value and the preset threshold value, such as a probability value greater than or equal to 0.5 indicates qualified, and a probability value less than 0.5 indicates unqualified.

[0054] Step 103: Determine the predicted glue weight data corresponding to the candidate glue dispensing parameter data based on the candidate glue dispensing parameter data and the preset glue weight regression model.

[0055] Exemplarily, glue weight prediction can be regarded as a regression task, which is used to predict the glue weight of glue dispensed under specified glue dispensing process parameters. The preset glue weight regression model can be obtained by training using a training set.

[0056] Optionally, the preset glue-weight regression model includes a first glue-weight regression model, which is trained using a local training set and may specifically be a regression model based on XGBoost.

[0057] Exemplarily, the collected data is preprocessed. For example, in the collection of glue weight data, each set of dispensing parameters is weighed a third number (recorded as q, for example, q=5) times, the average of each weighing is recorded, and the average of the q weighing values ​​is recorded as the glue weight value of the set of dispensing parameters. Optionally, in order to ensure data quality, only the dispensing parameter groups whose standard deviation of the q weighings divided by the mean is less than a third ratio value (such as 5%) can be retained.

[0058] Exemplary, first-order regression model is a feature space Function mapped to target space R: , Represents the predicted rubber weight data, is the optimal parameter of the model. The predicted glue weight is: ,in, is the parameter of the model. The training goal of the regression model is to obtain the optimal parameters by minimizing the loss function (such as mean square error) of the rubber weight prediction error:

[0059] .

[0060] The principle of XGBoost in regression tasks is similar to that of classification tasks. It is still based on the idea of ​​gradient boosting tree (GBDT) and reduces model errors by gradually building multiple weak regression models (decision trees). The core idea is that each round of iteration corrects the prediction error of the previous round and finally builds a powerful regression model. The working principle of XGBoost regression can be summarized in the following steps:

[0061] (1) Initializing the model: XGBoost starts with a simple model, usually with the same prediction value for all samples, such as using the mean of the target variable as the initial prediction.

[0062] (2) Calculating Errors (Residuals): XGBoost calculates the model’s current prediction error (i.e., the difference between the predicted value and the true value), also known as residuals. XGBoost uses mean squared error (MSE) as the loss function for regression tasks, which minimizes the sum of the squared differences between the predicted value and the true value. These errors are used to measure the model’s current prediction performance.

[0063] (3) Build a new decision tree: XGBoost builds a new decision tree to reduce the current error. Each node of this tree represents the division of features, and the value stored in each leaf node is the adjustment value of the residual (that is, the amount that the model needs to be corrected).

[0064] (4) Update the model: The output of the new tree (the adjusted value of the residual) is added to the predicted value of the existing model to update the prediction result of the overall model.

[0065] (5) Repeated iteration: XGBoost continues to repeat the above steps to gradually build new decision trees. Each new tree is built based on the residual of the current model. The output of each tree is used to further adjust the predicted value and correct the residual.

[0066] (6) Output the final prediction: After multiple rounds of iterations, the prediction results of all trees (the output value of each tree) are weighted and summed to obtain the final regression prediction value.

[0067] Exemplarily, in this step, the candidate dispensing parameter data currently required to be calculated is input into a preset glue weight regression model, and the predicted glue weight data corresponding to the currently input candidate dispensing parameter data is determined according to the data output by the preset glue weight regression model. The predicted glue weight data may be, for example, a glue weight value.

[0068] Step 104: determining target dispensing parameter data corresponding to the expected glue weight data from the candidate dispensing parameter data based on a first objective function, wherein the first objective function is determined according to the expected glue weight data, the predicted glue type category data and the predicted glue weight data.

[0069] For example, the search for dispensing process parameters can be regarded as an optimization problem of high-dimensional continuous variables. The preset search algorithm can effectively find the optimal (minimizing the first objective function) dispensing parameter combination (target dispensing parameter data) in the high-dimensional continuous parameter space (which can be regarded as the data space containing all candidate dispensing parameter data). The optimization goal is to find a set of dispensing parameter data so that the preset glue type classification model predicts that it is qualified, and the specification predicted by the preset glue weight regression model (predicted glue weight) is closest to the target specification (expected glue weight), which can be expressed as a multi-objective optimization problem:

[0070] .

