CN117472300B - Order dispatch method and system for distributed 3D printing manufacturing platform - Google Patents
Order dispatch method and system for distributed 3D printing manufacturing platform Download PDFInfo
- Publication number
- CN117472300B CN117472300B CN202311460390.6A CN202311460390A CN117472300B CN 117472300 B CN117472300 B CN 117472300B CN 202311460390 A CN202311460390 A CN 202311460390A CN 117472300 B CN117472300 B CN 117472300B
- Authority
- CN
- China
- Prior art keywords
- order
- data
- comment
- node
- user
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000004519 manufacturing process Methods 0.000 title claims abstract description 430
- 238000010146 3D printing Methods 0.000 title claims abstract description 258
- 238000000034 method Methods 0.000 title claims abstract description 61
- 238000004458 analytical method Methods 0.000 claims abstract description 169
- 238000012937 correction Methods 0.000 claims abstract description 111
- 238000001514 detection method Methods 0.000 claims abstract description 80
- 238000004364 calculation method Methods 0.000 claims abstract description 56
- 230000008451 emotion Effects 0.000 claims description 256
- 238000011156 evaluation Methods 0.000 claims description 90
- 238000005457 optimization Methods 0.000 claims description 73
- 238000012545 processing Methods 0.000 claims description 73
- 238000009826 distribution Methods 0.000 claims description 63
- 238000007639 printing Methods 0.000 claims description 46
- 230000008569 process Effects 0.000 claims description 23
- 230000007935 neutral effect Effects 0.000 claims description 22
- 238000012216 screening Methods 0.000 claims description 22
- 238000010586 diagram Methods 0.000 claims description 14
- 238000012163 sequencing technique Methods 0.000 claims description 14
- 238000005065 mining Methods 0.000 claims description 11
- 239000000463 material Substances 0.000 claims description 10
- 238000005303 weighing Methods 0.000 claims description 10
- 238000012098 association analyses Methods 0.000 claims description 4
- 238000009499 grossing Methods 0.000 claims description 4
- 238000012552 review Methods 0.000 claims description 2
- 230000009286 beneficial effect Effects 0.000 description 10
- 238000012384 transportation and delivery Methods 0.000 description 8
- 238000005516 engineering process Methods 0.000 description 7
- 238000007726 management method Methods 0.000 description 6
- 238000013461 design Methods 0.000 description 5
- 230000008859 change Effects 0.000 description 4
- 230000006872 improvement Effects 0.000 description 4
- 230000002159 abnormal effect Effects 0.000 description 2
- 238000004140 cleaning Methods 0.000 description 2
- 238000007418 data mining Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000003058 natural language processing Methods 0.000 description 2
- 238000013468 resource allocation Methods 0.000 description 2
- 230000001934 delay Effects 0.000 description 1
- 238000012854 evaluation process Methods 0.000 description 1
- 230000004807 localization Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000000116 mitigating effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000013439 planning Methods 0.000 description 1
- 230000003252 repetitive effect Effects 0.000 description 1
- 238000013077 scoring method Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B29—WORKING OF PLASTICS; WORKING OF SUBSTANCES IN A PLASTIC STATE IN GENERAL
- B29C—SHAPING OR JOINING OF PLASTICS; SHAPING OF MATERIAL IN A PLASTIC STATE, NOT OTHERWISE PROVIDED FOR; AFTER-TREATMENT OF THE SHAPED PRODUCTS, e.g. REPAIRING
- B29C64/00—Additive manufacturing, i.e. manufacturing of three-dimensional [3D] objects by additive deposition, additive agglomeration or additive layering, e.g. by 3D printing, stereolithography or selective laser sintering
- B29C64/30—Auxiliary operations or equipment
- B29C64/386—Data acquisition or data processing for additive manufacturing
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B33—ADDITIVE MANUFACTURING TECHNOLOGY
- B33Y—ADDITIVE MANUFACTURING, i.e. MANUFACTURING OF THREE-DIMENSIONAL [3-D] OBJECTS BY ADDITIVE DEPOSITION, ADDITIVE AGGLOMERATION OR ADDITIVE LAYERING, e.g. BY 3-D PRINTING, STEREOLITHOGRAPHY OR SELECTIVE LASER SINTERING
- B33Y50/00—Data acquisition or data processing for additive manufacturing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/12—Digital output to print unit, e.g. line printer, chain printer
- G06F3/1201—Dedicated interfaces to print systems
- G06F3/1202—Dedicated interfaces to print systems specifically adapted to achieve a particular effect
- G06F3/1211—Improving printing performance
- G06F3/1212—Improving printing performance achieving reduced delay between job submission and print start
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/12—Digital output to print unit, e.g. line printer, chain printer
- G06F3/1201—Dedicated interfaces to print systems
- G06F3/1223—Dedicated interfaces to print systems specifically adapted to use a particular technique
- G06F3/1237—Print job management
- G06F3/126—Job scheduling, e.g. queuing, determine appropriate device
- G06F3/1263—Job scheduling, e.g. queuing, determine appropriate device based on job priority, e.g. re-arranging the order of jobs, e.g. the printing sequence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/12—Digital output to print unit, e.g. line printer, chain printer
- G06F3/1201—Dedicated interfaces to print systems
- G06F3/1278—Dedicated interfaces to print systems specifically adapted to adopt a particular infrastructure
- G06F3/1281—Multi engine printer devices, e.g. one entity having multiple output engines
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Chemical & Material Sciences (AREA)
- Materials Engineering (AREA)
- Human Computer Interaction (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Manufacturing & Machinery (AREA)
- Mechanical Engineering (AREA)
- Optics & Photonics (AREA)
Abstract
The invention relates to the technical field of 3D printing and manufacturing, in particular to an order dispatch method and system of a distributed 3D printing and manufacturing platform. The method comprises the following steps: acquiring historical order information data of a distributed 3D printing manufacturing platform, and performing user information identification analysis on the historical order information data to obtain order user information data; performing credit score detection on the order user information data to obtain the credit score of the order user; performing reputation detection calculation on the historical order information data to obtain an order trust score and an order questioning score; carrying out questioning, evaluating and analyzing historical order information data according to the order questioning scores to obtain order questioning influence factors; and carrying out credit correction analysis on the credit scores of the users of the orders according to the order question influence factors to obtain credit correction scores of the users. The invention can improve the dispatch efficiency of the distributed 3D printing manufacturing platform.
Description
Technical Field
The invention relates to the technical field of 3D printing and manufacturing, in particular to an order dispatch method and system of a distributed 3D printing and manufacturing platform.
Background
Distributed 3D print manufacturing platforms have become an important area of manufacturing that allows for collaborative work among multiple 3D printers to meet order requirements. However, the existing order dispatch method is generally based on a fixed rule or a simple queuing manner, and fails to fully utilize the performance and characteristics of the 3D printing apparatus and feedback information of the order user, thereby resulting in low production efficiency and delay of order execution.
Disclosure of Invention
Accordingly, the present invention is directed to an order dispatch method for a distributed 3D printing manufacturing platform, which solves at least one of the above-mentioned problems.
In order to achieve the above object, an order dispatch method of a distributed 3D printing manufacturing platform includes the following steps:
Step S1: acquiring historical order information data of a distributed 3D printing manufacturing platform, and performing user information identification analysis on the historical order information data to obtain order user information data; performing credit score detection on the order user information data to obtain the credit score of the order user;
step S2: performing reputation detection calculation on the historical order information data to obtain an order trust score and an order questioning score; carrying out questioning, evaluating and analyzing historical order information data according to the order questioning scores to obtain order questioning influence factors; carrying out credit correction analysis on the credit scores of the order users according to the order challenge influencing factors to obtain credit correction scores of the users;
Step S3: acquiring a user real-time order of a distributed 3D printing manufacturing platform and a 3D printing manufacturing node; performing manufacturing capacity evaluation analysis on the 3D printing manufacturing node to obtain manufacturing node capacity bearing data; performing order screening processing on the real-time orders of the users according to the credit correction scores of the users to obtain credit user orders; carrying out priority emergency ordering treatment on the credit user orders to obtain a priority emergency order ordering sequence;
Step S4: performing node exploration analysis on the 3D printing manufacturing nodes by utilizing the order trust scores and the order question scores based on the historical order information data to obtain 3D printing manufacturing trust nodes and 3D printing manufacturing question nodes; performing node correction adjustment processing on the 3D printing manufacture question node to obtain a printing manufacture question correction node; combining the 3D printing manufacture trust node and the printing manufacture challenge correction node to obtain a 3D printing manufacture optimization node; based on the manufacturing node capacity bearing data and the 3D printing manufacturing optimization node, performing order dispatch processing on credit user orders in the priority emergency order sequencing sequence to obtain user order dispatch result data;
step S5: carrying out load analysis on the 3D printing manufacturing optimization node to obtain manufacturing node load condition data; and performing dispatching and single-dispatching adjustment processing on the user order dispatching result data according to the manufacturing node load condition data to obtain user order dispatching adjustment data.
According to the invention, the historical order information data of the distributed 3D printing manufacturing platform is collected, and user information identification analysis is carried out on the collected historical order information data to obtain order user information data, so that information about an order user, such as names, contact information and purchase history, can be extracted from the historical order data, the user file can be built, the order characteristics of the user, such as purchase habits and preferred product types, can be known, and the method can be used for personalized marketing of the platform, customer relationship management and improvement of customer satisfaction. Then, by performing credit score detection on the order user information data, accurate assessment of the credit status of the historical order users can be achieved, so that the platform is helped to know the credit reliability of the users, and the orders and resources can be managed better. Secondly, by performing reputation detection calculation on historical order information data to generate an order trust score and an order question score, the trust level of a user and questions of an order can be quantified, which is helpful for identifying high-reputation users, reducing bad transaction risks and identifying possible disputes and questions in advance, thereby reducing potential losses. Meanwhile, by carrying out question evaluation analysis on the historical order information data based on the order question scores, the method can determine which orders have disputes or problems and know the root causes of the questions, which is helpful for improving service quality, solving the disputes, improving user satisfaction and reducing refunds and disputes, thereby improving the reputation of the platform. Credit impact correction analysis is carried out on credit scores of order users by using the questioning credit impact factors obtained through analysis, and the credit scores of the users can be corrected by analyzing and generating corresponding correction indexes so as to more accurately reflect credit conditions of the users, so that fairness of the credit scores is improved, accuracy of risk management is ensured, more reliable credit information of the users is provided for a platform, the reliability and questioning conditions of the users can be known more accurately by the platform, and potential risks and losses are reduced. Then, the user orders on the distributed 3D printing manufacturing platform and the information of the 3D printing manufacturing nodes are acquired in real time, so that the data view of the overall production environment is beneficial to be established by acquiring corresponding data, the platform can provide basic data guarantee for the subsequent processing process, meanwhile, the orders are effectively distributed and scheduled, and the orders can be ensured to be smoothly manufactured in 3D printing. And the 3D printing manufacturing nodes are subjected to manufacturing capability assessment analysis to determine the manufacturing capability and the bearable manufacturing load of each 3D printing manufacturing node, so that the platform is helped to know the condition of available manufacturing resources, important information is provided for allocation and arrangement of orders, and the platform is helped to know which 3D printing manufacturing nodes can bear different types of orders, thereby better allocating the order resources and improving the manufacturing efficiency. Meanwhile, the order screening process is carried out on the real-time orders of the users by using the credit correction scores of the users so as to screen out the orders of the credit users, so that the reliable user orders can be distributed to the 3D printing manufacturing nodes, and the reliability of order execution is improved. And then, the priority emergency ordering processing is carried out on the screened credit user orders so as to analyze the urgency of the credit user orders, thereby generating a priority emergency order ordering sequence, optimizing order allocation, ensuring that the credit user orders are reasonably allocated and prioritized, and improving the order execution efficiency. Next, node exploration analysis is performed on the 3D print manufacturing nodes by using the historical order information data, the order trust score and the order challenge score to obtain 3D print manufacturing trust nodes and 3D print manufacturing challenge nodes. And correcting and adjusting the suspicious nodes to obtain print manufacturing suspicious correction nodes, and combining the trust nodes and the correction nodes to form the 3D print manufacturing optimization nodes. And carrying out dispatch processing on credit user orders in the priority emergency order sequencing sequence based on the manufacturing node capacity bearing data and the optimizing node to generate user order dispatch result data, so that the performance and the characteristics of the 3D printing equipment and feedback information of an order user can be fully utilized to carry out an order dispatch process, the selection of the manufacturing node and the intelligence of order dispatch are improved, and the successful execution rate of the orders is increased. Finally, load analysis is carried out on the 3D printing manufacturing optimization node, so that the platform is helped to monitor the load condition of the manufacturing node in real time, and orders are adjusted according to the load condition, so that resource utilization and user order satisfaction rate are optimized to the greatest extent, and therefore, the production efficiency of user orders and the order execution efficiency are improved, and user demands are met.
