A dynamic scheduling system and method for disinfection tissue production

Abstract

The present invention relates to the technical field of production scheduling, and proposes a dynamic scheduling system and method for the production of disinfectant tissues. The system includes: a data preparation module and an epidemic public opinion analysis module, which are responsible for collecting and analyzing information related to epidemics in the network, and providing epidemic public opinion analysis results in different regions; a production process monitoring module and a system scheduling module, which, in addition to collecting public opinion analysis results, also collect specific production information of each link in the production process of disinfectant tissues, and provide a production scheduling strategy that maximizes benefits based on public opinion results and production information. The present invention adjusts the output rate and orders of the production links based on public opinion results. Compared with traditional scheduling methods, the advantage of the present invention is that it takes into account the factors of epidemic public opinion. The sales of disinfectant wet tissues have a great positive correlation with whether there is an epidemic disease. Integrating public opinion information on epidemics into production scheduling can help companies seize the market faster to increase profits.

Description

Technical Field

[0001] The invention relates to the technical field of production scheduling, and in particular to a dynamic scheduling system and method for the production of disinfected paper towels. Background Art

[0002] The production process of disinfectant tissues includes multiple process links, such as raw material supply, disinfectant preparation, coating, cutting and packaging, and has strict requirements on hygiene, safety, efficiency, etc. In the context of large fluctuations in market demand and diversified product development, traditional static scheduling is difficult to adapt to the rapidly changing production environment, resulting in problems such as low production efficiency, waste of resources and delivery delays.

[0003] Disinfectant wipes are a product that is easily affected by epidemics. When an epidemic is prevalent, the demand for disinfectant wipes will increase significantly, but this factor has time uncertainty and regional uncertainty. The traditional scheduling method is to analyze the influencing factors in the production process, such as staff scheduling, machine operation, etc. The main purpose of this type of method is to optimize the scheduling of production links and does not consider social factors such as epidemics. The entire product production cycle is determined by the signed orders, and the production model is passive production, which is not conducive to seizing market opportunities.

[0004] Therefore, how to provide a dynamic scheduling and production strategy for disinfectant paper towels guided by epidemic public opinion to improve corporate production benefits is a technical problem that needs to be solved urgently. Summary of the invention

[0005] In order to solve the above-mentioned problems of the prior art, the present invention provides a dynamic scheduling system and method for the production of disinfectant paper towels, aiming to realize dynamic scheduling of the production of disinfectant paper towels based on epidemic public opinion and enhance the production benefits of enterprises.

[0006] The present invention provides a dynamic scheduling system for the production of disinfected tissues, comprising:

[0007] A data preparation module, wherein the data preparation module is configured to obtain epidemic-related information, process the epidemic-related information, generate a plurality of epidemic public opinion data containing keywords and content, and construct an epidemic public opinion data set;

[0008] An epidemic public opinion analysis module, wherein the epidemic public opinion analysis module is configured to score the attention level of the current epidemic public opinion according to the epidemic public opinion data set, and use the attention level score as the epidemic public opinion analysis result;

[0009] A production process monitoring module, wherein the production process monitoring module is configured to obtain production monitoring parameters, and construct an optimization function of production inventory and production profit according to the production monitoring parameters, the epidemic public opinion analysis results and the current production order;

[0010] A system scheduling module is configured to solve the optimization function with the goal of minimizing production inventory and maximizing production profit, obtain a production scheduling strategy, and execute production scheduling using the production scheduling strategy.

[0011] Optionally, the data preparation module specifically includes:

[0012] A data collection unit, wherein the data collection unit is configured to collect and store data using preset epidemic keywords to obtain epidemic-related information; wherein the epidemic-related information includes epidemic keywords and content;

[0013] The knowledge extraction unit is configured to merge the epidemic keywords and content from the same source to generate a plurality of epidemic public opinion data containing keywords and content to construct an epidemic public opinion data set.

