Polyester fiber dyeing process data recommendation method and system, medium and computer

Abstract

The invention relates to a polyester fiber dyeing process data recommendation method and system, a medium and a computer. Historical dyeing data are collected, dye vat data in the dyeing process are collected and analyzed, an auxiliary matched with dye can be correspondingly recommended according to the type of the dye, and according to the type of the auxiliary, the polyester fiber dyeing process data can be recommended according to the type of the auxiliary. By adopting the method disclosed by the invention, the problem that the color effect is deviated due to the deviation of the temperature level data can be effectively reduced, and the dyeing effect of the polyester fiber is improved.

Description

Technical Field

[0001] The invention relates to the technical field of dyeing, and more specifically to a method, system, medium and computer for recommending polyester fiber dyeing process data. Background Art

[0002] In the prior art, the dyeing process can be described by a dyeing curve. Under constant temperature conditions, a curve plotting the dyeing percentage of the dye in the dye bath against the dyeing time is called a dyeing curve, which is an important basis for studying the dyeing process. Among them, the dyeing percentage refers to the percentage of the amount of dye dyed to the total amount of dye in the dye solution. When the dyeing reaches a balanced state, it is called the equilibrium dyeing percentage. Half-dyeing time - the time required to reach half of the equilibrium dyeing percentage, the half-dyeing time can characterize the dyeing rate. In production, when using multiple dyes to match colors, dyes with similar dyeing rates should be selected to dye a consistent color.

[0003] The dyeing process curve of disperse dyes in the polyester fiber dyeing process is generally obtained by combining the temperature step dyeing curve of the dye combination through experience. When quality problems such as color flower occur, they are generally solved by increasing the amount of auxiliary leveling agent, reducing the heating rate or extending the insulation time. However, the above treatment methods have disadvantages. When the affinity of the leveling agent to the fiber is greater than the affinity of the dye to the fiber, the leveling agent and the dye compete with each other for dyeing. The leveling agent preferentially combines with the fiber, occupies the dyeing seat on the fiber, hinders the combination of the dye and the fiber, delays the dyeing of the dye, and causes the polyester fiber to deviate from the dyeing. And as the temperature of the dye bath increases, the dye gradually replaces the leveling agent from the fiber, and finally the dye occupies the dyeing seat, thereby achieving the purpose of leveling; if it is not known which stage of the heating rate is too fast to cause the color flower abnormality, and blindly reducing the heating rate will lead to problems such as extended production time and low production efficiency. Summary of the invention

[0004] In view of the shortcomings of the prior art, the purpose of the present invention is to provide a polyester fiber dyeing process data recommendation method, system, medium and computer to overcome the shortcomings of the prior art that temperature step data is difficult to select and easily affects the dyeing effect.

[0005] The above technical objectives of the present invention are achieved through the following technical solutions: A polyester fiber dyeing process data recommendation method, comprising:

[0006] S1. Acquire historical dyeing data of polyester fibers; the historical dyeing data includes: the type of dye in the dye vat, the type of auxiliary agent corresponding to the dye, and the temperature data in the dye vat;

[0007] S2. constructing a dye-auxiliary agent co-occurrence map according to the historical dyeing data; constructing an auxiliary agent-temperature step co-occurrence map according to the historical dyeing data;

[0008] S3, using a graph convolution algorithm, convolving the dye-auxiliary agent co-occurrence graph to obtain a plurality of dye-auxiliary agent co-occurrence graph embeddings; using a graph convolution algorithm, convolving the auxiliary agent-temperature step co-occurrence graph to obtain a plurality of auxiliary agent-temperature step co-occurrence graph embeddings;

[0009] S4. Using the attention mechanism, all dye-auxiliary agent co-occurrence graphs are embedded and fused to obtain a dye auxiliary agent graph representation; using the attention mechanism, all auxiliary agent-temperature step co-occurrence graphs are embedded and fused to obtain an auxiliary agent temperature step graph representation;

[0010] S5, obtaining a preset dyeing formula, determining the dye to be used according to the dyeing formula, and recording it as a predetermined dye; interacting the predetermined dye with the dye auxiliary agent graph to obtain a recommendation probability of each auxiliary agent; selecting the auxiliary agent with the highest recommendation probability, and recording it as a recommended auxiliary agent;

[0011] S6. Interact the recommended additives with the additive temperature step diagram to obtain the recommendation probability corresponding to each temperature step data, and select the temperature step data with the largest recommendation probability.