[0071] in, It is the rubber weight value predicted by the preset rubber weight regression model, that is, the predicted rubber weight data. is the target glue weight value, that is, the expected glue weight data. is the regression error, such as mean square error or squared error, such as , is the output of the preset glue type classification model (1 means qualified, 0 means unqualified), is the penalty factor for the conformity of the glue type ( ), () is the indicative function.

[0072] Exemplarily, a heuristic search algorithm based on a machine learning prediction model is started to randomly sample a set of process parameters As the initial point (that is, the first candidate dispensing parameter data determined), after iterative optimization, a set of optimal process parameters is obtained. ,in:

[0073] So is the optimization objective function of the target (the first objective function), is the penalty factor for the conformity of the glue type ( ), () is the indicative function, .

[0074] For example, considering the high dimensionality and complexity of the parameter space and avoiding global traversal, a heuristic algorithm (such as Bayesian optimization) can be used for parameter search. Of course, other search algorithms can also be used, such as grid search or random search, etc. Bayesian optimization is an efficient method for optimizing complex functions. Its core idea is to use a proxy model (such as Gaussian process or random forest, etc.) to approximate the target function, and continuously update this model through Bayes to find the optimal solution.

[0075] The search process of Bayesian optimization can be summarized as follows: First, by sampling the initial points of the objective function, use these points to train a proxy model, which can give the predicted mean and uncertainty of the objective function under different inputs. Then, use a collection function (such as expected improvement or confidence interval upper limit, etc.) to select the next point to be evaluated. This step weighs the balance between exploring new areas and using known good results based on the predicted value and uncertainty of the proxy model in the unexplored area. Evaluate the new point and update the proxy model. Repeat this process until the optimal value of the objective function is found.

[0076] The data processing method for dispensing provided by the embodiment of the present invention obtains expected glue weight data and a preset prediction model, determines the predicted glue type category data corresponding to the candidate glue dispensing parameter data based on the candidate glue dispensing parameter data and the preset glue type classification model in the preset prediction model, and the glue type category includes qualified and unqualified. Based on the candidate glue dispensing parameter data and the preset glue weight regression model in the preset prediction model, the predicted glue weight data corresponding to the candidate glue dispensing parameter data is determined, and based on the first objective function determined according to the expected glue weight data, the predicted glue type category data and the predicted glue weight data, the target glue dispensing parameter data corresponding to the expected glue weight data is determined from the candidate glue dispensing parameter data. By adopting the above technical solution, the model is used to predict the candidate glue dispensing process parameters in terms of glue type and glue weight, and the target glue dispensing process parameters that meet the constraints of glue type and glue weight are automatically determined using the objective function, thereby improving the efficiency and accuracy of determining the glue dispensing process parameters, reducing the cost of debugging the process parameters, and improving the debugging efficiency, thereby improving the production and manufacturing efficiency related to the glue dispensing process.

[0077] As time goes by, the equipment will be worn out during the production process. With the same dispensing parameters, the dispensing effect will be greatly different after a period of time (such as one month), and the process parameters need to be readjusted. Whenever there is a new dispensing requirement, the existing solution needs to re-debug the valve process parameters on site, affecting the project progress.

[0078] In the embodiment of the present invention, taking into account the influence of uncontrollable factors such as machine wear, environmental changes (such as temperature changes) and glue characteristics (such as inconsistent viscosity), the distribution of the collected glue weight data will shift over time. In order to reduce the impact of this shift on the model, a bias correction model is introduced to improve the prediction accuracy of the glue weight regression model in the latest environment. Specifically, a basic model can be constructed by using a large amount of stable data collected in the early stage, and then the bias regression model can be trained with the latest biased data. The two can be combined to construct a correction model to improve the generalization ability and prediction accuracy of the model on the latest data.

[0079] In some embodiments, the first glue weight regression model is trained in the following manner: divide the local training set into a first training set and a second training set, wherein the sampling time of any sample data in the second training set is later than the sampling time of any sample data in the first training set; use the first training set to train to obtain a first glue weight regression sub-model; use the first glue weight regression sub-model to predict the second training set to obtain a predicted value, and calculate the prediction error based on the predicted value; use the prediction error and the second training set to train to obtain a second glue weight regression sub-model; determine the first glue weight regression model based on the first glue weight regression sub-model and the second glue weight regression sub-model.

