Logistics abnormity reporting method and system based on AI chat and computer program

Abstract

The invention discloses a logistics anomaly reporting method and system based on AI chat and a computer program. The logistics anomaly reporting method based on AI chat comprises the steps that a user inputs a logistics anomaly reporting demand in an AI chat window; performing intelligent analysis on the business demand based on a large language model technology, and obtaining logistics abnormal information reported by a user; matching a corresponding logistics order based on the logistics abnormal information; generating a logistics abnormal work order according to the logistics abnormal information and the corresponding logistics order; and displaying the related information of the logistics abnormal work order in an AI chat window. According to the technical scheme provided by the invention, by introducing an advanced AI chat technology, natural and efficient interaction between the user and the AI application is realized, so that the process of reporting logistics abnormity and querying a work order by the user is greatly simplified, tedious clicking and filling of a form are not needed, and the user experience and the service efficiency are improved.

Description

Technical Field

[0001] The present invention relates to the field of logistics technology, and in particular to a logistics abnormality reporting method, system and computer program based on AI chat. Background Art

[0002] In the modern logistics system, the handling of logistics anomalies (such as package loss, delay, damage, etc.) is an important part of ensuring service quality and customer experience. In the traditional model, the discovery of logistics anomalies and the submission of work orders mostly rely on manual monitoring and reporting, which has problems such as slow response, easy omissions, and low processing efficiency.

[0003] For example, in the traditional mode, after the consignee discovers a logistics anomaly, he / she needs to manually report the problem through the provided telephone customer service, official website or APP channels. After the consignee submits the abnormal work order, the consignee needs to wait for the logistics service provider to reply and process it. The processing progress is usually notified to the consignee by phone, email, SMS or APP notification.

[0004] The above traditional means have the following disadvantages:

[0005] 1. Inefficiency: Manually reporting exceptions and filling in work order information is time-consuming and laborious, and is prone to processing delays due to incomplete or incorrect information.

[0006] 2. Poor user experience: When dealing with logistics anomalies, consignees need to communicate frequently with logistics service providers, which results in cumbersome processes and poor user experience. The long waiting time for processing results increases user dissatisfaction.

[0007] 3. Lack of intelligent support: Unable to automatically identify abnormal user types, lack of intelligent solution recommendations and optimization suggestions. Summary of the invention

[0008] In view of the above-mentioned deficiencies in the current technology, the present invention provides a logistics anomaly reporting method based on AI chat, which enables users to quickly and conveniently report logistics anomalies by applying AI chat and natural language processing technology.

[0009] To achieve the above object, the embodiments of the present invention adopt the following technical solutions:

[0010] A logistics abnormality reporting method based on AI chat, comprising the following steps:

[0011] The user enters the logistics anomaly reporting requirements in the AI ​​chat window;

[0012] Intelligently analyze business needs based on large language model technology to obtain logistics anomaly information reported by users;

[0013] Match the corresponding logistics orders based on logistics exception information;

[0014] Generate a logistics exception work order based on the logistics exception information and the corresponding logistics order;

[0015] The relevant information of the logistics abnormality work order is displayed in the AI ​​chat window.

[0016] According to one aspect of the present invention, the intelligent analysis of business requirements based on the large language model technology to obtain logistics abnormality information reported by users includes:

[0017] Use a large language model to accurately capture user intent and understand and summarize the exception types and descriptions reported by users.

[0018] According to one aspect of the present invention, matching corresponding logistics orders based on logistics abnormality information includes:

[0019] Based on logistics exception information and combined with pre-entered address information, intelligent screening and matching of eligible logistics orders are carried out.

[0020] According to one aspect of the present invention, the AI ​​chat-based logistics abnormality reporting method further includes:

[0021] The generated logistics exception work order is stored in the warehouse.

[0022] According to one aspect of the present invention, the AI ​​chat-based logistics abnormality reporting method further includes:

[0023] Users can query logistics exception work orders in the AI ​​chat window.