[0012] Optionally, constructing a dye-auxiliary agent co-occurrence map according to the historical dyeing data includes:

[0013] Construct a dye set based on all dyes that appear in the historical dyeing data:

[0014] A={a1,a2,…,a i}

[0015] Construct an auxiliary set based on all auxiliary agents appearing in historical dyeing data:

[0016] B={b1,b2,…,b j}

[0017] According to the co-occurrence of dyes and auxiliaries in each historical dyeing data, a dye-auxiliary co-occurrence set is constructed:

[0018] AB={(a1,b1),…,(a1,b j ),…,(a i ,b1),…,(a i ,b j )}

[0019] The mathematical representation of the elements in the dye-auxiliary co-occurrence set is:

[0020]

[0021] According to the dye-auxiliary co-occurrence set, a dye-auxiliary co-occurrence map is constructed.

[0022] Optionally, the interacting the predetermined dye with the dye auxiliary agent graphical representation to obtain the recommendation probability of each auxiliary agent includes: using a probability vector to represent the recommendation probability of the auxiliary agent type:

[0023]

[0024] in, is the j-dimensional probability vector output by the model; θ is the trainable parameter of the function f(·), A is the dye in the pre-set dyeing formula; B={b1,b2,…,b j}, represents the set of all auxiliary agent types in the historical dyeing data; in the j-dimensional probability vector, the value of the x-th dimension of the vector represents the auxiliary agent type b x The probability that it can be applied to a predetermined dye.

[0025] Optionally, the step of interacting the predetermined dye with the dye auxiliary agent graphical representation to obtain a recommendation probability of each auxiliary agent further includes:

[0026] Extracting features of the predetermined dye to obtain a corresponding dye feature matrix;

[0027] Calculate the matrix multiplication of the dye characteristic matrix and the dye auxiliary agent map representation to obtain the first probability vector:

[0028]

[0029] Among them, Y A represents the dye feature matrix, and D represents the dye auxiliary graph representation.

[0030] Optionally, constructing a dye-auxiliary agent co-occurrence map according to the historical dyeing data includes:

[0031] Construct an auxiliary set based on all auxiliary agents appearing in historical dyeing data:

[0032] b={b1,b2,…,bj}

[0033] According to all the temperature step data appearing in the historical dyeing data, a temperature step data set is constructed:

[0034] C={c1,c2,…,c k}

[0035] According to the co-occurrence of auxiliaries and temperature order data in each historical dyeing data, the auxiliaries-temperature order co-occurrence set is constructed:

[0036] BC={(b1,c1),…,(b1,c k ),…,(b j ,c1),…,(b j ,ck )}

[0037] The mathematical representation of the elements in the additive-temperature step co-occurrence set is:

[0038]

[0039] Based on the additive-temperature order co-occurrence set, an additive-temperature order co-occurrence map is constructed.

[0040] Optionally, the interacting the recommended additive with the additive temperature step diagram to obtain the recommendation probability corresponding to each temperature step data includes: using a probability vector to represent the recommendation probability of the additive type:

[0041]

[0042] in, is the k-dimensional probability vector output by the model; is the trainable parameter of the function f(·), B is the recommended type of additive; C={C1,C2,…,C k}, represents the temperature data set corresponding to the auxiliary agent in the historical dyeing data; in the k-dimensional probability vector, the value of the x-th dimension of the vector represents the temperature data c x The probability of being able to be applied to a specific type of additive.

[0043] Optionally, the step of interacting the recommended additive with the additive temperature step diagram to obtain a recommendation probability corresponding to each temperature step data includes:

[0044] Extracting features of the additive to obtain a corresponding additive feature matrix;

[0045] The matrix multiplication of the additive characteristic matrix and the additive temperature step diagram is calculated to obtain a second probability vector:

[0046]

[0047] Among them, Y B represents the additive characteristic matrix, and E represents the additive temperature step diagram.

[0048] A polyester fiber dyeing process data recommendation system, comprising:

[0049] Historical data collection module: used to obtain historical dyeing data of polyester fibers; the historical dyeing data includes: the type of dye in the dye vat, the type of auxiliary agent corresponding to the dye, and the temperature level data in the dye vat;

[0050] A co-occurrence map construction module: used to construct a dye-auxiliary agent co-occurrence map according to the historical dyeing data; and to construct an auxiliary agent-temperature step co-occurrence map according to the historical dyeing data;

[0051] A graph embedding calculation module: used to convolve the dye-auxiliary agent co-occurrence graph using a graph convolution algorithm to obtain a plurality of dye-auxiliary agent co-occurrence graph embeddings; and to convolve the auxiliary agent-temperature step co-occurrence graph using a graph convolution algorithm to obtain a plurality of auxiliary agent-temperature step co-occurrence graph embeddings;

