Intelligent logistics query system and method thereof

Abstract

The invention, which belongs to the technical field of logistics query, discloses an intelligent logistics query system comprising a query and report module, an information acquisition module, a cargo preparation time prediction module, a logistics time prediction module, a cargo preparation time prediction module, and a cargo abnormity early warning and notification module. The query and report module, the information acquisition module, the cargo preparation time prediction module, the logistics time prediction module, the cargo preparation time prediction module and the cargo abnormity early warning and notification module are in communication connection in sequence, and the query and report module allows a user to perform query operation including cargo state query and transportation record query. Meanwhile, the pushed logistics related information can be automatically received; according to the intelligent logistics query system and the method thereof, the cargo preparation time and the logistics transportation time can be predicted more accurately, and meanwhile, the system has a cargo abnormity early warning function, so that a user can know the cargo state more clearly.

Description

Technical Field

[0001] The present invention belongs to the technical field of logistics query, and specifically relates to an intelligent logistics query system and method thereof. Background Art

[0002] The logistics query system is a system used to track and manage logistics information. It can provide data and status updates on cargo transportation, warehousing, distribution, etc. With the rapid development of the modern economy and the growing prosperity of e-commerce, the logistics industry has become increasingly important in economic activities. In modern society, people have put forward higher and higher requirements for the timeliness, accuracy and queryability of logistics.

[0003] However, the logistics query in the prior art does not have the ability to accurately predict the transfer time. When a product is out of stock and needs to be transferred, the arrival time is usually directly estimated. The transfer time is not accurately predicted based on the transfer area and the weather conditions during the transfer process. At the same time, it does not have the ability to accurately predict the picking, packaging and logistics transportation time. Therefore, an intelligent logistics query system and method are proposed. Summary of the invention

[0004] The present invention aims to solve at least one of the technical problems existing in the prior art. To this end, the present invention proposes a smart logistics query system and method thereof, so that users can more accurately understand the transportation status of logistics.

[0005] In order to achieve the above object, the present invention adopts the following technical solutions:

[0006] A smart logistics query system, characterized in that it includes a query and report module, an information collection module, a cargo preparation time prediction module, a logistics time prediction module, a cargo preparation time prediction module, and a cargo abnormality warning and notification module, wherein the query and report module, the information collection module, the cargo preparation time prediction module, the logistics time prediction module, the cargo preparation time prediction module, and the cargo abnormality warning and notification module are sequentially connected in communication;

[0007] The query and report module allows users to perform query operations, including querying cargo status and transportation records, and automatically receive pushed logistics-related information;

[0008] The information collection module is used to obtain logistics-related data, including cargo status, cargo location, transportation status, weather during transportation, and historical data;

[0009] The cargo preparation time prediction module is used to predict the cargo preparation time. First, the inventory of the cargo is queried. When the cargo is in stock, the picking and packing time is directly predicted based on the cargo quantity. When the cargo is out of stock, the transfer time is predicted first, and then the purchase and packing time is predicted.

[0010] The logistics time prediction module predicts the transportation time of goods based on the weather during transportation and historical transportation data;

[0011] The cargo abnormality warning module processes the abnormal information of the cargo preparation time prediction module and the logistics time prediction module, determines the specific abnormality, and issues a warning message.

[0012] Furthermore, the query and report module allows users to perform query operations, including cargo status and transportation records, and automatically receive pushed logistics-related information. The processing process is as follows:

[0013] When users need to query logistics-related information, they must first log in to their account, enter query conditions after logging in, and query content includes cargo status and transportation records. After receiving the user's query request, the system will retrieve data that meets the query conditions from the database and feed the data back to the user's display interface;

[0014] The logistics messages of each stage will be automatically pushed to the user account. The specific push information includes completion of goods transfer, picking and packing, shipping notification, transportation node notification, and logistics abnormality notification.

[0015] The query and report module has the function of efficiently processing user query requests and timely pushing logistics-related information.

[0016] Furthermore, the information collection module is used to obtain logistics-related data, including cargo status, cargo location, transportation status, transportation process weather, and historical data. The process is as follows:

[0017] Collect logistics-related data, including cargo status, cargo location, transportation status, historical data, and integrate these data into the same platform;

[0018] By collecting these data, we can provide strong support for subsequent data.

[0019] Collect weather data during the cargo transfer process and weather data during the transportation process for subsequent calculation of the overall transportation process.

