Logistics report generation method and system based on large model technology

Abstract

The invention relates to the related field of logistics management, discloses a logistics report generation method and system based on a large model technology, processes large-scale logistics data through the large model technology, automatically generates various reports, and aims to improve the generation efficiency, accuracy and intelligent level of the logistics report. An efficient and convenient data analysis tool is provided for logistics enterprises, so that the technical threshold of logistics enterprise users in the logistics report generation process is reduced, the logistics report generation efficiency is improved, and the understanding and utilization of the logistics enterprise users on big data resources are improved.

Description

Technical Field

[0001] The present invention relates to the field of logistics management, and in particular to a logistics report generation method and system based on large model technology. Background Art

[0002] The generation of logistics reports plays an irreplaceable role in the logistics industry. It not only provides an important reference for the decision-making of enterprises, but also helps enterprises optimize resource allocation, improve operational efficiency, strengthen risk management, promote supply chain collaboration, support performance evaluation and promote logistics innovation. Therefore, logistics enterprises should attach great importance to the generation and analysis of logistics reports and continuously improve their logistics management level. In the existing technology, there are still many problems in the current logistics report generation technology, including:

[0003] Specifically, there are two aspects to the problem of data collection and integration. The first is information asymmetry. The logistics process involves multiple links and multiple parties, making data collection difficult and information asymmetry common. This may result in the inability to obtain complete and accurate data when generating logistics reports, affecting the accuracy and reliability of the reports. The second is the lack of unified data standards. The logistics processes and management methods of different companies, regions, and industries are different, and there is a lack of unified standards and specifications. This leads to serious information island problems in the logistics process, making data integration difficult, and increasing the complexity and difficulty of report generation.

[0004] Data quality issues include: first, data accuracy issues. Since the logistics process involves multiple links and multiple parties, data may be erroneous or distorted during transmission. In addition, some logistics companies have a low level of informatization and imperfect information system functions, which may also lead to inaccurate data collection. Second, data integrity issues. Since there are information asymmetry and inconsistent data standards in the logistics process, data may be incomplete when reports are generated. For example, data in certain transportation links may be missing or unavailable, affecting the comprehensiveness and accuracy of the report.

[0005] Technical bottlenecks and technical limitations. The level of informatization construction of some logistics companies is low, and the information system functions are imperfect, which cannot meet the needs of logistics report generation. For example, some companies still use traditional manual operations and manual management methods to manage logistics information, resulting in inefficient and error-prone report generation; and some companies lack intelligent technology. With the development of technologies such as artificial intelligence and big data, logistics report generation technology should also develop in an intelligent direction. However, some logistics companies currently still lack intelligent technology support and cannot realize automated and intelligent report generation processes.

[0006] Security and privacy issues can also be summarized as data security issues. Logistics reports involve a large amount of sensitive information, such as customer information, transportation routes, cargo information, etc. If the report generation technology has security loopholes or protective measures are not in place, it may lead to data leakage or illegal use, causing privacy protection issues and damaging customer trust and corporate reputation.

[0007] Problems with report generation efficiency and flexibility. The report generation technology of some logistics companies is backward, requiring manual intervention and a lot of time to process data, resulting in low report generation efficiency. This cannot meet the modern logistics industry's needs for rapid response and efficient decision-making. Different companies and different business scenarios may have different needs for logistics reports. However, some current logistics report generation technologies lack flexibility and cannot meet personalized customization needs, which limits the practicality and value of the reports.

[0008] Problems with report analysis and interpretation: The report generation technology of some logistics companies can only provide basic data aggregation and display functions, and lacks in-depth data analysis and mining capabilities. This results in the reports being unable to provide valuable information and insights, and unable to support the company's decision-making process. At the same time, since logistics reports involve a large amount of data and professional terms, non-professionals may find it difficult to understand and interpret the report content, which increases the difficulty and limitations of using the reports.