[0052] Graph representation fusion module: It is used to embed and fuse all dye-auxiliary co-occurrence graphs using the attention mechanism to obtain the dye auxiliary graph representation; it is used to embed and fuse all auxiliary-temperature step co-occurrence graphs using the attention mechanism to obtain the auxiliary temperature step graph representation;

[0053] Auxiliary agent recommendation module: used to obtain a preset dyeing formula, determine the dye to be used according to the dyeing formula, and record it as a predetermined dye; interact the predetermined dye with the dye auxiliary agent graph to obtain the recommendation probability of each auxiliary agent; select the auxiliary agent with the highest recommendation probability, and record it as the recommended auxiliary agent;

[0054] Temperature step data recommendation module: used for interacting the recommended additives with the additive temperature step diagram representation, obtaining the recommendation probability corresponding to each temperature step data, and selecting the temperature step data with the largest recommendation probability.

[0055] A computer-readable storage medium stores a computer program, which implements the steps of the above method when executed by a processor.

[0056] A computer device comprises a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above method when executing the computer program.

[0057] In summary, the present invention has the following beneficial effects: the present invention collects and analyzes the dye vat data in the dyeing process by collecting historical dyeing data, and can recommend auxiliary agents that match the dyes according to the types of dyes, and recommend temperature step data of the dye vats according to the types of auxiliary agents. The method of the present invention can effectively reduce the problem of deviation in human color effects caused by deviation in temperature step data, thereby improving the dyeing effect of polyester fibers. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] Figure 1 A flow chart of a polyester fiber dyeing process data recommendation method of the present invention;

[0059] Figure 2 This is a structural diagram of a polyester fiber dyeing process data recommendation system of the present invention;

[0060] Figure 3 1 is a diagram showing the internal structure of a computer device in an embodiment of the present invention.

[0061] In the figure: 1. Historical data collection module; 2. Co-occurrence graph construction module; 3. Graph embedding calculation module; 4. Graph representation fusion module; 5. Additive recommendation module; 6. Temperature step data recommendation module. DETAILED DESCRIPTION

[0062] In order to make the purpose, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings. Several embodiments of the present invention are shown in the accompanying drawings. However, the present invention can be implemented in many different forms and is not limited to the embodiments described herein.

[0063] In the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", "connected", "fixed" and the like should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal connection of two elements. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to the specific circumstances. The terms "first" and "second" are used for descriptive purposes only and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features.

[0064] In the present invention, unless otherwise clearly specified and limited, the first feature being "above" or "below" the second feature may include the first and second features being in direct contact, or may include the first and second features being in contact not directly but through another feature between them. Moreover, the first feature being "above", "above" and "above" the second feature includes the first feature being directly above and obliquely above the second feature, or simply indicates that the first feature is higher in level than the second feature. The first feature being "below", "below" and "below" the second feature includes the first feature being directly below and obliquely below the second feature, or simply indicates that the first feature is lower in level than the second feature. The terms "vertical", "horizontal", "left", "right", "above", "below" and similar expressions are for illustrative purposes only, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as limiting the present invention.

[0065] The present invention is described in detail below in conjunction with the accompanying drawings and embodiments.

[0066] The present invention provides a polyester fiber dyeing process data recommendation method, such as Figure 1 As shown, including:

[0067] S1. Acquire historical dyeing data of polyester fibers; the historical dyeing data includes: the type of dye in the dye vat, the type of auxiliary agent corresponding to the dye, and the temperature data in the dye vat;

[0068] S2. constructing a dye-auxiliary agent co-occurrence map according to the historical dyeing data; constructing an auxiliary agent-temperature step co-occurrence map according to the historical dyeing data;

[0069] In practical applications, historical dyeing data represents the training set of the system. Generally speaking, each dye, according to its different properties, will have a relatively suitable auxiliary agent to assist in dyeing. In order to ensure the dyeing effect, it is also necessary to correspond to the temperature data in the dyeing tank according to the type of auxiliary agent, including the maximum heating rate and cooling rate, the basic cloth ratio of various fabrics, etc. Therefore, in the historical dyeing data, some dyes and auxiliary agents usually appear in pairs, and some auxiliary agents and corresponding temperature data also appear in pairs. According to the characteristics of the above historical dyeing data, co-occurrence graphs are constructed respectively, which can effectively reflect some rules between dyes, auxiliary agents and temperature data in the dyeing process. Co-occurrence graph is a data visualization technology that is often used to show the relationship between multiple variables and the pattern of co-occurrence. By plotting the co-occurrence between multiple variables into a graph, it can help users understand the relationship and connection between variables more intuitively and discover the rules and trends therein. Co-occurrence graphs are usually displayed in the form of network graphs, in which nodes represent variables and edges represent the co-occurrence relationship between variables. Different variable characteristics or co-occurrence patterns can be displayed through different layouts and colors, helping users better understand and analyze data. Co-occurrence maps are used in many fields, such as academic research, social network analysis, and medical research.