[0014] Optionally, the data preparation module further includes:

[0015] An emotion dimension value determination unit, wherein the emotion dimension value determination unit is configured to define six emotion dimension values, namely desirable, undesirable, praiseworthy, blameworthy, certain, and uncertain, to represent cognitive inducing conditions as branch inputs of a mask encoding layer of a self-attention mechanism;

[0016] An auxiliary word extraction unit is configured to extract words expressing emotional opinions in each piece of epidemic public opinion data as auxiliary words.

[0017] Optionally, the epidemic public opinion analysis module specifically includes:

[0018] A position coding layer, wherein the position coding layer is configured to use Bert to judge the entity relationship in each piece of epidemic public opinion data to obtain the master-slave relationship between different entities;

[0019] A mask coding layer based on a self-attention mechanism, wherein the mask coding layer based on the self-attention mechanism is configured to obtain cognitive inducing conditions of six emotion dimension values, give corresponding weight values ​​according to the matching degree between the cognitive inducing conditions and the entity, and perform Transformer coding;

[0020] A linear classification layer, wherein the linear classification layer is configured to generate a current epidemic public opinion attention score as an epidemic public opinion analysis result according to the Transformer encoded data;

[0021] The adaptive fusion unit is configured to provide the auxiliary words output by the data preparation module and the attention score output by the previous linear classification layer as preconditions to the mask encoding layer based on the self-attention mechanism.

[0022] Optionally, the production process monitoring module specifically includes:

[0023] A production monitoring parameter acquisition unit, wherein the production monitoring parameter acquisition unit is configured to obtain production monitoring parameters in the production process of disinfectant tissues;

[0024] Among them, the disinfectant paper towel production process includes raw material pretreatment, pulp board preparation, paper towel preparation, and disinfectant spraying, and the production monitoring parameters include the output rate and equipment maintenance rate of each disinfectant paper towel production process.

[0025] Optionally, the production process monitoring module further includes:

[0026] An epidemic judgment unit, the epidemic judgment unit is configured to obtain an epidemic public opinion analysis result generated by the epidemic public opinion analysis module in the previous scheduling period, and judge whether there is an epidemic in the current scheduling period based on the attention score corresponding to the epidemic public opinion analysis result and a preset attention score;

[0027] An epidemic information extraction unit, wherein the epidemic information extraction unit is configured to obtain all epidemic public opinion data with an attention score higher than a preset attention score, use pre-trained Bert to obtain instance relationships, and use template matching to obtain epidemic information; wherein the epidemic information includes the time and place of the epidemic.

[0028] Optionally, the production process monitoring module further includes:

[0029] Address coincidence judgment unit;

[0030] Among them, the address coincidence judgment unit is configured to analyze the scheduled orders to determine whether the order time and address in the scheduled orders coincide with the time and place of the epidemic, and if so, output the coincident time address.

[0031] Optionally, the production process monitoring module further includes:

[0032] Optimize function building unit;

[0033] The optimization function establishment unit is configured to construct a first optimization function of production inventory and a second optimization function of production profit according to the production monitoring parameters, the epidemic public opinion analysis results and the current production scheduling order;

[0034] The expressions of the first optimization function and the second optimization function are specifically:

[0035] ;

[0036] ;

[0037] in, Represents the output of each link. This parameter is determined by the output rate and equipment maintenance rate collected by the production process monitoring module. Indicates the finished product conversion rate of each link, Indicates the expected sales volume of the order. It represents the ideal profit that each link of production can bring. represents the production cost of each link, is the order set, is the order collection of the public opinion area. This is the order collection for non-public opinion areas. is the fixed cost (machine operation) of each production link under different orders, For labor costs, The amount of damage to the product storage, If the public opinion area conditions are met, the former will be executed, and if they are not met, the latter will be executed. is the profit attenuation coefficient, t represents the tth order, and j represents the jth link.

[0038] Optionally, the system scheduling module specifically includes:

[0039] An optimization function solving unit, wherein the optimization function solving unit is configured to solve the constructed optimization function using a particle swarm optimization algorithm, and to produce an order region adjustment strategy and a link output rate adjustment strategy with the goal of minimizing production inventory and maximizing production profit;

[0040] The system scheduling unit is configured to send the output order area adjustment strategy and link output rate adjustment strategy and the epidemic public opinion data set as the final production scheduling strategy to the management personnel.