[0009] To sum up, the current logistics report generation technology still faces many challenges, such as data collection and integration problems, data quality problems, technical bottlenecks and limitations, security and privacy issues, report generation efficiency and flexibility problems, and report analysis and interpretation problems. In order to meet these challenges, logistics companies need to continuously strengthen information construction and technological innovation, and improve the intelligence, automation and personalization of report generation technology to meet the needs and development trends of the modern logistics industry. Summary of the invention

[0010] The purpose of the present invention is to provide a logistics report generation method and system based on large model technology to solve the problems raised in the above background technology.

[0011] To achieve the above object, the present invention provides the following technical solutions:

[0012] A logistics report generation method based on large model technology, comprising:

[0013] Obtaining raw logistics data through logistics systems and logistics-related equipment, and performing standardized preprocessing on the raw logistics data, wherein the raw logistics data includes planning data, order data, transportation data, inventory data, inbound and outbound data, distribution information, equipment operation information, and customer feedback;

[0014] Obtain the user's query requirements, identify and analyze them through the NLP natural language model, obtain the corresponding key logistics information, and convert it into structured query language;

[0015] Perform database retrieval based on structured query statements to obtain required data and perform report normalization processing, which includes data aggregation, calculation, and sorting;

[0016] The normalized demand data is processed based on a preset report template to create a logistics report, and the visual output of the logistics report is optimized through a data visualization tool.

[0017] As a further solution of the present invention: the step of obtaining raw data through the logistics system and logistics-related equipment and performing standardized preprocessing on the data specifically includes:

[0018] Conduct multi-link data monitoring of multiple business links and related operating equipment in the logistics park, and collect and record original logistics data;

[0019] Performing data cleaning on the original logistics data, and if missing values ​​are identified in the original logistics data, performing linear interpolation repair on the missing values ​​based on the time series and adjacent values;

[0020] Obtain preset data specification standards, and normalize the raw logistics data after data cleaning based on the data specification standards so that data from different sources share a common format standard, wherein the data specification standards correspond to the data type.

[0021] As a further solution of the present invention: the step of identifying and parsing by using the NLP natural language model specifically includes:

[0022] Determine the data type of the query demand, and perform scheduling matching of the NLP natural language model based on the determination result, wherein the data type is used to characterize the user's information expression method, including text information, image information, and language information;

[0023] Performing content recognition on the query demand based on the matching results, converting the query demand into machine-recognizable text, and identifying logistics data keywords in the machine-recognizable text;

[0024] A large model is trained based on annotated historical data sets to obtain the mapping relationship between logistics data and reports, and logistics data keywords are matched and mapped based on the mapping relationship.

[0025] As a further solution of the present invention: the reports specifically include inventory reports, transportation reports, distribution reports, coal loading reports, coal blending reports and shipping reports, and the report templates specifically include data fields, chart types, and screening condition elements to achieve an intuitive display of the park's road and railway logistics transportation data.

[0026] As a further solution of the present invention: the step of optimizing the visual output of the logistics report using the data visualization tool specifically includes:

[0027] Acquire display characteristics of a display device to be output, wherein the display characteristics include a display size, a display resolution, a display color space, and a display ratio of the output display device;

[0028] Based on the display characteristics, the size of the form and content of the logistics report is adjusted, wherein the text size has a minimum limit display standard;

[0029] The color display of the logistics report is adjusted based on the display characteristics. If the total number of colors in the display color space is less than the total number of report colors, the color of the report is replaced and the color difference of adjacent different-color contents is maintained.

[0030] The embodiment of the present invention aims to provide a logistics report generation system based on large model technology, comprising:

[0031] A data acquisition module is used to acquire raw logistics data through the logistics system and logistics-related equipment, and perform standardized preprocessing on the raw logistics data. The raw logistics data includes planning data, order data, transportation data, inventory data, inbound and outbound data, distribution information, equipment operation information, and customer feedback;

[0032] The query demand module is used to obtain the user's query requirements, identify and parse them through the NLP natural language model, obtain the corresponding key logistics information, and convert it into structured query language;

[0033] A data retrieval module is used to perform database retrieval based on structured query statements to obtain required data and perform report normalization processing, wherein the normalization processing includes data aggregation, calculation and sorting;

[0034] The report creation module is used to process the normalized demand data based on a preset report template to create a logistics report, and to optimize the visual output of the logistics report through a data visualization tool.