[0070] S3, using a graph convolution algorithm, convolving the dye-auxiliary agent co-occurrence graph to obtain a plurality of dye-auxiliary agent co-occurrence graph embeddings; using a graph convolution algorithm, convolving the auxiliary agent-temperature step co-occurrence graph to obtain a plurality of auxiliary agent-temperature step co-occurrence graph embeddings;

[0071] In practical applications, graph embedding means assigning a multidimensional vector that can represent each node in the graph. Therefore, after the actual convolution, the graph embedding obtained by each co-occurrence graph is the same as the number of nodes in the co-occurrence graph. The nodes on the co-occurrence graph refer to each individual element in the co-occurrence edge set. Two nodes that are connected in the co-occurrence graph represent a co-occurrence relationship between the two nodes. The graph convolution operation is to take each qualified node in the co-occurrence graph as the central node, and other nodes that have a co-occurrence relationship with it as neighbor nodes, and perform weighted summation on these nodes based on these neighboring information, and use the result as the central node to replace the original central node. For a co-occurrence graph, each time a convolution operation is performed, it can be regarded as the graph entering the next layer.

[0072] S4. Using the attention mechanism, all dye-auxiliary agent co-occurrence graphs are embedded and fused to obtain a dye auxiliary agent graph representation; using the attention mechanism, all auxiliary agent-temperature step co-occurrence graphs are embedded and fused to obtain an auxiliary agent temperature step graph representation;

[0073] In this application, the attention mechanism is used to fuse the dye-auxiliary co-occurrence map embedding and the auxiliary-temperature step co-occurrence map embedding respectively to obtain the dye auxiliary map representation and the auxiliary temperature step map representation. The attention mechanism enables the model to perceive the relationship between various elements in the recommendation system.

[0074] S5, obtaining a preset dyeing formula, determining the dye to be used according to the dyeing formula, and recording it as a predetermined dye; interacting the predetermined dye with the dye auxiliary agent graph to obtain a recommendation probability of each auxiliary agent; selecting the auxiliary agent with the highest recommendation probability, and recording it as a recommended auxiliary agent;

[0075] S6. Interact the recommended additives with the additive temperature step diagram to obtain the recommendation probability corresponding to each temperature step data, and select the temperature step data with the largest recommendation probability.

[0076] Furthermore, constructing a dye-auxiliary agent co-occurrence map based on the historical dyeing data includes:

[0077] Construct a dye set based on all dyes that appear in the historical dyeing data:

[0078] A={a1,a2,…,a i}

[0079] Construct an auxiliary set based on all auxiliary agents appearing in historical dyeing data:

[0080] B={b1,b2,…,b j}

[0081] According to the co-occurrence of dyes and auxiliaries in each historical dyeing data, a dye-auxiliary co-occurrence set is constructed:

[0082] AB={(a1,b1),…,(a1,b j ),…,(a i ,b1),…,(a i ,b j )}

[0083] The mathematical representation of the elements in the dye-auxiliary co-occurrence set is:

[0084]

[0085] According to the dye-auxiliary co-occurrence set, a dye-auxiliary co-occurrence map is constructed.

[0086] Furthermore, the predetermined dye is interacted with the dye auxiliary agent graph representation to obtain the recommendation probability of each auxiliary agent, including: using a probability vector to represent the recommendation probability of the auxiliary agent type:

[0087]

[0088] in, is the j-dimensional probability vector output by the model; θ is the trainable parameter of the function f(·), A is the dye in the pre-set dyeing formula; B={b1,b2,…,b j}, represents the set of all auxiliary agent types in the historical dyeing data; in the j-dimensional probability vector, the value of the x-th dimension of the vector represents the auxiliary agent type b x The probability that it can be applied to a predetermined dye.

[0089] Furthermore, the step of interacting the predetermined dye with the dye auxiliary agent graphical representation to obtain a recommendation probability of each auxiliary agent further includes:

[0090] Extracting features of the predetermined dye to obtain a corresponding dye feature matrix;

[0091] Calculate the matrix multiplication of the dye characteristic matrix and the dye auxiliary agent map representation to obtain the first probability vector:

[0092]

[0093] Among them, Y A represents the dye feature matrix, and D represents the dye auxiliary graph representation.