[0041] The present invention also provides a dynamic scheduling method for the production of disinfected paper towels, the method comprising:

[0042] S1: Obtain epidemic-related information, process the epidemic-related information, generate several pieces of epidemic public opinion data containing keywords and content, and construct an epidemic public opinion dataset;

[0043] S2: According to the epidemic public opinion dataset, the current epidemic public opinion is scored for attention, and the attention score is used as the epidemic public opinion analysis result;

[0044] S3: Obtain production monitoring parameters, and construct an optimization function of production inventory and production profit according to the production monitoring parameters, the epidemic public opinion analysis results and the current production order;

[0045] S4: solving the optimization function with the goal of minimizing production inventory and maximizing production profit, obtaining a production scheduling strategy, and executing production scheduling using the production scheduling strategy.

[0046] The beneficial effects of the present invention are: a dynamic scheduling system and method for the production of disinfectant paper towels are proposed, the system includes: a data preparation module and an epidemic public opinion analysis module, which are responsible for collecting and analyzing current news, comments, public policies and other information related to epidemics on the network, and providing the results of epidemic public opinion analysis in different regions, so that the system scheduling module can provide a production scheduling strategy based on the public opinion analysis results; a production process monitoring module and a system scheduling module, in addition to collecting the public opinion analysis results, will also collect specific production information of each link in the production process of disinfectant paper towels, and provide a production scheduling strategy that maximizes benefits based on the public opinion results and production information. The present invention obtains whether there is public opinion related to epidemics in each region during a preset period of time, and then adjusts the output rate and orders of the production links based on the public opinion results. Compared with the traditional scheduling method, the advantage is that the factor of epidemic public opinion is taken into account. The sales of disinfectant wet wipes have a great positive correlation with whether there is an epidemic disease. Integrating public opinion information on epidemics into production scheduling can help companies seize the market faster to increase profits. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 This is a schematic diagram of the structure of the dynamic scheduling system for disinfected tissue production provided in this embodiment.

[0048] Figure 2 This is a schematic diagram of the structure of the epidemic public opinion analysis module provided in this embodiment.

[0049] Figure 3 A schematic flow chart of the dynamic scheduling method for the production of disinfected tissues provided in this embodiment.

[0050] Reference numerals:

[0051] 10-Data preparation module; 20-Epidemic public opinion analysis module; 30-Production process monitoring module; 40-System scheduling module. DETAILED DESCRIPTION

[0052] 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 only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0053] Embodiment 1:

[0054] like Figure 1 As shown, a dynamic scheduling system for the production of disinfectant paper towels includes: a data preparation module 10, the data preparation module 10 is configured to obtain epidemic-related information, and process the epidemic-related information to generate a number of epidemic public opinion data containing keywords and content to construct an epidemic public opinion data set; an epidemic public opinion analysis module 20, the epidemic public opinion analysis module 20 is configured to score the attention of the current epidemic public opinion according to the epidemic public opinion data set, and use the attention score as the epidemic public opinion analysis result; a production process monitoring module 30, the production process monitoring module 30 is configured to obtain production monitoring parameters, and construct an optimization function of production inventory and production profit according to the production monitoring parameters, the epidemic public opinion analysis result and the current production order; a system scheduling module 40, the system scheduling module 40 is configured to solve the optimization function with the goal of minimizing production inventory and maximizing production profit, obtain a production scheduling strategy, and use the production scheduling strategy to perform production scheduling.

