Dyeing method and device based on dyeing prediction model, computer equipment and storage medium

Abstract

The invention relates to the field of textile printing and dyeing, and discloses a dyeing method and device based on a dyeing prediction model, computer equipment and a storage medium. Processing the dyeing demand through the dyeing prediction model to obtain an initial dyeing process and the credibility of the initial dyeing process; setting experimental parameters of a dyeing test experiment according to the initial dyeing process and the credibility; obtaining a test result of the dyeing test experiment; and determining a target dyeing process meeting the dyeing requirement according to the test result. The problems of less dyeing data and low model result accuracy can be solved.

Description

Technical Field

[0001] The present invention relates to the field of textile printing and dyeing, and in particular to a dyeing method, device, computer equipment and storage medium based on a dyeing prediction model. Background Art

[0002] In the textile printing and dyeing industry, accurate color reproduction is crucial to product quality and market competitiveness. Traditional color matching methods rely on experienced technicians to manually mix dyes, which is not only time-consuming and labor-intensive, but also easily affected by human factors, resulting in unstable color matching results. In recent years, with the development of information technology, data-driven methods have gradually been introduced into the field of textile printing and dyeing to improve the efficiency and accuracy of the color matching process.

[0003] However, on the one hand, due to the limited accumulation of historical data and high experimental costs, the amount of available printing and dyeing data is relatively small. This limits the learning ability and generalization performance of the model. On the other hand, due to the lack of sufficient data support and complex and changeable dyeing process conditions, the existing models are difficult to achieve ideal prediction accuracy in some cases. Especially when faced with new colors or special materials, the performance of the model is often unsatisfactory. Even if the model can give reasonable formula suggestions, due to many uncontrollable factors in the dyeing process, such as differences in water quality, changes in equipment status, etc., the final dyeing effect may be somewhat different from expectations. Summary of the invention

[0004] Based on this, it is necessary to provide a dyeing method, device, computer equipment and storage medium based on a dyeing prediction model to address the above-mentioned technical problems, so as to solve the problems of insufficient dyeing data and low accuracy of model results.

[0005] A dyeing method based on a dyeing prediction model, comprising: Get dyeing requirements; Processing the dyeing demand through a dyeing prediction model to obtain an initial dyeing process and the credibility of the initial dyeing process; Setting experimental parameters of a dyeing test experiment according to the initial dyeing process and the reliability; Obtaining the test result of the dyeing test experiment; A target dyeing process that meets the dyeing requirements is determined based on the test results.

[0006] Optionally, before processing the dyeing demand by using a dyeing prediction model, the method further includes: Get historical dyeing data; A plurality of dyeing index initial models are trained according to the historical dyeing data to obtain a plurality of dyeing index prediction models; the dyeing prediction model includes a plurality of the dyeing index prediction models.

[0007] Optionally, the dyeing index prediction model includes a color accuracy prediction model; The training of multiple staining index initial models according to the historical staining data to obtain multiple staining index prediction models includes: Performing a first preprocessing on the historical dyeing data to obtain a color feature data set; The color feature data set is trained by a support vector regression algorithm to obtain the color accuracy prediction model.

[0008] Optionally, the dyeing index prediction model includes a color fastness prediction model; The training of multiple staining index initial models according to the historical staining data to obtain multiple staining index prediction models includes: Performing a second preprocessing on the historical dyeing data to obtain a color fastness characteristic data set; The color fastness feature data set is trained by a logistic regression algorithm to obtain the color fastness prediction model.

[0009] Optionally, setting the experimental parameters of the dyeing test experiment according to the initial dyeing process and the credibility includes: Extracting a value range and parameter credibility of each dyeing parameter from the initial dyeing process and the credibility; Setting a plurality of test points according to the value range and parameter credibility; Processing the plurality of test points through the dyeing prediction model to obtain simulation test results; The simulation test results are processed by response surface methodology to obtain the experimental parameters.

[0010] Optionally, determining a target dyeing process that meets the dyeing requirement according to the test result includes: If the test result meets the dyeing requirement, the target dyeing process is determined according to the experimental parameters.