Preferably, the present invention further provides an order dispatch system of a distributed 3D printing manufacturing platform, for executing an order dispatch method of the distributed 3D printing manufacturing platform as described above, where the order dispatch system of the distributed 3D printing manufacturing platform includes:
the user credit score detection module is used for acquiring historical order information data of the distributed 3D printing manufacturing platform, and carrying out user information identification analysis on the historical order information data to obtain order user information data; performing credit score detection on the order user information data so as to obtain the credit score of the order user;
The user credit score correction module is used for performing credit detection calculation on the historical order information data to obtain an order trust score and an order questioning score; carrying out questioning, evaluating and analyzing historical order information data according to the order questioning scores to obtain order questioning influence factors; carrying out credit correction analysis on the credit scores of the order users according to the order question influence factors so as to obtain the credit correction scores of the users;
the user order screening and sorting module is used for acquiring a user real-time order of the distributed 3D printing and manufacturing platform and 3D printing and manufacturing nodes; performing manufacturing capacity evaluation analysis on the 3D printing manufacturing node to obtain manufacturing node capacity bearing data; performing order screening processing on the real-time orders of the users according to the credit correction scores of the users to obtain credit user orders; carrying out priority emergency ordering treatment on the credit user orders, thereby obtaining a priority emergency order ordering sequence;
The printing node order dispatching module is used for carrying out node exploration analysis on the 3D printing manufacturing nodes by utilizing the order trust scores and the order questioning scores based on the historical order information data to obtain the 3D printing manufacturing trust nodes and the 3D printing manufacturing questioning nodes; performing node correction adjustment processing on the 3D printing manufacture question node to obtain a printing manufacture question correction node; combining the 3D printing manufacture trust node and the printing manufacture challenge correction node to obtain a 3D printing manufacture optimization node; based on the manufacturing node capacity bearing data and the 3D printing manufacturing optimization node, performing order dispatch processing on credit user orders in the priority emergency order sequencing sequence, so as to obtain user order dispatch result data;
The printing node dispatch adjustment module is used for carrying out load analysis on the 3D printing manufacture optimization node to obtain manufacture node load condition data; and performing dispatching and single-dispatching adjustment processing on the user order dispatching result data according to the manufacturing node load condition data, thereby obtaining user order dispatching adjustment data.
In summary, the invention provides an order dispatching system of a distributed 3D printing manufacturing platform, which consists of a user credit score detection module, a user credit score correction module, a user order screening and sorting module, a printing node order dispatching module and a printing node dispatching adjustment module.
Drawings
Other features, objects and advantages of the invention will become more apparent upon reading of the detailed description of a non-limiting implementation, made with reference to the accompanying drawings in which:
FIG. 1 is a schematic flow chart of the order dispatch method of the distributed 3D printing manufacturing platform according to the present invention;
FIG. 2 is a detailed step flow chart of step S1 in FIG. 1;
fig. 3 is a detailed step flow chart of step S2 in fig. 1.
Detailed Description
The following is a clear and complete description of the technical method of the present patent in conjunction with the accompanying drawings, and it is evident that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present invention without making any inventive effort, are intended to fall within the scope of the present invention.
Furthermore, the drawings are merely schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and thus a repetitive description thereof will be omitted. Some of the block diagrams shown in the figures are functional entities and do not necessarily correspond to physically or logically separate entities. The functional entities may be implemented in software or in one or more hardware modules or integrated circuits or in different networks and/or processor methods and/or microcontroller methods.
It will be understood that, although the terms "first," "second," etc. may be used herein to describe various elements, these elements should not be limited by these terms. These terms are only used to distinguish one element from another element. For example, a first element could be termed a second element, and, similarly, a second element could be termed a first element, without departing from the scope of example embodiments. The term "and/or" as used herein includes any and all combinations of one or more of the associated listed items.
In order to achieve the above objective, referring to fig. 1 to 3, the present invention provides an order dispatch method for a distributed 3D printing manufacturing platform, the method includes the following steps:
Step S1: acquiring historical order information data of a distributed 3D printing manufacturing platform, and performing user information identification analysis on the historical order information data to obtain order user information data; performing credit score detection on the order user information data to obtain the credit score of the order user;
step S2: performing reputation detection calculation on the historical order information data to obtain an order trust score and an order questioning score; carrying out questioning, evaluating and analyzing historical order information data according to the order questioning scores to obtain order questioning influence factors; carrying out credit correction analysis on the credit scores of the order users according to the order challenge influencing factors to obtain credit correction scores of the users;
Step S3: acquiring a user real-time order of a distributed 3D printing manufacturing platform and a 3D printing manufacturing node; performing manufacturing capacity evaluation analysis on the 3D printing manufacturing node to obtain manufacturing node capacity bearing data; performing order screening processing on the real-time orders of the users according to the credit correction scores of the users to obtain credit user orders; carrying out priority emergency ordering treatment on the credit user orders to obtain a priority emergency order ordering sequence;
Step S4: performing node exploration analysis on the 3D printing manufacturing nodes by utilizing the order trust scores and the order question scores based on the historical order information data to obtain 3D printing manufacturing trust nodes and 3D printing manufacturing question nodes; performing node correction adjustment processing on the 3D printing manufacture question node to obtain a printing manufacture question correction node; combining the 3D printing manufacture trust node and the printing manufacture challenge correction node to obtain a 3D printing manufacture optimization node; based on the manufacturing node capacity bearing data and the 3D printing manufacturing optimization node, performing order dispatch processing on credit user orders in the priority emergency order sequencing sequence to obtain user order dispatch result data;
step S5: carrying out load analysis on the 3D printing manufacturing optimization node to obtain manufacturing node load condition data; and performing dispatching and single-dispatching adjustment processing on the user order dispatching result data according to the manufacturing node load condition data to obtain user order dispatching adjustment data.
In the embodiment of the present invention, please refer to fig. 1, which is a schematic flow chart of steps of an order dispatch method of a distributed 3D printing manufacturing platform of the present invention, in this example, the steps of the order dispatch method of the distributed 3D printing manufacturing platform include:
Step S1: acquiring historical order information data of a distributed 3D printing manufacturing platform, and performing user information identification analysis on the historical order information data to obtain order user information data; performing credit score detection on the order user information data to obtain the credit score of the order user;
According to the embodiment of the invention, the necessary historical information data including the order number, the order date, the order amount, the product/service information, the client information and the related order state information are extracted from the database or the log file of the distributed 3D printing manufacturing platform, so that the historical order information data is obtained. Then, information data related to the user is extracted from the historical order information data by using a data mining technique or a text analysis technique, thereby obtaining order user information data. And finally, evaluating the information data of the order users, and grading the credit of each user according to the evaluation result to determine the credit level of the corresponding user, thereby finally obtaining the credit grade of the order users.
Step S2: performing reputation detection calculation on the historical order information data to obtain an order trust score and an order questioning score; carrying out questioning, evaluating and analyzing historical order information data according to the order questioning scores to obtain order questioning influence factors; carrying out credit correction analysis on the credit scores of the order users according to the order challenge influencing factors to obtain credit correction scores of the users;
According to the embodiment of the invention, the natural language processing technology is used for mining and analyzing the user comment text in the historical order information data so as to extract the evaluation information of the products and services manufactured by the platform by the user in the historical order, meanwhile, the relation between emotion vocabulary and reputation in the evaluation information is analyzed so as to help more accurately know emotion feedback of the user on order completion, the reputation level of the user comment is evaluated, the trust degree and the question degree of the user on the order are quantitatively analyzed according to the reputation level, and thus the order trust score and the order question score are obtained. And then, evaluating and analyzing the corresponding orders in the historical order information data by using the calculated order questioning scores so as to identify influence factors which cause the corresponding orders to be questioned, including order delivery delay, order product quality problems and the like, thereby obtaining the order questioning influence factors. And finally, analyzing the credit score of the order user by using the questioning credit influence factor obtained by analysis to detect the factor with the most obvious influence on the credit of the user and generate a corresponding credit correction index, and correcting the credit score of the order user according to the generated credit correction index so as to more accurately reflect the credit condition of the order user and finally obtain the credit correction score of the user.
Step S3: acquiring a user real-time order of a distributed 3D printing manufacturing platform and a 3D printing manufacturing node; performing manufacturing capacity evaluation analysis on the 3D printing manufacturing node to obtain manufacturing node capacity bearing data; performing order screening processing on the real-time orders of the users according to the credit correction scores of the users to obtain credit user orders; carrying out priority emergency ordering treatment on the credit user orders to obtain a priority emergency order ordering sequence;
the embodiment of the invention collects real-time order information from users on a distributed 3D printing and manufacturing platform, comprising design files of orders and related order design requirements, and simultaneously collects and acquires 3D printing and manufacturing nodes related to order manufacture, wherein the nodes comprise 3D printing equipment and 3D printing materials required by a bearing order manufacturer, so that the real-time orders of the users and the 3D printing and manufacturing nodes are obtained. Then, the manufacturing capability of each 3D printing manufacturing node is evaluated and analyzed by using a capability evaluation method to determine the manufacturing capability and the sustainable manufacturing load of each 3D printing manufacturing node, thereby obtaining manufacturing node capability withstand data. And then, judging the credit and payment history of the user in the user real-time order by using the credit correction score of the user, and screening out the user order with higher credit in the user real-time order according to the judgment result so as to obtain the credit user order. And finally, carrying out emergency detection analysis on the credit user order by using the order expiration date, the delivery time or other related factors in the credit user order to determine the emergency degree of the credit user order, determining the priority condition according to the emergency degree obtained by analysis, carrying out sequencing processing on the credit user order, establishing a reasonable order processing sequence according to the priority condition, and finally obtaining the priority emergency order sequencing sequence.
Step S4: performing node exploration analysis on the 3D printing manufacturing nodes by utilizing the order trust scores and the order question scores based on the historical order information data to obtain 3D printing manufacturing trust nodes and 3D printing manufacturing question nodes; performing node correction adjustment processing on the 3D printing manufacture question node to obtain a printing manufacture question correction node; combining the 3D printing manufacture trust node and the printing manufacture challenge correction node to obtain a 3D printing manufacture optimization node; based on the manufacturing node capacity bearing data and the 3D printing manufacturing optimization node, performing order dispatch processing on credit user orders in the priority emergency order sequencing sequence to obtain user order dispatch result data;
According to the embodiment of the invention, corresponding 3D printing manufacture nodes are explored and analyzed according to the order completion conditions (comprising using which 3D printing manufacture node is used for completing), user feedback and other information data in combination with order trust scores and order challenge scores on the historical order information data, so that the 3D printing manufacture nodes which are trustworthy and have a challenge on the printing manufacture capability in the historical order are analyzed, and the 3D printing manufacture trust nodes and the 3D printing manufacture challenge nodes are obtained. And then, carrying out detailed root cause analysis on each 3D printing manufacture questioning node to determine specific reasons causing user questioning, including reasons of printing manufacture quality problems, order completion delays and the like, and carrying out targeted correction adjustment on the specific reasons obtained by analysis to improve the performance and the reliability of the corresponding 3D printing manufacture questioning node and eliminate the user questioning problems in the corresponding 3D printing manufacture questioning node, thereby obtaining the printing manufacture questioning correction node. Next, a 3D print manufacturing optimization node is obtained by merging together the 3D print manufacturing trust node and the print manufacturing challenge correction node after correction processing to create a more reliable and optimized print manufacturing node set. Finally, the order allocation situation of the 3D printing manufacture optimization node is determined by analyzing the capacity bearing data corresponding to the 3D printing manufacture optimization node, and a corresponding order allocation strategy is formulated to allocate the credit user orders in the priority emergency order sorting sequence to the corresponding 3D printing manufacture optimization node, so that the order allocation strategy allocates the credit user orders in the priority emergency order sorting sequence to the user order allocation result data finally.