[0055] It should be noted that the traditional scheduling method is to analyze the influencing factors in the production process, such as the staff's shift schedule, the operation of the machinery, etc. The main purpose of this type of method is to optimize the scheduling of the production link without considering social factors such as epidemics. The production cycle of the entire product is determined by the signed order, and the production mode is passive production, which is not conducive to seizing the market opportunity. In order to solve the above problems, this embodiment uses the data preparation module and the epidemic public opinion analysis module to collect and analyze the current news, comments, public policies and other information related to the epidemic in the network, and gives the epidemic public opinion analysis results in different regions, so that the system scheduling module can give a production scheduling strategy based on the public opinion analysis results; using the production process monitoring module and the system scheduling module, in addition to collecting the public opinion analysis results, it will also collect the specific production information of each link in the production process of disinfection paper towels, and give a production scheduling strategy that maximizes the benefits based on the public opinion results and production information. Therefore, the dynamic scheduling method of this embodiment dynamically adjusts the production plan by real-time monitoring of the resource status and production progress in the production process, combined with optimization algorithms and intelligent scheduling technology, to ensure the efficient operation of the production line. By obtaining whether there is epidemic-related public opinion in various regions during a preset period of time, and then adjusting the output rate and orders of the production process based on the public opinion results, the advantage compared to the traditional scheduling method is that the factor of epidemic public opinion is taken into consideration. The sales of disinfectant wet wipes have a great positive correlation with whether there is an epidemic disease. Integrating epidemic public opinion information into production scheduling can help companies seize the market faster to increase profits.

[0056] In a preferred embodiment, the data preparation module specifically includes: a data collection unit, which is configured to collect and store data using preset epidemic keywords to obtain epidemic-related information; wherein the epidemic-related information includes epidemic keywords and content; a knowledge extraction unit, which is configured to merge epidemic keywords and content from the same source to generate a number of epidemic public opinion data containing keywords and content to construct an epidemic public opinion data set.

[0057] On this basis, the data preparation module also includes: an emotion dimension value determination unit, which is configured to define six emotion dimension values ​​of desirable, undesirable, praiseworthy, blameworthy, certain, and uncertain to represent cognitive inducing conditions, as branch inputs of the mask encoding layer of the self-attention mechanism; an auxiliary word extraction unit, which is configured to extract words expressing emotional opinions in each piece of epidemic public opinion data as auxiliary words.

[0058] In this embodiment, the data preparation module is used to collect data from news websites, social media platforms, forums and question-and-answer platforms, blogs and self-media, government and institutional websites. In practical applications, Scrapy can be used as a data collection framework to collect relevant information using common epidemic-related nouns as keywords. The specific steps are: Step 1: Set keywords, such as virus name, symptoms, vaccines, treatment, epidemic prevention and control, etc.; Step 2: Set the initial network address, and data collection will first start from the set address; Step 3: Define the logic of finding the next page in the parsing function, and when the initial network address content is collected, it will automatically find the next page for content collection; Step 4: Store the collected content, specifically the storage fields include crawling time, website source, title, content, release time, and keywords.

[0059] After that, knowledge is extracted and extracted from the stored data. In practical applications, the data in the two storage fields of keywords and content are used as analysis content. ,in Indicates the combined content of the first acquired keyword and content, such as "New Coronavirus & New Coronavirus infection is an infectious disease caused by the new coronavirus (SARS-CoV-2, hereinafter referred to as the new coronavirus). The new coronavirus belongs to the β coronavirus and is sensitive to ultraviolet rays and heat...", and the special mark & ​​is used to separate the keyword and content.

[0060] At the same time, the data preparation module is also used to define the emotional dimension values ​​and extract auxiliary words from the data. In practical applications, for the definition of emotional dimension values, six emotional dimension values, namely desirable, undesirable, praiseworthy, blameworthy, certain, and uncertain, are used to represent cognitive inducing conditions, and they are used as branch inputs of the mask encoding layer of the self-attention mechanism; for the extraction of auxiliary words, words that directly express emotional opinions, such as "disaster", "congratulatory", and "admiration", are retrieved in each analyzed content and used as auxiliary words.

[0061] In a preferred embodiment, the epidemic public opinion analysis module specifically includes: a position encoding layer, which is configured to use Bert to judge the entity relationship in each epidemic public opinion data to obtain the master-slave relationship between different entities; a mask encoding layer based on a self-attention mechanism, which is configured to obtain the cognitive inducing conditions of the six emotional dimension values, give corresponding weight values ​​according to the matching degree between the cognitive inducing conditions and the entities, and perform Transformer encoding; a linear classification layer, which is configured to generate the attention score of the current epidemic public opinion as the epidemic public opinion analysis result based on the Transformer encoded data; an adaptive fusion unit, which is configured to provide the auxiliary words output by the data preparation module and the attention score output by the previous linear classification layer as preconditions to the mask encoding layer based on the self-attention mechanism.