[0094] Furthermore, constructing a dye-auxiliary agent co-occurrence map based on the historical dyeing data includes:

[0095] Construct an auxiliary set based on all auxiliary agents appearing in historical dyeing data:

[0096] B={b1,b2,…,b j}

[0097] According to all the temperature step data appearing in the historical dyeing data, a temperature step data set is constructed:

[0098] C={c1,c2,…,c k}

[0099] According to the co-occurrence of auxiliaries and temperature order data in each historical dyeing data, the auxiliaries-temperature order co-occurrence set is constructed:

[0100] BC={(b1,c1),…,(b1,c k ),…,(b j ,c1),…,(bj ,c k )}

[0101] The mathematical representation of the elements in the additive-temperature step co-occurrence set is:

[0102]

[0103] Based on the additive-temperature order co-occurrence set, an additive-temperature order co-occurrence map is constructed.

[0104] Furthermore, the recommended additives are interacted with the additive temperature step diagram to obtain the recommendation probability corresponding to each temperature step data, including: using a probability vector to represent the recommendation probability of the additive type:

[0105]

[0106] in, is the k-dimensional probability vector output by the model; is the trainable parameter of the function f(·), B is the recommended type of additive; C={C1,C2,…,C k}, represents the temperature data set corresponding to the auxiliary agent in the historical dyeing data; in the k-dimensional probability vector, the value of the x-th dimension of the vector represents the temperature data c x The probability of being able to be applied to a specific type of additive.

[0107] Furthermore, the recommended additives are interacted with the additive temperature step diagram to obtain the recommendation probability corresponding to each temperature step data, including:

[0108] Extracting features of the additive to obtain a corresponding additive feature matrix;

[0109] The matrix multiplication of the additive characteristic matrix and the additive temperature step diagram is calculated to obtain a second probability vector:

[0110]

[0111] Among them, Y B represents the additive characteristic matrix, and E represents the additive temperature step diagram.

[0112] Furthermore, this algorithm uses cross loss entropy as the loss function:

[0113]

[0114] Where H is the true value in the data set, x i is the scalar of the i-th dimension of the probability vector, y i is a scalar of the true value i-th dimension.

[0115] By calculating the loss function, the learnable parameters in the model are updated to make the model output more accurate.

[0116] like Figure 2 As shown, the present invention also provides a polyester fiber dyeing process data recommendation system comprising:

[0117] Historical data collection module: used to obtain historical dyeing data of polyester fibers; the historical dyeing data includes: the type of dye in the dye vat, the type of auxiliary agent corresponding to the dye, and the temperature level data in the dye vat;

[0118] A co-occurrence map construction module: used to construct a dye-auxiliary agent co-occurrence map according to the historical dyeing data; and to construct an auxiliary agent-temperature step co-occurrence map according to the historical dyeing data;

[0119] A graph embedding calculation module: used to convolve the dye-auxiliary agent co-occurrence graph using a graph convolution algorithm to obtain a plurality of dye-auxiliary agent co-occurrence graph embeddings; and to convolve the auxiliary agent-temperature step co-occurrence graph using a graph convolution algorithm to obtain a plurality of auxiliary agent-temperature step co-occurrence graph embeddings;

[0120] Graph representation fusion module: It is used to embed and fuse all dye-auxiliary co-occurrence graphs using the attention mechanism to obtain the dye auxiliary graph representation; it is used to embed and fuse all auxiliary-temperature step co-occurrence graphs using the attention mechanism to obtain the auxiliary temperature step graph representation;

[0121] Auxiliary agent recommendation module: used to obtain a preset dyeing formula, determine the dye to be used according to the dyeing formula, and record it as a predetermined dye; interact the predetermined dye with the dye auxiliary agent graph to obtain the recommendation probability of each auxiliary agent; select the auxiliary agent with the highest recommendation probability, and record it as the recommended auxiliary agent;

[0122] Temperature step data recommendation module: used for interacting the recommended additives with the additive temperature step diagram representation, obtaining the recommendation probability corresponding to each temperature step data, and selecting the temperature step data with the largest recommendation probability.

[0123] The specific definition of a polyester fiber dyeing process data recommendation system can be found in the definition of a polyester fiber dyeing process data recommendation method mentioned above, which will not be repeated here. Each module in the above polyester fiber dyeing process data recommendation system 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 of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0124] 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 3As shown. The computer device includes a processor, a memory, a network interface and a database connected through a system bus. 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. When the computer program is executed by the processor, a polyester fiber dyeing process data recommendation method is implemented.