Step S5: carrying out load analysis on the 3D printing manufacturing optimization node to obtain manufacturing node load condition data; and performing dispatching and single-dispatching adjustment processing on the user order dispatching result data according to the manufacturing node load condition data to obtain user order dispatching adjustment data.
According to the embodiment of the invention, the current working state and the load condition of the resource utilization condition of each 3D printing manufacture optimization node are analyzed and determined by analyzing the resource utilization condition of 3D printing equipment and 3D printing materials and the 3D printing task condition in the 3D printing manufacture optimization node, so that the manufacture node load condition data is obtained. And then, analyzing the load condition data of the manufacturing nodes, and carrying out reassignment adjustment on order dispatch results in the user order dispatch result data according to the analysis results so as to determine which order tasks should be reassigned to which 3D printing manufacturing optimization nodes without load conditions, so that the load conditions of the nodes are balanced to the greatest extent, and finally, the user order dispatch adjustment data is obtained.
According to the invention, the historical order information data of the distributed 3D printing manufacturing platform is collected, and user information identification analysis is carried out on the collected historical order information data to obtain order user information data, so that information about an order user, such as names, contact information and purchase history, can be extracted from the historical order data, the user file can be built, the order characteristics of the user, such as purchase habits and preferred product types, can be known, and the method can be used for personalized marketing of the platform, customer relationship management and improvement of customer satisfaction. Then, by performing credit score detection on the order user information data, accurate assessment of the credit status of the historical order users can be achieved, so that the platform is helped to know the credit reliability of the users, and the orders and resources can be managed better. Secondly, by performing reputation detection calculation on historical order information data to generate an order trust score and an order question score, the trust level of a user and questions of an order can be quantified, which is helpful for identifying high-reputation users, reducing bad transaction risks and identifying possible disputes and questions in advance, thereby reducing potential losses. Meanwhile, by carrying out question evaluation analysis on the historical order information data based on the order question scores, the method can determine which orders have disputes or problems and know the root causes of the questions, which is helpful for improving service quality, solving the disputes, improving user satisfaction and reducing refunds and disputes, thereby improving the reputation of the platform. Credit impact correction analysis is carried out on credit scores of order users by using the questioning credit impact factors obtained through analysis, and the credit scores of the users can be corrected by analyzing and generating corresponding correction indexes so as to more accurately reflect credit conditions of the users, so that fairness of the credit scores is improved, accuracy of risk management is ensured, more reliable credit information of the users is provided for a platform, the reliability and questioning conditions of the users can be known more accurately by the platform, and potential risks and losses are reduced. Then, the user orders on the distributed 3D printing manufacturing platform and the information of the 3D printing manufacturing nodes are acquired in real time, so that the data view of the overall production environment is beneficial to be established by acquiring corresponding data, the platform can provide basic data guarantee for the subsequent processing process, meanwhile, the orders are effectively distributed and scheduled, and the orders can be ensured to be smoothly manufactured in 3D printing. And the 3D printing manufacturing nodes are subjected to manufacturing capability assessment analysis to determine the manufacturing capability and the bearable manufacturing load of each 3D printing manufacturing node, so that the platform is helped to know the condition of available manufacturing resources, important information is provided for allocation and arrangement of orders, and the platform is helped to know which 3D printing manufacturing nodes can bear different types of orders, thereby better allocating the order resources and improving the manufacturing efficiency. Meanwhile, the order screening process is carried out on the real-time orders of the users by using the credit correction scores of the users so as to screen out the orders of the credit users, so that the reliable user orders can be distributed to the 3D printing manufacturing nodes, and the reliability of order execution is improved. And then, the priority emergency ordering processing is carried out on the screened credit user orders so as to analyze the urgency of the credit user orders, thereby generating a priority emergency order ordering sequence, optimizing order allocation, ensuring that the credit user orders are reasonably allocated and prioritized, and improving the order execution efficiency. Next, node exploration analysis is performed on the 3D print manufacturing nodes by using the historical order information data, the order trust score and the order challenge score to obtain 3D print manufacturing trust nodes and 3D print manufacturing challenge nodes. And correcting and adjusting the suspicious nodes to obtain print manufacturing suspicious correction nodes, and combining the trust nodes and the correction nodes to form the 3D print manufacturing optimization nodes. And carrying out dispatch processing on credit user orders in the priority emergency order sequencing sequence based on the manufacturing node capacity bearing data and the optimizing node to generate user order dispatch result data, so that the performance and the characteristics of the 3D printing equipment and feedback information of an order user can be fully utilized to carry out an order dispatch process, the selection of the manufacturing node and the intelligence of order dispatch are improved, and the successful execution rate of the orders is increased. Finally, load analysis is carried out on the 3D printing manufacturing optimization node, so that the platform is helped to monitor the load condition of the manufacturing node in real time, and orders are adjusted according to the load condition, so that resource utilization and user order satisfaction rate are optimized to the greatest extent, and therefore, the production efficiency of user orders and the order execution efficiency are improved, and user demands are met.
Preferably, step S1 comprises the steps of:
step S11: acquiring historical order information data of a distributed 3D printing manufacturing platform;
Step S12: performing data quality screening processing on the historical order information data to obtain order information high-quality data;
step S13: user information identification analysis is carried out on the order information high-quality data to obtain order user information data;
Step S14: performing user portrait mining analysis on the order user information data to obtain order user portrait data;
Step S15: user evaluation analysis is carried out on the order user portrait data to obtain order user evaluation data;
step S16: and carrying out credit score detection on the order user evaluation data to obtain the credit score of the order user.
As an embodiment of the present invention, referring to fig. 2, a detailed step flow chart of step S1 in fig. 1 is shown, in which step S1 includes the following steps:
step S11: acquiring historical order information data of a distributed 3D printing manufacturing platform;
According to the embodiment of the invention, the necessary historical information data including the order number, the order date, the order amount, the product/service information, the client information and the related order state information are extracted from the database or the log file of the distributed 3D printing manufacturing platform, so that the historical order information data is finally obtained.
Step S12: performing data quality screening processing on the historical order information data to obtain order information high-quality data;
According to the embodiment of the invention, firstly, the data cleaning is carried out on the historical order information data, including repeated record removal, missing value processing, data format error correction and the like, so that the quality of the data is ensured, and the abnormal value detection is carried out to identify and process the abnormal order data existing in the historical order information data, so that the order information high-quality data is finally obtained.
Step S13: user information identification analysis is carried out on the order information high-quality data to obtain order user information data;
According to the embodiment of the invention, the data mining technology or the text analysis technology is used for extracting the information data related to the user from the order information high-quality data, and finally the order user information data is obtained.
Step S14: performing user portrait mining analysis on the order user information data to obtain order user portrait data;
According to the embodiment of the invention, the user portrait mining model is built by using the order user information data, then the detailed user portrait is built by analyzing the order user information data by using the built user portrait mining model so as to identify the purchase characteristics and preferences of the user, including information such as age, gender, interests, purchase history and preferences, and finally the order user portrait data is obtained.
Step S15: user evaluation analysis is carried out on the order user portrait data to obtain order user evaluation data;
According to the method and the system for analyzing the image data of the order users, the image data of the order users are analyzed through an evaluation analysis technology, so that feedback of the users on the order products including satisfaction, suggestion of comments, complaints, comments and the like is thoroughly known, and finally the evaluation data of the order users are obtained.
Step S16: and carrying out credit score detection on the order user evaluation data to obtain the credit score of the order user.
The embodiment of the invention carries out credit scoring on each user by using the evaluation result of the order user evaluation data so as to determine the credit level of the corresponding user and finally obtain the credit score of the order user.
According to the invention, firstly, by collecting historical order information data of the distributed 3D printing manufacturing platform, a comprehensive platform order service data set can be established, which is helpful for tracking the change of the number, the type and the transaction scale of orders, so that the trend and the historical evolution of order service operation can be better known. By collecting historical order data, time series data may be created to better predict user demand, user portraits, and user ratings. Meanwhile, the collected historical order information data is subjected to data quality screening processing, so that the collected data set can be ensured to be accurate, consistent and reliable, and the step is used for removing error items, de-duplication items and filling missing values by cleaning the data, so that the influence of quality problems of the historical order information data on subsequent analysis is reduced. The data cleansing helps to improve the reliability of the subsequent analysis process, ensuring that the subsequent processing steps are strategically selected based on high quality data. Second, by performing user information identification analysis on the order information high-quality data, information about the order user, such as name, contact information and purchase history, can be extracted from the historical order data, which helps to build a user profile, learn about the order characteristics of the user, such as purchasing habits and preferred product categories, which can be used for personalized marketing of the platform, customer relationship management and improving customer satisfaction. Then, by performing user profile mining analysis on the order user information data, detailed user profiles can be created, including information on age, gender, interests, purchase history, preferences, etc., which helps to better understand the user population, provide personalized products and services for them, enhance user loyalty, and provide base data for subsequent credit score detection. And then, user evaluation analysis is carried out on the user portrait data of the order, so that feedback of the user on the order product can be deeply known according to the user portrait data, the analysis comprises satisfaction, opinion suggestion, complaint, comments and the like, the analysis is helpful for improving the product quality of platform manufacture, optimizing the platform service flow, and timely responding to the user demand, thereby improving the user satisfaction and loyalty and providing data guarantee for the follow-up credit score detection. Finally, by performing credit score detection on the order user evaluation data, the credit risk of the user can be quantified according to the evaluation result data, which is critical for formulating credit policies, determining payment conditions, reducing bad account risk and pricing strategies. In addition, the detected credit score helps to reduce risk, and ensures that order traffic in the subsequent process cooperates with the trusted user.
Preferably, step S2 comprises the steps of:
Step S21: comment mining analysis is carried out on the historical order information data to obtain historical order comment information data;
step S22: word cloud key identification analysis is carried out on the historical order comment information data to obtain order comment key word information data;
step S23: performing reputation evaluation analysis on the order comment keyword information data to obtain order comment reputation evaluation data;
Step S24: performing scoring calculation on the order comment credit evaluation data by using a credit score detection calculation formula to obtain an order trust score and an order questioning score;
Step S25: carrying out questioning, evaluating and analyzing historical order information data according to the order questioning scores to obtain order questioning influence factors;
Step S26: carrying out credit influence detection analysis on credit scores of order users according to the order questioning influence factors to obtain questioning credit influence correction indexes; and carrying out credit correction processing on the credit scores of the order users according to the questioning credit influence correction index to obtain the credit correction scores of the users.
As an embodiment of the present invention, referring to fig. 3, a detailed step flow chart of step S2 in fig. 1 is shown, in which step S2 includes the following steps:
Step S21: comment mining analysis is carried out on the historical order information data to obtain historical order comment information data;
According to the embodiment of the invention, through using a natural language processing technology to mine and analyze the user comment text in the historical order information data, the evaluation information of the user on the products and services manufactured by the platform in the historical order is extracted, and finally the historical order comment information data is obtained.