[0062] In this embodiment, Figure 2 As shown in the figure, the position encoding layer is responsible for introducing the relative or absolute position of the elements in the sequence. The position encoding layer can help the mask encoding layer based on the self-attention mechanism understand the order of the sequence data, specifically the order relationship between words. The mask encoding layer based on the self-attention mechanism uses an extended matrix to avoid the impact of non-target content on public opinion analysis. Considering that in some websites, due to page editing problems, multiple contents are often placed closely together. The data collection unit cannot distinguish this situation when acquiring content, and the cost of manual screening is too high (using script rules for filtering may damage the target content and cannot guarantee sufficient filtering). The working steps of this module are as follows: Step 1: First, use Bert to judge the entity relationship and obtain the master-slave relationship between different entities; Step 2: Obtain the induced condition; Step 3: If the subject and the induced condition match highly, a weight of 1 is given, and if the match is not high, a weight of 0 is given. The specific expression is: Step 4: Encode through Transformer.

[0063] After that, the encoded data is finally passed through the linear classification layer to give an attention score of 0 to 9. The adaptive fusion layer is used to provide pre-information for the inducing conditions, which is composed of auxiliary words and the output of the previous linear classification layer. Finally, the epidemic public opinion analysis module will give the output results to the system scheduling module.

[0064] Therefore, this embodiment collects, processes and analyzes information about epidemics (such as current news, comments, public policies, etc.) on the Internet through data collection, rule construction, knowledge extraction and public opinion analysis. The collected and processed data are used for epidemic public opinion analysis, and the results of the epidemic public opinion analysis are used to output to the system scheduling module, so that the system scheduling module can provide a production scheduling strategy based on the public opinion analysis results, and realize a production scheduling strategy that maximizes benefits based on public opinion results and production information.

[0065] In a preferred embodiment, the production process monitoring module specifically includes: a production monitoring parameter collection unit, which is configured to obtain production monitoring parameters in the disinfectant paper towel production link; wherein, the disinfectant paper towel production link includes raw material pretreatment, pulp board preparation, paper towel preparation, and disinfectant spraying, and the production monitoring parameters include the output rate and equipment maintenance rate of each disinfectant paper towel production link.

[0066] On this basis, the production process monitoring module also includes: an epidemic judgment unit, which is configured to obtain the epidemic public opinion analysis results generated by the epidemic public opinion analysis module in the previous scheduling cycle, and judge whether there is an epidemic in the current scheduling cycle based on the attention score corresponding to the epidemic public opinion analysis results and the preset attention score; an epidemic information extraction unit, which is configured to obtain all epidemic public opinion data with attention scores higher than the preset attention score, use pre-trained Bert to obtain instance relationships, and use template matching to obtain epidemic information; wherein, the epidemic information includes the time and place of the epidemic.

[0067] On this basis, the production process monitoring module also includes: an address coincidence judgment unit; wherein the address coincidence judgment unit is configured to analyze the scheduled orders to determine whether the order time and address in the scheduled orders coincide with the time and place of the epidemic, and if so, output the coincident time address.

[0068] Furthermore, the production process monitoring module also includes: an optimization function establishment unit; wherein the optimization function establishment unit is configured to construct a first optimization function of production inventory and a second optimization function of production profit based on the production monitoring parameters, the epidemic public opinion analysis results and the current production scheduling orders.

[0069] In this embodiment, the production process monitoring module collects monitoring parameters (including output rate and equipment maintenance rate) of five links, including raw material pretreatment, pulp board preparation, paper towel preparation, disinfectant spraying, and packaging, through the edge computing box; wherein, output rate refers to the products that can be processed per unit time, and equipment maintenance rate is proportional to the equipment operation time. The production process monitoring module is also used to construct a first optimization function of production inventory and a second optimization function of production profit by obtaining monitoring parameters, attention scores, and scheduled production orders.

