Intelligent work order management system and method based on cue word optimization

Abstract

The invention discloses an intelligent work order management system and method based on cue word optimization, and relates to the technical field of customer service and work order management. According to the system, by integrating natural language processing, image processing and machine learning technologies, user information is obtained, a large model is integrated, replies meeting specific scenes and requirements are generated by utilizing a designed cue word guiding model, and structural order data such as consultation, handling and complaint are automatically created according to dialogue contexts. The AI abstract shorthand realizes intelligent analysis, classification, distribution and tracking of work order contents so as to improve work order processing efficiency and accuracy. Meanwhile, the system has the functions of intelligent work order classification, automatic quality inspection and the like, and the customer service operation efficiency is comprehensively improved.

Description

Technical Field

[0001] The invention discloses an intelligent work order management system and method based on prompt word optimization, and relates to the technical field of customer service and work order management. Background Art

[0002] With the diversification of online customer service channels, enterprises are facing problems such as a surge in user consultations and low efficiency in work order processing. Traditional work order management systems lack intelligent support in work order creation, classification and quality inspection, resulting in long processing cycles and low user satisfaction.

[0003] In the existing technology, the system processing flexibility is poor, it is difficult to handle complex and changeable work order requests, and the rule base may need to be frequently updated and maintained. The semi-automatic work order management system combines the characteristics of manual and automated. In the work order receiving and preliminary classification stage, the system can automatically complete some basic tasks, such as keyword extraction, work order type judgment, etc. However, in the subsequent allocation, processing and feedback stages, human participation and decision-making are still required. Summary of the invention

[0004] The present invention intends to provide an intelligent work order management system and method, electronic device, and storage medium based on prompt word optimization to solve the deficiencies in the prior art. The technical problem to be solved by the present invention is achieved through the following technical solutions.

[0005] In a first aspect, an intelligent work order management system based on prompt word optimization is provided, the system comprising: Intelligent parsing module, used to extract key user information through NLP and OCR pre-processing based on the work order data submitted by the user; An intelligent reply module, used to generate preliminary intelligent replies based on the user's key information through a large language model and a prompt word library; An intelligent processing module, used to intelligently analyze user intentions based on the user key information and classify information work orders through a machine learning algorithm; An intelligent dispatching module is used to classify work orders according to the information classification, classify work orders through a large language model, and allocate work orders according to preset rules; An intelligent quality inspection module, used to perform automatic quality inspection by setting quality inspection prompt words according to the distribution processing status of the work order; The data analysis module is used to perform data statistics and trend forecasting based on the data of the work order through the data analysis model; based on the data of the work order, key performance indicators are extracted, such as the number of work orders, the proportion of work orders by type, high-frequency problems, average response time, problem resolution rate, customer satisfaction, etc. A customer service data analysis report can be automatically generated based on the analysis results, including text descriptions, chart displays, etc. Monitor abnormal situations in customer service data, such as a sudden increase in the number of consultations, abnormal distribution of problem types, a sharp drop in customer satisfaction, etc. The large model can establish the pattern and range of normal data by learning from historical data, and issue a timely warning when new data exceeds this range; The language support module is used to automatically translate into multiple languages ​​according to the data of the work order.

[0006] In some implementations, the intelligent processing module specifically includes: A smart ticket creation unit, which is used to intelligently analyze the user's intention to obtain the user's key information based on the conversation context, and automatically generate a ticket by presetting the ticket type and prompt words; The intelligent order creation unit is used to automatically complete and classify according to the user's key information through a machine learning algorithm, and process and classify according to the classification.

[0007] In some implementations, the intelligent dispatching module specifically includes: A tracking and feedback unit, used to generate a visual interface and an evaluation window according to the status, progress and results of the work order; The work order quality inspection unit is used to check whether the work order reply accurately and completely answers the customer's question based on the result of the work order if the customer inquires about the use of the product function. The large model can understand the semantics of the text and calculate the similarity between the two. The higher the similarity, the higher the accuracy of the work order reply. For complaint work orders, check whether the key elements of the complaint are included, such as the object of the complaint, the specific problem, the time, etc. If the user's key information is missing or incomplete, it can be determined that there is a problem with the work order. Check whether the format of the work order meets the requirements, such as whether the format of the date, time, number, etc. is correct. The large model can learn the specifications of various formats and automatically verify the data in the work order. Automatic quality inspection is thus performed.

[0008] In some implementations, the system further includes a system integration interface module for providing an API interface for integration with other systems.