[0020] Furthermore, the cargo preparation time prediction module is used to predict the cargo preparation time. First, the inventory of the cargo is queried. When the cargo is in stock, the picking and packing time is directly predicted based on the cargo quantity. When the cargo is out of stock, the transfer time is predicted first, and then the purchase and packing time prediction process is as follows:

[0021] After the user places an order, the system will automatically check the inventory. If the inventory is insufficient, it will check the warehouse with inventory and predict the arrival time of the inventory based on the weather conditions of the warehouse receiving the inventory combined with historical data, and then predict the picking and packaging time;

[0022] When the inventory is sufficient, the picking and packing time is predicted directly. The specific formula is:

[0023] T 处理 =α0+α1×Q 货物 +α2×p 位置 +α3×M 材料 +e;

[0024] Among them, T 处理 is the comprehensive predicted processing time, including picking and packing time, α0 is the intercept term, α1 is the regression coefficient of the number of goods, Q 货物 is the number of goods picked and packed, α2 is the regression coefficient of storage location complexity, indicating the impact of storage location on processing time, p 位置 is the storage location complexity, which indicates the difficulty of the goods storage location; α3 is the regression coefficient of the packaging material complexity, which indicates the impact of packaging materials on processing time; M 材料 The complexity of the packaging material, e is the error term;

[0025] The formula for the final prediction time is: T 总 = predicted transfer time + predicted picking and packing time;

[0026] Finally, the forecast data is fed back to the query and report module so that users can receive logistics information in a timely manner.

[0027] By predicting when inventory will arrive, you can prepare for receiving and handling the goods before they arrive, including allocating resources and adjusting plans so that the goods can be packed quickly after they arrive.

[0028] Furthermore, after the user places an order, the system will automatically query the inventory. When the inventory is insufficient, the system will query the warehouse with inventory, and predict the arrival time of the inventory based on the weather conditions of the warehouse receiving the inventory combined with historical data, and then perform the picking and packaging time prediction processing process as follows:

[0029] Combine the weather data of the inventory warehouse with the historical cargo transfer data to establish a prediction model to predict the arrival time. The weather data of the inventory warehouse includes the weather conditions during transportation, the data of the inventory warehouse, and the data of the arrival warehouse.

[0030] The prediction formula is as follows: 到货 =β0+β1×T 天气 +β2×H 历史 +e;

[0031] Among them, β0 is the intercept term of the model, β1 is the regression coefficient of weather factors, β2 is the regression coefficient of historical data, e is the error term, T 天气 For weather factors, H 历史 is the average arrival time of similar orders in history, T 到货 is the predicted arrival time of the goods.

[0032] Furthermore, the logistics time prediction module predicts the transportation time of goods according to the weather during transportation and historical transportation data as follows:

[0033] The historical transportation data of logistics transportation includes the transportation time, transportation route, starting point and end point, transportation method, cargo type, weight, and volume of similar goods in the past. The historical data is preprocessed, including processing missing values, outliers, and duplicate data. The weather data includes historical weather records and weather conditions for transportation in the next few days.

[0034] Data in different formats are uniformly converted into the format required by the model, and important features are extracted from the original data, including daily average temperature, rainfall, wind speed in weather characteristics, average transportation time and historical average delay in historical data characteristics, and then the gradient boosting tree is used as the prediction model. After the prediction model is selected, the selected model is first trained using the training data set, and then the prediction performance of the model is evaluated using the validation set.

[0035] Reduce noise and errors in model training and ensure data integrity and consistency, thereby improving model accuracy.

[0036] Furthermore, the cargo abnormality warning module processes the abnormal information of the cargo preparation time prediction module and the logistics time prediction module, determines the specific abnormality, and issues the warning information. The processing process is as follows:

[0037] First, define the cargo abnormality standards, including cargo preparation time forecast abnormality and logistics time forecast abnormality, set the cargo transfer time abnormality standards, picking and packing time abnormality standards, and transportation time abnormality standards. If the cargo transfer time exceeds the expected time by 30%, it is considered as cargo transfer abnormality. If the picking and packing time exceeds the expected time by 20%, it is considered as picking and packing abnormality. If the logistics time exceeds the expected time by 30%, it is considered as transportation time abnormality.

[0038] Based on the specific abnormal information detected, it will be transmitted to the query and report module for users to view.

[0039] Standardized exception definitions help clarify responsibilities, ensure that problems can be tracked and resolved, and promote collaboration and cooperation among all links.