[0070] In practical applications, first determine whether there is data with high attention scores (more than 5 points) in the public opinion analysis results generated in the previous scheduling cycle. If the data with high attention scores exceeds a certain number, it is considered that there is an epidemic situation at present. Obtain all data with high scores, use pre-trained Bert to obtain instance relationships again, and use template matching to obtain time and place; then analyze the scheduled orders to determine whether the order address overlaps with the address in the public opinion data. If there is an overlap, output the overlapping address; finally, construct an optimization function to minimize the inventory holding and maximize the profit. The inventory refers to the possible inventory per unit time, and the profit refers to the possible profit per unit time. Among them, the expressions of the first optimization function and the second optimization function are specifically:

[0071] ;

[0072] ;

[0073] in, Represents the output of each link. This parameter is determined by the output rate and equipment maintenance rate collected by the production process monitoring module. Indicates the finished product conversion rate of each link, Indicates the expected sales volume of the order. It represents the ideal profit that each link of production can bring. represents the production cost of each link, is the order set, is the order collection of the public opinion area. This is the order collection for non-public opinion areas. is the fixed cost (machine operation) of each production link under different orders, For labor costs, The amount of damage to the product storage, If the public opinion area conditions are met, the former will be executed, and if they are not met, the latter will be executed. is the profit attenuation coefficient, t represents the tth order, and j represents the jth link.

[0074] In a preferred embodiment, the system scheduling module specifically includes: an optimization function solving unit, which is configured to use a particle swarm optimization algorithm to solve the constructed optimization function, and to produce an order area adjustment strategy and a link output rate adjustment strategy with the goal of minimizing production inventory and maximizing production profit; a system scheduling unit, which is configured to send the output order area adjustment strategy and link output rate adjustment strategy and the epidemic public opinion data set as the final production scheduling strategy to management personnel.

[0075] In this embodiment, the particle swarm optimization algorithm is used to solve the optimization function, and the output is the order area adjustment and link output rate adjustment; (order area adjustment refers to adjusting orders from non-public opinion areas to public opinion areas, and link output rate adjustment refers to adjusting the length of time the equipment works), and the public opinion data is classified and stored according to the region, and both are regarded as the final strategy and sent to the management personnel for reference. Therefore, by obtaining whether there is epidemic-related public opinion in each region during the preset period, and then adjusting the output rate and orders of the production link based on the public opinion results, the advantage compared to the traditional scheduling method is that the factor of epidemic public opinion is considered. The sales of disinfectant wet wipes have a great positive correlation with whether there is an epidemic disease. Integrating public opinion information on epidemics into production scheduling can help companies seize the market faster to increase profits.

[0076] Embodiment 2:

[0077] Reference Figure 3 , Figure 3 A schematic flow chart of a dynamic scheduling method for the production of disinfected tissue provided in an embodiment of the present invention.

[0078] like Figure 3 As shown, a dynamic scheduling method for the production of disinfected tissue paper is used in the dynamic scheduling system for the production of disinfected tissue paper as described above, comprising:

[0079] S1: Obtain epidemic-related information, process the epidemic-related information, generate several pieces of epidemic public opinion data containing keywords and content, and construct an epidemic public opinion dataset;

[0080] S2: According to the epidemic public opinion dataset, the current epidemic public opinion is scored for attention, and the attention score is used as the epidemic public opinion analysis result;

[0081] S3: Obtain production monitoring parameters, and construct an optimization function of production inventory and production profit according to the production monitoring parameters, the epidemic public opinion analysis results and the current production order;

[0082] S4: solving the optimization function with the goal of minimizing production inventory and maximizing production profit, obtaining a production scheduling strategy, and executing production scheduling using the production scheduling strategy.

[0083] This embodiment provides a dynamic scheduling method for the production of disinfectant tissues. By adjusting the output rate and orders of the production links based on the public opinion results, compared with the traditional scheduling method, the advantage is that the factor of epidemic public opinion is taken into account. The sales of disinfectant wet tissues have a great positive correlation with whether there is an epidemic disease. Integrating the public opinion information of the epidemic into the production scheduling can help enterprises seize the market faster to increase profits.