[0035] As a further solution of the present invention: the data acquisition module includes:

[0036] The object monitoring unit is used to monitor multiple business links and related operating equipment in the logistics park, and collect and record raw logistics data;

[0037] A data cleaning unit, used to clean the original logistics data, and if missing values ​​are identified in the original logistics data, perform linear interpolation repair on the missing values ​​based on the time series and adjacent values;

[0038] The data standardization unit is used to obtain a preset data standardization standard, and normalize the raw logistics data after data cleaning based on the data standardization standard so that data from different sources share a common format standard. The data standardization standard corresponds to the data type.

[0039] As a further solution of the present invention: the query requirement module includes:

[0040] A content determination unit, configured to determine the data type of the query requirement, and to perform scheduling matching of an NLP natural language model based on the determination result, wherein the data type is used to characterize the user's information expression method, including text information, image information, and language information;

[0041] A content recognition unit, configured to perform content recognition on the query requirement based on the matching result, convert the query requirement into a machine-recognizable text, and recognize logistics data keywords in the machine-recognizable text;

[0042] The table mapping unit is used to perform large model training based on the annotated historical data set, obtain the mapping relationship between logistics data and reports, and match and map logistics data keywords based on the mapping relationship.

[0043] As a further solution of the present invention: the reports specifically include inventory reports, transportation reports, distribution reports, coal loading reports, coal blending reports and shipping reports, and the report templates specifically include data fields, chart types, and screening condition elements to achieve an intuitive display of the park's road and railway logistics transportation data.

[0044] As a further solution of the present invention: the report creation module includes:

[0045] A display evaluation unit, used to obtain display characteristics of a display device to be output, wherein the display characteristics include a display size, a display resolution, a display color space, and a display ratio of the output display device;

[0046] A size optimization unit, used to adjust the size of the table and content of the logistics report based on the display characteristics, wherein the text size is set with a minimum limit display standard;

[0047] The color optimization unit is used to adjust the color display of the logistics report based on the display characteristics. If the total number of colors in the display color space is less than the total number of colors in the report, the color of the report is replaced and the color difference of adjacent different-color contents is maintained.

[0048] Compared with the prior art, the beneficial effects of the present invention are: processing large-scale logistics data through big model technology, automatically generating various reports, aiming to improve the efficiency, accuracy and intelligence level of logistics report generation, and providing logistics companies with efficient and convenient data analysis tools to reduce the technical threshold of logistics company users in the process of logistics report generation, improve the efficiency of logistics report generation, and improve the understanding and utilization of big data resources by logistics company users. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 The flowchart is a method for generating logistics reports based on large model technology.

[0050] Figure 2 The logical block diagram of a logistics report generation method based on large model technology.

[0051] Figure 3 This is a block diagram of the composition of a logistics report generation system based on large model technology. DETAILED DESCRIPTION

[0052] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0053] The specific implementation of the present invention is described in detail below in conjunction with specific embodiments.

[0054] like Figure 1 and Figure 2 The above-mentioned method for generating a logistics report based on a large model technology provided by an embodiment of the present invention comprises the following steps:

[0055] S10, obtaining raw logistics data through the logistics system and logistics-related equipment, and performing standardized preprocessing on the raw logistics data, wherein the raw logistics data includes planning data, order data, transportation data, inventory data, inbound and outbound data, distribution information, equipment operation information, and customer feedback;

[0056] S20, obtaining the user's query requirements, identifying and parsing them through the NLP natural language model, obtaining the corresponding key logistics information, and converting it into a structured query language;

[0057] S30, performing database retrieval based on structured query statements to obtain required data and perform report normalization processing, wherein the normalization processing includes data aggregation, calculation, and sorting;

[0058] S40, processing the normalized demand data based on a preset report template to create a logistics report, and optimizing the visual output of the logistics report through a data visualization tool.

