Cloud printing order resource dynamic allocation system based on artificial intelligence algorithm

Abstract

The invention relates to the technical field of artificial intelligence, in particular to a cloud printing order resource dynamic allocation system based on an artificial intelligence algorithm, which comprises an order analysis and clustering module, a cloud printer performance state sensing module, an order matching and allocation strategy making module and a real-time monitoring and dynamic adjustment module. The order analysis and clustering module extracts order features by using a composite technology, carries out clustering analysis and determines the emergency degree of the order features; the cloud printer performance state sensing module collects information through the Internet of Things and a sensor network, monitors the state of the cloud printer in real time and predicts the fault probability; the order matching and distribution strategy making module optimizes an order distribution strategy according to the order emergency degree and the cloud printer state so as to improve the efficiency; the real-time monitoring and dynamic adjusting module monitors the working efficiency of the cloud printer in real time, compares order requirements and adjusts the order requirements in time, and it is ensured that the printing task is completed smoothly. The method is used for solving the technical problem that the current cloud printing order processing effect is poor.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to a cloud printing order resource dynamic allocation system based on artificial intelligence algorithm. Background Art

[0002] In the current cloud printing order processing, the following problems still exist: low order processing efficiency, the whole process from order receiving, allocation to printing completion takes a long time, resulting in long user waiting time, high degree of manual participation, low level of automation, affecting overall efficiency; inaccurate prediction of cloud printer faults, resulting in false alarms or missed alarms, affecting equipment maintenance plans, untimely fault handling, prolonged equipment downtime, affecting printing service continuity; unreasonable order allocation, resulting in some printers being overloaded while other printers are idle, and uneven resource utilization; untimely handling of exceptions during printing, and failure to respond quickly when paper jams, insufficient ink, and other exceptions occur during printing; energy waste, the printer remains in operation during non-working hours or low load, resulting in energy waste. Therefore, a series of targeted methods are urgently needed to deal with these problems in order to improve the efficiency and level of cloud printing order processing. Summary of the invention

[0003] The purpose of the present invention is to solve the problems in the background technology and to propose a cloud printing order resource dynamic allocation system based on artificial intelligence algorithm.

[0004] In order to achieve the above object, the present invention adopts the following technical solutions: A cloud printing order resource dynamic allocation system based on artificial intelligence algorithm, including: order analysis and clustering module, cloud printer performance status perception module, order matching and allocation strategy formulation module and real-time monitoring and dynamic adjustment module; Order analysis and clustering module: Use composite technology to extract order features, use clustering algorithms to classify orders based on the extracted features, determine the urgency of orders based on multi-dimensional processing factors of orders, calculate the urgency coefficient and mark it on the clustered order group; composite technology includes image recognition technology and natural language processing technology; Cloud printer performance status perception module: collects cloud printer status information through IoT technology and sensor networks, and embeds intelligent diagnostic units to monitor component operating parameters in real time. At the same time, it uses historical fault records and machine learning algorithms to predict the probability of future failures of cloud printers, providing a basis for cloud printer availability assessment; Order matching and allocation strategy formulation module: For orders with high urgency coefficients, cloud printers with the best performance and low failure probability are matched first, and batch processing capabilities are considered to avoid delays; for orders with low urgency coefficients, the idle time and energy consumption of cloud printers are predicted, and allocation is optimized to maximize energy efficiency; Real-time monitoring and dynamic adjustment module: monitor the working efficiency of cloud printers in real time and conduct comparative analysis. If any abnormality is found, the order will be reallocated to other cloud printers.

[0005] Furthermore, the order analysis and clustering module uses composite technology to extract order features, classifies orders based on the extracted features using clustering algorithms, determines the urgency of orders based on multi-dimensional processing factors of orders, and calculates the urgency coefficient and marks it on the clustered order group. The process includes: By combining image recognition and natural language processing technology, we extract features from the content of each order: for orders containing images or graphics, we use convolutional neural networks to decompose the images and identify the complexity of the graphics, the color pattern of the images, and the features of the resolution of the images; for the text part of the order, we use the word vector model to convert the text into vector representation, analyze the text layout format, the semantic features of the text content, and the key information of the text quantity; various feature information obtained through image recognition and natural language processing are integrated into a complete order feature vector; Based on the extracted order features, a clustering algorithm is used to cluster the feature vectors of all orders, taking the distance between the order feature vectors as the similarity measurement standard, and the orders with similar distances are classified into one category; among them, orders with similar distances are orders with similar features: when the multi-dimensional differences of the order feature vectors in terms of graphic complexity, color mode, and text key information are all less than the set clustering threshold, these orders are classified into the same cluster; in the clustering process, the center and threshold of the cluster are continuously adjusted according to the historical order data to adapt to the distribution changes of different types of orders; According to the classification results of the order feature vector by the clustering algorithm, the multi-dimensional processing factors of the order are further integrated, and the urgency coefficient is obtained through weighted calculation. The coefficient is marked on the clustered order group to reflect the urgency of the order. Specifically, it includes: extracting the timestamp of order submission and calculating the interval from submission to the current time; identifying the priority identifier set by the customer in the order, where the priority identifier set by the customer is divided into three levels: high, medium and low; Combining multi-dimensional processing factors, a weighted calculation method is adopted to obtain an urgency coefficient, and the value range of the urgency coefficient is set; wherein, the multi-dimensional processing factors of orders include order submission time, customer set priority, order attributes and order size; The urgency coefficient is obtained and marked on each clustered order group.