[0084] The specific implementation of the dynamic scheduling method for disinfectant tissue production of the present application is basically the same as the above-mentioned dynamic scheduling system embodiment for disinfectant tissue production, and will not be repeated here.

[0085] In the description of the embodiments of the present invention, it should be understood that the terms "upper", "lower", "front", "back", "left", "right", "vertical", "horizontal", "center", "top", "bottom", "top", "bottom", "inside", "outside", "inner side", "outer side" and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present invention. Among them, "inside" refers to an internal or enclosed area or space. "Periphery" refers to the area surrounding a specific component or a specific area.

[0086] In the description of the embodiments of the present invention, the terms "first", "second", "third", and "fourth" are used for descriptive purposes only and are not to be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first", "second", "third", and "fourth" may explicitly or implicitly include one or more of the features. In the description of the present invention, unless otherwise specified, "multiple" means two or more.

[0087] In the description of the embodiments of the present invention, it should be noted that, unless otherwise clearly specified and limited, the terms "install", "connect", "connect", and "assemble" 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 direct connection, or an indirect connection through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0088] In the description of the embodiments of the present invention, specific features, structures, materials or characteristics may be combined in a suitable manner in any one or more embodiments or examples.

[0089] In the description of the embodiments of the present invention, it should be understood that "-" and "~" represent a range between two values, and the range includes the endpoints. For example: "AB" represents a range greater than or equal to A and less than or equal to B. "A~B" represents a range greater than or equal to A and less than or equal to B.

[0090] In the description of the embodiments of the present invention, the term "and / or" herein is merely a description of the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B may represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " herein generally indicates that the associated objects before and after are in an "or" relationship.

[0091] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A dynamic scheduling system for the production of disinfected tissues, characterized in that: include: A data preparation module, wherein the data preparation module is configured to obtain epidemic-related information, process the epidemic-related information, generate a plurality of epidemic public opinion data containing keywords and content, and construct an epidemic public opinion data set; An epidemic public opinion analysis module, wherein the epidemic public opinion analysis module is configured to score the attention level of the current epidemic public opinion according to the epidemic public opinion data set, and use the attention level score as the epidemic public opinion analysis result; A production process monitoring module, wherein the production process monitoring module is configured to obtain production monitoring parameters, and construct an optimization function of production inventory and production profit according to the production monitoring parameters, the epidemic public opinion analysis results and the current production order; The production process monitoring module specifically includes: A production monitoring parameter acquisition unit, wherein the production monitoring parameter acquisition unit is configured to obtain production monitoring parameters in the production process of disinfectant tissues; The disinfectant tissue production process includes raw material pretreatment, pulp board preparation, tissue preparation, and disinfectant spraying, and the production monitoring parameters include the output rate and equipment maintenance rate of each disinfectant tissue production process; The production process monitoring module further includes: An epidemic judgment unit, the epidemic judgment unit is configured to obtain an epidemic public opinion analysis result generated by the epidemic public opinion analysis module in the previous scheduling period, and judge whether there is an epidemic in the current scheduling period based on the attention score corresponding to the epidemic public opinion analysis result and a preset attention score; An epidemic information extraction unit, the epidemic information extraction unit is configured to obtain all epidemic public opinion data with a degree of attention higher than a preset degree of attention, obtain instance relations using pre-trained Bert, and obtain epidemic information using template matching; wherein the epidemic information includes the time and place of the epidemic; The production process monitoring module further includes: Address coincidence judgment unit; Wherein, the address coincidence judgment unit is configured to analyze the scheduled orders to determine whether the order time and address in the scheduled orders coincide with the time and place where the epidemic exists, and if so, output the coincident time and address; The production process monitoring module further includes: Optimize function building unit; The optimization function establishment unit is configured to construct a first optimization function of production inventory and a second optimization function of production profit according to the production monitoring parameters, the epidemic public opinion analysis results and the current production scheduling order; The expressions of the first optimization function and the second optimization function are specifically: ； ； in, Represents the output of each link. This parameter is determined by the output rate and equipment maintenance rate collected by the production process monitoring module. Indicates the finished product conversion rate of each link, Indicates the expected sales volume of the order. It represents the ideal profit that each link of production can bring. represents the production cost of each link, is the order set, is the order collection of the public opinion area. This is the order collection for non-public opinion areas. is the fixed cost of each production link under different orders, For labor costs, The amount of damage to the product storage, If the public opinion area conditions are met, the former will be executed, and if they are not met, the latter will be executed. is the profit attenuation coefficient, t represents the t-th order, and j represents the j-th link; The system scheduling module specifically includes: An optimization function solving unit, wherein the optimization function solving unit is configured to solve the constructed optimization function using a particle swarm optimization algorithm, and to produce an order region adjustment strategy and a link output rate adjustment strategy with the goal of minimizing production inventory and maximizing production profit; A system scheduling unit, wherein the system scheduling unit is configured to send the output order region adjustment strategy and link output rate adjustment strategy and the epidemic public opinion data set as the final production scheduling strategy to the management personnel; The system scheduling module is configured to solve the optimization function with the goal of minimizing production inventory and maximizing production profit, obtain a production scheduling strategy, and execute production scheduling using the production scheduling strategy.

