Intelligent order scheduling system of cloud printing platform

By designing an intelligent scheduling system on the cloud printing platform, using technologies such as printing demand vector analysis, attention mechanism scoring and neural network prediction, the problems of low efficiency and low accuracy of order scheduling in the existing technology are solved, and load balancing is achieved The optimization of collaborative work meets the intelligent needs of modern cloud printing platforms.

CN118915983AInactive Publication Date: 2024-11-08FUJIAN SHUNYIN INFORMATION TECH CO LTD

Patent Information

Application Number
CN202411420618.3
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-10-12
Publication Date
2024-11-08
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

The existing cloud printing platform has low order scheduling efficiency and low accuracy, making it difficult to cope with the needs of large-scale printing and load balancing. Traditional scheduling methods are difficult to meet the intelligent and refined needs of modern cloud printing platforms.

Method used

An intelligent order scheduling system for cloud printing platform was designed, including information collection unit, printing platform matching scoring module, collaborative work scheduling module and automatic detection block. Through printing demand vector analysis, attention mechanism scoring, neural network prediction and automatic detection and other technical means to realize intelligent scheduling and collaborative work optimization of the printing platform.

Benefits of technology

It improves the scheduling accuracy and collaborative work coordination effect of the printing platform, ensures load balancing and security, and meets the intelligent needs of modern cloud printing platforms.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118915983A_ABST
    Figure CN118915983A_ABST
Patent Text Reader

Abstract

The invention discloses an order intelligent scheduling system of a cloud printing platform, which relates to the field of intelligent scheduling and comprises an automatic detection block, a cooperative work scheduling module and a printing platform scheduling module. According to the order intelligent scheduling system of the cloud printing platform, printing platform printing ink stored in the printing platform is scheduled through the printing platform scheduling module according to the matching score of the printing platform matching scoring module in the use process of the printing platform, so that the scheduling accuracy of the printing platform can be ensured; meanwhile, cooperative work of the multiple printing platform scheduling modules is controlled through the cooperative work scheduling module, and the work cooperation effect of the multiple printing platform scheduling modules is guaranteed; and the automatic detection block judges whether automatic reclosing operation needs to be carried out or not according to the working performance of the printing platform, so that the safety of the printing platform can be ensured.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to intelligent scheduling technology, and in particular to an order intelligent scheduling system for a cloud printing platform. Background Art

[0002] With the rapid development of cloud computing technology, cloud printing services, as a new printing service model, are gradually replacing traditional local printing methods. Cloud printing platforms connect printers and terminal devices through the Internet, allowing users to print anytime and anywhere, greatly improving the flexibility and convenience of printing services. However, with the continuous increase in the number of cloud printing platform users and the increasing diversification of printing needs, how to efficiently and accurately schedule the orders of the printing platform has become an important challenge facing cloud printing service providers.

[0003] In the existing technology, the order scheduling of cloud printing platforms mostly relies on simple rule matching or manual intervention, which has problems such as low scheduling efficiency, low accuracy, and difficulty in coping with large-scale printing needs. Especially when multiple printing platforms work together, how to reasonably allocate printing tasks and ensure load balancing and efficient operation of each printing platform has become an urgent problem to be solved.

[0004] In addition, with the continuous advancement of printing technology, the working performance of the printing platform is also constantly improving, and the requirements for intelligent and refined order scheduling are becoming higher and higher. The traditional order scheduling method can no longer meet the needs of modern cloud printing platforms, so a more intelligent and efficient order scheduling system is needed to meet the current challenges. Summary of the invention

[0005] The purpose of the present invention is to provide an intelligent order scheduling system for a cloud printing platform to solve the above-mentioned deficiencies in the prior art.