[0040] A smart logistics query method comprises the following steps:

[0041] S1. Obtain logistics-related data, including cargo status, cargo location, transportation status, weather during transportation, and historical data;

[0042] S2. Process the acquired data, first check the inventory, and when the inventory is insufficient, first predict the time of transferring goods, and then predict the time of picking and packing. When the inventory is sufficient, directly predict the time of picking and packing;

[0043] S3. Based on the predicted time for picking and packing, the logistics time is predicted. The logistics time prediction is also combined with transportation weather and historical data.

[0044] S4. Provide abnormal warning based on the predicted cargo preparation time and logistics transportation time, and set abnormal standards to quickly judge abnormalities;

[0045] S5. Users can check the specific time of goods transfer, picking and packaging, and logistics, and can also receive abnormal information about goods.

[0046] Compared with the prior art, the present invention has the following beneficial effects:

[0047] By setting up the cargo preparation time prediction module, the cargo transfer time can be predicted more accurately. When the inventory is insufficient, the weather conditions in the transfer area and the weather conditions during the transfer process will be combined with historical data to predict the transfer time, and then the picking and packing time will be predicted. When the inventory is sufficient, the picking and packing time will be directly predicted;

[0048] By setting up the logistics time prediction module, the logistics transportation time can be predicted more accurately. The logistics transportation time will also be predicted in combination with weather conditions and historical data;

[0049] By setting up a logistics abnormality warning module, the overall logistics abnormal status can be identified, including abnormal transfer time, picking and packing time, and logistics abnormalities. According to the specific abnormalities, abnormal standards are set, which can quickly and automatically judge the specific abnormalities and transmit the specific abnormalities to the user;

[0050] This system has accurate forecasts of transfer time, picking, packing time and logistics time, as well as specific abnormal warnings, allowing users to obtain logistics data information more comprehensively and accurately. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 A block diagram of a smart logistics query system of the present invention;

[0052] Figure 2 A diagram showing the specific steps of cargo preparation time prediction in a smart logistics query system of the present invention;

[0053] Figure 3 This is a flow chart of a smart logistics query method of the present invention. DETAILED DESCRIPTION

[0054] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than 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.

[0055] like Figure 1-Figure 3 As shown, a smart logistics query system includes a query and report module, an information collection module, a cargo preparation time prediction module, a logistics time prediction module, a cargo preparation time prediction module, and a cargo abnormality warning and notification module. The query and report module, the information collection module, the cargo preparation time prediction module, the logistics time prediction module, the cargo preparation time prediction module, and the cargo abnormality warning and notification module are sequentially connected in communication;

[0056] The query and report module allows users to perform query operations, including querying cargo status and transportation records, and automatically receive push logistics-related information;

[0057] In this embodiment, the query and report module allows users to perform query operations, including cargo status and transportation records, and automatically receive pushed logistics-related information. The processing process is as follows:

[0058] When users need to query logistics-related information, they must first log in to their account, enter query conditions after logging in, and query content includes cargo status and transportation records. After receiving the user's query request, the system will retrieve data that meets the query conditions from the database and feed the data back to the user's display interface;

[0059] The logistics messages of each stage will be automatically pushed to the user account. The specific push information includes completion of goods transfer, picking and packing, shipping notification, transportation node notification, and logistics abnormality notification.

[0060] It should be noted that the system can push information such as the completion of goods transfer, picking, and packaging in real time, so that users can grasp the status of goods at any time and avoid information lag. From order processing to final delivery, the status of each stage can be tracked and viewed, which improves the transparency of information and enables users to always understand the progress of logistics;

[0061] Information collection module, used to obtain logistics-related data, including cargo status, cargo location, transportation status, weather during transportation, and historical data;

[0062] In this embodiment, the information collection module is used to obtain logistics-related data, including cargo status, cargo location, transportation status, transportation process weather, and historical data. The process is as follows:

[0063] Collect logistics-related data, including cargo status, cargo location, transportation status, historical data, and integrate these data into the same platform;

[0064] Collect weather data during the cargo transfer process and weather data during the transportation process for subsequent calculation of the overall transportation process.

[0065] It should be noted that by integrating the data on cargo status, location and transportation status, a complete view of the transportation process can be provided, allowing users to monitor the flow and current status of cargo in real time. By collecting weather data during the cargo transfer process and weather data during the transportation process and using the data in subsequent calculations, the transportation time can be calculated more accurately.