[0006] Furthermore, the cloud printer performance status perception module collects cloud printer status information through the Internet of Things technology and sensor network, and embeds the intelligent diagnosis unit to monitor component operating parameters in real time, including: Through the Internet of Things technology, a connection is established with each cloud printer connected to the cloud printing service for comprehensive testing; Utilize sensor networks to collect general status information of cloud printers; Embedding an intelligent diagnostic unit inside the cloud printer to evaluate the health of components, wherein the intelligent diagnostic unit is used to monitor the operating parameters of the components inside the cloud printer in real time; All information obtained from the sensor network and intelligent diagnostic unit is integrated to build a performance vector of the cloud printer.

[0007] Furthermore, the process of the cloud printer performance status perception module using historical fault records and machine learning algorithms to predict the future fault probability of the cloud printer includes: Collect historical fault records from each cloud printer's maintenance log or database; Check and handle missing values, outliers, or duplicate records in the data; Extract features related to fault prediction from historical fault records; Use machine learning algorithms to build fault prediction models and complete model training; Get the performance vector of the current cloud printer; record the usage time of the cloud printer and the running time after the last maintenance; Input the performance vector of the current cloud printer, the usage time of the cloud printer, and the running time after the last maintenance into the trained fault prediction model to calculate the probability of each cloud printer failing in the future. The probability value output by the fault prediction model is used as an important basis for the availability evaluation of the cloud printer, where the output probability value ranges from 0 to 1, where 0 represents no fault risk and 1 represents an extremely high fault risk.

[0008] Furthermore, the order matching and allocation strategy formulation module prioritizes cloud printers with the best performance and low failure probability for orders with high urgency coefficients, and considers the process of batch processing capabilities, including: Set the normal operation probability range ,satisfy ; At the same time, set the urgency range ,satisfy , used to quantify the urgency of an order; For emergency coefficients higher than the upper limit of the emergency range The order clustering is used to select the order with the best performance vector and the probability value output by the fault prediction model is lower than the lower limit of the normal operation probability range. List of cloud printers; For the filtered cloud printer list, the batch processing capability of each cloud printer for the current order cluster is further analyzed; wherein the batch processing capability refers to the ability of the cloud printer to process multiple orders or printing tasks within a unit of time.

[0009] Furthermore, the order matching and allocation strategy formulation module predicts the idle time and energy consumption of cloud printers for orders with low urgency coefficients, and the process of optimizing allocation includes: For emergency coefficients below the lower limit of the emergency level range The order clustering is used to obtain the idle time prediction information of all cloud printers. At the same time, the energy consumption of each cloud printer is considered. According to the idle time prediction and energy consumption, the cloud printers that are about to enter a long idle state and currently have high energy consumption are found out, and then the orders with low urgency coefficients are assigned to the cloud printers, and the working mode of the cloud printers is adjusted accordingly.

[0010] Furthermore, the real-time monitoring and dynamic adjustment module monitors the working efficiency of the cloud printer in real time and conducts comparative analysis. If an abnormality is found, the order is reallocated to other cloud printers. The process includes: After the order is assigned to the cloud printer and the printing process is started, the sensor on the cloud printer side monitors the working efficiency of the cloud printer in real time; Compare and analyze the monitored cloud printers’ working efficiency with the original requirements and expected quality standards of the order: If any cloud printer is found to have an abnormality during the printing process during the comparative analysis, immediately suspend the printing task of the order on this cloud printer; Re-evaluate the status of all available cloud printers and reallocate the remaining unprinted orders to other cloud printers; at the same time, adjust the allocation plan for subsequent orders based on abnormal circumstances.

[0011] Compared with the existing technology, the advantages of the present invention providing a cloud printing order resource dynamic allocation system based on artificial intelligence algorithm are: 1. The present invention uses composite technology to extract cloud printing order features, classifies orders based on the extracted features using a clustering algorithm, determines the urgency of the orders based on the multi-dimensional processing factors of the orders, and calculates the urgency coefficient and marks it on the clustered order group, thereby improving the accuracy and efficiency of feature extraction, helping to quickly identify and prioritize orders with high urgency coefficients, and ensuring that key tasks are processed in a timely manner; 2. The present invention collects printer status information through Internet of Things technology and sensor networks, embeds intelligent diagnostic units to monitor component operating parameters in real time, and uses historical fault records and machine learning algorithms to predict the probability of future printer failures, providing a basis for printer availability assessment, ensuring that the operating status of cloud printers is always known, helping to discover and handle potential faults in advance, reduce the occurrence rate of faults, and improve the reliability and stability of cloud printers; by predicting the probability of failure, a more scientific and reasonable maintenance plan can be formulated to reduce unnecessary downtime and maintenance costs, and extend the service life of cloud printers; 3. For orders with high urgency coefficients, priority is given to cloud printers with the best performance and low probability of failure. At the same time, batch processing capabilities are considered to further improve printing efficiency. For orders with low urgency coefficients, the idle time and energy consumption of cloud printers are predicted, and allocation is optimized to maximize energy efficiency, which helps to reduce operating costs and achieve green printing. Through real-time monitoring and dynamic adjustment, the probability of similar anomalies is reduced, ensuring that orders can be completed on time and with high quality, thereby improving customer satisfaction and trust. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Figure 1 This is a module diagram of a cloud printing order resource dynamic allocation system based on artificial intelligence algorithm proposed by the present invention. DETAILED DESCRIPTION

[0013] 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 implementation regulations described 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.