[0006] In order to achieve the above object, the present invention provides the following technical solution: an order intelligent scheduling system for a cloud printing platform, comprising: An information acquisition unit, the information acquisition unit is used to collect measurement data of different printing platforms; A printing platform matching scoring module, which is used to score the working vectors and printing requirement vectors of the printing platforms in the printing platform library, wherein the printing platforms whose scores meet the working requirements are selected, and the printing platforms whose scores do not meet the working requirements are replaced. The printing platform matching scoring module includes: A printing demand vector analysis module, wherein the printing demand vector analysis module is used to perform vector analysis on printing demand; A printing platform vector analysis module, the printing platform vector analysis module is used to analyze the working vector under the current working condition of the printing platform; A scoring module, which is used to perform matching scoring between the printing demand analysis module and the printing platform vector analysis module; A display unit, the display unit is used to display the data processed by the data processing unit; A printing platform scheduling module, the printing platform scheduling module is used to schedule the printing platform according to the matching score of the printing platform matching scoring module; A collaborative work scheduling module, which is used to control the collaborative work of multiple printing platforms mobilized by the printing platform scheduling module; The automatic detection block is used to detect the working performance of the printing platform and determine whether an automatic joining operation is required based on the working performance of the printing platform.

[0007] Furthermore, the working steps of the printing platform matching scoring module are: E1, filter out useless features in the printing demand feature information, use the sigmoid activation function as the gate state, and then multiply it with the printing demand feature, and then use the tanh activation function to obtain the feature screening of the gate unit; E2, use the attention mechanism to strengthen the key vector feature information in the printing platform library, and obtain the embedding vector t and the feature representation of the text according to the vector feature type. , represents the i-th eigenvector, m represents the number of features, and t T , score each feature in the text to perceive the important information in the text, as shown in the following formula: ; Represents the kth printing platform vector The attention weight, m ​​represents the number of features; E3, the print platform library representation after evaluation can be obtained , as shown below: , in , is the attention vector, represents the features of the printing platform library weighted by the attention weights, represents the first feature vector weighted by the attention weight, is the vector matrix of the printing platform library; E4, query representation is obtained by the vector feature information fusion module and print platform library feature representation , and then calculated by the maximum similarity (MaxSim), through and The score between the query and the printing platform library can be calculated, which is the sum of the maximum similarities between each printing requirement in the query and each printing platform work vector in the printing platform library, as shown in the following formula: .

[0008] Furthermore, the specific working steps of the collaborative work scheduling module are: C1, artificially set system constraints and objective functions; C2, artificially define the Lagrangian function as: , Where i represents the i-th single printing platform, PiG represents the printing efficiency generated by the i-th single printing platform, and P i G represents the output power of the ink storage system within the i-th printing platform, Represents printing platform G i The total economic cost and environmental impact of represents the level of unreasonable utilization of ink B of the ink storage system, λ represents any positive real number, P represents the power input / output of the printing platform, and D represents the difference between the total printing ink demand and the output power of the ink storage system; C3, then the dual problem of step E2 is ,in: ; C4, then step E3 is solved as follows , in and Respectively Functions and The inverse of a function; C5, solved by gradient descent method: , Among them, γ(k) represents the step size of the kth step; C6, let each agent i include a scalar variable w i (k), y i (k), λ i (k) and v i (k), at the kth step, each agent is updated by the following formula , Among them, D i Represents the virtual power requirement of a single printing platform i, ensuring ; C7, the step size γ(k+1) satisfies the following attenuation requirements: ; C8, then the termination condition of the iterative algorithm is: , When s1 and s2 satisfy the above conditions at the same time, it can be considered that the optimization problem has converged to the optimal solution, that is, the optimal power scheduling of collaborative work is achieved.

[0009] Furthermore, the printing platform scheduling module includes: A printing demand prediction module, which is used to predict the printing demand curve of the printing platform for the next day based on a neural network; A printing ink price prediction module, the printing ink price prediction module is used to obtain the printing ink price predicted for the next day; A next-day real-time price optimization module, which is used to optimize the real-time price of next-day printing ink with the goal of minimizing the economic cost of a single printing platform and the loss of user comfort; A single printing platform system status acquisition module, the single printing platform system status acquisition module is used to acquire the system status of the single printing platform in the next period; A printing platform group equipment optimization module is used to optimize the printing platform group with the goal of minimizing the cost of a single printing platform.