[0009] In some implementations, the system also includes a database module for storing all work order data, user information, and processing results.

[0010] In some implementations, the system also includes an external system module for connecting to a new customer service platform to achieve data synchronization.

[0011] In a second aspect, an embodiment of the present invention provides an intelligent work order management method based on prompt word optimization, the method comprising: S1, based on the work order data submitted by the user, extract the user's key information through NLP and OCR pre-processing; S2, generating a preliminary intelligent reply based on the user's key information through a large language model and a prompt word library; S3, intelligently analyzing the user's intention based on the user's key information, and classifying the information ticket through a machine learning algorithm; S4, classifying the work orders according to the information classification using a large language model, and assigning the work orders according to preset rules; S5, performing automatic quality inspection by setting quality inspection prompt words according to the distribution processing status of the work order; S6, based on the data of the work order, data statistics and trend forecasting are performed through data analysis models; based on historical data, the big model can predict the future trend of customer service indicators and help enterprises discover potential problems or opportunities in advance. For example, by analyzing the customer consultation volume and problem type distribution data in the past period of time, the customer service workload and demand in a certain period of time in the future can be predicted so that enterprises can arrange human resources reasonably; S7, performing multi-language automatic translation according to the data of the work order.

[0012] In some implementations, the S3 specifically includes: S31, intelligently analyzing the conversation context to obtain the user's intention of the key user information, and automatically generating a work order by presetting the work order type and prompt words; S32, automatically completing and classifying based on the user key information through a machine learning algorithm, and processing and classifying according to the classification.

[0013] In some implementations, the S5 specifically includes: S51, generating a visualization interface and an evaluation window according to the status, progress and result of the work order; S52, based on the results of the work order, if the customer inquires about how to use the product function, whether the work order reply content accurately and completely answers the customer's question. The big model can understand the semantics of the text and calculate the similarity between the two. The higher the similarity, the higher the accuracy of the work order reply. For complaint work orders, check whether the key elements of the complaint are included, such as the object of the complaint, the specific problem, the time, etc. If the user's key information is missing or incomplete, it can be determined that there is a problem with the work order. Check whether the format of the work order meets the requirements, such as whether the format of the date, time, number, etc. is correct. The big model can learn the specifications of various formats and automatically verify the data in the work order. Automatic quality inspection is thus performed.

[0014] In a third aspect, an embodiment of the present invention provides an electronic device, comprising a memory and a processor, wherein the memory is used to store one or more computer instructions, wherein when the one or more computer instructions are executed by the processor, the method described in the first aspect above is implemented.

[0015] In a fourth aspect, an embodiment of the present invention provides a computer storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, it is used to implement the method described in the first aspect.

[0016] The embodiments of the present invention include the following advantages: The present invention designs an intelligent work order management system based on prompt word optimization. The system obtains user information and integrates large models (such as the GPT series) by integrating natural language processing (NLP), image processing and machine learning technologies. It uses the designed prompt words to guide the model to generate replies that meet specific scenarios and needs, and automatically creates structured work order data such as consultation, handling, and complaints based on the conversation context. AI summary shorthand realizes intelligent analysis, classification, allocation and tracking of work order content to improve the efficiency and accuracy of work order processing. At the same time, the system has functions such as intelligent classification of work orders and automatic quality inspection, which comprehensively improves the efficiency of customer service operations. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 It is a structural block diagram of an intelligent work order management system based on prompt word optimization provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0019] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present invention will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0020] Embodiment 1: Figure 1The structure diagram of an intelligent work order management system based on prompt word optimization is shown in FIG. Figure 1 As shown, the intelligent work order management system based on prompt word optimization provided by this embodiment includes: Intelligent parsing module, used to extract key user information through NLP and OCR pre-processing based on the work order data submitted by the user; An intelligent reply module, used to generate preliminary intelligent replies based on the user's key information through a large language model and a prompt word library; The intelligent processing module is used to intelligently analyze the user's intention based on the user's key information, classify the information ticket (inquiry / handling / complaint) through machine learning algorithms, and generate specific ticket content based on the classification results and preset ticket types and prompt words to ensure the accuracy and efficiency of ticket allocation; An intelligent dispatching module is used to classify work orders according to the information classification, classify work orders through a large language model, and allocate work orders according to preset rules; An intelligent quality inspection module, used to perform automatic quality inspection by setting quality inspection prompt words according to the distribution processing status of the work order; The data analysis module is used to perform data statistics and trend forecasting based on the data of the work order through the data analysis model; based on the data of the work order, key performance indicators are extracted, such as the number of work orders, the proportion of work orders by type, high-frequency problems, average response time, problem resolution rate, customer satisfaction, etc. A customer service data analysis report can be automatically generated based on the analysis results, including text descriptions, chart displays, etc. Monitor abnormal situations in customer service data, such as a sudden increase in the number of consultations, abnormal distribution of problem types, a sharp drop in customer satisfaction, etc. The large model can establish the pattern and range of normal data by learning from historical data, and issue a timely warning when new data exceeds this range; The language support module is used to automatically translate into multiple languages ​​according to the data of the work order.