[0059] In this embodiment, a logistics report generation method based on big model technology is proposed, which aims to improve the generation efficiency, accuracy and intelligence level of logistics reports. By processing large-scale logistics data through big model technology, various reports are automatically generated, and efficient and convenient data analysis tools are provided for logistics companies to reduce the technical threshold of logistics company users in the process of logistics report generation, improve the efficiency of logistics report generation, and improve the understanding and utilization of big data resources by logistics company users; Specifically, the implementation principles include: First, big model technology: a big model (AI big model) is an artificial intelligence model based on deep learning, usually with billions or even tens of billions of parameters. These models are trained for natural language processing tasks, such as text generation, machine translation, question-answering systems, etc. The core idea is to predict through large-scale text data sets. Training to learn language patterns, syntax and semantics. In the field of logistics, big models can process large amounts of text data, including transportation records, warehousing information, customer feedback, etc., so as to dig out valuable information hidden in them; second, natural language processing: the natural language processing (NLP) capability in big model technology enables computers to understand and generate human language. In logistics report generation, NLP technology can be used to parse natural language queries raised by users and convert them into structured query language (SQL) to query databases and generate reports; third, data analysis and visualization: big model technology can also be combined with data analysis and visualization tools to conduct in-depth mining and analysis of logistics data, and intuitively display the analysis results in the form of charts, tables, etc., which helps logistics companies better understand operating conditions and optimize decision-making processes.

[0060] Compared with the prior art, the technical solution in this embodiment has the following technical effects: improving report generation efficiency: the large model technology automatically processes and analyzes a large amount of logistics data, quickly generates the required reports, improves the efficiency of report generation, and automated report generation can greatly reduce the time and cost of manual operations;

[0061] Enhanced report accuracy: Big model technology can more accurately identify and process logistics data through deep learning and data analysis. It has powerful data processing and analysis capabilities, reduces human errors and omissions, and ensures the accuracy and reliability of report data.

[0062] Improve report flexibility: The report generation system based on big model technology can be customized and expanded according to the user's personalized needs to meet the report requirements of management demand scenarios at different levels and angles;

[0063] Optimize logistics management decisions: Through visual report display, users can intuitively understand logistics data and provide strong support for logistics management decisions;

[0064] Real-time monitoring and early warning: Big model technology can monitor changes in logistics data in real time, detect abnormal situations in a timely manner and generate early warning reports to help park managers respond to and handle problems quickly.

[0065] As another preferred embodiment of the present invention, the step of obtaining raw data through the logistics system and logistics-related equipment and performing standardized preprocessing on the data specifically includes:

[0066] Conduct multi-link data monitoring of multiple business links and related operating equipment in the logistics park, and collect and record original logistics data;

[0067] Performing data cleaning on the original logistics data, and if missing values ​​are identified in the original logistics data, performing linear interpolation repair on the missing values ​​based on the time series and adjacent values;

[0068] Obtain preset data specification standards, and normalize the raw logistics data after data cleaning based on the data specification standards so that data from different sources share a common format standard, wherein the data specification standards correspond to the data type.

[0069] In this embodiment, raw data is collected from the equipment involved in the logistics system or logistics scenario, including planning data, order data, transportation data, inventory data, in-and-out warehouse data, distribution information, equipment operation information, and customer feedback. These data may come from different systems and data sources. Therefore, it is necessary to pre-process the raw data collected above, including data cleaning, data deduplication, data classification, format conversion, and standardization processing to make it suitable for the input of large models.

[0070] As another preferred embodiment of the present invention, the step of identifying and parsing by using the NLP natural language model specifically includes:

[0071] Determine the data type of the query demand, and perform scheduling matching of the NLP natural language model based on the determination result, wherein the data type is used to characterize the user's information expression method, including text information, image information, and language information;

[0072] Performing content recognition on the query demand based on the matching results, converting the query demand into machine-recognizable text, and identifying logistics data keywords in the machine-recognizable text;

[0073] A large model is trained based on annotated historical data sets to obtain the mapping relationship between logistics data and reports, and logistics data keywords are matched and mapped based on the mapping relationship.

[0074] In this embodiment, the user puts forward query requirements through natural language, such as "query the top ten routes in terms of coal transportation volume last month". The NLP module in the big model technology will parse these queries, identify key information (such as time, transportation volume, route, etc.), and convert it into structured query language (SQL); according to the needs of logistics report generation, a suitable big model architecture is selected, and the big model is trained using annotated data sets so that the model can learn the mapping relationship between logistics data and reports.

[0075] As another preferred embodiment of the present invention, the report specifically includes inventory report, transportation report, distribution report, coal loading report, coal blending report and shipping report, and the report template specifically includes data fields, chart types, and screening condition elements to achieve intuitive display of park road and railway logistics transportation data.

[0076] Furthermore, the step of optimizing the visual output of the logistics report using the data visualization tool specifically includes:

[0077] Acquire display characteristics of a display device to be output, wherein the display characteristics include a display size, a display resolution, a display color space, and a display ratio of the output display device;

[0078] Based on the display characteristics, the size of the form and content of the logistics report is adjusted, wherein the text size has a minimum limit display standard;

[0079] The color display of the logistics report is adjusted based on the display characteristics. If the total number of colors in the display color space is less than the total number of report colors, the color of the report is replaced and the color difference of adjacent different-color contents is maintained.

[0080] In this embodiment, the processed data will be passed to the report generation module, which will generate logistics reports according to the preset report template or the user-defined style. The report can be displayed in the form of tables, charts, dashboards, etc., so that users can intuitively understand the logistics operation status. At the same time, the large model technology can also be combined with data visualization tools to beautify and optimize the report to enhance the user experience; the report can be displayed to the user through a variety of methods such as web pages, mobile terminals, and large screens, and supports downloading and printing. However, because the display modes and display resources that can be called by the display devices that are not standardized are limited and different, it is also necessary to adjust the display format of the report according to the display specifications of the corresponding display device when outputting it to adapt it to the corresponding display device.

[0081] like Figure 3 As shown, the present invention also provides a logistics report generation system based on large model technology, which includes:

[0082] The data acquisition module 100 is used to acquire original logistics data through the logistics system and logistics-related equipment, and perform standardized preprocessing on the original logistics data, wherein the original logistics data includes planning data, order data, transportation data, inventory data, inbound and outbound data, distribution information, equipment operation information and customer feedback;

[0083] The query demand module 200 is used to obtain the user's query demand, identify and analyze it through the NLP natural language model, obtain the corresponding key logistics information, and convert it into a structured query language;

[0084] The data retrieval module 300 is used to perform database retrieval based on structured query statements to obtain required data and perform report normalization processing, wherein the normalization processing includes data aggregation, calculation and sorting;

[0085] The report creation module 400 is used to process the normalized demand data based on a preset report template to create a logistics report, and to optimize the visual output of the logistics report through a data visualization tool.

[0086] As another preferred embodiment of the present invention, the data acquisition module includes:

[0087] The object monitoring unit is used to monitor multiple business links and related operating equipment in the logistics park, and collect and record raw logistics data;

[0088] A data cleaning unit, used to clean the original logistics data, and if missing values ​​are identified in the original logistics data, perform linear interpolation repair on the missing values ​​based on the time series and adjacent values;

[0089] The data standardization unit is used to obtain a preset data standardization standard, and normalize the raw logistics data after data cleaning based on the data standardization standard so that data from different sources share a common format standard. The data standardization standard corresponds to the data type.

[0090] As another preferred embodiment of the present invention, the query requirement module includes:

[0091] A content determination unit, configured to determine the data type of the query requirement, and to perform scheduling matching of an NLP natural language model based on the determination result, wherein the data type is used to characterize the user's information expression method, including text information, image information, and language information;

[0092] A content recognition unit, configured to perform content recognition on the query requirement based on the matching result, convert the query requirement into a machine-recognizable text, and recognize logistics data keywords in the machine-recognizable text;

[0093] The table mapping unit is used to perform large model training based on the annotated historical data set, obtain the mapping relationship between logistics data and reports, and match and map logistics data keywords based on the mapping relationship.

[0094] As another preferred embodiment of the present invention, the report specifically includes inventory report, transportation report, distribution report, coal loading report, coal blending report and shipping report, and the report template specifically includes data fields, chart types, and screening condition elements to achieve intuitive display of park road and railway logistics transportation data.

[0095] As another preferred embodiment of the present invention, the report creation module includes:

[0096] A display evaluation unit, used to obtain display characteristics of a display device to be output, wherein the display characteristics include a display size, a display resolution, a display color space, and a display ratio of the output display device;

[0097] A size optimization unit, used to adjust the size of the table and content of the logistics report based on the display characteristics, wherein the text size is set with a minimum limit display standard;

[0098] The color optimization unit is used to adjust the color display of the logistics report based on the display characteristics. If the total number of colors in the display color space is less than the total number of colors in the report, the color of the report is replaced and the color difference of adjacent different-color contents is maintained.

[0099] Among them, any reference to memory, storage, database or other media used in the embodiments provided in the present application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0100] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the disclosure in the specification and examples. This application is intended to cover any variations, uses or adaptations of the present disclosure, which follow the general principles of the present disclosure and include common knowledge or customary techniques in the art that are not disclosed in the present disclosure. The specification and examples are intended to be exemplary only, and the true scope and spirit of the present disclosure are indicated by the claims.

[0101] It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. A logistics report generation method based on large model technology, characterized in that: Include: Obtaining raw logistics data through logistics systems and logistics-related equipment, and performing standardized preprocessing on the raw logistics data, wherein the raw logistics data includes planning data, order data, transportation data, inventory data, inbound and outbound data, distribution information, equipment operation information, and customer feedback; Obtain the user's query requirements, identify and analyze them through the NLP natural language model, obtain the corresponding key logistics information, and convert it into structured query language; Perform database retrieval based on structured query statements to obtain required data and perform report normalization processing, which includes data aggregation, calculation, and sorting; The normalized demand data is processed based on a preset report template to create a logistics report, and the visual output of the logistics report is optimized through a data visualization tool.

2. According to the method for generating a logistics report based on large model technology according to claim 1, it is characterized in that: The steps of obtaining raw data through the logistics system and logistics-related equipment and performing standardized preprocessing on the data specifically include: Conduct multi-link data monitoring of multiple business links and related operating equipment in the logistics park, and collect and record original logistics data; Performing data cleaning on the original logistics data, and if missing values ​​are identified in the original logistics data, performing linear interpolation repair on the missing values ​​based on the time series and adjacent values; Obtain preset data specification standards, and normalize the raw logistics data after data cleaning based on the data specification standards so that data from different sources share a common format standard, wherein the data specification standards correspond to the data type.

3. The method for generating a logistics report based on a large model technology according to claim 2 is characterized in that: The steps of identifying and parsing by using the NLP natural language model specifically include: Determine the data type of the query demand, and perform scheduling matching of the NLP natural language model based on the determination result, wherein the data type is used to characterize the user's information expression method, including text information, image information, and language information; Performing content recognition on the query demand based on the matching results, converting the query demand into machine-recognizable text, and identifying logistics data keywords in the machine-recognizable text; A large model is trained based on annotated historical data sets to obtain the mapping relationship between logistics data and reports, and logistics data keywords are matched and mapped based on the mapping relationship.