[0024] According to one aspect of the present invention, the user can query the abnormal logistics work order in the AI ​​chat window including:

[0025] The user enters the query conditions in the AI ​​chat window;

[0026] Parse query conditions based on large language model technology and filter out corresponding logistics exception work orders;

[0027] Display relevant information of logistics exception work orders in the AI ​​chat window.

[0028] According to one aspect of the present invention, the user can query the abnormal logistics work order in the AI ​​chat window, which also includes:

[0029] Users can query the logistics exception work order to obtain the progress of logistics exception handling.

[0030] According to one aspect of the present invention, the AI ​​chat-based logistics abnormality reporting method further includes:

[0031] Can handle multiple users' logistics exception reporting requests at the same time.

[0032] A logistics abnormality reporting system based on AI chat, based on the logistics abnormality reporting method based on AI chat as described above, comprising:

[0033] User interface, including AI chat window, for users to input logistics anomaly reporting requirements and display relevant information of logistics anomaly work orders;

[0034] The parsing module is used to intelligently parse business needs based on large language model technology and obtain logistics anomaly information reported by users;

[0035] The matching module is used to match the corresponding logistics orders based on the logistics exception information;

[0036] The work order generation module is used to generate logistics exception work orders based on logistics exception information and corresponding logistics orders.

[0037] A computer program which, when executed, implements the steps of the logistics anomaly reporting method based on AI chat as described above.

[0038] Advantages of the present invention:

[0039] The present invention provides a logistics abnormality reporting method based on AI chat, which realizes natural and efficient interaction between users and AI applications by introducing advanced AI chat technology, thereby greatly simplifying the process of users reporting logistics abnormalities and improving user experience and service efficiency. Users can report abnormalities and query work orders through AI chat, without tedious clicks and form filling, and communicate with AI applications directly in natural language, which greatly improves the convenience of operation and user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0041] Figure 1 This is a flow chart of a logistics abnormality reporting method based on AI chat according to the present invention;

[0042] Figure 2 This is a flow chart of abnormal logistics reporting according to the present invention. DETAILED DESCRIPTION

[0043] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0044] Embodiment 1

[0045] like Figure 1 As shown, a logistics abnormality reporting method based on AI chat includes the following steps:

[0046] S1: The user enters the logistics anomaly reporting requirements in the AI ​​chat window.

[0047] In actual applications, the logistics anomalies that need to be handled include package loss, delay, damage, and long-term non-updated logistics information.

[0048] In actual applications, users can easily express their exception reporting needs in text form through the intuitive AI chat interface.

[0049] In actual applications, the AI ​​chat window can receive user input dialogues through WebSocket.

[0050] S2: Intelligently analyze business needs based on large language model technology to obtain logistics anomaly information reported by users.

[0051] Step S2 includes:

[0052] Use a large language model to accurately capture user intent and understand and summarize the exception types and descriptions reported by users.

[0053] Large Language Model (LLM) is an important technology in the field of natural language processing. It is based on deep learning technology and understands and generates natural language text by training large amounts of text data.

[0054] In actual applications, after the user inputs the logistics anomaly reporting requirements, the AI ​​application immediately calls the large language model to accurately capture the user's intentions and understand and summarize the user's anomaly type and anomaly description.

[0055] In actual applications, the parsed user exception type and exception description can be transmitted to the back-end server through HTTP communication for business logic and exception storage.

[0056] S3: Match the corresponding logistics orders based on the logistics exception information.

[0057] Step S3 includes:

[0058] Based on logistics exception information and combined with pre-entered address information, intelligent screening and matching of eligible logistics orders are carried out.

[0059] S4: Generate a logistics exception work order based on the logistics exception information and the corresponding logistics order.

[0060] Based on the user exception information parsed by the large language model, the system seamlessly connects and triggers the back-end service interface to achieve smooth interaction between the front and back ends.

[0061] The backend service interface responds quickly via Http, processes the request in depth, obtains the corresponding logistics order, generates a logistics exception work order, and then returns comprehensive and detailed information on the work order to ensure the integrity and timeliness of the data.

