Yarn matching scheme model training method, yarn matching method, equipment, yarn matching system and readable storage medium

By establishing a yarn distribution scheme training model based on historical data, the problem of insufficient reliability of yarn configuration is solved, reliable configuration and accurate matching of yarn performance are achieved, and cost is reduced.

CN118940854APending Publication Date: 2024-11-12GUANGDONG ESQUEL TEXTILES CO LTD
View PDF 0 Cites 4 Cited by

Patent Information

Application Number
CN202410846090.X
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-06-27
Publication Date
2024-11-12

AI Technical Summary

Technical Problem

In the textile industry, the tear tensile strength index of yarn affects the performance of textiles, and the prior art is difficult to effectively improve the reliability of yarn configuration.

Method used

By obtaining the historical data training set, including cotton fiber attribute data and fabric performance indicators, data preprocessing and inputting into the machine learning model, a yarn distribution scheme training model is established, which is used to determine the fabric performance indicators that meet the user's expectations during a new order. Alternative yarn.

Benefits of technology

The reliability and stability of yarn configuration are achieved, the prediction accuracy and configuration accuracy of yarn performance are improved, and the cost is reduced while meeting customer needs.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118940854A_ABST
    Figure CN118940854A_ABST
Patent Text Reader

Abstract

The invention relates to a yarn matching scheme model training method, a yarn matching method, equipment, a yarn matching system and a readable storage medium, and the method comprises the steps: obtaining a historical data training set, and carrying out the data preprocessing of cotton fiber attribute data, fabric performance indexes and technological parameters corresponding to historical orders in the historical data training set; the input refers to a preset machine learning model, a yarn matching scheme training model adaptive to a historical data training set can be obtained, and the yarn matching scheme training model can reliably reflect the specific performance of yarn performance in historical orders. Through the yarn distribution scheme training model, a reliable and stable model basis can be provided for yarn distribution in the next order, and then accurate yarn distribution is achieved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the technical field of yarn matching, and in particular to a yarn matching scheme model training method, a yarn matching method, a yarn matching device, a yarn matching system and a readable storage medium. Background Art

[0002] In the textile industry, the tear tensile strength of yarn is very important. This index directly affects the performance of textiles made of yarn in practical applications. With the continuous development and innovation of the textile industry, yarn configuration has become one of the problems that the industry urgently needs to solve. Summary of the invention

[0003] Based on this, it is necessary to provide a yarn matching scheme model training method, yarn matching method, equipment, yarn matching system and readable storage medium that can improve the reliability of yarn configuration in response to the above-mentioned technical problems.

[0004] In a first aspect, the present application provides a yarn matching scheme model training method, comprising:

[0005] Obtain a historical data training set, where the historical data training set includes cotton fiber attribute data, fabric performance indicators, and process parameters corresponding to historical orders, where the fabric performance indicators include tear and stretch indicators;

[0006] Preprocessing the data in the historical data training set; wherein the preprocessing includes removing abnormal data in the historical data training set, normalizing the cotton fiber attribute data and fabric performance indicators after the removal, and performing unique hot encoding on the process parameters after the removal;

[0007] The data in the preprocessed historical data training set is input into the preset machine learning model to determine the yarn matching scheme training model.

[0008] In one embodiment, the step of obtaining a historical data training set includes:

[0009] Obtain cotton fiber attribute data and process parameters corresponding to multiple historical orders;

[0010] Test the fabric products produced for each historical order to determine the fabric performance indicators corresponding to each historical order.

[0011] In one embodiment, the yarn matching scheme model training method further includes:

[0012] When there are new orders, the historical data training set is updated based on the cotton fiber property data and process parameters corresponding to the completed new orders, as well as the fabric performance indicators determined by testing the fabric products of the new orders, and the step of preprocessing the data in the historical data training set is entered.

[0013] In one embodiment, the step of updating the historical data training set and preprocessing the data in the historical data training set includes:

[0014] Update the historical data training set and immediately proceed to the step of preprocessing the data in the historical data training set; or,

[0015] The historical data training set is updated, and at a predetermined time, the step of preprocessing the data in the historical data training set is entered.