[0021] When the system of the present invention is working, first, the intelligent parsing module is responsible for receiving the text, pictures, and videos submitted by users for online consultation, and uses NLP technology to perform preprocessing such as word segmentation, part-of-speech tagging, and named entity recognition, and uses OCR image recognition and video detection technology to extract user key information (such as work order type, user information, problem description, time, etc.).

[0022] Then, through the intelligent reply module, the large model is combined with the preset prompt word library to obtain the recommended best reply, guide the user to choose, and generate preliminary knowledge base intelligent replies. The prompt word library contains optimized prompt words for different business scenarios and common problems to ensure the accuracy and personalization of the reply.

[0023] Next, through the intelligent classification module, specifically including: A smart ticket creation unit, which is used to intelligently analyze the user's intention to obtain the user's key information based on the conversation context, and automatically generate a ticket by presetting the ticket type and prompt words; The intelligent order creation unit is used to automatically complete and classify according to the user's key information through a machine learning algorithm, and process and classify according to the classification.

[0024] Based on machine learning algorithms (such as decision trees, random forests, or deep learning models), the parsed user key information is automatically completed and classified and assigned to corresponding processing categories.

[0025] According to the context of the conversation, the system automatically analyzes the user's intention, obtains the user's demands based on the preset work order type (inquiry, handling, complaint) and the corresponding prompt words, and intelligently generates work orders. The work order information includes the first-level classification, second-level classification, third-level classification, fourth-level classification, user information, mobile phone number, location, product type, product name, product order time, order channel, order work number, whether it is finally cancelled, reason for cancellation, complaint content, solution, processing status, satisfaction, etc.

[0026] Next, through the intelligent dispatching module, a large language model is used to classify work orders and assign work orders according to preset rules.

[0027] Using large language models to intelligently classify work orders, the work orders are automatically assigned to appropriate processing personnel or teams based on the classification results and preset allocation rules (such as personnel skills, current availability, etc.). The processing personnel or teams verify or supplement the solutions provided by the system. Specifically, it includes: The intelligent dispatching module specifically includes: The tracking and feedback unit is used to generate a visual interface and an evaluation window according to the status, progress and results of the work order; record the status, progress and results of the work order, and provide a visual interface.

[0028] The processing status, progress and results of work orders are recorded in real time, and a visual interface is provided for users and administrators to query. At the same time, user evaluation and feedback from processing personnel are supported, and the solution is automatically improved and updated to form a closed-loop management.

[0029] The work order quality inspection unit is used to check whether the work order reply accurately and completely answers the customer's question if the customer inquires about the use of the product function based on the result of the work order. The big model can understand the semantics of the text and calculate the similarity between the two. The higher the similarity, the higher the accuracy of the work order reply. For complaint work orders, check whether the key elements of the complaint are included, such as the object of the complaint, the specific problem, the time, etc. If the user's key information is missing or incomplete, it can be determined that there is a problem with the work order. Check whether the format filled in the work order meets the requirements, such as whether the format of the date, time, number, etc. is correct. The big model can learn the specifications of various formats and automatically verify the data in the work order. Thus, automatic quality inspection is performed. The work order processing results are automatically quality inspected through quality inspection prompt words. By setting quality inspection prompt words, the work order processing results are automatically quality inspected to improve the processing quality and efficiency.

[0030] Next, an intelligent quality inspection module is used to perform automatic quality inspection by setting quality inspection prompt words according to the distribution processing status of the work order; Next, the data analysis module is used to perform data statistics and trend forecasts based on the data of the work order through the data analysis model; such as the number of work orders, the proportion of work orders by type, high-frequency problems, average response time, problem resolution rate, customer satisfaction, etc. A customer service data analysis report can be automatically generated based on the analysis results, including text descriptions, chart displays, etc. Monitor abnormal situations in customer service data, such as a sudden increase in the number of consultations, abnormal distribution of problem types, a sharp drop in customer satisfaction, etc. The large model can establish the pattern and range of normal data by learning from historical data, and issue a warning in a timely manner when new data exceeds this range; The language support module is used to perform automatic multi-language translation based on the data of the work order.