[0062] The acquired work order information data is instantly and securely transmitted back to the AI ​​application layer, ready for the next step of presentation.

[0063] Preferably, the method further comprises:

[0064] The generated logistics exception work order is stored in the warehouse.

[0065] In actual applications, the fourth-party logistics (4PL) system can be called to store and warehouse abnormal logistics work orders.

[0066] S5: Display the relevant information of the logistics abnormality work order in the AI ​​chat window.

[0067] The AI ​​application uses its intelligent characteristics to present the exception reporting method in a clear and easy-to-read manner in the chat window, allowing users to easily understand the details of the abnormal situation at a glance.

[0068] Specifically, the specific process for users to report logistics anomalies is as follows: Figure 2 shown.

[0069] Preferably, the method further comprises:

[0070] Can handle multiple users' logistics exception reporting requests at the same time.

[0071] Compared with traditional manual customer service, AI applications can handle multiple user requests at the same time, reducing labor costs while improving service efficiency and quality, helping companies reduce costs and improve competitiveness.

[0072] AI applications can be on standby around the clock and respond to user needs at any time, without being restricted by time and manpower, providing a more flexible and convenient service experience.

[0073] AI applications can intelligently understand user intentions, respond quickly and provide personalized service suggestions, greatly shortening operation time and improving communication efficiency.

[0074] The beneficial effect of this embodiment is that this method enables users to quickly and conveniently report logistics anomalies by applying AI chat and natural language processing technology. Through the automated AI chat interface and background processing flow, errors and omissions caused by human operations are reduced, and the accuracy and reliability of data are improved. Using advanced AI technology to provide customer service can demonstrate the company's innovation ability and technical strength, and help enhance brand image and user loyalty.

[0075] Embodiment 2

[0076] like Figure 1 As shown, a logistics abnormality reporting method based on AI chat includes the following steps:

[0077] S1: The user enters the logistics anomaly reporting requirements in the AI ​​chat window.

[0078] In actual applications, the logistics anomalies that need to be handled include package loss, delay, damage, and long-term non-updated logistics information.

[0079] In actual applications, users can easily express their exception reporting needs in text form through the intuitive AI chat interface.

[0080] In actual applications, the AI ​​chat window can receive user input dialogues through WebSocket.

[0081] S2: Intelligently analyze business needs based on large language model technology to obtain logistics anomaly information reported by users.

[0082] Step S2 includes:

[0083] Use a large language model to accurately capture user intent and understand and summarize the exception types and descriptions reported by users.

[0084] Large Language Model (LLM) is an important technology in the field of natural language processing. It is based on deep learning technology and understands and generates natural language text by training large amounts of text data.

[0085] In actual applications, after the user inputs the logistics anomaly reporting requirements, the AI ​​application immediately calls the large language model to accurately capture the user's intentions and understand and summarize the user's anomaly type and anomaly description.

[0086] In actual applications, the parsed user exception type and exception description can be transmitted to the back-end server through HTTP communication for business logic and exception storage.

[0087] S3: Match the corresponding logistics orders based on the logistics exception information.

[0088] Step S3 includes:

[0089] Based on logistics exception information and combined with pre-entered address information, intelligent screening and matching of eligible logistics orders are carried out.

[0090] S4: Generate a logistics exception work order based on the logistics exception information and the corresponding logistics order.

[0091] Based on the user exception information parsed by the large language model, the system seamlessly connects and triggers the back-end service interface to achieve smooth interaction between the front and back ends.

[0092] The backend service interface responds quickly via Http, processes the request in depth, obtains the corresponding logistics order, generates a logistics exception work order, and then returns comprehensive and detailed information on the work order to ensure the integrity and timeliness of the data.

[0093] The acquired work order information data is instantly and securely transmitted back to the AI ​​application layer, ready for the next step of presentation.

[0094] The method further comprises:

[0095] The generated logistics exception work order is stored in the warehouse.