[0014] Reference Figure 1 , a cloud printing order resource dynamic allocation system based on artificial intelligence algorithm, the system includes an order analysis and clustering module, a cloud printer performance status perception module, an order matching and allocation strategy formulation module, and a real-time monitoring and dynamic adjustment module; Order analysis and clustering module: Use composite technology to extract order features, use clustering algorithms to classify orders based on the extracted features, determine the urgency of orders based on multi-dimensional processing factors of orders, calculate the urgency coefficient and mark it on the clustered order group; composite technology includes image recognition technology and natural language processing technology; Cloud printer performance status perception module: collects cloud printer status information through IoT technology and sensor networks, and embeds intelligent diagnostic units to monitor component operating parameters in real time. At the same time, it uses historical fault records and machine learning algorithms to predict the probability of future failures of cloud printers, providing a basis for cloud printer availability assessment; Order matching and allocation strategy formulation module: For orders with high urgency coefficients, cloud printers with the best performance and low failure probability are matched first, and batch processing capabilities are considered to avoid delays; for orders with low urgency coefficients, the idle time and energy consumption of cloud printers are predicted, and allocation is optimized to maximize energy efficiency; Real-time monitoring and dynamic adjustment module: monitor the working efficiency of cloud printers in real time and conduct comparative analysis. If any abnormality is found, the order will be reallocated to other cloud printers.