[0125] Those skilled in the art will understand that Figure 3 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.

[0126] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0127] include:

[0128] S1. Acquire historical dyeing data of polyester fibers; the historical dyeing data includes: the type of dye in the dye vat, the type of auxiliary agent corresponding to the dye, and the temperature data in the dye vat;

[0129] S2. constructing a dye-auxiliary agent co-occurrence map according to the historical dyeing data; constructing an auxiliary agent-temperature step co-occurrence map according to the historical dyeing data;

[0130] S3, using a graph convolution algorithm, convolving the dye-auxiliary agent co-occurrence graph to obtain a plurality of dye-auxiliary agent co-occurrence graph embeddings; using a graph convolution algorithm, convolving the auxiliary agent-temperature step co-occurrence graph to obtain a plurality of auxiliary agent-temperature step co-occurrence graph embeddings;

[0131] S4. Using the attention mechanism, all dye-auxiliary agent co-occurrence graphs are embedded and fused to obtain a dye auxiliary agent graph representation; using the attention mechanism, all auxiliary agent-temperature step co-occurrence graphs are embedded and fused to obtain an auxiliary agent temperature step graph representation;

[0132] S5, obtaining a preset dyeing formula, determining the dye to be used according to the dyeing formula, and recording it as a predetermined dye; interacting the predetermined dye with the dye auxiliary agent graph to obtain a recommendation probability of each auxiliary agent; selecting the auxiliary agent with the highest recommendation probability, and recording it as a recommended auxiliary agent;

[0133] S6. Interact the recommended additives with the additive temperature step diagram to obtain the recommendation probability corresponding to each temperature step data, and select the temperature step data with the largest recommendation probability.

[0134] In one embodiment, constructing a dye-auxiliary co-occurrence map according to the historical dyeing data comprises:

[0135] Construct a dye set based on all dyes that appear in the historical dyeing data:

[0136] A={a1,a2,…,a i}

[0137] Construct an auxiliary set based on all auxiliary agents appearing in historical dyeing data:

[0138] B={b1,b2,…,b j}

[0139] According to the co-occurrence of dyes and auxiliaries in each historical dyeing data, a dye-auxiliary co-occurrence set is constructed:

[0140] AB={(a1,b1),…,(a1,b j ),…,(a i ,b1),…,(a i ,b j )}

[0141] The mathematical representation of the elements in the dye-auxiliary co-occurrence set is:

[0142]

[0143] According to the dye-auxiliary co-occurrence set, a dye-auxiliary co-occurrence map is constructed.

[0144] In one embodiment, the interacting the predetermined dye with the dye auxiliary agent graph to obtain the recommendation probability of each auxiliary agent includes: using a probability vector to represent the recommendation probability of the auxiliary agent type:

[0145]

[0146] in, is the j-dimensional probability vector output by the model; θ is the trainable parameter of the function f(·), A is the dye in the pre-set dyeing formula; B={b1,b2,…,b j}, represents the set of all auxiliary agent types in the historical dyeing data; in the j-dimensional probability vector, the value of the x-th dimension of the vector represents the auxiliary agent type b x The probability that it can be applied to a predetermined dye.

[0147] In one embodiment, the step of interacting the predetermined dye with the dye auxiliary agent graphical representation to obtain a recommendation probability of each auxiliary agent further includes:

[0148] Extracting features of the predetermined dye to obtain a corresponding dye feature matrix;

[0149] Calculate the matrix multiplication of the dye characteristic matrix and the dye auxiliary agent map representation to obtain the first probability vector:

[0150]

[0151] Among them, Y A represents the dye feature matrix, and D represents the dye auxiliary graph representation.

[0152] In one embodiment, constructing a dye-auxiliary co-occurrence map according to the historical dyeing data comprises:

[0153] Construct an auxiliary set based on all auxiliary agents appearing in historical dyeing data:

[0154] B={b1,b2,…,b j}

[0155] According to all the temperature step data appearing in the historical dyeing data, a temperature step data set is constructed:

[0156] C={c1,c2,…,c k}

[0157] According to the co-occurrence of auxiliaries and temperature order data in each historical dyeing data, the auxiliaries-temperature order co-occurrence set is constructed:

[0158] BC={(b1,c1),…,(b1,c k ),…,(b j ,c1),…,(b j ,c k )}

[0159] The mathematical representation of the elements in the additive-temperature step co-occurrence set is:

[0160]

[0161] Based on the additive-temperature order co-occurrence set, an additive-temperature order co-occurrence map is constructed.