[0096] In actual applications, the fourth-party logistics (4PL) system can be called to store and warehouse abnormal logistics work orders.

[0097] S5: Display the relevant information of the logistics abnormality work order in the AI ​​chat window.

[0098] The AI ​​application uses its intelligent characteristics to present the exception reporting method in a clear and easy-to-read manner in the chat window, allowing users to easily understand the details of the abnormal situation at a glance.

[0099] Specifically, the specific process for users to report logistics anomalies is as follows: Figure 2 shown.

[0100] The method further comprises:

[0101] Users can query logistics exception work orders in the AI ​​chat window.

[0102] The user can query the abnormal logistics work order in the AI ​​chat window including:

[0103] B1: The user enters query conditions in the AI ​​chat window.

[0104] Users can easily express their query requirements in text form through the intuitive AI chat interface.

[0105] B2: Analyze the query conditions based on the large language model technology and filter out the corresponding logistics exception work orders.

[0106] The AI ​​chat window receives query statements entered by users and parses them using natural language processing technology. The AI ​​application calls a large language model to accurately capture the user's query intention and automatically and efficiently extract logistics exception work orders from the input, or filter and match corresponding logistics exception work orders based on user query conditions to ensure the accuracy of the query.

[0107] Based on the analysis results, the AI ​​application calls the backend service and executes the corresponding query logic. The query logic may include database query, business rule verification, etc. The backend service interface responds quickly, performs in-depth processing on the query request, and then returns comprehensive and detailed work order information to ensure the integrity and timeliness of the data.

[0108] Based on user needs and system data, AI applications should be able to accurately match the query results that best meet user needs.

[0109] B3: Display the relevant information of the logistics abnormality work order in the AI ​​chat window.

[0110] The query results are organized into a form that is easy for users to understand and displayed to users through the AI ​​chat window. At the same time, necessary feedback and prompts are provided, such as successful query, no results, error prompts, etc.

[0111] In actual applications, the work order information data obtained is instantly and securely transmitted back to the AI ​​application. The AI ​​application uses its intelligent characteristics to present complex order information in a clear and easy-to-read manner in the chat window, allowing users to easily understand the order details at a glance.

[0112] Preferably, the user can query the abnormal logistics work order in the AI ​​chat window and further include:

[0113] Users can query the logistics exception work order to obtain the progress of logistics exception handling.

[0114] In actual applications, after users report logistics anomalies, logistics service providers will handle them and update the corresponding processing progress to the work order information in real time. Therefore, when users query logistics anomaly work orders later, they can also obtain the anomaly processing progress.

[0115] Preferably, the method further comprises:

[0116] Can handle multiple users' logistics exception reporting requests at the same time.

[0117] Compared with traditional manual customer service, AI applications can handle multiple user requests at the same time, reducing labor costs while improving service efficiency and quality, helping companies reduce costs and improve competitiveness.

[0118] AI applications can be on standby around the clock and respond to user needs at any time, without being restricted by time and manpower, providing a more flexible and convenient service experience.

[0119] AI applications can intelligently understand user intentions, respond quickly and provide personalized service suggestions, greatly shortening operation time and improving communication efficiency.

[0120] Preferably, the method further comprises:

[0121] The AI ​​chat interface should be concise and clear, easy for users to operate.

[0122] Establish a user feedback mechanism to continuously optimize the performance and functions of AI applications based on user feedback.

[0123] The beneficial effect of this embodiment is that in this method, users can report exceptions and query work orders through AI chat, without the need for tedious clicks and form filling, and can directly communicate with AI applications in natural language, which greatly improves the convenience of operation and user experience.

[0124] Embodiment 3

[0125] A logistics abnormality reporting system based on AI chat, based on the logistics abnormality reporting method based on AI chat as described in Embodiment 1 or 2, comprising:

[0126] User interface, including AI chat window, for users to input logistics anomaly reporting requirements and display relevant information of logistics anomaly work orders;

[0127] The parsing module is used to intelligently parse business needs based on large language model technology and obtain logistics anomaly information reported by users;

[0128] The matching module is used to match the corresponding logistics orders based on the logistics exception information;

[0129] The work order generation module is used to generate logistics exception work orders based on logistics exception information and corresponding logistics orders.