[0015] The order analysis and clustering module uses composite technology to extract order features, classifies orders based on the extracted features using clustering algorithms, determines the urgency of orders based on multi-dimensional processing factors of orders, calculates the urgency coefficient and marks it on the clustered order group. The steps include: Step 101: Use a combination of image recognition and natural language processing technology to extract features from the content of each order: For the order part containing images or graphics, convolutional neural network is used to decompose the image and identify the complexity of the graphics, the color mode of the image and the characteristics of the resolution of the image. The complexity of the graphics includes the number of lines, color types, and the number of nested layers of the graphics, and the color mode of the image includes RGB, CMYK, etc. For the text part of the order, the word vector model is used to convert the text into a vector representation, and the text layout format, semantic features of the text content, and key information of the text quantity are analyzed. The text layout format includes font type, font size, line spacing setting, paragraph format and other layout details. Through semantic analysis, it is determined whether the text content belongs to a specific category such as technical documents, business documents, etc. At the same time, the total amount of text is counted to obtain the length information of the document; Various feature information obtained through image recognition and natural language processing are integrated into a complete order feature vector, which comprehensively describes the printing demand characteristics of the order; Step 102: Based on the extracted order features, a clustering algorithm is used to perform clustering operations on the feature vectors of all orders, using the distance between the order feature vectors as a similarity measurement standard, and the orders with similar distances are classified into one category; wherein, the orders with similar distances are orders with similar features: When the multi-dimensional differences of order feature vectors in terms of graphic complexity, color pattern, and text key information are all less than the set clustering threshold, these orders are divided into the same cluster. During the clustering process, the center and threshold of the cluster are continuously adjusted according to the historical order data to adapt to the distribution changes of different types of orders. Step 103: Based on the classification result of the order feature vector by the clustering algorithm, the multi-dimensional processing factors of the order are further integrated, and the urgency coefficient is obtained by weighted calculation. The coefficient is marked on the clustered order group to reflect the urgency of the order. The multi-dimensional processing factors of the order include order submission time, customer setting priority, order attributes and order size: Extract the timestamp of order submission and calculate the interval from submission to the current time; Identify the priority flag set by the customer in the order. The priority flag set by the customer is divided into three levels: high, medium, and low, which directly reflect the customer's expectations and needs for the order processing speed. If the customer does not set a flag, the priority is estimated based on the order attributes and order size. The order attributes include but are not limited to business urgent documents, ordinary documents, etc. These attributes can indirectly reflect the urgency of the order. At the same time, the order size is also an important consideration. Large documents may have a relatively low urgency because the processing process may be more complicated and require more time to process. Combining the multi-dimensional processing factors of order submission time, customer-set priority, order attributes, and order size, a weighted calculation method is used to obtain an urgency coefficient, where the urgency coefficient will comprehensively consider multiple dimensions such as the order time interval, customer-set priority (or estimated priority), order attributes, and order size to ensure its accuracy and rationality; Set the value range of the emergency coefficient: 0-1 (0 represents the lowest emergency level, 1 represents the highest emergency level); Obtain the urgency coefficient and mark it on each clustered order group so that subsequent processing and scheduling can be carried out more efficiently and orderly, ensuring that each order can be processed promptly and appropriately according to its urgency; For example, (1) Order feature extraction: For the order part containing images or graphics: Step Q1: Assume that there is an order image, which is represented as a matrix , the elements in the matrix Represents the image at coordinates The pixel value at ; Let the convolution kernel be , whose size is (Assumption ), for each position in the image, the convolutional layer outputs ,in , In the formula, is the coordinate index within the convolution kernel; for example, when hour, ; Through the convolution operation, an image can be decomposed into different feature layers; Step Q2: Set the number of lines of the figure to , the number of color types to , and the number of nested layers of the figure to ; if the figure is a circle nested in a rectangle, the number of lines (the contour line of the circle can be approximately regarded as composed of many small straight lines, assumed to be 10 approximate straight lines here), the number of color types (assumed to be a single color), and the number of nested layers (assumed to be one layer of nesting); define the figure complexity function , that is , In the formula, are the weight coefficients of the number of lines, the number of color types, and the number of nested layers respectively, used to measure the relative importance of the number of lines, the number of color types, and the number of nested layers to the figure complexity; if , then ; Step Q3: Assume the image is in the RGB color mode, then each pixel in the image , where represent the values of the red, green, and blue channels respectively, with a value range of 0 - 255; represent the color mode features by statistically calculating features such as the average value and variance of different color channels in the entire image; Step Q4: Let the number of horizontal pixels of the image be , and the number of vertical pixels be ; assume the number of horizontal pixels of the image , and the number of vertical pixels , then the resolution is expressed as pixels; For the text part in the order, assume the text part in the order is "This is a business document, the font is Song typeface, the font size is 12, the line spacing is 1.5 times the line spacing, the paragraph format is first line indented by 2 characters, the content is mainly about the detailed information of the product order, and the number of words is 50", then the specific processing steps are as follows: Step R1: Use the word vector model. Assume there is a pre-trained word vector model, where each word is mapped to a -dimensional vector space; for the word "business document", assume the mapped vector is ; similarly, the mapped vector of the word "Song typeface" is ; therefore, the entire sentence can be represented as a combination of these word vectors. For example, connect to obtain a long vector ; Step R2: Set the font type to be represented by (here = "Song typeface"), the font size , the line spacing setting , and the paragraph format = "First line indented by 2 characters"; Define the typesetting feature function , that is , In the formula, are the weight coefficients of the font type, font size, line spacing setting, and paragraph format respectively, used to measure the relative importance of the font type, font size, line spacing setting, and paragraph format to the typesetting features; among them, ; Step R3: Since the text content belongs to a business document, mark its semantic category as (assuming the business document category is 1, and other categories have different markings), among which, The value of is obtained according to the predefined semantic category encoding; Step R4: Define the number of characters ; Among them, the number of characters can be directly used as a feature. For example, in subsequent processing, a larger number of characters may mean more detailed order content, which may affect the urgency or processing method of the order, etc.; (2) Order clustering operation: Assume there are three feature vectors of orders , and the dimension of the feature vector is 3 (composed of image complexity, a certain feature of the color mode (such as the average value of the red channel), text typesetting features, semantic features, and the number of characters); Define the distance metric. Arbitrarily select two feature vectors and , then the Euclidean distance is ; Define the clustering threshold , calculate , and ; If , then classify Order 1 and Order 2 into one category; Step Z1: Set the order submission time to , the current time to , the time interval , assume hours, and the time weight is , among which, the time weight represents the relative importance of the order submission time in calculating the emergency coefficient; Step Z2: Known customers set the priority to high priority , priority weight ,in, It is the value mapped according to the priority level set by the customer. Indicates the importance of customer-set priority in the calculation of the urgency factor; Step Z3: If the order attribute is business emergency document, set the value corresponding to business emergency document to , order attribute weight ,in, It is the value obtained by mapping the type of the order attribute. Indicates the relative importance of order attributes in the calculation of the urgency coefficient; Step Z4: The order size is small, and the coefficient corresponding to the size is , order size weight ,in, It is a value mapped according to the size of the order (for example, measured by the number of words, file size, etc.). Indicates the relative importance of order size in the calculation of the urgency coefficient; Step Z5: Calculate the urgency factor based on the order submission time, customer priority, order attributes, and order size. ,Right now .