[0016] In one embodiment, the process parameters include finishing method, fabric structure and fabric color depth; and / or,

[0017] Fabric performance indicators include tear stretch indicators; and / or,

[0018] Cotton fiber attribute data include yarn count, yarn density and spinning method.

[0019] In a second aspect, a yarn matching method comprises:

[0020] Preprocess the data to be predicted corresponding to the order; the data to be predicted includes cotton fiber attribute data, fabric performance indicators and process parameters expected by the user;

[0021] The pre-processed data to be predicted is input into the yarn matching plan training model to determine the candidate yarns that meet the fabric performance index requirements expected by the user;

[0022] Obtain the actual inventory data of the yarn and determine the target yarn; the target yarn is the yarn in stock and with the lowest strength index among the candidate yarns;

[0023] Among them, the yarn matching plan training model is determined based on the steps of executing the above-mentioned yarn matching plan model training method.

[0024] In one embodiment, the step of preprocessing the data to be predicted corresponding to the order is the same as the preprocessing step in the above-mentioned yarn matching scheme model training method.

[0025] In a third aspect, the present application further provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of any one of the above-mentioned yarn matching methods when executing the computer program.

[0026] In a fourth aspect, a yarn distribution system comprises:

[0027] Computer equipment as described above;

[0028] Human-computer interaction equipment, connected to computer equipment, is used for:

[0029] In response to a user's input operation of the data to be predicted, sending the data to be predicted to a computer device;

[0030] receiving and displaying the target yarn fed back by the computer device;

[0031] In response to the user's selection operation on the displayed target yarn, the to-be-predicted data corresponding to the target yarn is displayed.

[0032] In a fifth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, which implements the steps of any one of the above-mentioned yarn matching methods when the computer program is executed by a processor.

[0033] The above-mentioned yarn matching scheme model training method, yarn matching method, equipment, yarn matching system and readable storage medium obtain a historical data training set, and pre-process the cotton fiber attribute data, fabric performance indicators and process parameters corresponding to the historical orders in the historical data training set, and then input them into a preset machine learning model, so as to obtain a yarn matching scheme training model that is suitable for the historical data training set. The yarn matching scheme training model can reliably reflect the specific performance of the yarn performance in the historical orders. Through the yarn matching scheme training model, a reliable and stable model basis can be provided for the yarn configuration in the next order, thereby achieving accurate configuration. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0035] Figure 1 A diagram showing an application environment of a yarn matching scheme model training method in one embodiment;

[0036] Figure 2 One of the flow charts of a yarn matching scheme model training method in one embodiment;

[0037] Figure 3 The second flowchart of the yarn matching scheme model training method in one embodiment;

[0038] Figure 4 A schematic diagram of a yarn matching method in one embodiment;

[0039] Figure 5 It is a structural block diagram of a yarn matching scheme model training device in one embodiment;

[0040] Figure 6It is a structural block diagram of a yarn distribution device in one embodiment;

[0041] Figure 7 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0042] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0043] The yarn matching scheme model training method provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown. Among them, the data storage system 102 is connected to the server 104. The data storage system 102 can store data that the server 104 needs to process, such as a historical data training set. The data storage system 102 can be integrated on the server 104, or it can be placed on the cloud or other network servers. The server 104 obtains the historical data training set stored in the data storage system 102, and preprocesses the data in the historical data training set to obtain data processing such as data cleaning, feature selection, and feature transformation, so as to improve the prediction accuracy and stability of the subsequent yarn matching scheme training model; then the data in the preprocessed historical data training set is input into the machine learning model preset in the server 104 to determine the yarn matching scheme training model. Among them, the historical data training set includes cotton fiber attribute data, fabric performance indicators and process parameters corresponding to historical orders, and the fabric performance indicators include tearing and stretching indicators.

[0044] In an exemplary embodiment, Figure 2 As shown, a yarn matching scheme model training method is provided, and the method is applied to Figure 1 Taking the server 104 in the example as an example, the yarn matching scheme model training method includes:

[0045] S202, obtaining a historical data training set, where the historical data training set includes cotton fiber attribute data, fabric performance indicators, and process parameters corresponding to historical orders, where the fabric performance indicators include tear and stretch indicators.