[0010] Furthermore, the specific working steps of the printing platform scheduling module are: B1, predicting the next day printing demand curve of the printing platform based on neural network; B2, obtain the next day's predicted printing ink price; B3, optimizes the next day’s real-time price with the goal of minimizing the economic cost and user comfort loss of a single printing platform; B4, obtain the status of the single printing platform in the next period; B5, optimize the printing platform group with the goal of minimizing the cost of a single printing platform; B6, periodically detect system power in the current time period; B7, determine whether the current power meets the balance constraint, if the judgment result is no, execute step B7, if the judgment result is yes, execute step B9; B8, controlling the idle printing platform to join with the goal of minimizing the power imbalance; B9, judging whether the current printing platform group exceeds the maximum printing demand, if the judgment result is no, the idle printing platform intervenes, and returns to step B8, if the judgment result is yes, execute step B10; B10, judging whether the total optimization cycle is over, if the judgment result is no, returning to step B4, if the judgment result is yes, the printing platform scheduling is over.

[0011] Furthermore, the automatic detection block includes: A data processing unit is used to receive and process data, and is used to receive the data selected by the data selection unit and process the data. The data processing unit transmits the processed data to the health assessment unit; A data acquisition unit, used to collect real-time data of the printing platform; A data storage unit, used to store the real-time data of the printing platform collected by the data collection unit; A data selection unit, used for selecting the real-time data of the printing platform stored in the data storage unit; Learning unit, through continuous learning, constantly adjust the accuracy of health assessment unit; The standard data unit stores the performance data of the printing platform when it is working under the standard working state; A result output unit, which outputs the real-time performance data and predicted performance data of the printing platform; A result judgment unit, used to judge the accuracy of the predicted performance data in the health assessment unit; A data comparison unit, used to compare the real-time performance data of the printing platform with the predicted performance data; The health assessment unit predicts the performance of the printing platform in the next working state by printing the performance in the previous state.

[0012] Furthermore, the automatic detection block includes the following working steps: A1. Collect real-time performance data of the printing platform through the data acquisition unit; A2. Receive and store the real-time data of the integrated printing platform collected by the storage data collection unit through the data storage unit; A3, randomly selecting data in the data storage unit through the data selection unit; A4. discarding, filling, replacing, and deduplicating the data received in the data selection unit through the data processing unit; A5. Predict the performance data of the printing platform under the next working state through the health assessment unit, and transmit the prediction result to the result output unit; A5. The data comparison unit receives the data from the data acquisition unit and compares it with the standard data in the standard data unit, thereby judging the working performance of the printing platform; A7, the result judgment unit judges the received prediction data and real-time data, thereby judging the prediction accuracy of the health assessment unit; A8, the data output unit simultaneously outputs the predicted data, real-time data, standard data and judgment results; A9. The staff can determine whether data adjustment is needed based on the accuracy of the forecast results; A10. Continuous adjustment of prediction data can be achieved through continuous learning and adjustment of learning units.

[0013] Compared with the prior art, the present invention provides an intelligent order scheduling system for a cloud printing platform. During the use of the printing platform, the printing platform scheduling module performs ink scheduling on the printing platform ink stored on the printing platform according to the matching score of the printing platform matching scoring module, thereby ensuring the scheduling accuracy of the printing platform. At the same time, the collaborative work scheduling module controls the collaborative work of multiple printing platform scheduling modules, thereby ensuring the working coordination effect of multiple printing platform scheduling modules. At the same time, during the operation of the printing platform, an automatic detection block is provided for detecting the working performance of the printing platform and judging whether automatic reclosing operation is required according to the working performance of the printing platform, thereby ensuring the safety of the printing platform. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0015] Figure 1 A schematic diagram of the overall structure provided for an embodiment of the present invention. DETAILED DESCRIPTION

[0016] In order to enable those skilled in the art to better understand the technical solution of the present invention, the present invention will be further described in detail below with reference to the accompanying drawings.