Step S22: word cloud key identification analysis is carried out on the historical order comment information data to obtain order comment key word information data;
According to the embodiment of the invention, firstly, text processing is carried out on the mined historical order comment information data, such as word segmentation, stop word removal and the like, so that the accuracy of the data is ensured, then, important phrases in the historical order comment information data are identified and extracted by using a text analysis technology, and the frequency and the importance of the phrases are intuitively displayed by generating a word cloud picture, so that key words are extracted from the phrases, and finally, order comment key word information data are obtained.
Step S23: performing reputation evaluation analysis on the order comment keyword information data to obtain order comment reputation evaluation data;
According to the embodiment of the invention, through analyzing the relation between the emotion vocabulary and the reputation in the order comment keyword information data, the emotion feedback of the user on order completion is more accurately known, the reputation level of the user comment is evaluated, and finally the order comment reputation evaluation data is obtained.
Step S24: performing scoring calculation on the order comment credit evaluation data by using a credit score detection calculation formula to obtain an order trust score and an order questioning score;
The embodiment of the invention forms a proper credit score detection calculation formula by combining the positive and negative comment feedback quantity parameter, the total comment feedback quantity parameter, the positive and negative comment quality parameter, the total comment quality parameter, the positive and negative comment vocabulary quantity parameter, the mean value and standard deviation of the positive and negative comment vocabulary quantity, the corresponding score adjustment parameter and related parameters to carry out score calculation on the comment credit evaluation data of the order so as to quantitatively analyze the trust degree and the question degree of the user on the order and finally obtain the trust score and the question score of the order. In addition, the reputation score detection calculation formula can also use any reputation detection algorithm in the field to replace the score calculation process, and is not limited to the reputation score detection calculation formula.
Step S25: carrying out questioning, evaluating and analyzing historical order information data according to the order questioning scores to obtain order questioning influence factors;
According to the embodiment of the invention, the corresponding orders in the historical order information data are evaluated and analyzed by using the calculated order questioning scores so as to identify the influence factors which cause the corresponding orders to be questioned, including order delivery delay, order product quality problems and the like, and finally the order questioning influence factors are obtained.
Step S26: carrying out credit influence detection analysis on credit scores of order users according to the order questioning influence factors to obtain questioning credit influence correction indexes; and carrying out credit correction processing on the credit scores of the order users according to the questioning credit influence correction index to obtain the credit correction scores of the users.
The embodiment of the invention firstly analyzes the credit score of the order user by using the questioning credit influence factor obtained by analysis so as to detect the factor with the most obvious influence on the credit of the user and generate a corresponding credit correction index, thereby obtaining the questioning credit influence correction index. And then, correcting the credit score of the order user according to the generated questioning credit influence correction index so as to more accurately reflect the credit condition of the order user and finally obtain the credit correction score of the user.
According to the invention, firstly, through comment mining analysis on historical order information data, the evaluation of products and services manufactured by a platform by a user can be deeply known, so that basic data is provided for the subsequent understanding of the root causes of satisfaction and dissatisfaction, the problem field of orders is identified, the product design and service flow are improved, and the user satisfaction and loyalty are improved. In addition, the method is helpful to find implicit requirements and provide data support for market positioning and strategic planning. Meanwhile, through word cloud key identification analysis on historical order comment information data, key words can be extracted from a large number of comments to find topics and feelings which are most concerned by users, so that the users can know demands of the users, strengthen product characteristics and quickly find possible problems. The platform can use this information to pinpoint the improvement points, providing products and services that are more consistent with the user's desires. Secondly, by performing reputation evaluation analysis on the extracted order comment keyword information data, the overall impression of the user on the manufactured products and services can be objectively evaluated, and the trust degree of the user on the platform and the satisfaction degree of the user can be known. Based on this analysis, the platform may calculate a user's trust score for the order based on the evaluation data, thereby providing a basic data guarantee for the subsequent score calculation process. Then, by scoring the order review reputation evaluation data using a suitable reputation score detection calculation formula, the platform can quantify the user's level of trust and questions of the order, which helps identify high reputation users, reduce risk of bad transactions, and identify possible disputes and questions in advance, thereby mitigating potential losses. And then, by carrying out question evaluation analysis on the historical order information data based on the order question scores, the method can determine which orders have disputes or problems and know the root causes of the questions, which is helpful for improving the service quality, solving the disputes, improving the user satisfaction and reducing refunds and disputes, thereby improving the reputation of the platform. Finally, credit influence detection analysis is carried out on credit scores of the order users by using the questioning credit influence factors obtained through analysis, so that factors with the most obvious influence on the credit of the users are detected, and corresponding credit correction indexes are generated, and the credit scores of the users can be corrected by the correction indexes to more accurately reflect the credit conditions of the users, so that the fairness of the credit scores is improved, the accuracy of risk management is ensured, more reliable credit information of the users is provided for a platform, and potential risks and losses are reduced.
Preferably, step S23 comprises the steps of:
step S231: carrying out emotion calculation on the order comment keyword information data by using a comment emotion calculation formula to obtain a comment emotion degree value;
According to the embodiment of the invention, a proper comment emotion calculation formula is formed by combining the emotion score of positive emotion, the emotion score of negative emotion, the emotion score of neutral emotion, the emotion intensity parameter, the corresponding emotion weight adjustment parameter, the reconciliation smoothing parameter of neutral emotion, the time parameter of opinion detection calculation, the time correlation parameter of emotion intensity and the correlation parameter, so that emotion calculation is carried out on order comment keyword information data to quantitatively reflect the emotion polarity of user comments, namely positive, neutral and negative emotion, and finally comment emotion degree values are obtained. In addition, the comment emotion calculation formula can also use any emotion measurement algorithm in the field to replace the emotion calculation process, and is not limited to the comment emotion calculation formula.
The comment emotion calculation formula is as follows:
Wherein S is a comment emotion degree value, n is the number of emotion words in order comment keyword information data, Z i is emotion score of the ith emotion word in order comment keyword information data expressed as positive emotion, w Z is emotion weight adjustment parameter of the positive emotion, F i is emotion score of the ith emotion word in order comment keyword information data expressed as negative emotion, w Z is emotion weight adjustment parameter of the negative emotion, E i is emotion score of the ith emotion word in order comment keyword information data expressed as neutral emotion, w E is emotion weight adjustment parameter of the neutral emotion, alpha is harmonic smoothing parameter of the neutral emotion, t 1 is initial time of opinion detection calculation, t 2 is termination time of opinion detection calculation, t is integral time variable of opinion detection calculation, ζ (t) is emotion strength parameter of emotion words in order comment keyword information data at time t, w ξ is emotion weight adjustment parameter of emotion strength, and ε is time correlation parameter of emotion strength;
the comment emotion calculation formula is constructed and used for carrying out emotion calculation on the order comment keyword information data, comprehensively considers the quantity of emotion words, emotion scores and weights of the emotion words and the emotion scores in the total emotion, and also considers factors such as neutral emotion, time correlation and the like, so that emotion of an order comment is calculated more comprehensively and carefully, and meanwhile emotion intensity change in a time dimension is considered, so that emotion tendency of an integral comment can be understood, emotion intensity and time change are considered, and understanding of emotion integral expression and evaluation of a product or service in a user comment is facilitated. Through the evaluation process, the reputation evaluation data of the order comments can be obtained, so that the comments are objectively analyzed and evaluated. The formula fully considers comment emotion degree value S, the number n of emotion words in order comment keyword information data, emotion score Z i of the ith emotion word in order comment keyword information data expressed as positive emotion, emotion weight adjustment parameter w Z of the positive emotion, emotion weight adjustment parameter w Z of the negative emotion, emotion weight adjustment parameter w i of the neutral emotion, emotion weight adjustment parameter w E of the neutral emotion, harmonic smoothing parameter alpha of the neutral emotion, initial time t 1 of opinion detection calculation, final time t 2 of opinion detection calculation, emotion intensity parameter t of emotion words in order comment keyword information data at time t, emotion weight adjustment parameter w ξ of emotion intensity, time correlation parameter beta of emotion intensity, epsilon of comment emotion degree value and epsilon of a zeta correlation relation between comment emotion degree value S and the above parameters form a function:
The formula can realize the emotion calculation process of the order comment keyword information data, and meanwhile, the introduction of the correction value epsilon of the comment emotion degree value can be adjusted according to the error condition in the calculation process, so that the accuracy and the applicability of the comment emotion calculation formula are improved.
Step S232: the comment emotion degree value is subjected to subdivision judgment according to a preset comment emotion degree threshold value, and when the comment emotion degree value is larger than the preset comment emotion degree threshold value, the order comment keyword information data corresponding to the comment emotion degree value is marked as comment negative emotion data; when the comment emotion degree value is equal to a preset comment emotion degree threshold value, marking the order comment keyword information data corresponding to the comment emotion degree value as comment neutral emotion data and removing the comment neutral emotion data from the order comment keyword information data; when the comment emotion degree value is smaller than a preset comment emotion degree threshold value, marking the order comment keyword information data corresponding to the comment emotion degree value as comment front emotion data;
According to the embodiment of the invention, the calculated comment emotion degree value is compared and judged according to the preset comment emotion degree threshold value, and if the comment emotion degree value is larger than the preset comment emotion degree threshold value, the comment content of the comment keyword information data corresponding to the comment emotion degree value is indicated to be negative emotion content, the comment keyword information data corresponding to the comment emotion degree value is marked as comment negative emotion data; if the comment emotion degree value is equal to a preset comment emotion degree threshold value, the comment content of the comment emotion degree value corresponding to the order comment keyword information data is neutral emotion content, the subsequent analysis process is not affected, the order comment keyword information data corresponding to the comment emotion degree value is marked as comment neutral emotion data, and the comment neutral emotion data is removed from the order comment keyword information data; if the comment emotion degree value is smaller than a preset comment emotion degree threshold value, the comment content of the comment emotion degree value corresponding to the order comment keyword information data is the positive emotion content, and the order comment keyword information data corresponding to the comment emotion degree value is marked as comment positive emotion data.
Step S233: carrying out emotion distribution detection analysis on the negative emotion data of the comment and the positive emotion data of the comment to obtain negative emotion distribution data and positive emotion distribution data;
According to the embodiment of the invention, the negative emotion data marked as the comment and the positive emotion data marked as the comment are analyzed by using the data distribution detection method so as to detect the data distribution conditions of the negative emotion data and the positive emotion data under the conditions of time, place or other relevant factors, and finally the negative emotion distribution data and the positive emotion distribution data are obtained.
Step S234: carrying out emotion difference analysis on the negative emotion distribution data and the positive emotion distribution data to obtain comment emotion distribution difference data;
According to the embodiment of the invention, the distribution conditions of the negative emotion distribution data and the positive emotion distribution data are compared, and the distribution difference condition between the negative emotion distribution data and the positive emotion distribution data is searched to determine which factors cause emotion differences, so that comment emotion distribution difference data is finally obtained.
Step S235: performing reputation factor identification analysis on comment emotion distribution difference data to obtain emotion difference reputation key factors; performing reputation association analysis on comment emotion distribution difference data according to emotion difference reputation key factors to obtain emotion difference reputation association data;
According to the embodiment of the invention, the reputation of the user comment is analyzed through comment emotion distribution difference data so as to identify the key factors affecting the reputation of the user comment in emotion differences, thereby obtaining the emotion difference reputation key factors. And then, carrying out further association analysis on the emotion difference reputation key factors and comment emotion distribution difference data by using an association rule analysis technology so as to analyze the association relation between emotion differences and reputations, ensuring that the interaction relation between emotion differences and reputations can be analyzed more accurately, and finally obtaining emotion difference reputation association data.
Step S236: and evaluating and analyzing the order comment keyword information data according to the emotion difference reputation association data to obtain order comment reputation evaluation data.
According to the embodiment of the invention, the comment emotion difference in the emotion difference reputation associated data and the association relation between the user reputation are used for analyzing the order comment keyword information data, so that emotion feedback of a user on order completion can be accurately known, factors related to reputation are identified, and finally the order comment reputation evaluation data is obtained.