[0046] By analyzing the yarn generated by historical orders and the fabrics made from the yarn, we can determine the corresponding cotton fiber property data, fabric performance indicators and process parameters.

[0047] S204, preprocessing the data in the historical data training set; wherein the preprocessing includes eliminating abnormal data in the historical data training set, normalizing the cotton fiber attribute data and fabric performance indicators after the elimination process, and unique-hot encoding the process parameters after the elimination process.

[0048] Abnormal data includes null value data, data with special quality requirements in historical orders, abnormal data, and data input by human error. Eliminating abnormal data can reduce data noise and improve the reliability of historical data training sets.

[0049] Normalizing the cotton fiber property data and fabric performance indicators after the elimination process can scale the cotton fiber property data and fabric performance indicators of different dimensions or numerical ranges in each historical order to the same range, which helps to accelerate the convergence speed of the yarn matching scheme training model, thereby improving the stability and accuracy of the yarn matching scheme training model.

[0050] One-hot encoding can convert data into binary code and represent it as a sparse matrix to avoid the algorithm misinterpreting the data as ordered continuous data. Each process parameter is independent of each other and has no connection with each other. Therefore, the process parameters after elimination are processed by one-hot encoding to convert the process parameters into transposed sparse vectors to avoid sorting the size of each dimensional parameter in the process parameters and affecting the yarn matching scheme training model, thereby improving the accuracy of the yarn matching scheme training model.

[0051] Furthermore, the data in the historical data training set may be processed, such as data clarification and normalization, to improve the reliability of the historical data training set.

[0052] S206, inputting the preprocessed data in the historical data training set into a preset machine learning model to determine the yarn matching scheme training model.

[0053] The machine learning model can be selected according to the actual needs of the production line. For example, the machine learning model can be Xgboost (Extreme Gradient Boosting), KAN (Kolmogorov-Arnold Networks), artificial neural network, etc.

[0054] The above-mentioned yarn matching scheme model training method obtains the historical data training set, and after preprocessing the cotton fiber attribute data, fabric performance indicators and process parameters corresponding to the historical orders in the historical data training set, the input refers to the preset machine learning model, and a yarn matching scheme training model suitable for the historical data training set can be obtained. The yarn matching scheme training model can reliably reflect the specific performance of the yarn performance in the historical orders. Through the yarn matching scheme training model, a reliable and stable model basis can be provided for the yarn configuration in the next order, thereby achieving accurate configuration.

[0055] In an exemplary embodiment, Figure 3 As shown, the steps of obtaining the historical data training set include:

[0056] S2022, obtaining cotton fiber property data and process parameters corresponding to multiple historical orders.

[0057] S2024, testing the fabric products produced for each historical order to determine the fabric performance indicators corresponding to each historical order.

[0058] Cotton fiber property data and process parameters can be determined based on customer requirements in historical orders.

[0059] By testing the fabric products produced for each historical order through tearing, tensile and strength tests, the fabric performance indicators corresponding to each historical order can be determined.

[0060] Determining a historical data training set based on historical orders can improve the reliability of a data set used to train a yarn matching scheme training model, thereby improving the reliability of the yarn matching scheme training model.

[0061] In an exemplary embodiment, the yarn matching scheme model training method further includes:

[0062] When there are new orders, the historical data training set is updated based on the cotton fiber property data and process parameters corresponding to the completed new orders, as well as the fabric performance indicators determined by testing the fabric products of the new orders, and the step of preprocessing the data in the historical data training set is entered.

[0063] Timely updating of the historical data training set can increase the sample data of the historical data training set, balance various cotton fiber attribute data and process parameters, thereby improving the robustness of the yarn matching scheme training model; it can also ensure that the yarn matching scheme training model is more adaptable to and matches new market demands.

[0064] In an exemplary embodiment, the steps of updating the historical data training set and preprocessing the data in the historical data training set include:

[0065] The historical data training set is updated, and the step of preprocessing the data in the historical data training set is immediately entered.

[0066] In an exemplary embodiment, the steps of updating the historical data training set and preprocessing the data in the historical data training set include:

[0067] The historical data training set is updated, and at a predetermined time, the step of preprocessing the data in the historical data training set is entered.