[0017] See also Figure 1 , an order intelligent scheduling system for a cloud printing platform, comprising: An information collection unit, which is used to collect measurement data of different printing platforms; Print platform matching scoring module, the printing platform matching scoring module is used to score the working vector of the printing platform in the printing platform library with the printing requirement vector, wherein the printing platform whose score meets the working requirement is selected, and the printing platform whose score does not meet the working requirement is replaced. The printing platform matching scoring module package block: Printing demand vector analysis module, used for performing vector analysis on printing demand; Printing platform vector analysis module, used to analyze the working vector under the current working condition of the printing platform; A scoring module, used for performing matching scoring between the printing demand analysis module and the printing platform vector analysis module; A display unit, the display unit is used to display the data processed by the data processing unit; A printing platform scheduling module, the printing platform scheduling module is used to schedule the printing platform ink stored on the printing platform according to the matching score of the printing platform matching scoring module; A collaborative work scheduling module, which is used to control the collaborative work of multiple printing platform scheduling modules; Automatic detection block, the automatic detection block is used to detect the working performance of the printing platform, and determine whether automatic reclosing operation is required based on the working performance of the printing platform.

[0018] In this arrangement, the measurement data of different printing platforms are collected in real time through the information collection unit, and the working vector and the printing demand vector of the printing platform in the printing platform library are scored through the printing platform matching scoring module, wherein the printing platform whose score meets the working demand is selected, and the printing platform whose score does not meet the working demand is replaced, and at the same time, during the use of the printing platform, the printing platform ink stored in the printing platform is scheduled by the printing platform scheduling module according to the matching score of the printing platform matching scoring module, so as to ensure the scheduling accuracy of the printing platform, and at the same time, the collaborative work scheduling module controls the collaborative work of multiple printing platform scheduling modules to ensure the working coordination effect of multiple printing platform scheduling modules, and at the same time, during the operation of the printing platform, an automatic detection block is provided to detect the working performance of the printing platform and determine whether automatic reclosing operation is required according to the working performance of the printing platform, so as to ensure the safety of the printing platform.

[0019] The working steps of the printing platform matching scoring module are: E1, filter out useless features in the printing demand feature information, use the sigmoid activation function as the gate state, and then multiply it with the printing demand feature, and then use the tanh activation function to obtain the feature screening of the gate unit; E2, use the attention mechanism to strengthen the key vector feature information in the printing platform library, and obtain the embedding vector t and the feature representation of the text according to the vector feature type. , represents the i-th eigenvector, m represents the number of features, and t T , score each feature in the text to perceive the important information in the text, as shown in the following formula: ; Represents the kth printing platform vector The attention weight, m ​​represents the number of features; E3, the print platform library representation after evaluation can be obtained , as shown below: , in , is the attention vector, represents the features of the printing platform library weighted by the attention weights, represents the first feature vector weighted by the attention weight, is the vector matrix of the printing platform library; E4, query representation is obtained by the vector feature information fusion module and print platform library feature representation , and then calculated by the maximum similarity (MaxSim), through and The score between the query and the printing platform library can be calculated, which is the sum of the maximum similarities between each printing requirement in the query and each printing platform work vector in the printing platform library, as shown in the following formula: .

[0020] The specific working steps of the collaborative work scheduling module are: C1, artificially set system constraints and objective functions; C2, artificially define the Lagrangian function as: , Where i represents the i-th single printing platform, PiG represents the printing efficiency generated by the i-th single printing platform, and P i G represents the output power of the ink storage system within the i-th printing platform, Represents printing platform G i The total economic cost and environmental impact of represents the level of unreasonable utilization of ink B of the ink storage system, λ represents any positive real number, P represents the power input / output of the printing platform, and D represents the difference between the total printing ink demand and the output power of the ink storage system; C3, then the dual problem of step E2 is ,in: ; C4, then step E3 is solved as follows , in and Respectively Functions and The inverse of a function; C5, solved by gradient descent method: , Among them, γ(k) represents the step size of the kth step; C6, let each agent i include a scalar variable w i (k), y i (k), λ i (k) and v i (k), at the kth step, each agent is updated by the following formula , Among them, D i Represents the virtual power requirement of a single printing platform i, ensuring ; C7, the step size γ(k+1) satisfies the following attenuation requirements: ; C8, then the termination condition of the iterative algorithm is: , When s1 and s2 satisfy the above conditions at the same time, it can be considered that the optimization problem has converged to the optimal solution, that is, the optimal power scheduling of collaborative work is achieved.