[0011] Optionally, determining a target dyeing process that meets the dyeing requirement according to the test result includes: If the test result does not meet the dyeing requirement, optimizing the dyeing prediction model according to the test result to obtain a dyeing prediction optimization model; Processing the dyeing demand through the dyeing prediction optimization model to obtain an optimized dyeing process and the credibility of the optimized dyeing process; According to the optimized dyeing process and the optimized dyeing process, the optimized experimental parameters of the optimized dyeing test experiment are set, and the optimized test results of the optimized dyeing test experiment are obtained; If the optimization test result meets the dyeing requirement, determining the target dyeing process according to the optimization experiment parameters; If the optimization test result does not meet the dyeing requirement, the dyeing prediction optimization model is further optimized according to the optimization test result until the test result finally obtained meets the dyeing requirement.

[0012] A dyeing device based on a dyeing prediction model, comprising: A dyeing requirement acquisition module is used to acquire dyeing requirements; A model prediction module, used for processing the dyeing demand through a dyeing prediction model to obtain an initial dyeing process and the credibility of the initial dyeing process; An experimental parameter setting module is used to set the experimental parameters of the dyeing test experiment according to the initial dyeing process and the credibility; A test result acquisition module is used to acquire the test result of the dyeing test experiment; Determine a target dyeing process, which is used to determine a target dyeing process that meets the dyeing requirements according to the test results.

[0013] A computer device comprises a memory, a processor and computer-readable instructions stored in the memory and executable on the processor, wherein the processor implements the above-mentioned dyeing method based on the dyeing prediction model when executing the computer-readable instructions.

[0014] One or more readable storage media storing computer-readable instructions, which, when executed by one or more processors, enable the one or more processors to perform the staining method based on the staining prediction model as described above.

[0015] In the dyeing method, device, computer equipment and storage medium based on the dyeing prediction model, the dyeing prediction model can quickly simulate different dyeing conditions, screen out the best or better initial dyeing process, thereby avoiding the time-consuming and laborious trial and error process in the traditional method, reducing the number of experiments, saving the cost of resources such as dyes, energy, water and labor, and helping to achieve accurate control of the dyeing process, improve the uniformity and color fastness of dyeing, thereby improving the quality of the final product, helping to establish a standardized dyeing process, making the production process more stable and reliable, and through continuous experimental verification, a large amount of data can be accumulated for further training and optimization of the model, forming a virtuous circle. The present invention can solve the problem of little dyeing data and low accuracy of model results. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments of the present invention will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative labor.

[0017] Figure 1 is a schematic flow chart of a dyeing method based on a dyeing prediction model in one embodiment of the present invention; Figure 2 is a structural schematic diagram of a dyeing device based on a dyeing prediction model in one embodiment of the present invention; Figure 3 is a schematic diagram of a computer device in one embodiment of the present invention. DETAILED DESCRIPTION

[0018] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are 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 are within the scope of protection of the present invention.

[0019] In one embodiment, if Figure 1 As shown, a dyeing method based on a dyeing prediction model is provided, comprising the following steps S10 to S50.

[0020] S10, obtaining dyeing requirements; S20, processing the dyeing demand through a dyeing prediction model to obtain an initial dyeing process and the credibility of the initial dyeing process; S30, setting experimental parameters of the dyeing test experiment according to the initial dyeing process and the credibility; S40, obtaining the test result of the dyeing test experiment; S50, determining a target dyeing process that meets the dyeing requirements according to the test results.

[0021] Understandably, dyeing requirements refer to requirements for color changes of textiles, including but not limited to color requirements, fabric types, dye types, and color fastness requirements. In some examples, dyeing requirements can be customized by users.

[0022] The dyeing prediction model is a prediction model obtained by training historical dyeing data based on a machine learning algorithm. Here, the machine learning algorithm can be selected from support vector machines (SVM), neural networks (NN), random forests (RF), etc. The initial dyeing process is the output result of the dyeing prediction model, including pretreatment before dyeing, parameters during the dyeing process (such as temperature, time, dye concentration, etc.), and color fixation and post-processing steps after dyeing. The credibility of the initial dyeing process includes the credibility of each parameter in the process. The credibility can be a single value or a confidence interval. In one example, the initial process and its credibility can be expressed as: Dye type: A, confidence level 0.9; Dye concentration: 2%, confidence level 0.8; Staining temperature: 80°C, confidence level 0.7; Staining time: 60 minutes, reliability 0.6; pH value: 5.0, reliability 0.8.