According to the method, the comment keyword information data of the order comment is subjected to emotion calculation by using a proper comment emotion calculation formula, and the emotion degree value obtained through calculation can reflect the emotion polarity of the comment of the user, namely positive, neutral or negative emotion, so that comment content can be quantized, and emotion experience of the user can be understood deeply. Meanwhile, comment emotion degree values are divided by using a preset comment emotion degree threshold value, and when the emotion degree value is larger than the threshold value, comments are marked as negative emotion, so that unsatisfactory or negative comments can be identified. When the emotion level value is equal to the threshold, the comments are marked as neutral emotion and removed because they do not have a positive or negative trend for the subsequent analysis process. And when the emotion degree value is smaller than the threshold value, the comment is marked as positive emotion, which is helpful for identifying satisfactory or positive comments, so that the platform can be helped to quickly screen out potential problems and good comments, and clear emotion data is provided for subsequent analysis. Secondly, through carrying out emotion distribution detection analysis on marked comment negative emotion data and comment positive emotion data, distribution conditions of negative emotion and positive emotion are obtained, the distribution degree of the negative emotion and the positive emotion in the comment is known, and emotion distribution data support is provided for subsequent analysis. And then, through emotion difference analysis on the negative emotion distribution data and the positive emotion distribution data, the difference between the positive emotion and the negative emotion can be revealed by comparing the distribution conditions of the negative emotion and the positive emotion, so that the distribution conditions of different types of emotions in comments and the change trend of the emotion of the user can be known. Next, by performing reputation factor identification analysis on the comment emotion distribution difference data to determine key factors that affect emotion differences, such as product characteristics, quality of service, etc., this can help the platform identify potential problems and opportunities and provide directions for improving products or services. In addition, the comment emotion distribution difference data is subjected to association analysis through emotion difference reputation key factors, so that key factors of user requirements and satisfaction can be known more accurately. Finally, through the evaluation and analysis of the order comment keyword information data by using the emotion difference reputation association data obtained through the analysis, the emotion feedback of the user on the product or service can be accurately known, and the factors related to the reputation are identified, so that the improvement of the product, service and user experience is facilitated, the satisfaction degree of the user is enhanced, the brand reputation is maintained, the risk is reduced, and a targeted strategic decision is made.
Preferably, the reputation score detection calculation formula in step S24 is specifically:
Wherein T s is the order trust score, N is the number of order comment reputation evaluation data, P j is the positive comment feedback number parameter in the jth order comment reputation evaluation data, C j is the total comment feedback number parameter in the jth order comment reputation evaluation data, a 1 is the score adjustment parameter of the positive comment feedback number, T j is the positive comment quality parameter in the jth order comment reputation evaluation data, T is the total comment quality parameter in the order comment reputation evaluation data, b 1 is the score adjustment parameter of the positive comment quality, x j is the positive comment vocabulary quantity parameter in the j-th order comment reputation evaluation data, mu 1 is the average value of the positive comment vocabulary quantity, sigma 1 is the standard deviation of the positive comment vocabulary quantity, x is the integral vocabulary parameter of the positive comment vocabulary quantity, c 1 is the score adjustment parameter of the positive comment vocabulary quantity, epsilon 1 is the correction value of the order trust score, D s is the order question score, Q j is the negative comment feedback quantity parameter in the j-th order comment reputation evaluation data, a 2 is a grading adjustment parameter of the feedback quantity of the negative comments, R j is a grading adjustment parameter of the quality of the negative comments in the credit evaluation data of the jth order comment, b 2 is a grading adjustment parameter of the quality of the negative comments, y j is a grading adjustment parameter of the quantity of the negative comments in the credit evaluation data of the jth order comment, mu 2 is a mean value of the quantity of the negative comments, sigma 2 is a standard deviation of the quantity of the negative comments, y is a grading adjustment parameter of the quantity of the negative comments, c 2 is a grading adjustment parameter of the quantity of the negative comments, epsilon 2 is the correction value of the order challenge score.
The credit score detection calculation formula is constructed and used for carrying out score calculation on the credit evaluation data of the orders, and comprehensively considers factors such as positive comment feedback, positive comment quality, positive comment vocabulary quantity, negative comment feedback, negative comment quality, negative comment vocabulary quantity and the like, calculates trust scores and question scores of the orders, and can be used for evaluating the overall quality and the trust degree of the orders. The calculated score reflects the trust and challenge of the user order, which is useful to both the user and the service provider, and the trust score can help the user select a trusted 3D print manufacturer, while the challenge score can help the platform identify 3D print manufacturers that may have manufacturing problems and make adjustments accordingly. The formula fully considers the quantity N of the order comment reputation evaluation data, the positive comment feedback quantity parameter P j in the jth order comment reputation evaluation data, the total comment feedback quantity parameter C j in the jth order comment reputation evaluation data, the positive comment quality parameter a 1 of the positive comment feedback quantity, the positive comment quality parameter T j in the jth order comment reputation evaluation data, the total comment quality parameter T in the order comment reputation evaluation data, the positive comment quality score adjustment parameter b 1, the positive comment vocabulary quantity parameter x j in the jth order comment reputation evaluation data, the average mu 1 of the positive comment vocabulary quantity, the standard deviation sigma 1 of the positive comment vocabulary quantity, the integral vocabulary parameter x of the positive comment vocabulary quantity and the score adjustment parameter C 1 of the positive comment vocabulary quantity form a function relation of an order trust score T s:
In addition, the j-th order comment reputation evaluation data, the negative comment feedback quantity parameter Q j, the negative comment feedback quantity score adjustment parameter a 2, the j-th order comment reputation evaluation data, the negative comment quality parameter R j, the negative comment quality score adjustment parameter b 2, the j-th order comment reputation evaluation data, the negative comment vocabulary quantity parameter y j, the negative comment vocabulary quantity average μ 2, the negative comment vocabulary quantity standard deviation σ 2, the negative comment vocabulary quantity integral vocabulary parameter y and the negative comment vocabulary quantity score adjustment parameter c 2 form a functional relationship of the order question score D s:
the formula can realize the grading calculation process of the order comment reputation evaluation data, and meanwhile, the correction value epsilon 1 of the order trust grading and the correction value epsilon 2 of the order question grading can be adjusted according to the error condition in the calculation process, so that the accuracy and the stability of the reputation grading detection calculation formula are improved.
Preferably, step S25 comprises the steps of:
step S251: carrying out questioning influence factor detection on the historical order information data according to the order questioning scores to obtain order questioning influence factors;
According to the embodiment of the invention, the corresponding order information data in the historical order information data is detected and analyzed by using the calculated order question score, various potential factors which cause the quality question influence of the order are identified according to the analyzed order information data (including feedback, return situation, delivery delay or other related factors based on clients), and finally the order question influence factors are obtained.
Step S252: carrying out influence mode detection analysis on the order questioning influence factors to obtain questioning influence factor mode data;
According to the embodiment of the invention, the influence modes among the order questioning influence factors are determined by carrying out deep detection analysis on the identified order questioning influence factors, so that the reason of the occurrence of the order questioning can be better understood, and finally the questioning influence factor mode data can be obtained.
Step S253: carrying out mode topology analysis on the questioning influence factor mode data to obtain an influence factor topology relation diagram;
According to the embodiment of the invention, the topology analysis tool is used for carrying out the topology analysis on the suspected influence factor mode data so as to analyze and establish the topology relation among the suspected influence factor mode data, and meanwhile, the association among different influence factors is visualized by using the form of a chart so as to better understand the interaction among the different influence factors and finally obtain the influence factor topology relation diagram.
Step S254: carrying out influence factor weighing processing on the influence factor topological relation diagram to obtain questioning influence factor weighing data;
according to the embodiment of the invention, each influence factor is weighed according to the analyzed influence factor topological relation diagram, and the relative importance of different influence factors is evaluated to determine which influence factors have more remarkable influence on order questioning, so that questioning influence factor weighing data is finally obtained.
Step S255: factor adjustment is carried out on the order questioning influence factors according to questioning influence factor weighing data and the influence factor topological relation diagram so as to obtain main questioning influence factors;
According to the embodiment of the invention, the relative weights of all the influence factors are adjusted by analyzing the weighing data and the topological relation diagram of the questioning influence factors, so that the key order questioning influence factors are determined when the questioning problem is solved, and the main questioning influence factors are finally obtained.
Step S256: and carrying out influence evaluation analysis on the main factors of the questioning influence to obtain the order questioning influence factors.
According to the embodiment of the invention, the determined main factors of the questioning influence are evaluated and analyzed to analyze and determine the specific influence degree of each influence factor on the questioning of the order, and the influence factors for deeply knowing the questioning problem of the order are provided, so that the influence factors of the questioning of the order are finally obtained.
The invention analyzes the historical order information data by using the calculated order question score to identify factors affecting the order question, which is beneficial to determining the root cause of the user question, providing a direction for problem resolution, and improving user satisfaction. Meanwhile, by detecting and analyzing the influence modes of the order questioning influence factors detected and analyzed, the relation among different order questioning influence factors can be determined, including how they influence each other and how they influence the mode of the order questioning, so that potential modes and trends can be identified, and the platform can be helped to better know the root cause of the user questioning problem. And secondly, carrying out mode topology analysis on the questioning influence factor mode data, constructing and obtaining a topological relation diagram between corresponding order questioning influence factors according to the questioning influence factor mode data, wherein the diagram can indicate the relation between different order questioning influence factors, including causality and relativity, and provides a visual tool for subsequent analysis, so that a platform can better understand the structure and the interrelationship of user questioning problems. Then, by carrying out influence factor weighing processing on the influence factor topological relation diagram, the influence factors with larger influence on order question can be determined, which is beneficial to optimizing resource allocation and concentrating on solving the most important problems, thereby improving efficiency and customer satisfaction. And then, by considering the weighing data and the topological relation diagram of the questioning influence factors, the factor adjustment can be carried out on the order questioning influence factors so as to determine which order questioning influence factors are most critical in solving the questioning problem, so that the platform can be helped to more accurately identify the main questioning influence factors, and the flow and efficiency of the solution of the problem are optimized. Finally, through carrying out influence evaluation analysis on main factors of the questioning influence, the influence factors for deeply knowing the order questioning problem can be provided, the influence factors obtained through analysis can help a platform to take targeted measures to improve the order processing flow, improve the user satisfaction, reduce the questioning rate and enhance the user relationship, and the series of steps enables the platform to be capable of more effectively dealing with the order questioning, improves the operation efficiency and provides more excellent user experience.
Preferably, step S3 comprises the steps of:
step S31: acquiring a user real-time order of a distributed 3D printing manufacturing platform and a 3D printing manufacturing node, wherein the 3D printing manufacturing node comprises 3D printing equipment and 3D printing materials of a party bearing the order manufacturing;
The embodiment of the invention collects real-time order information from users on a distributed 3D printing and manufacturing platform, comprising design files of orders and related order design requirements, and simultaneously collects and acquires 3D printing and manufacturing nodes related to order manufacture, wherein the nodes comprise 3D printing equipment and 3D printing materials required by a bearing order manufacturer, and finally obtains real-time orders of the users and 3D printing and manufacturing nodes.
Step S32: performing manufacturing capacity evaluation analysis on the 3D printing manufacturing node to obtain manufacturing node capacity bearing data;
The embodiment of the invention evaluates and analyzes the manufacturing capacity of each 3D printing manufacturing node by using a capacity evaluation method, and comprises the steps of examining the performance and availability of 3D printing equipment of the 3D printing manufacturing node and the supply condition of related 3D printing materials so as to determine the manufacturing capacity and bearable manufacturing load of each 3D printing manufacturing node and finally obtain manufacturing node capacity bearing data.
Step S33: performing order screening processing on the real-time orders of the users according to the credit correction scores of the users to obtain credit user orders;
the credit correction scoring method and the credit correction scoring system judge the credit and payment history of the user in the user real-time order, screen out the user order with higher credit in the user real-time order according to the judgment result, ensure that the reliable user order can be distributed to the 3D printing manufacturing node, and finally obtain the credit user order.