[0021] The printing platform scheduling module includes: A printing demand prediction module, which is used to predict the printing demand curve of the printing platform for the next day based on a neural network; Printing ink price prediction module, which is used to obtain the printing ink price prediction for the next day; Next-day real-time price optimization module: The next-day real-time price optimization module is used to optimize the real-time price of next-day printing ink with the goal of minimizing the economic cost of a single printing platform and the loss of user comfort; A single printing platform system status acquisition module, which is used to acquire the system status of the single printing platform in the next period; The printing platform group equipment optimization module is used to optimize the printing platform group with the goal of minimizing the cost of a single printing platform.

[0022] The specific working steps of the printing platform scheduling module are: B1, predicting the next day printing demand curve of the printing platform based on neural network; B2, obtain the next day's predicted printing ink price; B3, optimizes the next day’s real-time price with the goal of minimizing the economic cost and user comfort loss of a single printing platform; B4, obtain the status of the single printing platform in the next period; B5, optimize the printing platform group with the goal of minimizing the cost of a single printing platform; B6, periodically detect system power in the current time period; B7, determine whether the current power meets the balance constraint, if the judgment result is no, execute step B7, if the judgment result is yes, execute step B9; B8, controlling the idle printing platform to join with the goal of minimizing the power imbalance; B9, judging whether the current printing platform group exceeds the maximum printing demand, if the judgment result is no, the idle printing platform intervenes, and returns to step B8, if the judgment result is yes, execute step B10; B10, judging whether the total optimization cycle is over, if the judgment result is no, returning to step B4, if the judgment result is yes, the printing platform scheduling is over.

[0023] The auto-detect blocks include: A data processing unit is used to receive and process data, and is used to receive the data selected by the data selection unit and process the data. The data processing unit transmits the processed data to the health assessment unit; A data acquisition unit, used to collect real-time data of the printing platform; A data storage unit, used to store the real-time data of the printing platform collected by the data collection unit; A data selection unit, used for selecting the real-time data of the printing platform stored in the data storage unit; Learning unit, through continuous learning, constantly adjust the accuracy of health assessment unit; The standard data unit stores the performance data of the printing platform when it is working under the standard working state; A result output unit, which outputs the real-time performance data and predicted performance data of the printing platform; A result judgment unit, used to judge the accuracy of the predicted performance data in the health assessment unit; A data comparison unit, used to compare the real-time performance data of the printing platform with the predicted performance data; The health assessment unit predicts the performance of the printing platform in the next working state by printing the performance in the previous state.

[0024] Automatic block detection includes the following steps: A1. Collect real-time performance data of the printing platform through the data acquisition unit; A2. Receive and store the real-time data of the integrated printing platform collected by the storage data collection unit through the data storage unit; A3, randomly selecting data in the data storage unit through the data selection unit; A4. discarding, filling, replacing, and deduplicating the data received in the data selection unit through the data processing unit; A5. Predict the performance data of the printing platform under the next working state through the health assessment unit, and transmit the prediction result to the result output unit; A5. The data comparison unit receives the data from the data acquisition unit and compares it with the standard data in the standard data unit, thereby judging the working performance of the printing platform; A7, the result judgment unit judges the received prediction data and real-time data, thereby judging the prediction accuracy of the health assessment unit; A8, the data output unit simultaneously outputs the predicted data, real-time data, standard data and judgment results; A9. The staff can determine whether data adjustment is needed based on the accuracy of the forecast results; A10. Continuous adjustment of prediction data can be achieved through continuous learning and adjustment of learning units.

[0025] The above description is only by way of illustration of certain exemplary embodiments of the present invention. It is undoubted that those skilled in the art can modify the described embodiments in various ways without departing from the spirit and scope of the present invention. Therefore, the above drawings and descriptions are illustrative in nature and should not be construed as limiting the scope of protection of the claims of the present invention.