[0068] After each order is completed, the historical data training set can be updated, and a new yarn matching scheme training model can be immediately determined based on the updated historical data training set to improve the reliability of the yarn matching scheme training model.

[0069] After each order is completed, the historical data training set can be updated first, or updated at a scheduled time, and the updated historical data training set can be added to the original historical data training set at a scheduled time for training. Specifically, it can be set to pre-process the updated historical data training set at 5 pm every day. Before 5 pm every day, the orders completed within the day need to be tested to obtain the newly added cotton fiber attribute data, fabric performance indicators and process parameters, and these newly added data are added to the original historical data training set; at 5 pm every day, the updated historical data training set is pre-processed to determine the new yarn matching scheme training model. This update method can greatly reduce the operating pressure.

[0070] Of course, the above-mentioned scheduled time is only for illustration and is not intended to be limiting.

[0071] In an exemplary embodiment, the process parameters include finishing method, fabric structure and fabric color depth; and / or, the fabric performance indicators include tear stretch index; and / or, the cotton fiber attribute data includes yarn count, yarn count density and spinning method.

[0072] Specifically, finishing methods refer to various post-treatments of yarns, such as stretching, twisting, and shrinking. Different finishing methods will directly affect the quality and performance of the yarn. For example, parameters such as finishing temperature, humidity, and pressure will affect the strength, appearance, feel, and other characteristics of the yarn. The uniformity, stability, and appearance of the yarn can be improved through appropriate finishing methods, thereby improving the quality and performance of the textile. The color depth of the yarn reflects the uniformity and color stability of the yarn dyeing. Colors of uniform depth can make textiles colorful, symmetrical, and beautiful, enhancing the attractiveness and market competitiveness of the product. Fabric structure refers to the weaving structure and braiding structure of textiles, such as yarn density, spinning method, pattern, etc. Different fabric structures will affect the appearance, comfort, thickness, and other properties of textiles.

[0073] The tear tensile index refers to the maximum tensile force that the yarn can withstand during the tearing process, which reflects the yarn's tensile resistance when it is torn by external force. The higher the tear tensile index, the stronger the yarn's tensile resistance, the yarn and textiles are not easy to break or damage during use, and have good wear resistance. Yarn count refers to the fineness of the yarn per unit length. The higher the yarn count, the finer the yarn, and the thickness of the yarn directly affects the texture, feel and appearance of the textile. Generally, coarse yarn is used for thick fabrics or workwear fabrics, while fine yarn is used for light fabrics or underwear; yarn density is expressed as the yarn density per unit length, which is specifically manifested as yarn count and textile texture density, and yarn density affects the strength, wear resistance and breathability of textiles; spinning method refers to the process method of generating yarn, and yarns produced by different process methods have different performances in stability, uniformity and neatness.

[0074] In an exemplary embodiment, a yarn matching method is provided, such as Figure 4 As shown, the yarn matching method comprises:

[0075] S402, preprocessing the data to be predicted corresponding to the order; the data to be predicted includes cotton fiber attribute data, fabric performance indicators and process parameters expected by the user.

[0076] The corresponding data to be tested can be obtained according to the order, and the data to be predicted represents the fabric demand of the user.

[0077] S404, input the pre-processed data to be predicted into the yarn matching scheme training model to determine the candidate yarns that meet the fabric performance index requirements expected by the user. The yarn matching scheme training model is determined based on the steps of the yarn matching scheme model training method.

[0078] Since the yarn matching plan training model is determined based on the historical data training set and machine learning model corresponding to the historical orders, the yarn matching plan training model has the data characteristics of the historical data training set. Based on these data characteristics, reliable alternative yarns that meet the user's expected fabric performance index requirements can be determined.

[0079] S406, obtaining actual inventory data of the yarn and determining the target yarn; the target yarn is the yarn in stock among the candidate yarns and having the lowest strength index.

[0080] The strength index refers to the maximum tensile force that a unit yarn can withstand before breaking. The strength index reflects the mechanical strength of the yarn, that is, the ability of the yarn to resist stretching and breaking under external force. The higher the strength index, the stronger and more durable the yarn. The target yarn that meets the fabric performance index requirements and has the lowest strength index can meet customer requirements while reducing costs.