Step S34: carrying out order emergency detection analysis on the credit user order to obtain order emergency data; carrying out manufacturing difficulty level assessment on the credit user order based on the order emergency data to obtain emergency manufacturing difficulty level data;
The embodiment of the invention carries out emergency detection analysis on the credit user order by using the order expiration date, the delivery time or other related factors in the credit user order so as to determine the emergency degree of the credit user order, thereby obtaining the order emergency data. And then, carrying out manufacturing grade evaluation on the corresponding credit user orders by using the analyzed order emergency data so as to evaluate the manufacturing difficulty grade of the credit user orders, and finally obtaining emergency manufacturing difficulty grade data.
Step S35: carrying out priority detection analysis on credit user orders according to the emergency manufacturing difficulty level data to obtain user order priorities;
According to the embodiment of the invention, the priority of the corresponding credit user orders is distributed according to the analysis result by analyzing the emergency manufacturing difficulty level data, so that the priority of each credit user order is determined, the more complex or emergency orders can be ensured to obtain higher processing priority, and finally the user order priority is obtained.
Step S36: and carrying out order sorting processing on the credit user orders according to the user order priority, and obtaining a priority emergency order sorting sequence.
The credit user orders are ordered by using the analyzed user order priority, and a reasonable order processing sequence is established according to the priority, so that reasonable allocation of the credit user orders and effective utilization of manufacturing nodes are ensured, and a priority emergency order ordering sequence is finally obtained.
According to the invention, the user order and the information of the 3D printing manufacturing nodes on the distributed 3D printing manufacturing platform are acquired in real time, wherein the 3D printing manufacturing nodes comprise 3D printing equipment for bearing order manufacture and corresponding 3D printing materials, so that the platform can provide basic data guarantee for the subsequent processing process by acquiring corresponding data to be beneficial to establishing a data view of a comprehensive production environment, and meanwhile, the order is effectively distributed and scheduled, so that the order can be smoothly subjected to 3D printing manufacture. Secondly, the manufacturing capacity evaluation analysis is carried out on the 3D printing manufacturing nodes to determine the manufacturing capacity and the bearable manufacturing load of each 3D printing manufacturing node, so that the platform is helped to know the condition of available manufacturing resources, important information is provided for allocation and arrangement of orders, and the platform is helped to know which 3D printing manufacturing nodes can bear different types of orders, thereby better allocating the order resources and improving the manufacturing efficiency. And then, carrying out order screening processing on the real-time orders of the users by using the credit correction scores of the users so as to screen out the orders of the credit users, thereby being beneficial to ensuring that reliable user orders are distributed for the 3D printing manufacturing nodes, ensuring the reliability and payment feasibility of the users, reducing potential risks and disputes and improving the reliability of order execution. Then, the emergency situation data of the order is generated by carrying out order emergency detection analysis on the screened credit user order to analyze the emergency of the credit user order. And, the manufacturing difficulty of credit user orders is evaluated and analyzed based on the generated order emergency data to obtain emergency manufacturing difficulty level data, which is helpful for the platform to know which orders need to be completed more quickly and the production difficulty of the orders, and is helpful for optimizing order scheduling and resource allocation. In addition, the priority detection analysis is carried out on the credit user orders by using the emergency manufacturing difficulty level data obtained through evaluation, so that more complex or emergency orders can be ensured to obtain higher processing priority, the user demands are met, and the timeliness of order delivery is improved. Finally, by using the user order priority obtained by analysis to order sorting the credit user orders, a reasonable order processing sequence can be established, so that the 3D printing manufacturing node can efficiently process the orders, better user experience is provided, and meanwhile, the overall production efficiency of the platform is improved.
Preferably, step S4 comprises the steps of:
Step S41: carrying out trust exploration analysis on the 3D printing manufacturing node according to the order trust scores and the historical order information data to obtain a 3D printing manufacturing trust node;
according to the embodiment of the invention, corresponding 3D printing manufacture nodes are explored and analyzed according to the order completion conditions (comprising which 3D printing manufacture nodes are used for completing) on the historical order information data and the information data such as user feedback and the like combined with the order trust scores, so that the trusted 3D printing manufacture nodes obtained in the historical order completion are analyzed, and finally the 3D printing manufacture trust nodes are obtained.
Step S42: carrying out questioning, exploring and analyzing on the 3D printing and manufacturing nodes according to the order questioning scores and the historical order information data to obtain 3D printing and manufacturing questioning nodes;
according to the embodiment of the invention, corresponding 3D printing manufacture nodes are explored and analyzed according to the order completion conditions (comprising which 3D printing manufacture node is used for completion), the user suspected complaint conditions and other information data in combination with the order suspected scores, so that the 3D printing manufacture nodes with suspected printing manufacture capability of the user in the historical order are analyzed and completed, and finally the 3D printing manufacture suspected nodes are obtained.
Step S43: root cause analysis is carried out on the 3D printing manufacturing suspicious nodes, and node suspicious root cause information data are obtained;
According to the embodiment of the invention, detailed root cause analysis is carried out on each 3D printing manufacture question node so as to determine specific reasons causing user question, including reasons such as printing manufacture quality problems, order completion delay and the like, and finally node question root cause information data is obtained.
Step S44: according to the node question root cause information data, performing node correction adjustment processing on the 3D printing manufacture question node to obtain a printing manufacture question correction node;
According to the embodiment of the invention, the node question root information data obtained through analysis is used for carrying out targeted correction adjustment on the user question problems found in each 3D printing manufacture question node so as to improve the performance and the credibility of the corresponding 3D printing manufacture question node, and meanwhile, the user question problems in the corresponding 3D printing manufacture question node are eliminated, and finally, the printing manufacture question correction node is obtained.
Step S45: combining the 3D printing manufacture trust node and the printing manufacture challenge correction node to obtain a 3D printing manufacture optimization node;
According to the embodiment of the invention, the 3D printing manufacture trust node and the printing manufacture question correction node after correction processing are combined together to establish a more reliable and optimized printing manufacture node set, and finally the 3D printing manufacture optimization node is obtained.
Step S46: extracting capacity bearing data corresponding to each 3D printing manufacture optimization node from the manufacture node capacity bearing data to obtain optimization node capacity bearing data;
According to the method and the device, the capability bearing data corresponding to each 3D printing manufacture optimization node are extracted from the manufacture node capability bearing data obtained after evaluation and analysis, and the capability bearing data of the optimization node is finally obtained by including information such as manufacturing processing speed, available resources, production capability conditions and the like of the corresponding 3D printing manufacture optimization node.
Step S47: performing order dispatch analysis on the 3D printing manufacture optimization nodes according to the capacity bearing data of the optimization nodes to obtain an optimization node order dispatch strategy;
According to the embodiment of the invention, the order distribution condition of the 3D printing manufacture optimization node is determined by analyzing the capacity bearing data of the optimization node corresponding to the 3D printing manufacture optimization node, and a corresponding order distribution strategy is formulated at the same time, so that the order can be effectively and efficiently distributed to the most suitable node, and finally the optimal node order distribution strategy is obtained.
Step S48: and carrying out order dispatching processing on the credit user orders in the priority emergency order sequencing sequence according to the optimizing node order dispatching strategy to obtain user order dispatching result data.
According to the embodiment of the invention, the credit user orders in the priority emergency order sorting sequence are distributed by using the optimized node order distribution strategy obtained through analysis, so that the credit user orders in the priority emergency order sorting sequence are distributed to the corresponding 3D printing manufacturing optimized nodes according to the optimized node order distribution strategy, and finally the user order distribution result data is obtained.
The invention firstly performs trust exploration analysis on the 3D printing manufacture nodes by using the order trust scores and the historical order information data to analyze and identify the 3D printing manufacture nodes which are reliable to the user orders, namely the 3D printing manufacture trust nodes, which is beneficial to establishing a reliable manufacture network, ensuring that the orders are distributed to the reliable nodes, improving the production efficiency and the user satisfaction, eliminating the risk of unreliable nodes and ensuring the reliability of order processing and high-quality manufacture service. Meanwhile, 3D printing manufacture nodes with questioning exist in the user, namely 3D printing manufacture questioning nodes, are found out by questioning and exploring analysis on the 3D printing manufacture nodes by using the order questioning scores and the historical order information data, and the step is helpful for identifying the nodes possibly with the questioning problems of the user and provides a basis for subsequent root cause analysis. The localization and identification of suspect nodes helps to improve the transparency and quality of the manufacturing process, thereby improving the reliability of the overall manufacturing network. Root cause analysis is performed on the identified 3D printing manufacturing suspicious nodes so as to identify the cause possibly causing the problem of user suspicious, so that the problem and bottleneck existing in the suspicious nodes are deeply known, and a basis is provided for solving the uncertainty of the nodes. By analyzing the root causes, the stability and the credibility of the nodes can be purposefully adjusted and improved. And secondly, carrying out node correction adjustment processing on the 3D printing manufacturing questioning node by using the node questioning root information data, and carrying out targeted adjustment on the discovered user questioning problem so as to improve the performance and the credibility of the node. The correction of the nodes is helpful to eliminate the problem of user question, and the reliability of the nodes and the stability of the manufacturing process are improved. Next, a 3D print manufacturing optimization node is obtained by merging the trust node and the revised challenge node. The process helps to improve overall manufacturing efficiency and quality by integrating trusted nodes and modified challenge nodes to build a more reliable and optimized manufacturing network, ensuring that orders are distributed to the most appropriate and trusted nodes. And moreover, the capacity bearing data of the optimized node is extracted from the capacity bearing data of the manufacturing node to obtain the production capacity condition of the optimized node, so that the order is distributed to the node capable of optimally completing the task, the overall production efficiency is improved, and the high-quality completion of the order is ensured. In addition, the 3D printing manufacture optimization nodes are subjected to order dispatch and dispatch analysis by using the extracted optimization node capacity bearing data so as to analyze and obtain an optimal order dispatch strategy, so that order allocation is optimized, and the orders can be effectively and efficiently distributed to the most suitable nodes, thereby improving the efficiency and the production capacity of the whole manufacture network. Finally, the credit user orders in the priority emergency order sequencing sequence are subjected to order dispatching processing by using the optimized node order dispatching strategy obtained through analysis, so that efficient order dispatching is realized, the emergency orders and the orders with high priority can be rapidly and accurately distributed to proper nodes, and efficient production and customer requirements are guaranteed.
Preferably, step S5 comprises the steps of:
Step S51: performing resource detection analysis on the 3D printing manufacture optimization node to obtain node resource utilization information data;
The embodiment of the invention firstly collects and detects the resource utilization conditions of 3D printing equipment and 3D printing materials in the 3D printing manufacture optimization node, wherein the resource utilization conditions comprise information such as calculation resources, storage resources, material inventory, equipment states and the like, analyzes the detected resource utilization information to describe the resource states and utilization conditions of all nodes so as to know the availability and utilization rate of the resources, and finally obtains node resource utilization information data.
Step S52: performing print job detection analysis on the 3D print manufacturing optimization node to obtain node print job arrangement information data;
According to the embodiment of the invention, the queuing and execution conditions of the printing tasks on each 3D printing manufacture optimization node are known by detecting the current queuing 3D printing task conditions in the 3D printing manufacture optimization node, including the order task type, priority, size and other information, and then analyzing the printing task conditions obtained through analysis, so that node printing task arrangement information data is finally obtained.
Step S53: carrying out load analysis on the 3D printing manufacture optimization node according to the node resource utilization information data and the node printing task arrangement information data to obtain manufacture node load condition data;
According to the embodiment of the invention, the printing manufacture load condition of each 3D printing manufacture optimization node is analyzed by combining the node resource utilization information data and the node printing task arrangement information data obtained by detection and analysis, so that the current working state and the resource utilization condition of each 3D printing manufacture optimization node are determined, and finally the manufacture node load condition data is obtained.