4. The method for generating a logistics report based on a large model technology according to claim 4 is characterized in that: The reports specifically include inventory reports, transportation reports, distribution reports, coal loading reports, coal blending reports and shipping reports. The report templates specifically include data fields, chart types, and screening condition elements to achieve an intuitive display of the park's road and rail logistics transportation data.

5. The method for generating a logistics report based on a large model technology according to claim 4 is characterized in that: The steps of optimizing the visual output of the logistics report using the data visualization tool specifically include: Acquire display characteristics of a display device to be output, wherein the display characteristics include a display size, a display resolution, a display color space, and a display ratio of the output display device; Based on the display characteristics, the size of the form and content of the logistics report is adjusted, wherein the text size has a minimum limit display standard; The color display of the logistics report is adjusted based on the display characteristics. If the total number of colors in the display color space is less than the total number of report colors, the color of the report is replaced and the color difference of adjacent different-color contents is maintained.

6. A logistics report generation system based on large model technology, characterized in that: Include: A data acquisition module is used to acquire raw logistics data through the logistics system and logistics-related equipment, and perform standardized preprocessing on the raw logistics data. The raw logistics data includes planning data, order data, transportation data, inventory data, inbound and outbound data, distribution information, equipment operation information, and customer feedback; The query demand module is used to obtain the user's query requirements, identify and analyze them through the NLP natural language model, obtain the corresponding key logistics information, and convert it into structured query language; A data retrieval module is used to perform database retrieval based on structured query statements to obtain required data and perform report normalization processing, wherein the normalization processing includes data aggregation, calculation and sorting; The report creation module is used to process the normalized demand data based on a preset report template to create a logistics report, and to optimize the visual output of the logistics report through a data visualization tool.

7. A logistics report generation system based on large model technology according to claim 6, characterized in that: The data acquisition module comprises: The object monitoring unit is used to monitor multiple business links and related operating equipment in the logistics park, and collect and record raw logistics data; A data cleaning unit, used to clean the original logistics data, and if missing values ​​are identified in the original logistics data, perform linear interpolation repair on the missing values ​​based on the time series and adjacent values; The data standardization unit is used to obtain a preset data standardization standard, and normalize the raw logistics data after data cleaning based on the data standardization standard so that data from different sources share a common format standard. The data standardization standard corresponds to the data type.

8. A logistics report generation system based on large model technology according to claim 7, characterized in that: The query requirement module includes: A content determination unit, configured to determine the data type of the query requirement, and to perform scheduling matching of an NLP natural language model based on the determination result, wherein the data type is used to characterize the user's information expression method, including text information, image information, and language information; A content recognition unit, configured to perform content recognition on the query requirement based on the matching result, convert the query requirement into a machine-recognizable text, and recognize logistics data keywords in the machine-recognizable text; The table mapping unit is used to perform large model training based on the annotated historical data set, obtain the mapping relationship between logistics data and reports, and match and map logistics data keywords based on the mapping relationship.

9. A logistics report generation system based on large model technology according to claim 8, characterized in that: The reports specifically include inventory reports, transportation reports, distribution reports, coal loading reports, coal blending reports and shipping reports. The report templates specifically include data fields, chart types, and screening condition elements to achieve an intuitive display of the park's road and rail logistics transportation data.

10. A logistics report generation system based on large model technology according to claim 9, characterized in that: The report creation module includes: A display evaluation unit, used to obtain display characteristics of a display device to be output, wherein the display characteristics include a display size, a display resolution, a display color space, and a display ratio of the output display device; The size optimization unit is used to adjust the size of the table and content of the logistics report based on the display characteristics, wherein There is a minimum display standard for text size; The color optimization unit is used to adjust the color display of the logistics report based on the display characteristics. If the total number of colors in the display color space is less than the total number of colors in the report, the color of the report is replaced and the color difference of adjacent different-color contents is maintained.

Images