Claims

1. An intelligent order scheduling system for a cloud printing platform, characterized in that: include: An information acquisition unit, the information acquisition unit is used to collect measurement data of different printing platforms; A printing platform matching scoring module, which is used to score the working vectors and printing requirement vectors of the printing platforms in the printing platform library, wherein the printing platforms whose scores meet the working requirements are selected, and the printing platforms whose scores do not meet the working requirements are replaced. The printing platform matching scoring module includes: A printing demand vector analysis module, wherein the printing demand vector analysis module is used to perform vector analysis on printing demand; A printing platform vector analysis module, the printing platform vector analysis module is used to analyze the working vector under the current working condition of the printing platform; A scoring module, which is used to perform matching scoring between the printing demand analysis module and the printing platform vector analysis module; A display unit, the display unit is used to display the data processed by the data processing unit; A printing platform scheduling module, the printing platform scheduling module is used to schedule the printing platform according to the matching score of the printing platform matching scoring module; A collaborative work scheduling module, which is used to control the collaborative work of multiple printing platforms mobilized by the printing platform scheduling module; The automatic detection block is used to detect the working performance of the printing platform and determine whether an automatic joining operation is required based on the working performance of the printing platform.

2. According to claim 1, the order intelligent scheduling system of the cloud printing platform is characterized in that: The working steps of the printing platform matching scoring module are as follows: E1, filter out useless features in the printing demand feature information, use the sigmoid activation function as the gate state, and then multiply it with the printing demand feature, and then use the tanh activation function to obtain the feature screening of the gate unit; E2, use the attention mechanism to strengthen the key vector feature information in the printing platform library, and obtain the embedding vector t and the feature representation of the text according to the vector feature type. , represents the i-th eigenvector, m represents the number of features, and t T , score each feature in the text to perceive the important information in the text, as shown in the following formula: ; Represents the kth printing platform vector The attention weight, m ​​represents the number of features; E3, the print platform library representation after evaluation can be obtained , as shown below: , in , is the attention vector, represents the features of the printing platform library weighted by the attention weights, represents the first feature vector weighted by the attention weight, is the vector matrix of the printing platform library; E4, query representation is obtained by the vector feature information fusion module and print platform library feature representation , and then calculated by the maximum similarity (MaxSim), through and The score between the query and the printing platform library can be calculated, which is the sum of the maximum similarities between each printing requirement in the query and each printing platform work vector in the printing platform library, as shown in the following formula: 。 3. According to claim 2, the order intelligent scheduling system of the cloud printing platform is characterized in that: The specific working steps of the collaborative work scheduling module are: C1, artificially set system constraints and objective functions; C2, artificially define the Lagrangian function as: , Where i represents the i-th single printing platform, P i G represents the output power of the ink storage system within the i-th printing platform, Represents printing platform G i The total economic cost and environmental impact of represents the level of unreasonable utilization of ink B of the ink storage system, λ represents any positive real number, P represents the power input / output of the printing platform, and D represents the difference between the total printing ink demand and the output power of the ink storage system; C3, then the dual problem of step E2 is ,in: ; C4, then step E3 is solved as follows , in and Respectively Functions and The inverse of a function; C5, solved by gradient descent method: , Among them, γ(k) represents the step length of the kth step; C6, let each agent i include a scalar variable w i (k), y i (k), λ i (k) and v i (k), at the kth step, each agent is updated by the following formula , Among them, D i Represents the virtual power requirement of a single printing platform i, ensuring ; C7, the step size γ(k+1) satisfies the following attenuation requirements: ; C8, then the termination condition of the iterative algorithm is: , When s1 and s2 satisfy the above conditions at the same time, it can be considered that the optimization problem has converged to the optimal solution, that is, the optimal power scheduling of collaborative work is achieved.