Step S54: carrying out load distribution scheme analysis on user order distribution result data according to the load condition data of the manufacturing nodes so as to obtain a load order distribution scheme;
According to the embodiment of the invention, the load condition data of the manufacturing nodes are analyzed, then the order dispatching results in the user order dispatching result data are redistributed according to the analysis results, so that the order tasks are determined to be redistributed to the 3D printing manufacturing optimization nodes without the load condition, the load condition of the nodes is balanced to the greatest extent, and finally the load order distribution scheme is obtained.
Step S55: and carrying out dispatching and single adjustment processing on the user order dispatching result data according to the load order dispatching scheme to obtain user order dispatching adjustment data.
According to the embodiment of the invention, the analyzed load order distribution scheme is used for redistributing the order distribution result in the user order distribution result data so as to adjust the order distribution on each 3D printing manufacture optimization node to accord with load balancing, and finally the user order distribution adjustment data is obtained.
According to the invention, firstly, the 3D printing manufacture optimization node is subjected to resource detection analysis, so that the resource utilization condition of the 3D printing manufacture optimization node can be examined in detail, including printing equipment, materials, manpower and the like, to acquire node resource utilization information data, which is beneficial to knowing the resource condition of the manufacture node, helping to effectively manage the resources, ensuring that the resources are fully utilized, reducing resource waste, improving production efficiency and reducing cost, so as to meet production requirements. Secondly, by detecting and analyzing the printing tasks of the 3D printing manufacture optimization node, the printing task arrangement of the 3D printing manufacture optimization node can be studied in detail to obtain task arrangement information data inside the node, so that the task distribution and arrangement condition inside the manufacturing node can be known, the production flow can be planned and managed better, the production efficiency is improved, and the manufacturing period is shortened. Then, load analysis is performed on the 3D print manufacturing optimization node by means of the node resource utilization information data and the node print job arrangement information data to evaluate the print manufacturing load condition of the 3D print manufacturing optimization node, which is beneficial to determining the workload and the production efficiency of the node, and provides a basis for effective production scheduling. By knowing the load condition of the nodes, tasks can be better distributed, ensuring efficient production operation. And then, according to the load condition data of the manufacturing nodes, carrying out load distribution scheme analysis of the user order distribution result data, thereby being beneficial to optimizing the distribution of the user orders according to the load condition data, ensuring that the user orders are distributed to proper nodes so as to balance the workload of the nodes and improve the overall manufacturing efficiency. Through reasonable load distribution, the node overload risk can be reduced, and timely delivery of orders is ensured. And finally, based on the load order distribution scheme obtained by analysis, performing dispatch adjustment processing on the user order dispatch result data to obtain user order dispatch adjustment data. This step helps to rearrange orders according to load conditions, ensure load balancing of each node, and improve production efficiency and utilization rate of manufacturing nodes. By adjusting order dispatch, the method can better cope with the busy manufacturing period and high load condition, and improves timeliness and accuracy of order delivery.
Preferably, the present invention further provides an order dispatch system of a distributed 3D printing manufacturing platform, for executing an order dispatch method of the distributed 3D printing manufacturing platform as described above, where the order dispatch system of the distributed 3D printing manufacturing platform includes:
the user credit score detection module is used for acquiring historical order information data of the distributed 3D printing manufacturing platform, and carrying out user information identification analysis on the historical order information data to obtain order user information data; performing credit score detection on the order user information data so as to obtain the credit score of the order user;
The user credit score correction module is used for performing credit detection calculation on the historical order information data to obtain an order trust score and an order questioning score; carrying out questioning, evaluating and analyzing historical order information data according to the order questioning scores to obtain order questioning influence factors; carrying out credit correction analysis on the credit scores of the order users according to the order question influence factors so as to obtain the credit correction scores of the users;
the user order screening and sorting module is used for acquiring a user real-time order of the distributed 3D printing and manufacturing platform and 3D printing and manufacturing nodes; performing manufacturing capacity evaluation analysis on the 3D printing manufacturing node to obtain manufacturing node capacity bearing data; performing order screening processing on the real-time orders of the users according to the credit correction scores of the users to obtain credit user orders; carrying out priority emergency ordering treatment on the credit user orders, thereby obtaining a priority emergency order ordering sequence;
The printing node order dispatching module is used for carrying out node exploration analysis on the 3D printing manufacturing nodes by utilizing the order trust scores and the order questioning scores based on the historical order information data to obtain the 3D printing manufacturing trust nodes and the 3D printing manufacturing questioning nodes; performing node correction adjustment processing on the 3D printing manufacture question node to obtain a printing manufacture question correction node; combining the 3D printing manufacture trust node and the printing manufacture challenge correction node to obtain a 3D printing manufacture optimization node; based on the manufacturing node capacity bearing data and the 3D printing manufacturing optimization node, performing order dispatch processing on credit user orders in the priority emergency order sequencing sequence, so as to obtain user order dispatch result data;
The printing node dispatch adjustment module is used for carrying out load analysis on the 3D printing manufacture optimization node to obtain manufacture node load condition data; and performing dispatching and single-dispatching adjustment processing on the user order dispatching result data according to the manufacturing node load condition data, thereby obtaining user order dispatching adjustment data.
In summary, the invention provides an order dispatching system of a distributed 3D printing manufacturing platform, which consists of a user credit score detection module, a user credit score correction module, a user order screening and sorting module, a printing node order dispatching module and a printing node dispatching adjustment module.
The present embodiments are, therefore, to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein.
The foregoing is only a specific embodiment of the invention to enable those skilled in the art to understand or practice the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (6)
1. An order dispatch method for a distributed 3D printing manufacturing platform, comprising the steps of:
Step S1: acquiring historical order information data of a distributed 3D printing manufacturing platform, and performing user information identification analysis on the historical order information data to obtain order user information data; performing credit score detection on the order user information data to obtain the credit score of the order user;
step S2: performing reputation detection calculation on the historical order information data to obtain an order trust score and an order questioning score; carrying out questioning, evaluating and analyzing historical order information data according to the order questioning scores to obtain order questioning influence factors; carrying out credit correction analysis on the credit scores of the order users according to the order challenge influencing factors to obtain credit correction scores of the users; step S2 comprises the steps of:
Step S21: comment mining analysis is carried out on the historical order information data to obtain historical order comment information data;
step S22: word cloud key identification analysis is carried out on the historical order comment information data to obtain order comment key word information data;
step S23: performing reputation evaluation analysis on the order comment keyword information data to obtain order comment reputation evaluation data; step S23 includes the steps of:
step S231: carrying out emotion calculation on the order comment keyword information data by using a comment emotion calculation formula to obtain a comment emotion degree value; the comment emotion calculation formula is as follows:
;
In the method, in the process of the invention, For comment on emotion degree value,/>For the number of emotion vocabularies in order comment keyword information data,/>The first/>, in the keyword information data, is commented for the orderThe individual emotion vocabularies are expressed as emotion scores of positive emotions,/>Adjusting parameters for emotion weights of positive emotions,/>The first/>, in the keyword information data, is commented for the orderThe individual emotion vocabulary is expressed as emotion score of negative emotion,/>Adjusting parameters for emotion weights of negative emotions,/>The first/>, in the keyword information data, is commented for the orderThe emotion vocabulary is expressed as emotion score of neutral emotion,/>Adjusting parameters for emotion weight of neutral emotion,/>Is a harmonic smoothing parameter of neutral emotion,/>Calculated initial time for opinion detection,/>Calculated expiration time for opinion detection,/>Calculated integral time variable for opinion detection,/>Time/>, for emotion vocabulary in order comment keyword information dataEmotional intensity parameter of the place,/>Adjusting parameters for emotion weight of emotion intensity,/>Is a time-related parameter of emotion intensity,/>A correction value for comment emotion degree value;
step S232: the comment emotion degree value is subjected to subdivision judgment according to a preset comment emotion degree threshold value, and when the comment emotion degree value is larger than the preset comment emotion degree threshold value, the order comment keyword information data corresponding to the comment emotion degree value is marked as comment negative emotion data; when the comment emotion degree value is equal to a preset comment emotion degree threshold value, marking the order comment keyword information data corresponding to the comment emotion degree value as comment neutral emotion data and removing the comment neutral emotion data from the order comment keyword information data; when the comment emotion degree value is smaller than a preset comment emotion degree threshold value, marking the order comment keyword information data corresponding to the comment emotion degree value as comment front emotion data;
Step S233: carrying out emotion distribution detection analysis on the negative emotion data of the comment and the positive emotion data of the comment to obtain negative emotion distribution data and positive emotion distribution data;
Step S234: carrying out emotion difference analysis on the negative emotion distribution data and the positive emotion distribution data to obtain comment emotion distribution difference data;
step S235: performing reputation factor identification analysis on comment emotion distribution difference data to obtain emotion difference reputation key factors; performing reputation association analysis on comment emotion distribution difference data according to emotion difference reputation key factors to obtain emotion difference reputation association data;
step S236: evaluating and analyzing the order comment keyword information data according to the emotion difference reputation association data to obtain order comment reputation evaluation data;
Step S24: performing scoring calculation on the order comment credit evaluation data by using a credit score detection calculation formula to obtain an order trust score and an order questioning score; the reputation score detection calculation formula in step S24 is specifically:
;
;
In the method, in the process of the invention, Scoring order trust,/>Evaluating the amount of data for order comment reputation,/>For/>Positive comment feedback quantity parameter in individual order comment reputation evaluation data,/>For/>Overall comment feedback quantity parameter in individual order comment reputation evaluation data,/>Scoring adjustment parameters for positive comment feedback quantity,/>For/>Positive comment quality parameter,/>, in individual order comment reputation evaluation dataFor the total comment quality parameter in the order comment reputation evaluation data,/>Scoring adjustment parameters for aggressive review quality,/>For/>Positive comment vocabulary quantity parameter,/>, in individual order comment reputation evaluation dataAs the average value of the number of words of positive comments,/>For positive comment on standard deviation of vocabulary quantity,/>Integral vocabulary parameter for positive comment vocabulary quantity,/>Scoring adjustment parameters for positive comment vocabulary quantity,/>Correction value for order confidence score,/>Scoring order questions,/>For/>Negative comment feedback quantity parameter,/>, in individual order comment reputation evaluation dataScoring adjustment parameters for feedback quantity of negative comments,/>For/>Negative comment quality parameter,/>, in individual order comment reputation evaluation dataAdjusting parameters for scoring of negative comment quality,/>For/>Negative comment vocabulary quantity parameter,/>, in order comment reputation evaluation dataAs the average value of the number of negative comment words,/>Is the standard deviation of the number of negative comment words,/>Integral vocabulary parameter for negative comment vocabulary quantity,/>Adjusting parameters for scoring of negative comment vocabulary quantity,/>Correction values for order challenge scores;
Step S25: carrying out questioning, evaluating and analyzing historical order information data according to the order questioning scores to obtain order questioning influence factors; step S25 includes the steps of:
step S251: carrying out questioning influence factor detection on the historical order information data according to the order questioning scores to obtain order questioning influence factors;
step S252: carrying out influence mode detection analysis on the order questioning influence factors to obtain questioning influence factor mode data;
Step S253: carrying out mode topology analysis on the questioning influence factor mode data to obtain an influence factor topology relation diagram;
step S254: carrying out influence factor weighing processing on the influence factor topological relation diagram to obtain questioning influence factor weighing data;
Step S255: factor adjustment is carried out on the order questioning influence factors according to questioning influence factor weighing data and the influence factor topological relation diagram so as to obtain main questioning influence factors;
Step S256: performing influence evaluation analysis on main factors of the questioning influence to obtain order questioning influence factors;
Step S26: carrying out credit influence detection analysis on credit scores of order users according to the order questioning influence factors to obtain questioning credit influence correction indexes; carrying out credit correction processing on the credit scores of the order users according to the questioning credit influence correction index to obtain credit correction scores of the users;
Step S3: acquiring a user real-time order of a distributed 3D printing manufacturing platform and a 3D printing manufacturing node; performing manufacturing capacity evaluation analysis on the 3D printing manufacturing node to obtain manufacturing node capacity bearing data; performing order screening processing on the real-time orders of the users according to the credit correction scores of the users to obtain credit user orders; carrying out priority emergency ordering treatment on the credit user orders to obtain a priority emergency order ordering sequence;
Step S4: performing node exploration analysis on the 3D printing manufacturing nodes by utilizing the order trust scores and the order question scores based on the historical order information data to obtain 3D printing manufacturing trust nodes and 3D printing manufacturing question nodes; performing node correction adjustment processing on the 3D printing manufacture question node to obtain a printing manufacture question correction node; combining the 3D printing manufacture trust node and the printing manufacture challenge correction node to obtain a 3D printing manufacture optimization node; based on the manufacturing node capacity bearing data and the 3D printing manufacturing optimization node, performing order dispatch processing on credit user orders in the priority emergency order sequencing sequence to obtain user order dispatch result data;
step S5: carrying out load analysis on the 3D printing manufacturing optimization node to obtain manufacturing node load condition data; and performing dispatching and single-dispatching adjustment processing on the user order dispatching result data according to the manufacturing node load condition data to obtain user order dispatching adjustment data.