[0023] After obtaining the initial dyeing process, the experimental parameters of the dyeing test experiment can be set according to the initial dyeing process. Here, the dyeing test experiment generally has a set of test points. After setting the experimental parameters of the dyeing test experiment, the dyeing test experiment can be carried out and the test results can be recorded.

[0024] Table 1 Test results of an example of textile dyeing Experiment number Dye concentration (C, %) Dyeing temperature (T, °C) Staining time (t, min) L* a* b* Washing fastness Abrasion resistance 1 2 70 30 50 11 21 4 3 2 2 70 60 55 13 23 4 3 3 2 70 90 60 15 25 4 3 4 2 80 30 55 12 22 4 3 5 2 80 60 60 14 24 4 3 6 2 80 90 65 16 26 4 3 7 2 90 30 60 13 23 4 3 8 2 90 60 65 15 25 4 3 9 2 90 90 90 17 27 4 3 ; As shown in Table 1, Table 1 is a test result of dyeing an example of textile. Wherein, L* represents brightness, and the larger the value, the brighter the color. a* represents the red-green axis, and a positive value represents red, and a negative value represents green. b* represents the yellow-blue axis, and a positive value represents yellow, and a negative value represents blue. Washing fastness represents the color retention ability of dyed fabrics during washing. Rubbing fastness represents the color retention ability of dyed fabrics during rubbing.

[0025] After obtaining the test results, it can be determined whether the test results meet the dyeing requirements. If the test results meet the dyeing requirements, the target dyeing process that meets the dyeing requirements can be directly determined based on the experimental parameters of the dyeing test experiment. If the test results do not meet the dyeing requirements, but the deviation from the dyeing requirements is less than a preset threshold (the preset threshold can be set according to actual conditions), the experimental parameters of the dyeing test experiment can be adjusted according to industry experience to determine the target dyeing process that meets the dyeing requirements. If the test results do not meet the dyeing requirements, and the deviation from the dyeing requirements is greater than or equal to the preset threshold, the test results can be used to update the dyeing prediction model to improve the prediction accuracy of the dyeing prediction model.

[0026] In this embodiment, the dyeing prediction model can quickly simulate different dyeing conditions and screen out the best or better initial dyeing process, thereby avoiding the time-consuming and laborious trial and error process in the traditional method, reducing the number of experiments, saving resource costs such as dyes, energy, water and labor, and helping to achieve accurate control of the dyeing process, improve the uniformity and color fastness of dyeing, thereby improving the quality of the final product, and helping to establish a standardized dyeing process, making the production process more stable and reliable. Through continuous experimental verification, a large amount of data can be accumulated for further training and optimization of the model, forming a virtuous circle. This embodiment can solve the problem of less dyeing data and low accuracy of model results.

[0027] Optionally, before step S20, that is, before processing the dyeing requirement by using the dyeing prediction model, the method further includes: S21, obtaining historical dyeing data; S22. Training a plurality of dyeing index initial models according to the historical dyeing data to obtain a plurality of dyeing index prediction models; the dyeing prediction model includes a plurality of the dyeing index prediction models.

[0028] Understandably, historical dyeing data refers to dyeing data obtained through historical dyeing performance experiments, including but not limited to dye information, fabric information, process parameters, auxiliary agent information, environmental factors, characterization results, cost data, and abnormal records. After the historical dyeing data is sorted, cleaned, and standardized / normalized, a dyeing sample set can be obtained. Use the dyeing sample set to train multiple dyeing index initial models to obtain multiple dyeing index prediction models. Then combine all the dyeing index prediction models to form a dyeing prediction model. Here, the dyeing index initial model is based on the initial model set for specific dyeing indicators, such as color accuracy, color fastness, cost, etc. After each dyeing index initial model is trained using the dyeing sample set, the prediction accuracy of each dyeing index prediction model can be greatly improved.

[0029] This embodiment constructs multiple staining index prediction models to form a staining prediction model, which greatly reduces the complexity of the staining prediction model and improves the training efficiency of the model.