[0130] Preferably, the system further comprises:

[0131] The user interface can also be used for users to enter query conditions;

[0132] The parsing module can also be used to parse query conditions based on large language model technology and filter out corresponding logistics exception work orders.

[0133] Preferably, the system further comprises:

[0134] Backend services provide database services, business logic services, etc., which are used to store logistics exception work order data, process business logic, etc.

[0135] Embodiment 4

[0136] A computer program, which, when executed, implements the steps of the logistics abnormality reporting method based on AI chat as described in Example 1 or 2.

[0137] Embodiment 5

[0138] A readable storage medium having stored thereon a computer program as described in Example 4, wherein when the computer program is executed, the steps of the logistics anomaly reporting method based on AI chat as described in Example 1 or 2 are implemented.

[0139] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily thought of by any technician familiar with the art within the technical scope disclosed in the present invention should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A logistics abnormality reporting method based on AI chat, characterized in that: The following steps are involved: The user enters the logistics anomaly reporting requirements in the AI ​​chat window; Intelligently analyze business needs based on large language model technology to obtain logistics anomaly information reported by users; Match the corresponding logistics orders based on logistics exception information; Generate a logistics exception work order based on the logistics exception information and the corresponding logistics order; The relevant information of the logistics abnormality work order is displayed in the AI ​​chat window.

2. The logistics abnormality reporting method based on AI chat according to claim 1 is characterized in that: The intelligent analysis of business needs based on the large language model technology to obtain logistics abnormality information reported by users includes: Use a large language model to accurately capture user intent and understand and summarize the exception types and descriptions reported by users.

3. The logistics abnormality reporting method based on AI chat according to claim 1 is characterized in that: The matching of corresponding logistics orders based on logistics abnormality information includes: Based on logistics exception information and combined with pre-entered address information, intelligent screening and matching of eligible logistics orders are carried out.

4. The logistics abnormality reporting method based on AI chat according to claim 1 is characterized in that: The AI ​​chat-based logistics abnormality reporting method also includes: The generated logistics exception work order is stored in the warehouse.

5. The logistics abnormality reporting method based on AI chat according to claim 1 is characterized in that: The AI ​​chat-based logistics abnormality reporting method also includes: Users can query logistics exception work orders in the AI ​​chat window.

6. The logistics abnormality reporting method based on AI chat according to claim 5 is characterized in that: The user can query the abnormal logistics work order in the AI ​​chat window including: The user enters the query conditions in the AI ​​chat window; Parse query conditions based on large language model technology and filter out corresponding logistics exception work orders; Display relevant information of logistics exception work orders in the AI ​​chat window.

7. The method for reporting abnormal logistics based on AI chat according to claim 6 is characterized in that: The user can query the abnormal logistics work order in the AI ​​chat window, including: Users can query the logistics exception work order to obtain the progress of logistics exception handling.

8. The logistics abnormality reporting method based on AI chat according to claim 1 is characterized in that: The AI ​​chat-based logistics abnormality reporting method also includes: Can handle multiple users' logistics exception reporting requests at the same time.

9. A logistics abnormality reporting system based on AI chat, characterized in that: The method for reporting abnormal logistics based on AI chat according to any one of claims 1 to 8 comprises: User interface, including AI chat window, for users to input logistics anomaly reporting requirements and display relevant information of logistics anomaly work orders; The parsing module is used to intelligently parse business needs based on large language model technology and obtain logistics anomaly information reported by users; The matching module is used to match the corresponding logistics orders based on the logistics exception information; The work order generation module is used to generate logistics exception work orders based on logistics exception information and corresponding logistics orders.

10. A computer program, characterized in that When the computer program is executed, the steps of the logistics abnormality reporting method based on AI chat are implemented as described in any one of claims 1 to 8.

Images