[0066] The cargo preparation time prediction module is used to predict the cargo preparation time. First, the inventory of the cargo is queried. If the cargo is in stock, the picking and packing time will be predicted directly based on the cargo quantity. If the cargo is out of stock, the transfer time will be predicted first, and then the purchase and packing time will be predicted.

[0067] In this embodiment, the cargo preparation time prediction module is used to predict the cargo preparation time. First, the inventory of the cargo is queried. When the cargo is in stock, the picking and packing time is directly predicted based on the cargo quantity. When the cargo is out of stock, the transfer time is predicted first, and then the purchase and packing time prediction process is as follows:

[0068] After the user places an order, the system will automatically check the inventory. If the inventory is insufficient, it will check the warehouse with inventory and predict the arrival time of the inventory based on the weather conditions of the warehouse receiving the inventory combined with historical data, and then predict the picking and packaging time;

[0069] When the inventory is sufficient, the picking and packing time is predicted directly. The specific formula is:

[0070] T 处理 =α0+α1×Q 货物 +α2×p 位置 +α3×M 材料 +e;

[0071] Among them, T 处理 is the comprehensive predicted processing time, including picking and packing time, α0 is the intercept term, α1 is the regression coefficient of the number of goods, Q 货物 is the number of goods picked and packed, α2 is the regression coefficient of storage location complexity, indicating the impact of storage location on processing time, p 位置is the storage location complexity, which indicates the difficulty of the goods storage location; α3 is the regression coefficient of the packaging material complexity, which indicates the impact of packaging materials on processing time; M 材料 The complexity of the packaging material, e is the error term;

[0072] The formula for the final prediction time is: T 总 = predicted transfer time + predicted picking and packing time;

[0073] Finally, the forecast data is fed back to the query and report module so that users can receive logistics information in a timely manner.

[0074] It should be noted that by predicting the cargo transfer time, users can understand the status of the goods more clearly. At the same time, the cargo transfer time is combined with the weather conditions during transportation, which can make the transportation time prediction more accurate.

[0075] In this embodiment, after the user places an order, the system will automatically query the inventory. When the inventory is insufficient, the system will query the warehouse with inventory, and predict the arrival time of the inventory based on the weather conditions of the received inventory warehouse combined with historical data, and then perform the picking and packaging time prediction processing process as follows:

[0076] Combine the weather data of the inventory warehouse with the historical cargo transfer data to establish a prediction model to predict the arrival time. The weather data of the inventory warehouse includes the weather conditions during transportation, the data of the inventory warehouse, and the data of the arrival warehouse.

[0077] The prediction formula is as follows: 到货 =β0+β1×T 天气 +β2×H 历史 +e;

[0078] Among them, β0 is the intercept term of the model, β1 is the regression coefficient of weather factors, β2 is the regression coefficient of historical data, e is the error term, T 天气 For weather factors, H 历史 is the average arrival time of similar orders in history, T 到货 The predicted arrival time of the goods

[0079] Logistics time prediction module, which predicts the transportation time of goods based on the weather during transportation and historical transportation data;

[0080] In this embodiment, the logistics time prediction module predicts the transportation time of goods according to the weather during the transportation process and historical transportation data, and the processing process is as follows:

[0081] The historical transportation data of logistics transportation includes the transportation time, transportation route, starting point and end point, transportation method, cargo type, weight, and volume of similar goods in the past. The historical data is preprocessed, including processing missing values, outliers, and duplicate data. The weather data includes historical weather records and weather conditions for transportation in the next few days.

[0082] Data in different formats are uniformly converted into the format required by the model, and important features are extracted from the original data, including daily average temperature, rainfall, wind speed in weather characteristics, average transportation time and historical average delay in historical data characteristics, and then the gradient boosting tree is used as the prediction model. After the prediction model is selected, the selected model is first trained using the training data set, and then the prediction performance of the model is evaluated using the validation set.

[0083] It should be noted that weather characteristics directly affect transportation time. Accurately extracting and using these characteristics can help the model better understand the impact of weather on transportation time. The average transportation time and historical average delay in historical data characteristics reflect past transportation patterns and potential delays. Effective use of weather characteristics and historical data characteristics can improve prediction accuracy.