4. According to claim 3, the order intelligent scheduling system of the cloud printing platform is characterized in that: The printing platform scheduling module includes: A printing demand prediction module, which is used to predict the printing demand curve of the printing platform for the next day based on a neural network; A printing ink price prediction module, the printing ink price prediction module is used to obtain the printing ink price predicted for the next day; A next-day real-time price optimization module, which is used to optimize the real-time price of next-day printing ink with the goal of minimizing the economic cost of a single printing platform and the loss of user comfort; A single printing platform system status acquisition module, the single printing platform system status acquisition module is used to acquire the system status of the single printing platform in the next period; A printing platform group equipment optimization module is used to optimize the printing platform group with the goal of minimizing the cost of a single printing platform.

5. According to claim 4, the order intelligent scheduling system of the cloud printing platform is characterized in that: The specific working steps of the printing platform scheduling module are: B1, predicting the next day printing demand curve of the printing platform based on neural network; B2, obtain the next day's predicted printing ink price; B3, optimizes the next day’s real-time price with the goal of minimizing the economic cost and user comfort loss of a single printing platform; B4, obtain the status of the single printing platform in the next period; B5, optimize the printing platform group with the goal of minimizing the cost of a single printing platform; B6, periodically detect system power in the current time period; B7, determine whether the current power meets the balance constraint, if the judgment result is no, execute step B7, if the judgment result is yes, execute step B9; B8, controlling the idle printing platform to join with the goal of minimizing the power imbalance; B9, judging whether the current printing platform group exceeds the maximum printing demand, if the judgment result is no, the idle printing platform intervenes, and returns to step B8, if the judgment result is yes, execute step B10; B10, judging whether the total optimization cycle is over, if the judgment result is no, returning to step B4, if the judgment result is yes, the printing platform scheduling is over.

6. The order intelligent scheduling system of the cloud printing platform according to claim 5 is characterized in that: The automatic detection block includes: A data processing unit is used to receive and process data, and is used to receive the data selected by the data selection unit and process the data. The data processing unit transmits the processed data to the health assessment unit; A data acquisition unit, used to collect real-time data of the printing platform; A data storage unit, used to store the real-time data of the printing platform collected by the data collection unit; A data selection unit, used for selecting the real-time data of the printing platform stored in the data storage unit; Learning unit, through continuous learning, constantly adjust the accuracy of health assessment unit; The standard data unit stores the performance data of the printing platform when it is working under the standard working state; A result output unit, which outputs the real-time performance data and predicted performance data of the printing platform; A result judgment unit, used to judge the accuracy of the predicted performance data in the health assessment unit; A data comparison unit, used to compare the real-time performance data of the printing platform with the predicted performance data; The health assessment unit predicts the performance of the printing platform in the next working state by printing the performance in the previous state.

7. The order intelligent scheduling system of the cloud printing platform according to claim 6 is characterized in that: The automatic detection block includes the following working steps: A1. Collect real-time performance data of the printing platform through the data acquisition unit; A2. Receive and store the real-time data of the integrated printing platform collected by the storage data collection unit through the data storage unit; A3, randomly selecting data in the data storage unit through the data selection unit; A4. discarding, filling, replacing, and deduplicating the data received in the data selection unit through the data processing unit; A5. Predict the performance data of the printing platform under the next working state through the health assessment unit, and transmit the prediction result to the result output unit; A5. The data comparison unit receives the data from the data acquisition unit and compares it with the standard data in the standard data unit, thereby judging the working performance of the printing platform; A7, the result judgment unit judges the received prediction data and real-time data, thereby judging the prediction accuracy of the health assessment unit; A8, the data output unit simultaneously outputs the predicted data, real-time data, standard data and judgment results; A9. The staff can determine whether data adjustment is needed based on the accuracy of the forecast results; A10. Continuous adjustment of prediction data can be achieved through continuous learning and adjustment of learning units.

Citation Information

Patent Citations

  • Offset printing spot color ink color matching method considering cost factor

    CN102975490A

  • Effective-capacity-based resource allocation method in cognitive radio system

    CN103997743A

  • Bandwidth and power coordinated allocation method in inter-satellite communication link

    CN105846887A

  • Vehicle and goods matching recommendation method based on gated recurrent neural network

    CN115860625A

  • Intelligent printing system based on data exchange

    CN116560598A

Cited By

  • Electronic package supervision intelligent analysis and adjustment system

    CN120278447A