2. The order dispatch method of a distributed 3D print manufacturing platform of claim 1, wherein step S1 comprises the steps of:
step S11: acquiring historical order information data of a distributed 3D printing manufacturing platform;
Step S12: performing data quality screening processing on the historical order information data to obtain order information high-quality data;
step S13: user information identification analysis is carried out on the order information high-quality data to obtain order user information data;
Step S14: performing user portrait mining analysis on the order user information data to obtain order user portrait data;
Step S15: user evaluation analysis is carried out on the order user portrait data to obtain order user evaluation data;
step S16: and carrying out credit score detection on the order user evaluation data to obtain the credit score of the order user.
3. The order dispatch method of a distributed 3D print manufacturing platform of claim 1, wherein step S3 comprises the steps of:
step S31: acquiring a user real-time order of a distributed 3D printing manufacturing platform and a 3D printing manufacturing node, wherein the 3D printing manufacturing node comprises 3D printing equipment and 3D printing materials of a party bearing the order manufacturing;
Step S32: performing manufacturing capacity evaluation analysis on the 3D printing manufacturing node to obtain manufacturing node capacity bearing data;
Step S33: performing order screening processing on the real-time orders of the users according to the credit correction scores of the users to obtain credit user orders;
step S34: carrying out order emergency detection analysis on the credit user order to obtain order emergency data; carrying out manufacturing difficulty level assessment on the credit user order based on the order emergency data to obtain emergency manufacturing difficulty level data;
Step S35: carrying out priority detection analysis on credit user orders according to the emergency manufacturing difficulty level data to obtain user order priorities;
step S36: and carrying out order sorting processing on the credit user orders according to the user order priority, and obtaining a priority emergency order sorting sequence.
4. The order dispatch method of a distributed 3D print manufacturing platform of claim 1, wherein step S4 comprises the steps of:
Step S41: carrying out trust exploration analysis on the 3D printing manufacturing node according to the order trust scores and the historical order information data to obtain a 3D printing manufacturing trust node;
step S42: carrying out questioning, exploring and analyzing on the 3D printing and manufacturing nodes according to the order questioning scores and the historical order information data to obtain 3D printing and manufacturing questioning nodes;
step S43: root cause analysis is carried out on the 3D printing manufacturing suspicious nodes, and node suspicious root cause information data are obtained;
Step S44: according to the node question root cause information data, performing node correction adjustment processing on the 3D printing manufacture question node to obtain a printing manufacture question correction node;
step S45: combining the 3D printing manufacture trust node and the printing manufacture challenge correction node to obtain a 3D printing manufacture optimization node;
Step S46: extracting capacity bearing data corresponding to each 3D printing manufacture optimization node from the manufacture node capacity bearing data to obtain optimization node capacity bearing data;
step S47: performing order dispatch analysis on the 3D printing manufacture optimization nodes according to the capacity bearing data of the optimization nodes to obtain an optimization node order dispatch strategy;
Step S48: and carrying out order dispatching processing on the credit user orders in the priority emergency order sequencing sequence according to the optimizing node order dispatching strategy to obtain user order dispatching result data.
5. The order dispatch method of a distributed 3D print manufacturing platform of claim 1, wherein step S5 comprises the steps of:
Step S51: performing resource detection analysis on the 3D printing manufacture optimization node to obtain node resource utilization information data;
Step S52: performing print job detection analysis on the 3D print manufacturing optimization node to obtain node print job arrangement information data;
step S53: carrying out load analysis on the 3D printing manufacture optimization node according to the node resource utilization information data and the node printing task arrangement information data to obtain manufacture node load condition data;
step S54: carrying out load distribution scheme analysis on user order distribution result data according to the load condition data of the manufacturing nodes so as to obtain a load order distribution scheme;
Step S55: and carrying out dispatching and single adjustment processing on the user order dispatching result data according to the load order dispatching scheme to obtain user order dispatching adjustment data.
6. An order dispatch system for a distributed 3D print manufacturing platform for executing the order dispatch method for the distributed 3D print manufacturing platform of claim 1, the order dispatch system for the distributed 3D print manufacturing platform comprising:
the user credit score detection module is used for acquiring historical order information data of the distributed 3D printing manufacturing platform, and carrying out user information identification analysis on the historical order information data to obtain order user information data; performing credit score detection on the order user information data so as to obtain the credit score of the order user;
The user credit score correction module is used for performing credit detection calculation on the historical order information data to obtain an order trust score and an order questioning score; carrying out questioning, evaluating and analyzing historical order information data according to the order questioning scores to obtain order questioning influence factors; carrying out credit correction analysis on the credit scores of the order users according to the order question influence factors so as to obtain the credit correction scores of the users;
the user order screening and sorting module is used for acquiring a user real-time order of the distributed 3D printing and manufacturing platform and 3D printing and manufacturing nodes; performing manufacturing capacity evaluation analysis on the 3D printing manufacturing node to obtain manufacturing node capacity bearing data; performing order screening processing on the real-time orders of the users according to the credit correction scores of the users to obtain credit user orders; carrying out priority emergency ordering treatment on the credit user orders, thereby obtaining a priority emergency order ordering sequence;
The printing node order dispatching module is used for carrying out node exploration analysis on the 3D printing manufacturing nodes by utilizing the order trust scores and the order questioning scores based on the historical order information data to obtain the 3D printing manufacturing trust nodes and the 3D printing manufacturing questioning nodes; performing node correction adjustment processing on the 3D printing manufacture question node to obtain a printing manufacture question correction node; combining the 3D printing manufacture trust node and the printing manufacture challenge correction node to obtain a 3D printing manufacture optimization node; based on the manufacturing node capacity bearing data and the 3D printing manufacturing optimization node, performing order dispatch processing on credit user orders in the priority emergency order sequencing sequence, so as to obtain user order dispatch result data;
The printing node dispatch adjustment module is used for carrying out load analysis on the 3D printing manufacture optimization node to obtain manufacture node load condition data; and performing dispatching and single-dispatching adjustment processing on the user order dispatching result data according to the manufacturing node load condition data, thereby obtaining user order dispatching adjustment data.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311460390.6A CN117472300B (en) | 2023-11-03 | 2023-11-03 | Order dispatch method and system for distributed 3D printing manufacturing platform |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311460390.6A CN117472300B (en) | 2023-11-03 | 2023-11-03 | Order dispatch method and system for distributed 3D printing manufacturing platform |
Publications (2)
Publication Number | Publication Date |
---|---|
CN117472300A CN117472300A (en) | 2024-01-30 |
CN117472300B true CN117472300B (en) | 2024-06-14 |
Family
ID=89637550
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202311460390.6A Active CN117472300B (en) | 2023-11-03 | 2023-11-03 | Order dispatch method and system for distributed 3D printing manufacturing platform |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117472300B (en) |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102609852A (en) * | 2012-02-16 | 2012-07-25 | 南京邮电大学 | Implementation method of printing e-commerce platform for remote printing |
CN116728783A (en) * | 2023-08-09 | 2023-09-12 | 深圳市金石三维打印科技有限公司 | Simulation method and system based on 3D printer |
Family Cites Families (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
TWI601088B (en) * | 2014-10-06 | 2017-10-01 | Chunghwa Telecom Co Ltd | Topic management network public opinion evaluation management system and method |
CN106503883A (en) * | 2016-09-28 | 2017-03-15 | 海尔集团技术研发中心 | A kind of order distribute leaflets method and system of distributed 3D printing manufacturing platform |
CN115471133A (en) * | 2022-10-24 | 2022-12-13 | 北京航空航天大学 | Workshop comprehensive scheduling system based on order management and rolling optimization scheduling |
CN116542456B (en) * | 2023-04-25 | 2023-12-01 | 秒优大数据科技(杭州)有限公司 | Intelligent order sending method, device and equipment |
CN116664012A (en) * | 2023-07-19 | 2023-08-29 | 深圳市爱为物联科技有限公司 | Enterprise credit assessment method and system based on big data analysis |
CN116708519B (en) * | 2023-08-09 | 2023-11-07 | 深圳市金石三维打印科技有限公司 | Remote communication data processing method and system for 3D printer |
-
2023
- 2023-11-03 CN CN202311460390.6A patent/CN117472300B/en active Active
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102609852A (en) * | 2012-02-16 | 2012-07-25 | 南京邮电大学 | Implementation method of printing e-commerce platform for remote printing |
CN116728783A (en) * | 2023-08-09 | 2023-09-12 | 深圳市金石三维打印科技有限公司 | Simulation method and system based on 3D printer |
Also Published As
Publication number | Publication date |
---|---|
CN117472300A (en) | 2024-01-30 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP6034890B2 (en) | Specification, estimation, causal driver discovery and market response elasticity or lift coefficient automation | |
Ganguly et al. | A fuzzy AHP approach for inbound supply risk assessment | |
US20190034881A1 (en) | Automatic interview question recommendation and analysis | |
Lai et al. | Ranking of customer requirements in a competitive environment | |
Parthiban et al. | A multi criteria decision making approach for suppliers selection | |
JP4286296B2 (en) | Requirement Confirmation Support Program, Requirement Confirmation Support Method, and Requirement Confirmation Support Device | |
US10614495B2 (en) | Adaptive and tunable risk processing system and method | |
CN113537807B (en) | Intelligent wind control method and equipment for enterprises | |
US20100280861A1 (en) | Service Level Agreement Negotiation and Associated Methods | |
Devadasan et al. | Collaborative intelligence in knowledge based service planning | |
CN112148986B (en) | Top-N service re-recommendation method and system based on crowdsourcing | |
KR20160104064A (en) | A multidimensional recursive learning process and system used to discover complex dyadic or multiple counterparty relationships | |
CN113743615A (en) | Feature removal framework to simplify machine learning | |
CN116579640A (en) | Power marketing service channel user experience assessment method and system | |
CN116663909A (en) | Provider risk identification data processing method and device | |
CN117668205B (en) | Smart logistics customer service processing method, system, equipment and storage medium | |
CN113435713B (en) | Risk map compiling method and system based on GIS technology and two-model fusion | |
Gattermann-Itschert et al. | Using machine learning to include planners’ preferences in railway crew scheduling optimization | |
US20130024235A1 (en) | Conflicting Expert Systems | |
CN115964570B (en) | Cloud service recommendation method and device based on QoS multi-period change feature prediction | |
CN117472300B (en) | Order dispatch method and system for distributed 3D printing manufacturing platform | |
CN112860672A (en) | Method and device for determining label weight | |
CN113570114B (en) | Resource service intelligent matching method, system and computer equipment | |
Tin et al. | A business process decision model for client evaluation using fuzzy AHP and TOPSIS | |
US20220019918A1 (en) | Machine learning feature recommendation |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |