Processing system and method for wrong order of IT system of Internet of Things, and computer equipment
By designing a processing system for IoT IT systems, using AI technology to automatically identify, classify and repair misorder orders, the problems of low efficiency and poor accuracy of manual misorder handling in the existing technology are solved, and efficient and accurate misorder handling and order process optimization are achieved.
Patent Information
- Application Number
- CN202411940861.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-12-26
- Publication Date
- 2025-04-22
AI Technical Summary
In the existing CRM system of the telecommunications industry, relying on manual inspection to process wrong orders is inefficient, prone to errors, and consumes a lot of human resources and time, which cannot meet the needs of large-scale order processing.
A processing system for the Internet of Things IT system was designed, including an order statistics unit, a wrong order classification unit and a wrong order repair unit. AI technology is used to conduct data statistics and analysis of the entire process of orders, automatic identification and classification of wrong orders, and automatic repair of wrong orders or provide diagnostic suggestions.
It improves the efficiency and accuracy of wrong order processing, reduces the lag and error rate of manual processing, reduces the workload of manual operation and maintenance, and realizes timely understanding of order processing and intelligent intervention and repair.
Smart Images
Figure CN119863248A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of information processing of Internet of Things, and in particular to a processing system, method and computer equipment for error orders of an IT system of Internet of Things. Background Art
[0002] CRM (Customer Relationship Management) system is a system that effectively organizes enterprise resources according to customer classification, cultivates customer-centric business behaviors and implements customer-centric business processes. IoT CRM supports IoT IT business order acceptance, order data, instance data archiving, and triggers surrounding processes.
[0003] Currently, the CRM system in the telecommunications industry mainly relies on manual inspection to deal with the problem of wrong orders within the CRM. Manual inspection summarizes the existing experience in handling wrong orders, refers to the wrong order scenarios that have occurred, and checks the order information one by one for manual processing.
[0004] However, this manual processing method has many limitations. First, manual processing is inefficient, cannot meet the needs of large-scale order processing, and has a large lag. Second, manual processing is prone to errors, especially when processing a large number of orders, it is more likely to make omissions and errors. Finally, manual processing requires a lot of human resources and time costs, which is not conducive to the long-term healthy development of the IoT business. Summary of the invention
[0005] The present invention provides a system, method and computer device for processing error orders in an Internet of Things IT system with higher processing efficiency and accuracy, which can solve at least one of the above-mentioned technical problems.
[0006] In order to solve the above technical problems, the present invention adopts the following technical solutions:
[0007] The processing system for wrong orders in the IT system of the Internet of Things includes an order statistics unit, which is used to query the backend orders and to count and analyze the data of the entire order process to identify anomalies in the order, including an order data collection module, an order data analysis module, an order data processing module and a visual display module;
[0008] an error order classification unit, the error order classification unit being communicatively connected to the order statistics unit, and being used to combine abnormal information of a large number of orders with preset error order scenario categories, and to summarize and generate error order types and error order reports, including a first model building module, a first model training module, an error order diagnosis module, and a report generation module;
[0009] An error order repair unit is communicatively connected to the error order classification unit, and is used to collect and annotate a large number of error order cases of different types, and automatically repair or provide suggestions for different types of error orders, including a case learning module, a second model building module, a second model training module and an automatic repair module.
[0010] Furthermore, the order data collection module is used to periodically extract key information of orders from the order database; the order data analysis module is communicatively connected to the order data collection module, and is used to evaluate the performance of each link node in the entire order processing process based on the key information of each order received; the order data processing module is communicatively connected to the order data analysis module, and is used to identify bottlenecks and anomalies in the entire order processing process, and to judge and distinguish error orders; the visualization display module is communicatively connected to the order data processing module, and is used to dynamically display the data of various indicators in the entire order processing process.
[0011] Furthermore, the first model building module is used to perform AI automatic learning and identification based on preset wrong order scenarios, system order logic and table structure, define key attributes of wrong orders, and establish an wrong order classification model. The first model training module is communicatively connected to the order data processing module and the first model building module, and is used to input historical wrong order data received by the order data processing module into the first model building module to train the wrong order classification model and automatically identify the type of wrong orders. The wrong order diagnosis module is communicatively connected to the first model building module and the first model training module, and is used to mark and evaluate wrong orders of unrecognizable types. The report generation module is communicatively connected to the first model training module and the wrong order diagnosis module, and is used to integrate the error order information of identified or unrecognized types and generate a structured report for error order tracking.
[0012] Furthermore, the case learning module is communicatively connected to the report generation module, and is used to collect and annotate a large number of error order cases to form a training data set. The second model building module is communicatively connected to the case learning module and the error order diagnosis module, and is used to learn the complete data of the entire order processing process and manually input error order cases based on the deep learning framework, and establish an error order repair model. The second model training module is communicatively connected to the case learning module and the second model building module, and is used to input the training data set received by the case learning module into the second model building module to train the error order repair model and automatically generate corresponding processing solutions. The automatic repair module is communicatively connected to the second model building module, and is used to automatically execute repair scripts for known types of error orders, or provide diagnostic suggestions for new types of error orders of unknown types, and update data.
[0013] The method for processing wrong orders in an IT system for the Internet of Things is implemented by using the processing system for processing wrong orders in an IT system for the Internet of Things, and includes the following steps:
[0014] S1. Query backend orders, collect statistics and analyze data on the entire process of order processing, identify bottlenecks and abnormal points in each link, and judge and distinguish error orders;
[0015] S2. Combine the abnormal information of a large number of orders with the preset error order scenario categories to establish an error order classification model, automatically identify the error order type, integrate the error order information, and generate an error order report;
[0016] S3. Collect and annotate a large number of different types of error order cases, establish an error order repair model, and automatically repair or provide diagnostic suggestions for different types of error orders.
[0017] Furthermore, S1 further includes data for dynamically displaying various indicators in the entire process of order processing.
[0018] Furthermore, S2 further includes marking and evaluating wrong orders whose types cannot be identified.
[0019] Furthermore, S3 further includes tracing the source and troubleshooting the cause of unknown types of new wrong orders detected by the wrong order repair model in combination with the underlying data logic table and historical tag evaluation data, so as to provide diagnostic suggestions and update the data at the same time.
[0020] A computer device includes a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the above-mentioned method for processing error orders in an Internet of Things IT system.
[0021] The beneficial effects of the present invention are embodied in:
[0022] 1. Statistics on the completion of the entire order process: AI technology can query the backend order status to realize statistics and analysis of the entire order process, help understand the anomalies in each link of the order processing, and provide data support for optimizing the order processing process.
[0023] 2. Statistics and tracking of wrong order scenarios: Through the preset common wrong order scenarios, system order logic and table structure, AI automatically learns and identifies, and statistics and summarizes the wrong order scenarios under various situations, including the wrong order generation link, time, error log, cause and other basic elements, and generates an wrong order report for further wrong order tracking.
[0024] 3. Automatic repair of wrong orders: AI technology can build a wrong order repair model by learning complete order data and manually input wrong order cases. When the system detects an existing wrong order scenario, it directly generates a corresponding processing plan to achieve wrong order repair; when the system detects a new non-preset wrong order, the AI tool can combine the underlying data logic table to trace the source, troubleshoot the cause of the problem, and update or query the data to improve the accuracy and efficiency of order processing. BRIEF DESCRIPTION OF THE DRAWINGS
[0025] The drawings described herein are used to provide further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute improper limitations on the present application.
[0026] Figure 1 The present invention is a flowchart of a method for processing an error order in an IT system of the Internet of Things according to an embodiment of the present invention.
[0027] Figure 2 It is a structural framework diagram of a system for processing error orders in an Internet of Things IT system according to an embodiment of the present invention.
[0028] Figure 3 It is a structural block diagram of a computer device according to an embodiment of the present invention.
[0029] The components in the accompanying drawings are marked as: 1. Order data collection module; 2. Order data analysis module; 3. Order data processing module; 4. Visual display module; 5. First model building module; 6. First model training module; 7. Wrong order diagnosis module; 8. Report generation module; 9. Case study module; 10. Second model building module; 11. Second model training module; 12. Automatic repair module. DETAILED DESCRIPTION
[0030] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. In the absence of conflict, the embodiments in this application and the features in the embodiments can be combined with each other. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.
[0031] It should be noted that if there are descriptions involving "first", "second", etc. in the embodiments of the present invention, the descriptions of "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the meaning of "and / or" appearing in the full text includes three parallel schemes. Taking "A and / or B" as an example, it includes scheme A, or scheme B, or schemes that A and B meet at the same time. In addition, "multiple" refers to more than two. In addition, the technical solutions between the various embodiments can be combined with each other, but it must be based on the ability of ordinary technicians in the field to implement. When the combination of technical solutions is contradictory or cannot be implemented, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection required by the present invention.
[0032] See also Figure 2 , an embodiment of the present invention provides a processing system for wrong orders in an Internet of Things IT system, including an order statistics unit, the order statistics unit is used to query backend orders, and to count and analyze the order full process data to identify anomalies in the order, including an order data collection module 1, an order data analysis module 2, an order data processing module 3 and a visual display module 4;
[0033] An error order classification unit, the error order classification unit is communicatively connected to the order statistics unit, and is used to combine abnormal information of a large number of orders with preset error order scenario categories, and summarize and generate error order types and error order reports, including a first model building module 5, a first model training module 6, an error order diagnosis module 7 and a report generation module 8;
[0034] An error order repair unit, which is communicatively connected to the error order classification unit, is used to collect and annotate a large number of error order cases of different types, and automatically repair or provide suggestions for different types of error orders, including a case learning module 9, a second model building module 10, a second model training module 11 and an automatic repair module 12.
[0035] See also Figure 2 In this embodiment, the order data collection module 1 is used to extract key information of orders from the order database at regular intervals. The order data analysis module 2 is communicatively connected to the order data collection module 1, and is used to evaluate the performance of each link node in the entire order processing process based on the key information of each order received. The order data processing module 3 is communicatively connected to the order data analysis module 2, and is used to identify bottlenecks and abnormal points in the entire order processing process, and to judge and distinguish error orders. The visualization display module 4 is communicatively connected to the order data processing module 3, and is used to dynamically display the data of various indicators in the entire order processing process.
[0036] The order data collection module 1 uses ETL tools to periodically obtain key information of orders, including order status change records, processing time, etc. The order data analysis module 2 uses time series analysis, trend analysis and other methods to evaluate the performance of each processing node. The visualization display module 4 develops an interactive dashboard to display indicators such as order processing flowcharts, average processing time, and exception rate.
[0037] See also Figure 2 In this embodiment, the first model building module 5 is used to perform AI automatic learning and identification based on preset wrong order scenarios, system order logic and table structure, define key attributes of wrong orders, and establish an wrong order classification model. The first model training module 6 is communicatively connected to the order data processing module 3 and the first model building module 5, and is used to input the historical wrong order data received by the order data processing module 3 into the first model building module 5 to train the wrong order classification model and automatically identify the type of wrong orders. The wrong order diagnosis module 7 is communicatively connected to the first model building module 5 and the first model training module 6, and is used to mark and evaluate wrong orders whose types cannot be identified. The report generation module 8 is communicatively connected to the first model training module 6 and the wrong order diagnosis module 7, and is used to integrate the wrong order information of identified or unidentified types and generate a structured report for wrong order tracking.
[0038] Existing error order scenarios in IoT IT systems are generally divided into the following categories:
[0039] 1. Scenarios of wrong orders in the service opening process:
[0040] ①、Activation link not sent
[0041] ②. The order has been received during the activation process but the CRM has not received it
[0042] ③. The CRM has received the receipt in the activation phase but has not continued to process it
[0043] 2. Completion scene
[0044] ①、The completion phase has not been completed
[0045] ②. The work has actually been completed but not sent to the downstream process
[0046] 3. External delivery system scenario
[0047] ①、Interaction issues with billing
[0048] ②. Problems with interaction with the connection management platform
[0049] ③、Interaction issues with the completion interface
[0050] The error order classification model established by the first model building module 5 performs AI automatic learning and recognition based on the above-mentioned preset common error order scenarios, as well as the system order logic and table structure, and defines the key attributes of error orders, such as generation links, timestamps, error codes, etc. The error order classification model is trained based on historical error order data, and can automatically identify the type of input error orders, and mark and evaluate error orders of unrecognizable types through the error order diagnosis module 7. At the same time, the report generation module 8 generates a structured report for error orders of recognized or unrecognized types, and the report supports export and sharing for further tracking.
[0051] See also Figure 2 In this embodiment, the case learning module 9 is communicatively connected to the report generating module 8, and is used to collect and annotate a large number of wrong order cases to form a training data set. The second model building module 10 is communicatively connected to the case learning module 9 and the wrong order diagnosis module 7, and is used to learn the complete data of the entire process of order processing and manually input wrong order cases based on the deep learning framework, and establish an wrong order repair model. The second model training module 11 is communicatively connected to the case learning module 9 and the second model building module 10, and is used to input the training data set received by the case learning module 9 into the second model building module 10 to train the wrong order repair model and automatically generate a corresponding processing plan. The automatic repair module 12 is communicatively connected to the second model building module 10, and is used to automatically execute the repair script for a known type of wrong order, or provide diagnostic suggestions for a new type of wrong order of an unknown type, and update the data.
[0052] The second model building module 10 builds an order error repair model based on a deep learning neural network, supporting multi-step reasoning and complex decision-making. When the system detects an existing order error scenario, it directly generates a corresponding processing solution to achieve order error repair; when the system detects a new non-preset order error, the AI tool can combine the underlying data logic table to trace the source, troubleshoot the cause of the problem, and update or query the data to improve the accuracy and efficiency of order processing.
[0053] See also Figure 1 The embodiment of the present invention further provides a method for processing an error order in an IT system of the Internet of Things, which is implemented by the processing system for processing an error order in an IT system of the Internet of Things, and includes the following steps:
[0054] S1. Query backend orders, collect statistics and analyze data on the entire process of order processing, identify bottlenecks and abnormal points in each link, and judge and distinguish error orders;
[0055] S2. Combine the abnormal information of a large number of orders with the preset error order scenario categories to establish an error order classification model, automatically identify the error order type, integrate the error order information, and generate an error order report;
[0056] S3. Collect and annotate a large number of different types of error order cases, establish an error order repair model, and automatically repair or provide diagnostic suggestions for different types of error orders.
[0057] In this embodiment, S1 further includes data for dynamically displaying various indicators in the entire process of order processing.
[0058] In this embodiment, S2 further includes marking and evaluating the wrong orders whose types cannot be identified.
[0059] In this embodiment, S3 further includes tracing the source of new error orders of unknown types detected by the error order repair model, combining the underlying data logic table and historical tag evaluation data, troubleshooting the cause of the problem, providing diagnostic suggestions, and updating the data at the same time.
[0060] An embodiment of the present invention further provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, the processor executes the steps of the above-mentioned method for processing error orders in an Internet of Things IT system.
[0061] See also Figure 3 An embodiment of the present invention further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the above-mentioned method for processing error orders in an Internet of Things IT system.
[0062] An embodiment of the present invention also provides a computer program product comprising instructions, which, when executed on a computer, enables the computer to execute the steps of the above-mentioned method for processing error orders in an Internet of Things IT system.
[0063] It is understandable that the system, device and storage medium provided in the embodiments of the present invention correspond to the method provided in the embodiments of the present invention, and the explanation, examples and beneficial effects of the relevant contents can refer to the corresponding parts of the above-mentioned method for processing error orders in the IT system of the Internet of Things.
[0064] It should be noted that those skilled in the art can understand that all or part of the steps implemented in the embodiments of the present invention can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using hardware, it can be implemented in whole or in part in the form of purchasing standard parts or modified parts. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, server or data center. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrated. The available medium may be a magnetic medium (eg, a floppy disk, a hard disk, a magnetic tape), an optical medium (eg, a DVD), or a semiconductor medium (eg, a solid state disk (SSD)).
[0065] In summary, the present invention is independent of the IoT CRM production system. Through functions such as full-process order processing analysis, error order analysis and automated processing, it can solve order abnormality problems to a large extent, verify problems and intervene before customer complaints, meet customers' actual production demands, and reduce customer reports of faults. At the same time, through the optimization and processing of the order processing flow in the AI-based IoT CRM, it can effectively reduce the workload of manual operation and maintenance, reduce background operations, understand the order processing status more accurately and timely, and perform intelligent intervention and repair.
[0066] It should be understood that the examples and implementation modes described herein are for illustrative purposes only and are not intended to limit the present invention. Those skilled in the art may make various modifications or changes based on the examples and implementation modes. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.
Claims
1. A system for processing wrong orders in the IT system of the Internet of Things, characterized by: include: An order statistics unit, which is used to query backend orders and to collect statistics and analyze order data throughout the entire process to identify anomalies in the orders, and comprises an order data collection module (1), an order data analysis module (2), an order data processing module (3) and a visual display module (4); an error order classification unit, the error order classification unit being communicatively connected to the order statistics unit and used for combining abnormal information of a large number of orders with preset error order scenario categories, summarizing and generating error order types and error order reports, comprising a first model building module (5), a first model training module (6), an error order diagnosis module (7) and a report generation module (8); An error order repair unit, the error order repair unit is communicatively connected to the error order classification unit, and is used to collect and annotate a large number of error order cases of different types, and automatically repair or provide suggestions for different types of error orders, including a case learning module (9), a second model building module (10), a second model training module (11) and an automatic repair module (12).
2. The system for processing wrong orders in the Internet of Things IT system as claimed in claim 1, characterized in that: The order data collection module (1) is used to extract key information of orders from an order database at regular intervals; the order data analysis module (2) is communicatively connected to the order data collection module (1) and is used to evaluate the performance of each link node in the entire order processing process based on the key information of each order received; the order data processing module (3) is communicatively connected to the order data analysis module (2) and is used to identify bottlenecks and abnormal points in the entire order processing process, and to judge and distinguish error orders; the visual display module (4) is communicatively connected to the order data processing module (3) and is used to dynamically display the data of various indicators in the entire order processing process.
3. The system for processing wrong orders in the Internet of Things IT system as claimed in claim 1, characterized in that: The first model building module (5) is used to perform AI automatic learning and identification based on preset error order scenarios, system order logic and table structure, define key attributes of error orders, and establish an error order classification model. The first model training module (6) is communicatively connected to the order data processing module (3) and the first model building module (5), and is used to input historical error order data received by the order data processing module (3) into the first model building module (5) to train the error order classification model and automatically identify the type of error orders. The error order diagnosis module (7) is communicatively connected to the first model building module (5) and the first model training module (6), and is used to mark and evaluate error orders whose types cannot be identified. The report generation module (8) is communicatively connected to the first model training module (6) and the error order diagnosis module (7), and is used to integrate error order information of identified or unidentified types and generate a structured report for error order tracking.
4. The system for processing wrong orders in the Internet of Things IT system as claimed in claim 1, characterized in that: The case study module (9) is communicatively connected to the report generation module (8) for collecting and annotating a large number of wrong order cases to form a training data set. The second model building module (10) is communicatively connected to the case study module (9) and the wrong order diagnosis module (7) for learning the complete data of the entire order processing process and manually input wrong order cases based on a deep learning framework to establish an wrong order repair model. The second model training module (11) is communicatively connected to the case study module (9) and the second model building module (10) for inputting the training data set received by the case study module (9) into the second model building module (10) to train the wrong order repair model and automatically generate a corresponding processing plan. The automatic repair module (12) is communicatively connected to the second model building module (10) for automatically executing a repair script for a known type of wrong order, or providing diagnostic suggestions for a new type of wrong order of an unknown type, and updating data.
5. A method for processing wrong orders in an IT system for the Internet of Things, implemented by a system for processing wrong orders in an IT system for the Internet of Things as claimed in any one of claims 1 to 4, characterized in that: The following steps are involved: S1. Query backend orders, collect statistics and analyze data on the entire process of order processing, identify bottlenecks and abnormal points in each link, and judge and distinguish error orders; S2. Combine the abnormal information of a large number of orders with the preset error order scenario categories to establish an error order classification model, automatically identify the error order type, integrate the error order information, and generate an error order report; S3. Collect and annotate a large number of different types of error order cases, establish an error order repair model, and automatically repair or provide diagnostic suggestions for different types of error orders.
6. The method for processing wrong orders in an Internet of Things IT system according to claim 5, characterized in that: The S1 further includes data for dynamically displaying various indicators in the entire process of order processing.
7. The method for processing wrong orders in an Internet of Things IT system according to claim 5, characterized in that: The S2 further includes marking and evaluating the wrong orders whose types cannot be identified.
8. The method for processing wrong orders in an Internet of Things IT system according to claim 5, characterized in that: The S3 further includes tracing the source and troubleshooting the cause of new types of error orders of unknown types detected by the error order repair model, combining the underlying data logic table and historical tag evaluation data, so as to provide diagnostic suggestions and update the data at the same time.
9. Computer device, characterized in that It includes a memory and a processor, the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the method for processing error orders in an Internet of Things IT system as described in any one of claims 5 to 8.