[0030] Optionally, the dyeing index prediction model includes a color accuracy prediction model; step S22, i.e., training multiple dyeing index initial models according to the historical dyeing data to obtain multiple dyeing index prediction models, includes: S221, performing a first preprocessing on the historical dyeing data to obtain a color feature data set; S222. Training the color feature data set by using a support vector regression algorithm to obtain the color accuracy prediction model.

[0031] Understandably, after the historical dyeing data is sorted, cleaned, and standardized / normalized, a preliminary dyeing sample set can be obtained. Correlation analysis, principal component analysis (PCA), and other methods can be used to identify key features related to color accuracy in the dyeing sample set to form a color feature data set.

[0032] The color feature dataset can be trained using the support vector regression algorithm (SVR) to obtain a color accuracy prediction model. The support vector regression algorithm is a machine learning algorithm used for regression analysis. The support vector regression algorithm uses an optimization problem to determine an optimal hyperplane that should predict the target value, i.e., color accuracy, as accurately as possible.

[0033] This embodiment uses the support vector regression algorithm to construct a color accuracy prediction model, which can obtain good prediction results when there is less historical dyeing data, can effectively handle nonlinear problems, is insensitive to outliers, and has good robustness.

[0034] Optionally, the dyeing index prediction model includes a color fastness prediction model; step S22, i.e., training a plurality of dyeing index initial models according to the historical dyeing data to obtain a plurality of dyeing index prediction models, comprises: S223, performing a second preprocessing on the historical dyeing data to obtain a color fastness feature data set; S224. Training the color fastness feature data set by a logistic regression algorithm to obtain the color fastness prediction model.

[0035] Understandably, after collating, cleaning, and standardizing / normalizing the historical dyeing data, a preliminary dyeing sample set can be obtained. Correlation analysis, principal component analysis (PCA), and other methods can be used to identify key features related to color fastness in the dyeing sample set to form a color fastness feature data set.

[0036] The color fastness feature data set can be trained using the logistic regression algorithm (LR) to obtain a color fastness prediction model. The logistic regression algorithm is a classification algorithm that can be used to handle multi-classification problems. The color fastness prediction model can accurately classify the color fastness level.

[0037] This embodiment uses a logistic regression algorithm to construct a color fastness prediction model, which has high computational efficiency, is easy to implement and optimize, is relatively insensitive to outliers and multicollinearity, and is robust.

[0038] Optionally, step S30, i.e. setting the experimental parameters of the dyeing test experiment according to the initial dyeing process and the credibility, includes: S301, extracting a value range and parameter credibility of each dyeing parameter from the initial dyeing process and the credibility; S302, setting a plurality of test points according to the value range and parameter credibility; S303, processing the multiple test points through the dyeing prediction model to obtain simulation test results; S304: Process the simulation test results by using response surface methodology to obtain the experimental parameters.

[0039] Understandably, the value range and parameter credibility of each dyeing parameter can be extracted from the initial dyeing process and credibility, and then multiple test points can be set according to the value range and parameter credibility. A series of test points can be generated using a central composite design (CCD) method.

[0040] Then, the dyeing prediction model is used to process multiple test points to obtain simulation test results. Since the dyeing prediction model contains multiple dyeing index prediction models, the test points can be predicted by each dyeing index prediction model to obtain the corresponding dyeing index. The various dyeing indexes of each test point constitute the simulation test results of the test point.

[0041] After obtaining the simulation test results, the simulation test results can be processed by response surface methodology (RSM) to obtain the experimental parameters of the dyeing test experiment. Response surface methodology optimizes the combination of multiple parameters by constructing a quadratic polynomial model to obtain the best experimental parameters. RSM can effectively reduce the number of experiments and provide rich information.

[0042] This embodiment processes multiple test points through the dyeing prediction model to obtain simulated test results, which can greatly reduce the number of tests, save material costs and time costs of the tests, and improve prediction accuracy.

[0043] Optionally, step S50, i.e., determining a target dyeing process that meets the dyeing requirement according to the test result, includes: S501. If the test result meets the dyeing requirement, determine the target dyeing process according to the experimental parameters.

[0044] Understandably, if the test results meet the dyeing requirements, the target dyeing process can be determined based on the experimental parameters. The experimental parameters belong to the process of small-scale trials. The target dyeing process can be designed based on industry experience, and a pilot test can be carried out under conditions close to production to verify the feasibility and stability of the target dyeing process.