[0084] The cargo abnormality warning module processes the abnormal information of the cargo preparation time prediction module and the logistics time prediction module, determines the specific abnormality, and issues warning information;

[0085] In this embodiment, the cargo abnormality warning module processes the abnormal information of the cargo preparation time prediction module and the logistics time prediction module, determines the specific abnormality, and issues the warning information. The processing process is as follows:

[0086] First, define the cargo abnormality standards, including cargo preparation time forecast abnormality and logistics time forecast abnormality, set the cargo transfer time abnormality standards, picking and packing time abnormality standards, and transportation time abnormality standards. If the cargo transfer time exceeds the expected time by 30%, it is considered as cargo transfer abnormality. If the picking and packing time exceeds the expected time by 20%, it is considered as picking and packing abnormality. If the logistics time exceeds the expected time by 30%, it is considered as transportation time abnormality.

[0087] Based on the specific abnormal information detected, it will be transmitted to the query and report module for users to view.

[0088] It should be noted that by defining specific cargo abnormality standards, including abnormal standards for cargo transfer time, picking, packaging time and logistics time, the accuracy of abnormality detection and the efficiency of the early warning system can be significantly improved, and resource management and operation processes can be optimized.

[0089] A smart logistics query system, comprising:

[0090] S1. Obtain logistics-related data, including cargo status, cargo location, transportation status, weather during transportation, and historical data;

[0091] S2. Process the acquired data, first check the inventory, and when the inventory is insufficient, first predict the time of transferring goods, and then predict the time of picking and packing. When the inventory is sufficient, directly predict the time of picking and packing;

[0092] S3. Based on the predicted time for picking and packing, the logistics time is predicted. The logistics time prediction is also combined with transportation weather and historical data.

[0093] S4. Provide abnormal warning based on the predicted cargo preparation time and logistics transportation time, and set abnormal standards to quickly judge abnormalities;

[0094] S5. Users can check the specific time of goods transfer, picking and packing, and logistics, and can also receive abnormal information about goods.

[0095] In the embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the modules is only a logical function division, and there may be other division methods in actual implementation; the modules described as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the method of this embodiment.

[0096] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. A smart logistics query system, characterized by: It includes a query and report module, an information collection module, a cargo preparation time prediction module, a logistics time prediction module, a cargo preparation time prediction module, and a cargo abnormality warning and notification module, wherein the query and report module, the information collection module, the cargo preparation time prediction module, the logistics time prediction module, the cargo preparation time prediction module, and the cargo abnormality warning and notification module are sequentially connected in communication; The query and report module allows users to perform query operations, including querying cargo status and transportation records, and automatically receive pushed logistics-related information; The information collection module is used to obtain logistics-related data, including cargo status, cargo location, transportation status, weather during transportation, and historical data; The cargo preparation time prediction module is used to predict the cargo preparation time. First, the inventory of the cargo is queried. When the cargo is in stock, the picking and packing time is directly predicted based on the cargo quantity. When the cargo is out of stock, the transfer time is predicted first, and then the purchase and packing time is predicted. The logistics time prediction module predicts the transportation time of goods based on the weather during transportation and historical transportation data; The cargo abnormality warning module processes the abnormal information of the cargo preparation time prediction module and the logistics time prediction module, determines the specific abnormality, and issues a warning message.

2. According to claim 1, the intelligent logistics query system is characterized by: The query and report module allows users to query operations, including cargo status and transportation records, and automatically receive pushed logistics related information. The processing process is as follows: When users need to query logistics-related information, they must first log in to their account, enter query conditions after logging in, and query content includes cargo status and transportation records. After receiving the user's query request, the system will retrieve data that meets the query conditions from the database and feed the data back to the user's display interface; The logistics messages of each stage will be automatically pushed to the user account. The specific push information includes completion of goods transfer, picking and packing, shipping notification, transportation node notification, and logistics abnormality notification.

3. According to claim 1, the intelligent logistics query system is characterized by: The information collection module is used to obtain logistics-related data, including cargo status, cargo location, transportation status, transportation process weather, and historical data. The process is as follows: Collect logistics-related data, including cargo status, cargo location, transportation status, historical data, and integrate these data into the same platform; Collect weather data during the cargo transfer process and weather data during the transportation process for subsequent calculation of the overall transportation process.