[0016] The cloud printer performance status perception module collects cloud printer status information through IoT technology and sensor networks, and embeds an intelligent diagnostic unit to monitor component operating parameters in real time. At the same time, the steps of using historical fault records and machine learning algorithms to predict the future failure probability of cloud printers include: Step 201: Establish a connection with each cloud printer connected to the cloud printing service through the Internet of Things technology to conduct a comprehensive test; use the sensor network to collect general status information of the cloud printer; In step 201, the sensor network is a network composed of multiple sensor nodes (including ink level sensors, paper level sensors, temperature sensors, humidity sensors, etc.) distributed in different locations and having different sensing capabilities. These sensor nodes are interconnected through wireless communication, wired communication or hybrid communication to form a collaborative system for real-time monitoring, sensing and collecting various status information of the cloud printer; conventional status information includes the ink level, paper level, temperature, humidity, etc. of the cloud printer; Step 202: embedding an intelligent diagnostic unit inside the cloud printer to evaluate the health status of components; In step 202, the intelligent diagnosis unit is used to monitor the operating parameters of the internal components of the cloud printer in real time. For example, for an inkjet cloud printer, the health of the printhead is evaluated by monitoring the inkjet frequency of the printhead, the consistency of the ink droplet size and other parameters; for a laser cloud printer, the health of the heating component is evaluated by monitoring the stability of the heating temperature and the heating speed and other indicators; Step 203: Integrate all information obtained from the sensor network and the intelligent diagnosis unit (i.e., the general status information of the cloud printer and the operating parameters of the internal components of the cloud printer) to construct a performance vector of the cloud printer, wherein the performance vector includes various aspects of the cloud printer, such as the amount of ink, the amount of paper remaining, the health of the printhead, the efficiency of the heating component, the overall temperature of the cloud printer, the overall humidity of the cloud printer, etc.; Step 204: Collect historical fault records from the maintenance log or database of each cloud printer, wherein the historical fault records include but are not limited to the fault type, fault occurrence time, and detailed maintenance records (such as maintenance time, maintenance content, etc.); Step 205: Check and process missing values, abnormal values ​​or duplicate records in the data; Step 206: extracting features related to fault prediction from historical fault records, such as fault type, fault frequency, maintenance time interval, etc., and may also require converting time-related features, such as converting a timestamp into a specific time interval or time period; Step 207: Use a machine learning algorithm to build a fault prediction model and complete model training: select a random forest algorithm, divide the data set into a training set and a test set based on the data of historical fault records, usually with a ratio of 70% training set and 30% test set (or adjusted according to specific circumstances); use the training set data to train the selected random forest algorithm. During the training process, it may be necessary to adjust the parameters of the model to optimize its performance. Use the test set data to evaluate the trained model, calculate its performance indicators such as accuracy, recall rate, and F1 score, and tune the model according to the evaluation results to improve its prediction performance; Step 208: Obtain the performance vector of the current cloud printer; record the usage time of the cloud printer and the running time after the last maintenance; Step 209: Input the performance vector of the current cloud printer, the usage time of the cloud printer, and the running time after the last maintenance into the trained fault prediction model to calculate the probability of each cloud printer failing in the future (e.g., within the next hour); Step 210: The probability value output by the fault prediction model is used as an important basis for evaluating the availability of the cloud printer, with a value range of 0-1, where 0 indicates no fault risk and 1 indicates an extremely high fault risk; For example, step P1, from Collect historical fault records in the maintenance log or database of the TUV printer; Among them, the historical fault record of each cloud printer includes the fault type (Assuming there are 5 types of faults), fault occurrence time , and maintenance records (including maintenance time and maintenance contents); among which, Indicates the number of cloud printers. Indicates the cloud printer index, Indicates Failure time, for each cloud printer , at most Fault record; Step P2: For missing values ​​in the data, if the time of a certain failure of a printer is missing, fill it in according to the average of the time of the previous and subsequent failures (assuming a reasonable time series pattern); For abnormal values, if the maintenance time is too long or too short and exceeds the normal range, it will be adjusted to the boundary value or processed by other statistical methods; For duplicate records, delete the redundant identical records directly; Step P3: For each printer , the fault frequency is , where is a fixed observation period, and Days, the failure frequency is Indicates the proportion of failure times in the cycle; The fault time Converted to days relative to a fixed start time, the maintenance interval is ,in, Indicates The time interval between the first maintenance and the failure; Building Performance Vectors , including the features related to fault prediction, such as fault frequency and maintenance time interval; Step P4: Collect the The characteristic data of TUV printers (i.e., the constructed performance vector) is divided into a training set and a test set according to the ratio of 70% training set and 30% test set. The training set contains samples, the test set contains samples; Assume the number of decision trees in the random forest model is ,During the training process, other parameters of the random forest model are adjusted according to the data of the training set, such as the maximum depth of each decision tree; For the test set samples, and the number of samples predicted to be faulty is , the number of samples that are actually faulty is , the number of samples correctly predicted as faults is ; Calculate accuracy , recall rate as well as Fraction , where the accuracy Recall rate represents the proportion of samples predicted to be correct to samples predicted to be faulty. It indicates the proportion of correctly predicted fault samples to actual fault samples. The score takes into account the performance indicators of precision and recall; Analyze these evaluation results. If the accuracy is low, you need to increase the number of decision trees. ,If the recall rate is low, it is necessary to adjust the construction rules of the decision tree, etc.; Step P5: Get the performance vector and related time information of the current cloud printer: If there is a cloud printer , then its performance vector is ; Get usage time , operating time since the last maintenance sky; Vectorize performance , Usage time and the operating time since the last maintenance Input into the trained fault prediction model (random forest model); The fault prediction model calculates the probability of this cloud printer failing within the next hour based on the internal decision tree structure and the trained parameters. ,in, The calculation of is based on the prediction results of each decision tree in the random forest model for the sample (for example, the proportion of votes that each decision tree judges this sample as faulty); Assume that the fault prediction model calculates , indicating that this cloud printer has a 30% risk of failure in the next hour. According to the set value range of 0-1, it is in a state with a certain risk of failure.

[0017] The order matching and allocation strategy formulation module prioritizes cloud printers with the best performance and low failure probability for orders with high urgency coefficients, and considers batch processing capabilities. For orders with low urgency coefficients, it predicts the idle time and energy consumption of cloud printers. The steps for optimizing allocation include: Step 301: Set the normal operation probability range ,satisfy , indicating that the cloud printer is in an operating state ranging from a lower risk of failure to a higher risk of failure but still within an acceptable range; at the same time, set the urgency range ,satisfy , used to quantify the urgency of an order; Step 302: If the emergency coefficient is higher than the upper limit of the emergency level range (e.g. 0.7) order clustering, filter out the order with the best performance vector and the probability value output by the fault prediction model is lower than the lower limit of the normal operation probability range (e.g. 0.1, indicating a very low risk of failure) list of cloud printers; In step 302, during the screening process, the evaluation of the performance vector comprehensively considers multiple dimensions such as the cloud printer's printing speed, printing quality stability (determined by factors such as printhead health and heating component efficiency), and paper handling capabilities (such as supported paper types and maximum paper thickness); Step 303: for the filtered cloud printer list, further analyze the batch processing capability of each cloud printer for the current order clustering: if any cloud printer has a special function or algorithm, that is, processing multiple orders at the same time without affecting the printing quality (for example, some high-end cloud printers can achieve interleaved printing of multiple images or documents by optimizing task scheduling to improve printing efficiency), then such orders will be assigned to the cloud printer first. At the same time, when assigning orders, the current task queue of the cloud printer needs to be considered to avoid printing delays caused by task accumulation; Step 304: If the emergency coefficient is lower than the lower limit of the emergency level range (e.g., 0.3) orders are clustered to obtain the idle time prediction information of all cloud printers, where the idle time prediction is calculated based on factors such as the current task queue of the cloud printer, the estimated task completion time, and the strategy of the cloud printer entering the low power mode; at the same time, the energy consumption of each cloud printer is considered, where the energy consumption data is obtained by long-term monitoring of the energy consumption of cloud printers in different working modes (such as standby, printing, preheating, etc.); Step 305: according to the idle time prediction and energy consumption, find out the cloud printer that is about to enter a long idle state and has a high current energy consumption, then assign the order with a low urgency coefficient to the cloud printer, and adjust the working mode of the cloud printer accordingly; In step 305, the working mode of the cloud printer includes but is not limited to the standard mode and the energy-saving mode. The standard mode is the regular working mode of the cloud printer, which provides normal printing speed, printing quality and energy consumption. In this mode, the cloud printer can complete the printing task according to the standard settings and is suitable for most regular orders; the energy-saving mode means that when the cloud printer is expected to be idle for a long time or the current energy consumption is high, the cloud printer can switch to the mode. In this mode, the cloud printer will reduce its energy consumption (such as by reducing the printing speed, adjusting the printing brightness or color mode, etc.); it is understandable that if a cloud printer is expected to be idle for more than 20 minutes, the working mode of the cloud printer is adjusted from the standard mode to the energy-saving mode. At the same time, in order to ensure that the order can still be completed on time in the energy-saving mode, the printing parameters of the order are further adjusted (such as reducing the printing speed, adjusting the color mode, etc.) to adapt to the performance of the cloud printer in the energy-saving mode and maximize energy efficiency.

[0018] The real-time monitoring and dynamic adjustment module monitors the working efficiency of the cloud printer in real time and conducts comparative analysis. If an abnormality is found, the steps of reallocating orders to other cloud printers include: Step 401: After the order is assigned to the cloud printer and the printing process is started, the sensors on the cloud printer side (such as speed sensors and image quality detection sensors) monitor the working efficiency of the cloud printer in real time. The speed sensor is responsible for monitoring the paper transmission speed in real time to determine whether the printing speed is stable; the image quality detection sensor performs quality detection on the printed image or text to check whether there are problems such as blur, lack of ink, color deviation, etc. Step 402: Compare and analyze the monitored working efficiency of the cloud printers with the original requirements and expected quality standards of the order: if any cloud printer is found to have an abnormality during the printing process during the comparative analysis, such as the printing speed suddenly drops by more than a certain percentage (such as 10%) or the printing quality has an obvious deviation (such as the color deviation exceeds the set threshold), the printing task of the order on this cloud printer is immediately suspended; In step 402, the original requirements and expected quality standards of the order include but are not limited to the following aspects: the original requirements of the order specify the expected printing speed or the time frame for printing completion, in order to ensure that the order can be completed within the specified time to meet the customer's delivery date or other time-sensitive requirements; the expected quality standards detail the quality requirements for the printout, such as image clarity, text readability, color accuracy and consistency, etc.; Step 403: re-evaluate the status of all available cloud printers (including performance vectors, failure probability, current task queue, etc.), and reallocate the remaining unprinted portion of the order to other cloud printers; when reallocating, consider factors such as the warm-up time of the new cloud printer (if it is a laser cloud printer), the remaining amount of ink cartridges or toner cartridges, etc., to ensure that the order can continue to print without affecting the overall progress and quality; Step 404: Adjust the allocation plan of subsequent orders according to the abnormal situation. For example, for a cloud printer that may cause similar abnormalities, reduce the number of orders allocated to it for a period of time until its problem is solved or its performance is improved. For example, suppose there are three cloud printers, marked as printers ,printer and a printer ; Suppose the total number of pages in an order is Page; The order is allocated to 3 cloud printers in proportion, and the printers are set The number of pages allocated is Page, Printer The number of pages allocated is ,printer The number of pages allocated is ; Defining Printers The normal printing speed is Pages / minute, printer The normal printing speed is Pages / minute, printer The normal printing speed is Pages / minute; the normal printing speed of a cloud printer refers to the average number of pages printed per minute under normal and stable working conditions; The threshold value of the sudden drop in printing speed is set to During printing, if the printer The speed sensor detects that the printing speed has dropped to Pages / minute, the computing speed decreases by , then determine the printer An abnormality occurs; At this point, part of the order has been printed. Already printed If the printer The number of unprinted pages remaining is ; Re-evaluate your printer and printer state, assuming the printer The tasks in the current task queue are expected to require minutes to complete (this takes into account factors such as its performance vector and the current task queue), the printer The tasks in the current task queue are expected to require minutes to complete; and the printer The remaining ink cartridge can support printing Page, Printer The remaining ink cartridge can support printing Page, due to printer The remaining task completion time is short, although the remaining ink cartridge is relatively small, but considering all factors, the printer The remaining unprinted orders are reallocated to the printers ; In subsequent order allocation, due to the printer This exception occurred. In the following order cycle to reduce the number of orders assigned to it; if each order cycle is normally assigned to the printer The order volume is orders, then Order cycle, assigned to printer The order volume is reduced to orders.