[0045] In this embodiment, the test results meet the dyeing requirements, indicating that the prediction accuracy of the dyeing prediction model is high, which can greatly reduce the number of tests and save the material cost and time cost of the test.

[0046] Optionally, step S50, i.e., determining a target dyeing process that meets the dyeing requirement according to the test result, includes: S502: If the test result does not meet the dyeing requirement, optimize the dyeing prediction model according to the test result to obtain a dyeing prediction optimization model; S503, processing the dyeing demand through the dyeing prediction optimization model to obtain an optimized dyeing process and the credibility of the optimized dyeing process; S504, setting optimization experiment parameters of an optimized dyeing test experiment according to the optimized dyeing process and the optimized dyeing process, and obtaining optimization test results of the optimized dyeing test experiment; S505, if the optimization test result meets the dyeing requirement, determining the target dyeing process according to the optimization experiment parameters; S506. If the optimization test result does not meet the dyeing requirement, further optimize the dyeing prediction optimization model according to the optimization test result until the test result finally obtained meets the dyeing requirement.

[0047] Understandably, if the test results do not meet the dyeing requirements, the dyeing prediction model is optimized according to the test results to obtain the dyeing prediction optimization model, which can help improve the prediction accuracy of the dyeing prediction optimization model. After obtaining the dyeing prediction optimization model, the dyeing prediction optimization model can be used to process the dyeing requirements to obtain a new dyeing process and credibility, that is, to optimize the dyeing process and the credibility of the optimized dyeing process. Then, the optimization experimental parameters of the optimized dyeing test experiment are set according to the optimized dyeing process and the optimized dyeing process, and the optimization test results of the optimized dyeing test experiment are obtained. If the optimization test results meet the dyeing requirements, the target dyeing process is determined according to the optimization experimental parameters. If the optimization test results do not meet the dyeing requirements, the dyeing prediction optimization model is further optimized according to the optimization test results until the test results finally obtained meet the dyeing requirements. In some examples, if the optimization test results do not meet the dyeing requirements, but the deviation from the dyeing requirements is less than a preset threshold (such as 10%), the experimental parameters of the dyeing test experiment can be adjusted according to industry experience to determine the target dyeing process that meets the dyeing requirements.

[0048] In this embodiment, if the test results do not meet the dyeing requirements, the dyeing prediction model is optimized according to the test results to obtain a dyeing prediction optimization model, which can improve the accuracy of the dyeing prediction optimization model. Through more accurate model predictions, the number of trial and error times can be reduced, and the development speed of the dyeing process can be accelerated. The optimized dyeing prediction optimization model can guide the design of a better dyeing process and improve dyeing efficiency.

[0049] It should be understood that the order of execution of the steps in the above embodiment does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.

[0050] In one embodiment, a dyeing device based on a dyeing prediction model is provided, and the dyeing device based on a dyeing prediction model corresponds one-to-one to the dyeing method based on a dyeing prediction model in the above embodiment. Figure 2 As shown, the dyeing device based on the dyeing prediction model includes: A dyeing requirement acquisition module 10 is used to acquire dyeing requirements; A model prediction module 20, used for processing the dyeing demand through a dyeing prediction model to obtain an initial dyeing process and the credibility of the initial dyeing process; An experimental parameter setting module 30 is used to set experimental parameters of the dyeing test experiment according to the initial dyeing process and the credibility; The test result acquisition module 40 is used to acquire the test result of the dyeing test experiment; Determine a target dyeing process 50, for determining a target dyeing process that meets the dyeing requirement according to the test result.

[0051] Optionally, the dyeing device based on the dyeing prediction model further includes a model building module, and the model building module includes: A historical data acquisition unit is used to acquire historical dyeing data; A model building unit is used to train multiple dyeing index initial models according to the historical dyeing data to obtain multiple dyeing index prediction models; the dyeing prediction model includes multiple dyeing index prediction models.

[0052] Optionally, the dyeing index prediction model includes a color accuracy prediction model; and the model building unit includes: A first preprocessing unit, used for performing a first preprocessing on the historical dyeing data to obtain a color feature data set; The color accuracy prediction model building unit is used to train the color feature data set through a support vector regression algorithm to obtain the color accuracy prediction model.

[0053] Optionally, the dyeing index prediction model includes a color fastness prediction model; and the model building unit includes: A second preprocessing unit, used for performing a second preprocessing on the historical dyeing data to obtain a color fastness feature data set; The color fastness prediction model building unit is used to train the color fastness feature data set through a logistic regression algorithm to obtain the color fastness prediction model.

[0054] Optionally, the experiment parameter setting module 30 includes: An extraction range unit, used for extracting a value range and a parameter credibility of each dyeing parameter from the initial dyeing process and the credibility; A test point setting unit, used for setting a plurality of test points according to the value range and parameter credibility; A simulation result obtaining unit, used for processing the plurality of test points through the dyeing prediction model to obtain simulation test results; The experimental parameter obtaining unit is used to process the simulation test results through the response surface method to obtain the experimental parameters.

[0055] Optionally, determining the target dyeing process 50 includes: The first unit for determining a target dyeing process is used to determine the target dyeing process according to the experimental parameters if the test result meets the dyeing requirement.

[0056] Optionally, the target dyeing process determination 50 includes a second target dyeing process determination unit, wherein the second target dyeing process determination unit is configured to: If the test result does not meet the dyeing requirement, optimizing the dyeing prediction model according to the test result to obtain a dyeing prediction optimization model; Processing the dyeing demand through the dyeing prediction optimization model to obtain an optimized dyeing process and the credibility of the optimized dyeing process; According to the optimized dyeing process and the optimized dyeing process, the optimized experimental parameters of the optimized dyeing test experiment are set, and the optimized test results of the optimized dyeing test experiment are obtained; If the optimization test result meets the dyeing requirement, determining the target dyeing process according to the optimization experiment parameters; If the optimization test result does not meet the dyeing requirement, the dyeing prediction optimization model is further optimized according to the optimization test result until the test result finally obtained meets the dyeing requirement.

[0057] For the specific definition of the dyeing device based on the dyeing prediction model, please refer to the definition of the dyeing method based on the dyeing prediction model above, which will not be repeated here. The various modules in the dyeing device based on the dyeing prediction model can be implemented in whole or in part by software, hardware and a combination thereof. The above modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory in the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0058] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 3 As shown. The computer device includes a processor, a memory, a network interface and a database connected by a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a readable storage medium and an internal memory. The readable storage medium stores an operating system, a computer-readable instruction and a database. The internal memory provides an environment for the operation of the operating system and the computer-readable instructions in the readable storage medium. The database of the computer device is used to store data related to the dyeing method based on the dyeing prediction model. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer-readable instruction is executed by the processor, a dyeing method based on the dyeing prediction model is implemented. The readable storage medium provided in this embodiment includes a non-volatile readable storage medium and a volatile readable storage medium.

[0059] In one embodiment, a computer device is provided, including a memory, a processor, and computer-readable instructions stored in the memory and executable on the processor, wherein the processor executes the computer-readable instructions to implement the following steps: Get dyeing requirements; Processing the dyeing demand through a dyeing prediction model to obtain an initial dyeing process and the credibility of the initial dyeing process; Setting experimental parameters of a dyeing test experiment according to the initial dyeing process and the reliability; Obtaining the test result of the dyeing test experiment; A target dyeing process that meets the dyeing requirements is determined based on the test results.

[0060] In one embodiment, one or more computer-readable storage media storing computer-readable instructions are provided. The readable storage media provided in this embodiment include non-volatile readable storage media and volatile readable storage media. The readable storage media store computer-readable instructions, and when the computer-readable instructions are executed by one or more processors, the following steps are implemented: Get dyeing requirements; Processing the dyeing demand through a dyeing prediction model to obtain an initial dyeing process and the credibility of the initial dyeing process; Setting experimental parameters of a dyeing test experiment according to the initial dyeing process and the reliability; Obtaining the test result of the dyeing test experiment; A target dyeing process that meets the dyeing requirements is determined based on the test results.