4. The intelligent logistics query system according to claim 1 is characterized by: The cargo preparation time prediction module is used to predict the cargo preparation time. First, the inventory of the cargo is queried. When the cargo is in stock, the picking and packing time is directly predicted based on the cargo quantity. When the cargo is out of stock, the transfer time is predicted first, and then the purchase and packing time prediction process is as follows: After the user places an order, the system will automatically check the inventory. If the inventory is insufficient, it will check the warehouse with inventory and predict the arrival time of the inventory based on the weather conditions of the warehouse receiving the inventory combined with historical data, and then predict the picking and packaging time; When the inventory is sufficient, the picking and packing time is predicted directly. The specific formula is: T 处理 =α0+α1×Q 货物 +α2×p 位置 +α3×M 材料 +e; Among them, T 处理 is the comprehensive predicted processing time, including picking and packing time, α0 is the intercept term, α1 is the regression coefficient of the number of goods, Q 货物 is the number of goods picked and packed, α2 is the regression coefficient of storage location complexity, indicating the impact of storage location on processing time, p 位置 is the storage location complexity, which indicates the difficulty of the goods storage location; α3 is the regression coefficient of the packaging material complexity, which indicates the impact of packaging materials on processing time; M 材料 The complexity of the packaging material, e is the error term; The formula for the final prediction time is: T 总 = predicted transfer time + predicted picking and packing time; Finally, the forecast data is fed back to the query and report module so that users can receive logistics information in a timely manner.

5. According to claim 4, a smart logistics query system is characterized by: After the user places an order, the system will automatically query the inventory. When the inventory is insufficient, the system will query the warehouse with inventory and predict the arrival time of the inventory based on the weather conditions of the warehouse receiving the inventory combined with historical data. The picking and packaging time prediction process is as follows: Combine the weather data of the inventory warehouse with the historical cargo transfer data to establish a prediction model to predict the arrival time. The weather data of the inventory warehouse includes the weather conditions during transportation, the data of the inventory warehouse, and the data of the arrival warehouse. The prediction formula is as follows: 到货 =β0+β1×T 天气 +β2×H 历史 +e; Among them, β0 is the intercept term of the model, β1 is the regression coefficient of weather factors, β2 is the regression coefficient of historical data, e is the error term, T 天气 For weather factors, H 历史 is the average arrival time of similar orders in history, T 到货 is the predicted arrival time of the goods.

6. The intelligent logistics query system according to claim 1 is characterized by: The logistics time prediction module predicts the transportation time of goods based on the weather during transportation and historical transportation data as follows: The historical transportation data of logistics transportation includes the transportation time, transportation route, starting point and end point, transportation method, cargo type, weight, and volume of similar goods in the past. The historical data is preprocessed, including processing missing values, outliers, and duplicate data. The weather data includes historical weather records and weather conditions for transportation in the next few days. Data in different formats are uniformly converted into the format required by the model, and important features are extracted from the original data, including daily average temperature, rainfall, wind speed in weather characteristics, average transportation time and historical average delay in historical data characteristics, and then the gradient boosting tree is used as the prediction model. After the prediction model is selected, the selected model is first trained using the training data set, and then the prediction performance of the model is evaluated using the validation set.

7. The intelligent logistics query system according to claim 1 is characterized by: The cargo abnormality warning module processes the abnormal information of the cargo preparation time prediction module and the logistics time prediction module, determines the specific abnormality, and issues the warning information. The processing process is as follows: First, define the cargo abnormality standards, including cargo preparation time forecast abnormality and logistics time forecast abnormality, set the cargo transfer time abnormality standards, picking and packing time abnormality standards, and transportation time abnormality standards. If the cargo transfer time exceeds the expected time by 30%, it is considered as cargo transfer abnormality. If the picking and packing time exceeds the expected time by 20%, it is considered as picking and packing abnormality. If the logistics time exceeds the expected time by 30%, it is considered as transportation time abnormality. Based on the specific abnormal information detected, it will be transmitted to the query and report module for users to view.

8. A query method of the intelligent logistics query system according to any one of claims 1 to 7, the method comprising the following steps, characterized in that: S1. Obtain logistics-related data, including cargo status, cargo location, transportation status, weather during transportation, and historical data; S2. Process the acquired data, first check the inventory, and when the inventory is insufficient, first predict the time of transferring goods, and then predict the time of picking and packing. When the inventory is sufficient, directly predict the time of picking and packing; S3. Based on the predicted time for picking and packing, the logistics time is predicted. The logistics time prediction is also combined with transportation weather and historical data. S4. Provide abnormal warning based on the predicted cargo preparation time and logistics transportation time, and set abnormal standards to quickly judge abnormalities; S5. Users can check the specific time of goods transfer, picking and packing, and logistics, and can also receive abnormal information about goods.

Images