[0080] For example, Divide into (the first training set, equivalent to the early data) and (The second training set is equivalent to the later data, and the weight distribution is shifted). The specific division method is not limited. For example, The sample data are sorted according to the sampling time of each sample data in, and the split point is found from them. The first training set is determined according to the sample data before the split point, and the second training set is determined according to the sample data after the split point. First, the basic model is trained, such as based on Training a basic regression model with strong versatility (First glue weight regression submodel) is used to capture the overall relationship between dispensing parameters and glue weight. Then calculate the later data deviation, such as using right Make a prediction and get the predicted value , for example, The sample dispensing parameter data in the In The output of is used as the predicted value and the exist The prediction error on , that is, calculation The difference between the sample weight value and the predicted value is used to obtain the prediction error. Then the deviation prediction model is trained based on The prediction error on training the bias regression model for later data (Second regressor model), the second regressor model can specifically be a regression model based on XGBoost. The training process can refer to the relevant description in the previous article.

[0081] Exemplarily, the first glue weight regression model is determined according to the first glue weight regression sub-model and the second glue weight regression sub-model, and specifically, the first glue weight regression model is determined according to the sum of the first glue weight regression sub-model and the second glue weight regression sub-model. , that is, .

[0082] One of the keys to the bias correction regression model is the separation of the basic data set and the bias data set. In the embodiment of the present invention, an optimal change point position can be found by detecting the change point of the regression error sequence, and the sequence can be divided into two parts so that the distribution of the two parts is as different as possible, thereby achieving data separation.

[0083] In some embodiments, the local training set is divided into a first training set and a second training set, including: using an initial regression model to determine the regression error of each sample data in the local training set; sorting the regression errors according to the sampling time of each sample data in the local training set to obtain a regression error sequence; determining a target regression error in the regression error sequence, and dividing the local training set into a first training set and a second training set according to the target regression error, wherein the sample data corresponding to the target regression error is the last sample data in the first training set or the first sample data in the second training set, and the target regression error is determined with the goal of maximizing the difference between the sample distribution of the first training set and the sample distribution of the second training set. In this way, the training set can be segmented efficiently and accurately, and the model prediction accuracy can be improved.

[0084] The initial glue weight regression model may be a glue weight regression model to be updated, for example, it may be a first glue weight regression model obtained by first training with a local training set or a first glue weight regression model that needs to be updated in other cases.

[0085] Figure 2 is a schematic diagram of a process of generating a regression model according to an embodiment of the present invention. Figure 2 As shown, the initial weighted regression model is used to calculate the regression error (such as square error) of each sample data in the local training set (original data), the regression error is sorted according to the sampling time of each sample data in the local training set, and a regression error sequence is obtained. The regression error sequence is used to detect single-point errors, that is, to determine the target regression error, and the target regression error is used to classify the data. The local training set is divided into early data (first training set) and late data (second training set). The early data is used to train to obtain a basic regression model (first weighted regression sub-model), the basic regression model and the late data are used to calculate the prediction deviation, and the prediction deviation is used to train to obtain a deviation regression model (second weighted regression sub-model), and finally a deviation correction regression model (first weighted regression model) is obtained.

[0086] For example, the regression error sequence can be written as The error single change point detection process includes: finding a change point location , maximize the segmentation loss function ,in, is the data fitting loss function, such as the mean square error within the segment, , , where i, j and k represent positive integers. Then the data is separated according to the optimal position of the change point ,Will Divided into the initial basic data set (first training set) and the later bias dataset (second training set) .

[0087] In order to further control the impact of prediction deviation on target search, the embodiment of the present invention can correct the model in time while ensuring search efficiency, and thus adopts a mixed online update method of strong and weak models to achieve model correction.