[0019] In the embodiment of the present invention, by using composite technology (including image recognition technology and natural language processing technology) to extract order features, the order requirements can be quickly understood, laying the foundation for subsequent processing, and the orders are classified based on the extracted features using a clustering algorithm, and the urgency of the order is determined by combining multi-dimensional processing factors to ensure that orders with high urgency coefficients are given priority processing, thereby improving customer satisfaction. The cloud printer status information is collected through the Internet of Things technology and sensor networks, and the component operating parameters are monitored in real time to ensure the stable operation of the cloud printer. By using historical fault records and machine learning algorithms to predict the future failure probability of the cloud printer, measures can be taken in advance to reduce the downtime caused by the failure. The cloud printer availability assessment provides a basis to ensure that there are a sufficient number of available cloud printers to meet printing needs during high-demand periods. For orders with high urgency coefficients, cloud printers with the best performance and low failure probability are prioritized to ensure that orders are completed quickly and with high quality. For orders with low urgency coefficients, cloud printer idle time and energy consumption are predicted, and allocation is optimized to maximize energy efficiency and reduce operating costs. The work efficiency of cloud printers is monitored in real time and compared with order requirements. If anomalies are found, orders are immediately suspended and reallocated to ensure that printing quality meets standards. By adjusting subsequent order allocation plans according to abnormal situations, potential risks caused by equipment failures or quality problems are reduced. In summary, the examples of the present invention solve the problem of poor cloud printing order processing results. In actual situations, more data and contextual information may be required to make specific decisions and optimization plans.

[0020] In addition, the formulas involved in the above are all calculated by removing dimensions and taking their numerical values. They are a formula that is closest to the actual situation obtained by collecting a large amount of data and performing software simulation. The proportional coefficient in the formula and the various preset thresholds in the analysis process are set by technical personnel in this field according to actual conditions or obtained by simulating a large amount of data; the size of the proportional coefficient is to quantify each parameter to obtain a specific value for subsequent comparison. The size of the proportional coefficient depends on the amount of sample data and the preliminary setting of the corresponding processing coefficient for each group of sample data by technical personnel in this field; as long as it does not affect the proportional relationship between the parameter and the quantized value.

[0021] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device embodiment, since it is basically based on the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0022] For the convenience of description, the above device is described in various units according to their functions. Of course, when implementing the present application, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0023] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0024] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0025] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0026] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0027] Secondly: In the drawings of the embodiments disclosed in the present invention, only the structures related to the embodiments disclosed in the present invention are involved, and other structures can refer to the general design. In the absence of conflict, the same embodiment and different embodiments of the present invention can be combined with each other; Finally: The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. A cloud printing order resource dynamic allocation system based on artificial intelligence algorithm, characterized by: It includes order analysis and clustering module, cloud printer performance status perception module, order matching and allocation strategy formulation module, and real-time monitoring and dynamic adjustment module; Order analysis and clustering module: Use composite technology to extract order features, use clustering algorithms to classify orders based on the extracted features, determine the urgency of orders based on multi-dimensional processing factors of orders, calculate the urgency coefficient and mark it on the clustered order group; composite technology includes image recognition technology and natural language processing technology; Cloud printer performance status perception module: collects cloud printer status information through IoT technology and sensor networks, and embeds intelligent diagnostic units to monitor component operating parameters in real time. At the same time, it uses historical fault records and machine learning algorithms to predict the probability of future failures of cloud printers. Order matching and allocation strategy formulation module: For orders with high urgency coefficients, cloud printers with the best performance and low failure probability are matched first, and batch processing capabilities are considered; for orders with low urgency coefficients, the idle time and energy consumption of cloud printers are predicted to optimize allocation; Real-time monitoring and dynamic adjustment module: monitor the working efficiency of cloud printers in real time and conduct comparative analysis. If any abnormality is found, the order will be reallocated to other cloud printers.