[0081] In an exemplary embodiment, the step of preprocessing the data to be predicted corresponding to the order is the same as the preprocessing step in the above-mentioned yarn matching scheme model training method.

[0082] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0083] Based on the same inventive concept, the embodiment of the present application also provides a yarn matching scheme model training device for implementing the yarn matching scheme model training method involved above and a yarn matching device for the yarn matching method. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more yarn matching scheme model training devices and yarn matching device embodiments provided below can refer to the limitations of the yarn matching scheme model training method and the yarn matching method above, and will not be repeated here.

[0084] In an exemplary embodiment, Figure 5 As shown, a yarn matching scheme model training device 500 is provided, comprising: a data acquisition module 502 , a first preprocessing module 504 and a model determination module 506 .

[0085] Wherein: the data acquisition module 502 is used to acquire a historical data training set, the historical data training set includes cotton fiber attribute data, fabric performance indicators and process parameters corresponding to historical orders, and the fabric performance indicators include tearing and stretching indicators.

[0086] The first preprocessing module 504 is used to preprocess the data in the historical data training set; wherein the preprocessing includes eliminating abnormal data in the historical data training set, normalizing the cotton fiber attribute data and fabric performance indicators after the elimination process, and unique hot encoding the process parameters after the elimination process.

[0087] The model determination module 506 is used to input the preprocessed data in the historical data training set into a preset machine learning model to determine the yarn matching scheme training model.

[0088] In an exemplary embodiment, the data acquisition module 502 further includes: a first data module 5022 and a second data module 5024 .

[0089] The first data module 5022 is used to obtain cotton fiber attribute data and process parameters corresponding to multiple historical orders.

[0090] The second data module 5024 is used to test the fabric products produced for each historical order and determine the fabric performance index corresponding to each historical order.

[0091] In an exemplary embodiment, Figure 6 As shown, a yarn matching device 600 is provided, including: a second pre-processing module 602, an alternative yarn determination module 604 and a target yarn determination module 606.

[0092] The second preprocessing module 602 is used to preprocess the data to be predicted corresponding to the order; the data to be predicted includes cotton fiber attribute data, fabric performance indicators and process parameters expected by the user.

[0093] The candidate yarn determination module 604 is used to input the pre-processed data to be predicted into the yarn matching scheme training model to determine the candidate yarns that meet the fabric performance index requirements expected by the user.

[0094] The target yarn determination module 606 is used to obtain actual inventory data of the yarn and determine the target yarn; the target yarn is the yarn in stock and with the lowest strength index among the candidate yarns.

[0095] The yarn matching scheme training model is determined based on the yarn matching scheme model training device 500 mentioned above.

[0096] In an exemplary embodiment, the second pre-processing module 602 is the same as the first pre-processing module 502 .

[0097] Each module in the yarn matching scheme model training device and the yarn matching device can be implemented in whole or in part by software, hardware and a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each module.

[0098] In an exemplary embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in FIG. Figure 7As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store a historical data training set. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a yarn matching method is implemented.

[0099] Those skilled in the art will understand that Figure 7 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0100] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above-mentioned yarn matching method when executing the computer program.

[0101] Among them, the acquisition and preprocessing of historical data training sets and the determination of alternative yarns can be integrated into a cloud server, and the training of the yarn matching scheme training model can be integrated into the local server. Such division can realize data sharing and collaborative work among servers, thereby improving the efficiency and convenience of production management.

[0102] Furthermore, the update of the historical data training set can also be integrated into the above-mentioned cloud server.

[0103] Furthermore, in order to improve the security and convenience of the yarn production process, intranet access restrictions can also be set so that the cloud server and the local server are connected through intranet communication, and other devices connected to the same intranet can also view the specific progress of the yarn production at any time.

[0104] In an exemplary embodiment, a yarn distribution system is provided, comprising:

[0105] Such as the above-mentioned computer equipment and human-computer interaction equipment.

[0106] Among them, the human-computer interaction device is connected with the computer device.

[0107] Human-computer interaction equipment is used for:

[0108] In response to the user's input operation of the data to be predicted, the data to be predicted is sent to the computer device.

[0109] Receive and display the target yarn fed back by the computer device.

[0110] In response to the user's selection operation on the displayed target yarn, the to-be-predicted data corresponding to the target yarn is displayed.