[0162] In one embodiment, the interaction between the recommended additive and the additive temperature step diagram to obtain the recommendation probability corresponding to each temperature step data includes: using a probability vector to represent the recommendation probability of the additive type:

[0163]

[0164] in, is the k-dimensional probability vector output by the model; is the trainable parameter of the function f(·), B is the recommended type of additive; C={C1,C2,…,C k}, represents the temperature data set corresponding to the auxiliary agent in the historical dyeing data; in the k-dimensional probability vector, the value of the x-th dimension of the vector represents the temperature data c x The probability of being able to be applied to a specific type of additive.

[0165] In one embodiment, the interaction between the recommended additive and the additive temperature step diagram to obtain the recommendation probability corresponding to each temperature step data includes:

[0166] Extracting features of the additive to obtain a corresponding additive feature matrix;

[0167] The matrix multiplication of the additive characteristic matrix and the additive temperature step diagram is calculated to obtain a second probability vector:

[0168]

[0169] Among them, Y B represents the additive characteristic matrix, and E represents the additive temperature step diagram.

[0170] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods 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 memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an 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).

[0171] The technical features of the above embodiments may be arbitrarily combined. 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 specification.

[0172] The above is only a preferred embodiment of the present invention, and the protection scope of the present invention is not limited to the above embodiments. All technical solutions under the concept of the present invention belong to the protection scope of the present invention. It should be pointed out that for ordinary technicians in this technical field, some improvements and modifications without departing from the principle of the present invention should also be regarded as the protection scope of the present invention.

Claims

1. A polyester fiber dyeing process data recommendation method, characterized in that: include: S1. Obtain historical dyeing data of polyester fiber; The historical dyeing data includes: the type of dye in the dye vat, the type of auxiliary agent corresponding to the dye, and the temperature level data in the dye vat; S2. constructing a dye-auxiliary agent co-occurrence map according to the historical dyeing data; constructing an auxiliary agent-temperature step co-occurrence map according to the historical dyeing data; S3, using a graph convolution algorithm, convolving the dye-auxiliary agent co-occurrence graph to obtain a plurality of dye-auxiliary agent co-occurrence graph embeddings; using a graph convolution algorithm, convolving the auxiliary agent-temperature step co-occurrence graph to obtain a plurality of auxiliary agent-temperature step co-occurrence graph embeddings; S4. Using the attention mechanism, all dye-auxiliary agent co-occurrence graphs are embedded and fused to obtain a dye auxiliary agent graph representation; using the attention mechanism, all auxiliary agent-temperature step co-occurrence graphs are embedded and fused to obtain an auxiliary agent temperature step graph representation; S5, obtaining a preset dyeing formula, determining the dye to be used according to the dyeing formula, and recording it as a predetermined dye; interacting the predetermined dye with the dye auxiliary agent graph to obtain a recommendation probability of each auxiliary agent; selecting the auxiliary agent with the highest recommendation probability, and recording it as a recommended auxiliary agent; S6. Interact the recommended additives with the additive temperature step diagram to obtain the recommendation probability corresponding to each temperature step data, and select the temperature step data with the largest recommendation probability.

2. A polyester fiber dyeing process data recommendation method according to claim 1, characterized in that: The step of constructing a dye-auxiliary co-occurrence map according to the historical dyeing data comprises: Construct a dye set based on all dyes that appear in the historical dyeing data: <h2 style=";text-align:left;direction:ltr">A = {a1,a2,…,a<h2 style=";text-align:left;direction:ltr"> i <h2 style=";text-align:left;direction:ltr">} Construct an auxiliary set based on all auxiliary agents appearing in historical dyeing data: B={b1,b2,…,b j } According to the co-occurrence of dyes and auxiliaries in each historical dyeing data, a dye-auxiliary co-occurrence set is constructed: AB={(α1,b1),…,(a1,b j ),…,(and i ,b1),…,(a i ,b j )} The mathematical representations of the elements in the dye-auxiliary co-occurrence set are: According to the dye-auxiliary co-occurrence set, a dye-auxiliary co-occurrence map is constructed.