[0061] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing related hardware through computer-readable instructions, and the computer-readable instructions can be stored in a non-volatile readable storage medium or a volatile readable storage medium. When the computer-readable instructions are executed, they may include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0062] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0063] The embodiments described above are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A dyeing method based on a dyeing prediction model, characterized in that: include: Get dyeing requirements; Processing the dyeing demand through a dyeing prediction model to obtain an initial dyeing process and the credibility of the initial dyeing process; Setting experimental parameters of a dyeing test experiment according to the initial dyeing process and the reliability; Obtaining the test result of the dyeing test experiment; A target dyeing process that meets the dyeing requirements is determined based on the test results.

2. The dyeing method based on the dyeing prediction model according to claim 1, characterized in that: Before processing the dyeing demand by the dyeing prediction model, the method further includes: Get historical dyeing data; A plurality of dyeing index initial models are trained according to the historical dyeing data to obtain a plurality of dyeing index prediction models; the dyeing prediction model includes a plurality of the dyeing index prediction models.

3. The dyeing method based on the dyeing prediction model as claimed in claim 2, characterized in that: The dyeing index prediction model includes a color accuracy prediction model; The training of multiple staining index initial models according to the historical staining data to obtain multiple staining index prediction models includes: Performing a first preprocessing on the historical dyeing data to obtain a color feature data set; The color feature data set is trained by a support vector regression algorithm to obtain the color accuracy prediction model.

4. The dyeing method based on the dyeing prediction model as claimed in claim 2, characterized in that: The dyeing index prediction model includes a color fastness prediction model; The training of multiple staining index initial models according to the historical staining data to obtain multiple staining index prediction models includes: Performing a second preprocessing on the historical dyeing data to obtain a color fastness characteristic data set; The color fastness feature data set is trained by a logistic regression algorithm to obtain the color fastness prediction model.

5. The dyeing method based on the dyeing prediction model according to claim 1, characterized in that: The step of setting the experimental parameters of the dyeing test experiment according to the initial dyeing process and the credibility includes: Extracting a value range and parameter credibility of each dyeing parameter from the initial dyeing process and the credibility; Setting a plurality of test points according to the value range and parameter credibility; Processing the plurality of test points through the dyeing prediction model to obtain simulation test results; The simulation test results are processed by response surface methodology to obtain the experimental parameters.

6. The dyeing method based on the dyeing prediction model according to claim 1, characterized in that: Determining a target dyeing process that meets the dyeing requirements according to the test results includes: If the test result meets the dyeing requirement, the target dyeing process is determined according to the experimental parameters.

7. The dyeing method based on the dyeing prediction model according to claim 1, characterized in that: Determining a target dyeing process that meets the dyeing requirements according to the test results includes: If the test result does not meet the dyeing requirement, optimizing the dyeing prediction model according to the test result to obtain a dyeing prediction optimization model; Processing the dyeing demand through the dyeing prediction optimization model to obtain an optimized dyeing process and the credibility of the optimized dyeing process; According to the optimized dyeing process and the optimized dyeing process, the optimized experimental parameters of the optimized dyeing test experiment are set, and the optimized test results of the optimized dyeing test experiment are obtained; If the optimization test result meets the dyeing requirement, determining the target dyeing process according to the optimization experiment parameters; If the optimization test result does not meet the dyeing requirement, the dyeing prediction optimization model is further optimized according to the optimization test result until the test result finally obtained meets the dyeing requirement.

8. A dyeing device based on a dyeing prediction model, characterized in that: include: A dyeing requirement acquisition module is used to acquire dyeing requirements; A model prediction module, used for processing the dyeing demand through a dyeing prediction model to obtain an initial dyeing process and the credibility of the initial dyeing process; An experimental parameter setting module is used to set the experimental parameters of the dyeing test experiment according to the initial dyeing process and the credibility; A test result acquisition module is used to acquire the test result of the dyeing test experiment; Determine a target dyeing process, which is used to determine a target dyeing process that meets the dyeing requirements according to the test results.

9. A computer device comprising a memory, a processor, and computer-readable instructions stored in the memory and executed on the processor, characterized in that: When the processor executes the computer-readable instructions, the staining method based on the staining prediction model as described in any one of claims 1 to 7 is implemented.

10. One or more computer-readable storage media storing computer-readable instructions, characterized in that: When the computer-readable instructions are executed by one or more processors, the one or more processors perform the staining method based on the staining prediction model as described in any one of claims 1 to 7.

Images