[0111] The user can input the data to be predicted into the human-computer interaction device, and can also modify or delete the input data to be predicted to determine the correctness of the input data to be predicted. The user can also perform selection operations such as clicking or touching the target yarn displayed by the human-computer interaction device to trace back and display the corresponding data to be predicted for the target yarn.

[0112] The user can input and select through the human-computer interaction device, so that the user can easily view the data in the yarn matching process. Through the human-computer interaction interface module, the user can realize the comprehensive management and monitoring of the intelligent yarn matching system.

[0113] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the above-mentioned yarn matching method are implemented.

[0114] In one embodiment, a computer program product is provided, comprising a computer program, which implements the steps of the above-mentioned yarn distribution method when executed by a processor.

[0115] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0116] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0117] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A yarn matching scheme model training method, characterized in that: include: Acquire a historical data training set, wherein the historical data training set includes cotton fiber attribute data, fabric performance indicators, and process parameters corresponding to historical orders, wherein the fabric performance indicators include tearing and stretching indicators; Preprocessing the data in the historical data training set; wherein the preprocessing includes removing abnormal data in the historical data training set, normalizing the cotton fiber attribute data and the fabric performance index after the removal, and performing one-hot encoding on the process parameters after the removal; The data in the preprocessed historical data training set is input into the preset machine learning model to determine the yarn matching scheme training model.

2. The method according to claim 1, characterized in that Obtain historical data training sets, including: Obtain cotton fiber attribute data and process parameters corresponding to multiple historical orders; The fabric products produced for each of the historical orders are tested to determine fabric performance indicators corresponding to each of the historical orders.

3. The method according to claim 2, characterized in that Also includes: In the case of new orders, based on the cotton fiber attribute data and process parameters corresponding to the completed new orders, and the fabric performance indicators determined by testing the fabric products of the new orders, the historical data training set is updated, and the step of preprocessing the data in the historical data training set is entered.

4. The method according to claim 3, characterized in that The step of updating the historical data training set and entering into the step of preprocessing the data in the historical data training set includes: updating the historical data training set and immediately entering the step of preprocessing the data in the historical data training set; or, The historical data training set is updated, and the step of preprocessing the data in the historical data training set is entered at a predetermined time.

5. The method according to any one of claims 1 to 4, characterized in that: The process parameters include finishing method, fabric structure and fabric color depth; and / or, The fabric performance index includes a tearing tensile index; and / or, The cotton fiber attribute data includes yarn count, yarn count density and spinning method.

6. A yarn matching method, characterized in that: include: Preprocess the data to be predicted corresponding to the order; The data to be predicted include cotton fiber attribute data, fabric performance indicators and process parameters expected by users; The pre-processed data to be predicted is input into the yarn matching plan training model to determine the candidate yarns that meet the fabric performance index requirements expected by the user; Acquire actual inventory data of yarns and determine a target yarn; the target yarn is the yarn in stock among the candidate yarns and having the lowest strength index; Wherein, the yarn matching scheme training model is determined based on the steps of executing the yarn matching scheme model training method described in any one of claims 1-5.

7. The method according to claim 6, characterized in that The step of preprocessing the data to be predicted corresponding to the order is the same as the preprocessing step in the yarn matching scheme model training method described in any one of claims 1-5.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to claim 6 or 7 are implemented.

9. A yarn distribution system, characterized in that: include: The computer device as claimed in claim 8; A human-computer interaction device is connected to the computer device, and the human-computer interaction device is used to: In response to a user's input operation of data to be predicted, sending the data to be predicted to the computer device; receiving and displaying the target yarn fed back by the computer device; In response to a user's selection operation on the displayed target yarn, to-be-predicted data corresponding to the target yarn is displayed.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to claim 6 or 7 are implemented.

Citation Information

Cited By

  • Woven yarn and fabric bidirectional spectrum prediction construction method and system

    CN119394969A

  • Real-time anomaly prediction using extrapolated telemetry data

    US12705154B2

  • Consolidating anomaly detection methods using hybrid artificial intelligence

    US12792453B2

  • System and method for detection of proxy server key performance indicators (KPI) deterioration, alerting and mitigation

    US12801483B2