3. A polyester fiber dyeing process data recommendation method according to claim 2, characterized in that: The predetermined dye is interacted with the dye auxiliary agent graph representation to obtain the recommendation probability of each auxiliary agent, including: using a probability vector to represent the recommendation probability of the auxiliary agent type: in, is the j-dimensional probability vector output by the model; θ is the trainable parameter of the function f(·), A is the dye in the pre-set dyeing formula; B = {b1, b2, …, b j }, represents the set of all auxiliary agent types in the historical dyeing data; in the j-dimensional probability vector, the value of the x-th dimension of the vector represents the auxiliary agent type b x The probability that it can be applied to a predetermined dye.

4. A polyester fiber dyeing process data recommendation method according to claim 3, characterized in that: The step of interacting the predetermined dye with the dye auxiliary agent graphical representation to obtain a recommendation probability of each auxiliary agent further includes: Extracting features of the predetermined dye to obtain a corresponding dye feature matrix; Calculate the matrix multiplication of the dye characteristic matrix and the dye auxiliary agent map representation to obtain the first probability vector: Among them, Y A represents the dye feature matrix, and D represents the dye auxiliary graph representation.

5. The polyester fiber dyeing process data recommendation method according to claim 1, characterized in that: The step of constructing a dye-auxiliary co-occurrence map according to the historical dyeing data comprises: Construct an auxiliary set based on all auxiliary agents appearing in historical dyeing data: B={b1,b2,…,b j } According to all the temperature step data appearing in the historical dyeing data, a temperature step data set is constructed: C={c1,c2,…,c k } According to the co-occurrence of auxiliaries and temperature order data in each historical dyeing data, the auxiliaries-temperature order co-occurrence set is constructed: B-C={(b1,c1),…,(b1,c k ),…,(b j ,c1)…,(b j ,c k )} The mathematical representation of the elements in the additive-temperature step co-occurrence set is: According to the additive-temperature order co-occurrence set, an additive-temperature order co-occurrence map is constructed.

6. A polyester fiber dyeing process data recommendation method according to claim 5, characterized in that: The step of interacting the recommended additive with the additive temperature step diagram to obtain a recommendation probability corresponding to each temperature step data includes: using a probability vector to represent the recommendation probability of the additive type: in, is the k-dimensional probability vector output by the model; is the trainable parameter of the function f(·), B is the recommended type of additive; C={C1,C2,…,C k }, represents the temperature data set corresponding to the auxiliary agent in the historical dyeing data; in the k-dimensional probability vector, the value of the x-th dimension of the vector represents the temperature data c x The probability of being able to be applied to a specific type of additive.

7. A polyester fiber dyeing process data recommendation method according to claim 6, characterized in that: The step of interacting the recommended additive with the additive temperature step diagram to obtain a recommendation probability corresponding to each temperature step data includes: Extracting features of the additive to obtain a corresponding additive feature matrix; The matrix multiplication of the additive characteristic matrix and the additive temperature step diagram is calculated to obtain a second probability vector: Among them, Y B represents the additive characteristic matrix, and E represents the additive temperature step diagram.

8. A polyester fiber dyeing process data recommendation system, characterized in that: include: Historical data collection module: used to obtain historical dyeing data of polyester fibers; The historical dyeing data includes: the type of dye in the dye vat, the type of auxiliary agent corresponding to the dye, and the temperature level data in the dye vat; Co-occurrence map construction module: used to construct a dye-auxiliary agent co-occurrence map according to the historical dyeing data; construct an auxiliary agent-temperature step co-occurrence map according to the historical dyeing data; A graph embedding calculation module: used to convolve the dye-auxiliary agent co-occurrence graph using a graph convolution algorithm to obtain a plurality of dye-auxiliary agent co-occurrence graph embeddings; and to convolve the auxiliary agent-temperature step co-occurrence graph using a graph convolution algorithm to obtain a plurality of auxiliary agent-temperature step co-occurrence graph embeddings; Graph representation fusion module: It is used to embed and fuse all dye-auxiliary co-occurrence graphs using the attention mechanism to obtain the dye auxiliary graph representation; it is used to embed and fuse all auxiliary-temperature step co-occurrence graphs using the attention mechanism to obtain the auxiliary temperature step graph representation; Auxiliary agent recommendation module: used to obtain a preset dyeing formula, determine the dye to be used according to the dyeing formula, and record it as a predetermined dye; interact the predetermined dye with the dye auxiliary agent graph to obtain the recommendation probability of each auxiliary agent; select the auxiliary agent with the highest recommendation probability, and record it as the recommended auxiliary agent; Temperature step data recommendation module: used for interacting the recommended additives with the additive temperature step diagram representation, obtaining the recommendation probability corresponding to each temperature step data, and selecting the temperature step data with the largest recommendation probability.

9. 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 any one of claims 1 to 7 are implemented.

10. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

Images