2. According to claim 1, a cloud printing order resource dynamic allocation system based on artificial intelligence algorithm is characterized by: The order analysis and clustering module uses composite technology to extract order features, classifies orders based on the extracted features using clustering algorithms, determines the urgency of orders based on multi-dimensional processing factors of orders, calculates the urgency coefficient and marks it on the clustered order group. The process includes: By combining image recognition and natural language processing technology, we extract features from the content of each order: For the order part containing images or graphics, a convolutional neural network is used to decompose the image and identify the characteristics of the complexity of the graphics, the color pattern of the image, and the resolution of the image; For the text part of the order, the word vector model is used to convert the text into a vector representation, and the text layout format, semantic features of the text content, and key information of the number of words are analyzed; various feature information obtained through image recognition and natural language processing are integrated into a complete order feature vector; Based on the extracted order features, a clustering algorithm is used to cluster the feature vectors of all orders, taking the distance between the order feature vectors as the similarity measurement standard, and the orders with similar distances are classified into one category; among them, orders with similar distances are orders with similar features: when the multi-dimensional differences of the order feature vectors in terms of graphic complexity, color mode, and text key information are all less than the set clustering threshold, these orders are classified into the same cluster; in the clustering process, the center and threshold of the cluster are continuously adjusted according to the historical order data to adapt to the distribution changes of different types of orders; According to the classification results of the order feature vector by the clustering algorithm, the multi-dimensional processing factors of the order are further integrated, and the urgency coefficient is obtained through weighted calculation. The coefficient is marked on the clustered order group to reflect the urgency of the order, including: Extract the timestamp of order submission and calculate the interval from submission to the current time; identify the priority identifier set by the customer in the order, where the priority identifier set by the customer is divided into three levels: high, medium, and low; Combining multi-dimensional processing factors, a weighted calculation method is adopted to obtain an urgency coefficient, and the value range of the urgency coefficient is set; wherein, the multi-dimensional processing factors of orders include order submission time, customer set priority, order attributes and order size; The urgency coefficient is obtained and marked on each clustered order group.

3. According to claim 1, a cloud printing order resource dynamic allocation system based on artificial intelligence algorithm is characterized by: The cloud printer performance status perception module collects cloud printer status information through IoT technology and sensor networks, and embeds the intelligent diagnosis unit to monitor component operating parameters in real time. The process includes: Through the Internet of Things technology, a connection is established with each cloud printer connected to the cloud printing service for comprehensive testing; Utilize sensor networks to collect general status information of cloud printers; Embedding an intelligent diagnostic unit inside the cloud printer to evaluate the health of components, wherein the intelligent diagnostic unit is used to monitor the operating parameters of the components inside the cloud printer in real time; All information obtained from the sensor network and intelligent diagnostic unit is integrated to build a performance vector of the cloud printer.

4. According to claim 1, a cloud printing order resource dynamic allocation system based on artificial intelligence algorithm is characterized by: The process by which the cloud printer performance status perception module uses historical fault records and machine learning algorithms to predict the future fault probability of cloud printers includes: Collect historical fault records from each cloud printer’s maintenance log or database; Check and handle missing values, outliers, or duplicate records in the data; Extract features related to fault prediction from historical fault records; Use machine learning algorithms to build fault prediction models and complete model training; Get the performance vector of the current cloud printer; record the usage time of the cloud printer and the running time after the last maintenance; Input the performance vector of the current cloud printer, the usage time of the cloud printer, and the running time after the last maintenance into the trained fault prediction model to calculate the probability of each cloud printer failing in the future. The probability value output by the fault prediction model is used as an important basis for the availability evaluation of the cloud printer, where the output probability value ranges from 0 to 1, where 0 represents no fault risk and 1 represents an extremely high fault risk.

5. According to claim 1, a cloud printing order resource dynamic allocation system based on artificial intelligence algorithm is characterized by: The order matching and allocation strategy formulation module prioritizes cloud printers with the best performance and low failure probability for orders with high urgency coefficients, and considers the process of batch processing capabilities, including: Set the normal operation probability range ,satisfy ; At the same time, set the urgency range ,satisfy , used to quantify the urgency of an order; For emergency coefficients higher than the upper limit of the emergency range The order clustering is used to select the order with the best performance vector and the probability value output by the fault prediction model is lower than the lower limit of the normal operation probability range. List of cloud printers; For the filtered cloud printer list, the batch processing capability of each cloud printer for the current order cluster is further analyzed; wherein the batch processing capability refers to the ability of the cloud printer to process multiple orders or printing tasks within a unit of time.

6. The cloud printing order resource dynamic allocation system based on artificial intelligence algorithm according to claim 5 is characterized by: The order matching and allocation strategy formulation module predicts the idle time and energy consumption of cloud printers for orders with low urgency coefficients. The process of optimizing allocation includes: For emergency coefficients below the lower limit of the emergency level range The order clustering is used to obtain the idle time prediction information of all cloud printers. At the same time, the energy consumption of each cloud printer is considered. According to the idle time prediction and energy consumption, the cloud printers that are about to enter a long idle state and currently have high energy consumption are found out, and then the orders with low urgency coefficients are assigned to the cloud printers, and the working mode of the cloud printers is adjusted accordingly.

7. The cloud printing order resource dynamic allocation system based on artificial intelligence algorithm according to claim 1 is characterized by: The real-time monitoring and dynamic adjustment module monitors the working efficiency of cloud printers in real time and conducts comparative analysis. If an abnormality is found, the order is reallocated to other cloud printers. The process includes: After the order is assigned to the cloud printer and the printing process is started, the sensor on the cloud printer side monitors the working efficiency of the cloud printer in real time; Compare and analyze the monitored cloud printers’ working efficiency with the original requirements and expected quality standards of the order: If any cloud printer is found to have an abnormality during the printing process during the comparative analysis, immediately suspend the printing task of the order on this cloud printer; Re-evaluate the status of all available cloud printers and reallocate the remaining unprinted orders to other cloud printers; at the same time, adjust the allocation plan for subsequent orders based on abnormal circumstances.

Images