[0031] Furthermore, the system also includes a system integration interface module for providing an API interface for integration with other systems.

[0032] Furthermore, the system also includes a database module for storing all work order data, user information, and processing results.

[0033] Furthermore, the system also includes an external system module for connecting to a new customer service platform to achieve data synchronization.

[0034] The system of the present invention does not rely on complex machine learning or natural language processing technology, but processes work orders through preset rules and templates. For example, the system can assign work orders to different processing categories based on keyword matching, or determine the priority of work orders based on simple logical judgment. It is simple to implement and low cost, and is suitable for scenarios where the types of work orders are relatively fixed and the number is not large. While maintaining a certain degree of automation, it can make full use of human wisdom and experience to handle complex problems and improve processing quality.

[0035] Embodiment 2: In a second aspect, an embodiment of the present invention provides an intelligent work order management method based on prompt word optimization, the method comprising: S1, based on the work order data submitted by the user, extract the user's key information through NLP and OCR pre-processing; S2, generating a preliminary intelligent reply based on the user's key information through a large language model and a prompt word library; S3, based on the user's key information, intelligently analyzes the user's intention, classifies the information ticket (inquiry / handling / complaint) through machine learning algorithms, and generates specific ticket content based on the classification results and preset ticket types and prompt words to ensure the accuracy and efficiency of ticket allocation; S4, classifying the work orders according to the information classification using a large language model, and assigning the work orders according to preset rules; S5, performing automatic quality inspection by setting quality inspection prompt words according to the distribution processing status of the work order; S6, based on the data of the work order, data statistics and trend forecasting are performed through data analysis models; based on historical data, the big model can predict the future trend of customer service indicators and help enterprises discover potential problems or opportunities in advance. For example, by analyzing the customer consultation volume and problem type distribution data in the past period of time, the customer service workload and demand in a certain period of time in the future can be predicted so that enterprises can arrange human resources reasonably; S7, performing multi-language automatic translation according to the data of the work order.

[0036] Furthermore, the S3 specifically includes: S31, intelligently analyzing the conversation context to obtain the user's intention of the key user information, and automatically generating a work order by presetting the work order type and prompt words; S32, automatically completing and classifying based on the user key information through a machine learning algorithm, and processing and classifying according to the classification.

[0037] Furthermore, the S5 specifically includes: S51, generating a visualization interface and an evaluation window according to the status, progress and result of the work order; S52, perform automatic quality inspection based on the results of the work order. Pre-set content keywords for different types of work orders (consultation, handling, complaints, etc.). For example, for consultation work orders, keywords such as "inquiry" and "understanding" may be included; for handling work orders, keywords such as "application" and "handling" may be included; for complaint work orders, keywords such as "dissatisfaction" and "problem" may be included. Check whether the work order content contains keywords for the corresponding type of work order. If missing, it may indicate that the classification is inaccurate or the work order content is incomplete.

[0038] Embodiment three: This embodiment further provides an electronic device, including a memory and a processor, wherein the memory is used to store one or more computer instructions, wherein the one or more computer instructions implement the method of embodiment 1 when executed by the processor; In practical applications, the processor can be an application specific integrated circuit (ASIC), a digital signal processor (DSP), a digital signal processing device (DSPD), a programmable logic device (PLD), a field programmable gate array (FPGA), a controller, a microcontroller unit (MCU), a microprocessor or other electronic components to execute the methods in the above embodiments.

[0039] The method implemented in this embodiment is as shown in Embodiment 2.

[0040] Embodiment 4: This embodiment further provides a computer storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by one or more processors, the method of the first embodiment is implemented; Among them, the computer-readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk or optical disk.

[0041] The method implemented in this embodiment includes: The method implemented in this embodiment is as shown in Embodiment 2.

[0042] It should be noted that the above detailed descriptions are exemplary and are intended to provide further explanation of the present application. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the art to which the present application belongs.

[0043] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit the exemplary embodiments according to the present application. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should also be understood that when the terms "comprise" and / or "include" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or combinations thereof.

[0044] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the terms used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein.

[0045] In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units that are not explicitly listed or inherent to these processes, methods, products, or apparatuses.

[0046] For ease of description, spatially relative terms, such as "above", "above", "on the upper surface of", "above", etc., may be used herein to describe the spatial positional relationship between a device or feature and other devices or features as shown in the figure. It should be understood that spatially relative terms are intended to include different orientations of the device in use or operation in addition to the orientation described in the figure. For example, if the device in the accompanying drawings is inverted, the device described as "above other devices or structures" or "above other devices or structures" will be positioned as "below other devices or structures" or "below other devices or structures". Thus, the exemplary term "above" may include both "above" and "below". The device may also be positioned in other different ways, such as rotated 90 degrees or in other orientations, and the spatially relative descriptions used herein are interpreted accordingly.

[0047] In the above detailed description, reference is made to the accompanying drawings, which form a part of this document. In the accompanying drawings, similar symbols typically identify similar components unless the context indicates otherwise. The illustrated embodiments described in the detailed description, drawings, and claims are not meant to be limiting. Other embodiments may be used, and other changes may be made, without departing from the spirit or scope of the subject matter presented herein.

[0048] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. An intelligent work order management system based on prompt word optimization, characterized in that: The system comprises: Intelligent parsing module, used to extract key user information through NLP and OCR pre-processing based on the work order data submitted by the user; An intelligent reply module, used to generate preliminary intelligent replies based on the user's key information through a large language model and a prompt word library; An intelligent processing module, used to intelligently analyze user intentions based on the user key information and classify information work orders through a machine learning algorithm; An intelligent dispatching module is used to classify work orders according to the information classification, classify work orders through a large language model, and allocate work orders according to preset rules; An intelligent quality inspection module, used to perform automatic quality inspection by setting quality inspection prompt words according to the distribution processing status of the work order; A data analysis module, used to extract key performance indicators based on the data of the work order; The language support module is used to automatically translate into multiple languages ​​according to the data of the work order.

2. The intelligent work order management system based on prompt word optimization according to claim 1 is characterized in that: The intelligent processing module specifically includes: A smart ticket creation unit, which is used to intelligently analyze the user's intention to obtain the user's key information based on the conversation context, and automatically generate a ticket by presetting the ticket type and prompt words; The intelligent order creation unit is used to automatically complete and classify according to the user's key information through a machine learning algorithm, and process and classify according to the classification.

3. The intelligent work order management system based on prompt word optimization according to claim 1 is characterized in that: The intelligent dispatching module specifically includes: A tracking and feedback unit, used to generate a visual interface and an evaluation window according to the status, progress and results of the work order; The work order quality inspection unit is used to perform automatic quality inspection based on the results of the work order.

4. The intelligent work order management system based on prompt word optimization according to claim 1 is characterized in that: The system also includes a system integration interface module for providing an API interface for integration with other systems.

5. The intelligent work order management system based on prompt word optimization according to claim 1 is characterized in that: The system also includes a database module for storing all work order data, user information, and processing results.

6. The intelligent work order management system based on prompt word optimization according to claim 1 is characterized in that: The system also includes an external system module for connecting to the new customer service platform to achieve data synchronization.

7. An intelligent work order management method based on prompt word optimization, characterized in that: The method includes: S1, based on the work order data submitted by the user, extract the user's key information through NLP and OCR pre-processing; S2, generating a preliminary intelligent reply based on the user's key information through a large language model and a prompt word library; S3, intelligently analyzing the user's intention based on the user's key information, and classifying the information ticket through a machine learning algorithm; S4, classifying the work orders according to the information classification using a large language model, and assigning the work orders according to preset rules; S5, performing automatic quality inspection by setting quality inspection prompt words according to the distribution processing status of the work order; S6, performing data statistics and trend prediction through a data analysis model based on the data of the work order; S7, performing multi-language automatic translation according to the data of the work order.

8. The intelligent work order management method based on prompt word optimization according to claim 7 is characterized in that: The S3 specifically includes: S31, intelligently analyzing the conversation context to obtain the user's intention of the key user information, and automatically generating a work order by presetting the work order type and prompt words; S32, automatically completing and classifying based on the user key information through a machine learning algorithm, and processing and classifying according to the classification.

9. The intelligent work order management method based on prompt word optimization according to claim 7 is characterized in that: The S5 specifically includes: S51, generating a visualization interface and an evaluation window according to the status, progress and result of the work order; S52: Perform automatic quality inspection based on the result of the work order.

10. An electronic device, characterized in that: It includes a memory and a processor, wherein the memory is used to store one or more computer instructions, wherein the one or more computer instructions, when executed by the processor, implement the intelligent work order management method based on prompt word optimization as described in any one of claims 7 to 9.

Images