[0088] In some embodiments, the preset glue type classification model is determined by the weighted sum of the first glue type classification model and the second glue type classification model, and the preset glue weight regression model is determined by the weighted sum of the first glue weight regression model and the second glue weight regression model; the first glue type classification model and the first glue weight regression model are obtained by training with a local training set, and the second glue type classification model and the second glue weight regression model are obtained by training with an online training set, and the online training set includes test result data obtained after performing a glue dispensing test using at least one of the target glue dispensing parameter data; the training cost of the second glue type classification model is lower than the training cost of the first glue type classification model, and the training cost of the second glue weight regression model is lower than the training cost of the first glue weight regression model. Therefore, on the basis of timely correction of the model, the search efficiency is guaranteed, the impact of the prediction deviation on the search of the target glue dispensing parameter data can be further controlled, and the prediction accuracy can be improved.

[0089] The online training set can be a dynamically updated training set. After each prediction using the preset prediction model, the target dispensing parameter data can be obtained. The dispensing test using the target dispensing parameter data can obtain the corresponding test result data. The online training samples are constructed based on the test result data and stored in the online training set to dynamically update the online training set. For example, the online data set is recorded as , for the searched target dispensing process parameters , perform dispensing test in real time and obtain test glue type data (glue type result ) and test glue weight data (glue weight value ), and record the test result data , update the test result data to the online database, .

[0090] For example, the training cost can be measured based on model complexity and training cost. Models with high training cost can be recorded as strong models, including the first-order regression model (which can be recorded as ) and the first glue type classification model (which can be recorded as ); the low training cost can be recorded as a weak model, including the second glue regression model (which can be recorded as ) and the second glue type classification model (which can be recorded as ). Among them, the strong model selects models with high model complexity and high prediction accuracy, such as the XGBoost-based classification model, XGBoost-based regression model, and XGBoost-based bias correction regression model mentioned above; the weak model selects models with low model complexity and low training cost, such as the logistic regression model for classification tasks and the linear regression model for regression tasks. Based on the data set Perform weak model training to obtain a weak classification model and weak regression model , which is used to capture the simple relationship between machine parameters and the latest glue weight and glue type. Optionally, when the target dispensing parameter data fails the dispensing test, the weak model is updated using the current online training set. The prediction deviation is corrected by mixing strong and weak models. At the same time, the real-time update of the weak model ensures the real-time correction of the algorithm by the dispensing test results. The performance evaluation and automatic update of the strong model can ensure the accuracy of the prediction model. Since the training time cost of the weak model is low, and the automatic update of the strong model can only be performed when the model evaluation fails, the training frequency is low. Therefore, the online hybrid correction model update mechanism achieves real-time improvement of model accuracy at a very low time cost.

[0091] Exemplarily, the prediction results of the strong model and the weak model are weighted and summed to achieve correction of the model results.

[0092] For classification models, , ;

[0093] For regression models, .

[0094] in, and are the importance weights of the strong and weak models, , ,when When , the weak model has no effect on the results. It should be noted that for classification models and regression models, The value of can be different.

[0095] In some embodiments, the method may further include: in response to the first glue type classification model and / or the first glue regression model failing the performance evaluation result, moving the online training set into the local training set to obtain a new local training set; training the first glue type classification model and / or the first glue regression model based on the new local training set to obtain an updated first glue type classification model and / or an updated first glue regression model. In this way, the local training set used to train the strong model can be updated in a timely manner, and the local training set can be supplemented with more timely sample data in the online training set, thereby improving the prediction accuracy of the updated strong model.

[0096] Exemplarily, the performance evaluation trigger conditions of the first glue type classification model and / or the first glue regression model can be preset, recorded as preset evaluation trigger conditions, and the performance evaluation of the first glue type classification model and / or the first glue regression model is triggered when the preset evaluation trigger conditions are met, and the specific evaluation method is not limited. Among them, the preset evaluation trigger conditions can be set based on time conditions and / or the number of times the target dispensing parameter data fails to pass the corresponding dispensing test. For example, the time interval between the current time and the last performance evaluation time is greater than a preset interval threshold, such as 1 month. For another example, the continuous cumulative number of times the target dispensing parameter data fails to pass the corresponding dispensing test is greater than a preset number threshold, such as 3 times.

[0097] For example, the online training set can be used to evaluate the performance of the first glue type classification model and / or the first glue regression model. For example, for the first glue type classification model, if the model's precision is greater than the precision threshold, it is passed, otherwise, it is failed; for the first glue regression model, if the model's mean absolute error (MAE) is less than the mean absolute error threshold, it is passed, otherwise, it is failed. , .

[0098] Exemplarily, if the strong model fails the performance evaluation, the online database is merged into the local database. , ,in, represents the empty set; and based on Train a strong model to get a new strong classification model and / or new strong regression models , that is, obtaining an updated first glue type classification model and / or an updated first glue regression model.

[0099] Figure 3 is a schematic diagram of a model updating process provided according to an embodiment of the present invention. Figure 3 As shown, the online database is updated according to the dispensing test results, that is, the online training set is updated, and the weak model is trained using the online training set. For example, if the target dispensing parameter data fails the dispensing test, the weak model is updated using the current online training set. The performance of the strong model is evaluated. If it passes, there is no need to update the strong model. If it fails, the local database is updated according to the online database and the local database, that is, the local training set is updated, and the strong model is trained using the updated local data set. The weak model and the strong model form a hybrid correction model, that is, the preset prediction model.

[0100] Figure 4 It is a flow chart of a data processing method for dispensing provided according to an embodiment of the present invention. This embodiment is optimized based on the above-mentioned optional embodiments, and adds relevant processing steps for the situation where the dispensing test fails. Figure 5 is a schematic diagram of a data processing solution for dispensing according to an embodiment of the present invention, which can be combined with Figure 5 Understand the embodiments of the present invention.

[0101] like Figure 4 As shown, the method includes:

[0102] Step 401: Obtain expected glue weight data and a preset prediction model, wherein the preset prediction model includes a preset glue type classification model and a preset glue weight regression model.

[0103] For example, Figure 5 As shown, in the offline startup phase, data is collected for model training to obtain a machine learning prediction model, that is, a preset prediction model. In the online application phase, the target glue weight is input, that is, the expected glue weight data is input.

[0104] Step 402: Determine predicted glue type category data corresponding to the candidate glue dispensing parameter data based on the candidate glue dispensing parameter data and a preset glue type classification model.

[0105] Step 403: Determine predicted glue weight data corresponding to the candidate glue dispensing parameter data based on the candidate glue dispensing parameter data and a preset glue weight regression model.

[0106] Step 404: determine target dispensing parameter data corresponding to the expected glue weight data from the candidate dispensing parameter data based on a first objective function, wherein the first objective function is determined according to the expected glue weight data, the predicted glue type category data and the predicted glue weight data.

[0107] like Figure 5 As shown, according to the input target glue weight, the search algorithm is combined with the machine learning prediction model to search for the optimal process parameters, that is, the target dispensing parameter data.

[0108] Step 405: Acquire test result data after performing a dispensing test using the target dispensing parameter data.

[0109] For example, the target dispensing parameter data is recorded as ,based on Conduct dispensing test to obtain glue type results And glue weight .

[0110] Step 406: Add the test result data to the online training set.

[0111] Exemplarily, update the online training set: .

[0112] Step 407: Determine whether the target dispensing parameter data meets the preset requirements according to the difference between the test glue weight data in the test result data and the expected glue weight data, and the test glue type data in the test result data.

[0113] like Figure 5 As shown, after obtaining the optimal process parameters, it is determined whether the target is met, that is, whether the target dispensing parameter data meets the preset requirements.

[0114] Exemplarily, the test result data is evaluated, if the glue type is qualified ( ) and the glue weight error is less than the preset error threshold, it is determined that the target dispensing parameter data meets the preset requirements, that is, it meets the target; otherwise, it is determined that the target dispensing parameter data does not meet the preset requirements, that is, it does not meet the target. Among them, the preset error threshold can be set according to actual needs, such as 5%, .

[0115] Step 408: If not, the preset prediction model is trained based on the online training set to obtain an updated preset prediction model.

[0116] like Figure 5 As shown, if the preset requirements are met, that is, the target is met, the optimal process parameters can be output If it does not meet the preset requirements, that is, it does not meet the target, the preset prediction model is trained based on the online training set to obtain an updated preset prediction model. Specifically, the second glue type classification model and the second glue regression model in the preset prediction model are trained and updated based on the online training set. Exemplarily, the preset glue type classification model and the preset glue regression model included in the preset prediction model are respectively and , based on the online training set Trained and ,make , .

[0117] Step 409: Select target sample data from the online training set based on the second objective function, wherein the second objective function is determined according to the expected glue weight data, the sample glue weight value of the sample data in the online training set, and the sample glue type.

[0118] Exemplarily, after the preset prediction model is updated, the new target dispensing parameter data corresponding to the expected glue weight data can be determined based on the updated preset prediction model. In order to further improve the search efficiency, a more accurate search starting point can be determined so that the new target dispensing parameter data can be searched more quickly.

[0119] For example, from the online training set Select the second objective function Minimum sample dispensing parameter data (target sample data), where () is the indicative function.

[0120] Step 410: Taking the dispensing parameter data in the target sample data as the search starting point, new target dispensing parameter data corresponding to the expected glue weight data is determined based on the updated preset prediction model.

[0121] For example, let That is, taking the dispensing parameter data in the target sample data as the search starting point, the new target dispensing parameter data corresponding to the expected glue weight data is determined based on the updated preset prediction model until the dispensing test passes, that is, the target dispensing parameter data that meets the preset requirements is obtained.

[0122] The data processing method for dispensing provided in the embodiment of the present invention uses a strong and weak hybrid model that supports dynamic updating to predict candidate dispensing process parameters in terms of glue type and glue weight, and adopts a search algorithm to automatically determine the target dispensing process parameters that meet the constraints of glue type and glue weight using the objective function, and performs a dispensing test after determining the target dispensing process parameters. The dispensing test results are tested. If they do not meet the preset requirements, the preset prediction model can be updated through an online training set, and a more accurate search starting point can be selected from the online training set. Among them, the glue weight prediction model in the strong model includes a deviation regression part. If the glue state, environmental state or equipment state changes, the model algorithm can automatically correct the hyperparameters of the model to adapt to the latest changes, and can quickly meet new dispensing requirements, further improve the determination efficiency and accuracy of dispensing process parameters, reduce the cost of process parameter debugging, improve debugging efficiency, and further improve the production and manufacturing efficiency related to the dispensing process.

[0123] Figure 6 Schematic diagram of a data processing device for dispensing provided according to an embodiment of the present invention. Figure 6 As shown, the device comprises:

[0124] An acquisition module 601 is used to acquire expected glue weight data and a preset prediction model, wherein the preset prediction model includes a preset glue type classification model and a preset glue weight regression model;

[0125] A category prediction module 602 is used to determine predicted glue type category data corresponding to the candidate glue dispensing parameter data based on the candidate glue dispensing parameter data and the preset glue type classification model, wherein the glue type category includes qualified and unqualified;

[0126] The glue weight prediction module 603 is used to determine the predicted glue weight data corresponding to the candidate glue dispensing parameter data based on the candidate glue dispensing parameter data and the preset glue weight regression model;

[0127] The parameter data determination module 604 is used to determine the target dispensing parameter data corresponding to the expected glue weight data from the candidate dispensing parameter data based on a first objective function, wherein the first objective function is determined according to the expected glue weight data, the predicted glue type category data and the predicted glue weight data.

[0128] The data processing device for dispensing in the embodiment of the present invention uses a model to predict candidate dispensing process parameters in terms of glue type and glue weight, and uses an objective function to automatically determine target dispensing process parameters that meet the constraints of glue type and glue weight, thereby improving the efficiency and accuracy of determining the dispensing process parameters, reducing the cost of process parameter debugging, improving debugging efficiency, and further improving the production efficiency related to the dispensing process.

[0129] Optionally, the preset glue weight regression model includes a first glue weight regression model, which is trained in the following manner: dividing the local training set into a first training set and a second training set, wherein the sampling time of any sample data in the second training set is later than the sampling time of any sample data in the first training set; using the first training set to train a first glue weight regression sub-model; using the first glue weight regression sub-model to predict the second training set to obtain a predicted value, and calculating a prediction error based on the predicted value; using the prediction error and the second training set to train a second glue weight regression sub-model; determining the first glue weight regression model based on the first glue weight regression sub-model and the second glue weight regression sub-model.

[0130] Optionally, dividing the local training set into a first training set and a second training set includes: using an initial weighted regression model to determine the regression error of each sample data in the local training set; sorting the regression errors according to the sampling time of each sample data in the local training set to obtain a regression error sequence; determining a target regression error in the regression error sequence, and dividing the local training set into a first training set and a second training set according to the target regression error, wherein the sample data corresponding to the target regression error is the last sample data in the first training set or the first sample data in the second training set, and the target regression error is determined with the goal of maximizing the difference between the sample distribution of the first training set and the sample distribution of the second training set.

[0131] Optionally, the preset glue type classification model is determined by the weighted sum of the first glue type classification model and the second glue type classification model, and the preset glue weight regression model is determined by the weighted sum of the first glue weight regression model and the second glue weight regression model; the first glue type classification model and the first glue weight regression model are trained using a local training set, and the second glue type classification model and the second glue weight regression model are trained using an online training set, and the online training set includes test result data obtained after performing a glue dispensing test using at least one of the target glue dispensing parameter data; the training cost of the second glue type classification model is lower than the training cost of the first glue type classification model, and the training cost of the second glue weight regression model is lower than the training cost of the first glue weight regression model.

[0132] Optionally, the device further comprises:

[0133] A test result data acquisition module, configured to acquire test result data after performing a dispensing test using the target dispensing parameter data after determining the target dispensing parameter data corresponding to the expected glue weight data from the candidate dispensing parameter data based on the first objective function;

[0134] An online training set adding module, used for adding the test result data to the online training set;

[0135] A preset requirement determination module, used to determine whether the target dispensing parameter data meets the preset requirements according to the difference between the test glue weight data in the test result data and the expected glue weight data, and the test glue type data in the test result data;

[0136] A model updating module, used for training the preset prediction model based on the online training set to obtain an updated preset prediction model when it is determined that the target dispensing parameter data does not meet the preset requirements;

[0137] A target sample data acquisition module, used for selecting target sample data from the online training set based on a second objective function, wherein the second objective function is determined according to the expected glue weight data, the sample glue weight value of the sample data in the online training set, and the sample glue type;

[0138] The re-determination module is used to use the dispensing parameter data in the target sample data as a search starting point, and re-determine new target dispensing parameter data corresponding to the expected glue weight data based on the updated preset prediction model.

[0139] Optionally, the device further comprises:

[0140] A local training set updating module, configured to move the online training set into the local training set to obtain a new local training set in response to a performance evaluation result of the first glue type classification model and / or the first glue regression model being failed;

[0141] The training module is used to train the first adhesive type classification model and / or the first adhesive regression model based on the new local training set to obtain an updated first adhesive type classification model and / or an updated first adhesive regression model.

[0142] The data processing device for dispensing provided in the embodiment of the present invention can execute the data processing method for dispensing provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0143] Figure 7A schematic diagram of the structure of an electronic device 10 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) 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 the implementation of the present invention described and / or required herein.

[0144] like Figure 7 As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. The input / output (I / O) interface 15 is also connected to the bus 14.

[0145] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0146] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as a data processing method for dispensing.

[0147] In some embodiments, the data processing method for dispensing can be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the data processing method for dispensing described above can be performed. Alternatively, in other embodiments, the processor 11 can be configured to execute the data processing method for dispensing by any other appropriate means (for example, by means of firmware).

[0148] Various implementations of the systems 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), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can 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.

[0149] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program 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.

[0150] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, device, or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. 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.

[0151] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device 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 a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0152] The systems and techniques described herein may be implemented in a computing system that includes backend 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 frontend 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 backend components, middleware components, or frontend 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), a blockchain network, and the Internet.

[0153] A computing 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 client and server relationship 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.

[0154] The embodiments of the present disclosure provide a computer program product, including a computer program, which, when executed by a processor, implements the data processing method for dispensing provided in the above embodiments.

[0155] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0156] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A data processing method for dispensing, characterized in that: include: Acquire expected glue weight data and a preset prediction model, wherein the preset prediction model includes a preset glue type classification model and a preset glue weight regression model; Based on the candidate dispensing parameter data and the preset glue type classification model, determining the predicted glue type category data corresponding to the candidate dispensing parameter data; Based on the candidate dispensing parameter data and the preset glue weight regression model, determining the predicted glue weight data corresponding to the candidate dispensing parameter data; The target dispensing parameter data corresponding to the expected glue weight data is determined from the candidate dispensing parameter data based on a first objective function, wherein the first objective function is determined according to the expected glue weight data, the predicted glue type category data and the predicted glue weight data.

2. The data processing method for dispensing according to claim 1, characterized in that: The preset glue weight regression model includes a first glue weight regression model, and the first glue weight regression model is trained in the following way: Dividing the local training set into a first training set and a second training set, wherein a sampling time of any sample data in the second training set is later than a sampling time of any sample data in the first training set; Using the first training set to train a first regression model; Using the first multi-regression sub-model to predict the second training set, obtain a predicted value, and calculate a prediction error based on the predicted value; Using the prediction error and the second training set to train a second regression sub-model; A first glue weight regression model is determined according to the first glue weight regression sub-model and the second glue weight regression sub-model.

3. The data processing method for dispensing according to claim 2, characterized in that: The dividing the local training set into a first training set and a second training set comprises: The regression error of each sample data in the local training set is determined using the initial glue regression model; Sorting the regression errors according to the sampling time of each sample data in the local training set to obtain a regression error sequence; Determine a target regression error in the regression error sequence, and divide the local training set into a first training set and a second training set according to the target regression error, wherein the sample data corresponding to the target regression error is the last sample data of the first training set or the first sample data of the second training set, and determine the target regression error with the goal of maximizing the difference between the sample distribution of the first training set and the sample distribution of the second training set.

4. The data processing method for dispensing according to claim 1 is characterized in that: The preset glue type classification model is determined by the weighted sum of the first glue type classification model and the second glue type classification model, and the preset glue weight regression model is determined by the weighted sum of the first glue weight regression model and the second glue weight regression model; the first glue type classification model and the first glue weight regression model are trained using a local training set, and the second glue type classification model and the second glue weight regression model are trained using an online training set, and the online training set includes test result data obtained after performing a glue dispensing test using at least one of the target glue dispensing parameter data; the training cost of the second glue type classification model is lower than the training cost of the first glue type classification model, and the training cost of the second glue weight regression model is lower than the training cost of the first glue weight regression model.

5. The data processing method for dispensing according to claim 1, characterized in that: After determining the target dispensing parameter data corresponding to the expected glue weight data from the candidate dispensing parameter data based on the first objective function, the method further includes: Acquire test result data after performing a dispensing test using the target dispensing parameter data; Adding the test result data to an online training set; Determining whether the target dispensing parameter data meets preset requirements according to the difference between the test glue weight data in the test result data and the expected glue weight data, and the test glue type data in the test result data; If not, training the preset prediction model based on the online training set to obtain an updated preset prediction model; Selecting target sample data from the online training set based on a second objective function, wherein the second objective function is determined according to the expected glue weight data, the sample glue weight value of the sample data in the online training set, and the sample glue type; Taking the dispensing parameter data in the target sample data as the search starting point, new target dispensing parameter data corresponding to the expected glue weight data is determined based on the updated preset prediction model.

6. The data processing method for dispensing according to claim 4 is characterized in that: Also includes: In response to a performance evaluation result of the first glue type classification model and / or the first glue regression model being failed, moving the online training set into the local training set to obtain a new local training set; The first glue type classification model and / or the first glue regression model are trained based on the new local training set to obtain an updated first glue type classification model and / or an updated first glue regression model.

7. A data processing device for dispensing, characterized in that: include: An acquisition module, used for acquiring expected glue weight data and a preset prediction model, wherein the preset prediction model includes a preset glue type classification model and a preset glue weight regression model; A category prediction module, used to determine predicted glue type category data corresponding to the candidate glue dispensing parameter data based on the candidate glue dispensing parameter data and the preset glue type classification model; A glue weight prediction module, used to determine the predicted glue weight data corresponding to the candidate glue dispensing parameter data based on the candidate glue dispensing parameter data and the preset glue weight regression model; A parameter data determination module is used to determine the target dispensing parameter data corresponding to the expected glue weight data from the candidate dispensing parameter data based on a first objective function, wherein the first objective function is determined according to the expected glue weight data, the predicted glue type category data and the predicted glue weight data.

8. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the data processing method for dispensing according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the data processing method for dispensing according to any one of claims 1 to 6 when executed.

10. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the computer program implements the data processing method for dispensing according to any one of claims 1 to 6.

Images