2. The dynamic scheduling system for disinfection tissue production according to claim 1 is characterized in that: The data preparation module specifically includes: A data collection unit, wherein the data collection unit is configured to collect and store data using preset epidemic keywords to obtain epidemic-related information; wherein the epidemic-related information includes epidemic keywords and content; The knowledge extraction unit is configured to merge the epidemic keywords and content from the same source to generate a plurality of epidemic public opinion data containing keywords and content to construct an epidemic public opinion data set.

3. The dynamic scheduling system for disinfection tissue production according to claim 2 is characterized in that: The data preparation module further includes: An emotion dimension value determination unit, wherein the emotion dimension value determination unit is configured to define six emotion dimension values, namely desirable, undesirable, praiseworthy, blameworthy, certain, and uncertain, to represent cognitive inducing conditions as branch inputs of a mask encoding layer of a self-attention mechanism; An auxiliary word extraction unit is configured to extract words expressing emotional opinions in each piece of epidemic public opinion data as auxiliary words.

4. The dynamic scheduling system for disinfection tissue production according to claim 3 is characterized in that: The epidemic public opinion analysis module specifically includes: A position coding layer, wherein the position coding layer is configured to use Bert to judge the entity relationship in each piece of epidemic public opinion data to obtain the master-slave relationship between different entities; A mask coding layer based on a self-attention mechanism, wherein the mask coding layer based on the self-attention mechanism is configured to obtain cognitive inducing conditions of six emotion dimension values, give corresponding weight values ​​according to the matching degree between the cognitive inducing conditions and the entity, and perform Transformer coding; A linear classification layer, wherein the linear classification layer is configured to generate a current epidemic public opinion attention score as an epidemic public opinion analysis result according to the Transformer encoded data; The adaptive fusion unit is configured to provide the auxiliary words output by the data preparation module and the attention score output by the previous linear classification layer as preconditions to the mask encoding layer based on the self-attention mechanism.

5. A dynamic scheduling method for the production of disinfected tissue paper used in the dynamic scheduling system for the production of disinfected tissue paper as claimed in any one of claims 1 to 4, characterized in that: The method comprises: S1: Obtain epidemic-related information, process the epidemic-related information, generate several pieces of epidemic public opinion data containing keywords and content, and construct an epidemic public opinion dataset; S2: According to the epidemic public opinion dataset, the current epidemic public opinion is scored for attention, and the attention score is used as the epidemic public opinion analysis result; S3: Obtain production monitoring parameters, and construct an optimization function of production inventory and production profit according to the production monitoring parameters, the epidemic public opinion analysis results and the current production order; S4: Solving the optimization function with the goal of minimizing production inventory and maximizing production profit, obtaining a production scheduling strategy, and executing production scheduling using the production scheduling strategy.

Images