An intelligent logistics warehousing management method

Abstract

The present application discloses an intelligent logistics warehousing management method, which relates to the field of warehousing management technology, including: obtaining an original data set, performing shared information quantitative analysis on the original data set to obtain an information quantification index, and performing preliminary filtering on the original data set according to the information quantification index to obtain a calling data set; generating a basic database, identifying basic data and corresponding multi-level identification codes in the calling data set according to the basic database, marking the remaining data in the calling data set as identification data, and forming a shared data set with the multi-level identification code and the identification data; sharing data according to the shared data set to generate a warehousing management decision result; by adding multi-dimensional data features, achieving multi-dimensional dynamic adaptation to data changes, and improving the accuracy and practicality of data evaluation; achieving dynamic optimization and adaptive adjustment of the information quantification index, and improving the scientific nature and efficiency of warehousing management decisions.

Description

Technical Field

[0001] The present invention relates to the technical field of warehousing management, and in particular to an intelligent logistics warehousing management method. Background Art

[0002] Warehouse management is an important link in the logistics and transportation chain. In-depth research on logistics and warehouse management methods is of great significance for reducing transportation costs and improving transportation efficiency. At present, the analysis of warehouse management is mainly aimed at the warehouse optimization of a single node. By analyzing the warehousing needs of a single enterprise, and then establishing a central warehouse and distribution center, the enterprise's needs for warehouse management are met. However, with the continuous improvement of the supply chain, more and more enterprises are involved in the product production chain, and their businesses are integrated with each other. In the process of warehouse management, it is impossible to manage only one enterprise. It is necessary to share warehouse information to improve management efficiency and avoid the consequences of the warehouse information update cycle being too long, which leads to the warehouse being unable to meet the requirements. There are technical problems in the existing technology such as low accuracy of logistics and warehouse management data sharing analysis, which leads to chaotic warehouse management and inability to carry out normal logistics storage.

[0003] The Chinese invention patent application number 202310035890.9 provides a logistics warehousing management method and system based on information sharing, which obtains multiple information source modules for logistics warehousing management; performs data calls based on multiple information source modules to obtain multiple call data sets; inputs them into the information sharing platform; performs shared information quantitative analysis on the multiple call data sets based on the cloud server to obtain an information quantification index; obtains information identification instructions according to the information quantification index; inputs them into a matrix indicator model for identification to obtain multiple filtered data sets; connects the shared modules corresponding to the multiple filtered data sets for data sharing to generate warehousing management decision results.

[0004] However, in the above-mentioned invention patent technology, the information quantification index is calculated by relying on the call type quantification index and the call traffic quantification index, which makes it impossible to comprehensively evaluate the importance and complexity of the data and cannot reflect data changes in a timely manner. This is a technical problem that needs to be solved urgently. Summary of the Invention

[0005] This application solves the problem in the existing technology of being unable to timely and comprehensively evaluate the importance and complexity of data by providing an intelligent logistics warehousing management method, and achieves the technical effect of dynamically adapting to data changes in multiple dimensions and improving the accuracy and practicality of data evaluation.

[0006] This application provides an intelligent logistics warehousing management method, including:

[0007] S100: Acquire an original data set, perform a shared information quantitative analysis on the original data set to obtain an information quantification index, and perform a preliminary filtering on the original data set according to the information quantification index to obtain a call data set;

[0008] S200: Generate a basic database, identify the basic data and corresponding multi-level identification codes in the called data set based on the basic database, mark the remaining data in the called data set as identification data, and form a shared data set with the multi-level identification codes and identification data; share data based on the shared data set to generate a warehouse management decision result.

[0009] Furthermore, step S100 further includes:

[0010] S110: capturing each data item in the data stream in real time to form multiple sub-datasets, which are then fused to form an original data set, and using stream processing technology to perform shared information quantitative analysis on the original data set to form a processed original data set;

[0011] S120: extracting multi-dimensional data features from the processed original data set and analyzing them to obtain corresponding eigenvalues, performing weighted summation on the eigenvalues ​​to obtain an information quantization index;

[0012] S130: Pre-set a quantization index threshold, and mark data corresponding to information quantization indexes less than the quantization index threshold as callable data;

[0013] Filter the data corresponding to the information quantization index that is not less than the quantization index threshold, and recalculate the information quantization index of the filtered data. If it is less than the quantization index threshold, mark it as callable data; if it is not less than the quantization index threshold, discard it;

[0014] S130: Acquire all callable data to form a call data set.

[0015] Furthermore, the sub-datasets include: an original sub-dataset of order information, an original sub-dataset of capacity information, and an original sub-dataset of transportation monitoring; and the multi-dimensional data features include data real-time, data integrity, data importance, and data transmission.

[0016] Furthermore, in step S200, a basic database is generated, including: obtaining a historical shared data set, classifying the data in the historical shared data set into basic data and identification data; setting a unique multi-level identification code for each basic data, storing the basic data and the unique multi-level identification code in the database to form a basic database; wherein the correspondence between the basic data and the identification data is one-to-many.

[0017] Furthermore, the basic data includes first basic data and second basic data, the first basic data refers to basic data whose data update frequency is not greater than a preset first frequency threshold, and the second basic data is identification data that meets preset conditions; the multi-level identification code includes a header and a tail, the header corresponds to the first basic data, and the tail corresponds to the second basic data.

[0018] Furthermore, the preset conditions are set as: pre-setting a monitoring period, obtaining all identification data transmitted within the monitoring period, calculating the transmission frequency of different identification data, pre-setting a second frequency threshold, and marking the identification data corresponding to the transmission frequency greater than the second frequency threshold as second basic data.

[0019] Furthermore, the warehouse management decision result includes a current warehouse task decision result and a warehouse task prediction result for the next monitoring period, and the current warehouse task decision result is obtained based on the shared data set;

[0020] The second basic data within multiple monitoring cycles is obtained and marked as analysis data, the dynamic change factors in warehousing and logistics are identified, and a prediction model is constructed based on the analysis data and the analysis results of the dynamic change factors, thereby generating the warehousing task prediction results for the next monitoring cycle.

[0021] Furthermore, the dynamic factors in warehousing logistics are identified, including:

[0022] Use association rule mining technology to mine the analysis data and convert the analysis data into numerical data; use a layer-by-layer search method to generate frequent item sets, set the minimum support and minimum confidence, and build an association rule mining model;

[0023] Input numerical data into the association rule mining model to obtain frequent item sets and association rules, and then identify the dynamic change factors in warehousing logistics and the relationship between dynamic change factors;

[0024] The dynamic change factors include transport vehicle scheduling, cargo scheduling and transport date.

[0025] Furthermore, based on the analysis data and the analysis results of the dynamic change factors, a prediction model is constructed, including:

[0026] The analytical data is preprocessed to obtain processed analytical data, which is then divided into a training set and a validation set. The time series model is used as the basic model, and the training set is used to train the time series model to obtain an initial model. The initial model is validated and optimized based on the validation set to obtain a prediction model. The prediction model is used to predict the dynamic change factors in the next monitoring cycle, thereby obtaining the warehousing task prediction results for the next monitoring cycle.

[0027] Furthermore, the transport vehicle scheduling includes the vehicle's departure time, arrival time, driving route and cargo capacity, etc.; the cargo scheduling includes the cargo's warehousing time, outbound time, storage location, cargo type and cargo demand, etc.; the transport date refers to the arrival date agreed in advance by the logistics department.

[0028] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0029] By adding multi-dimensional data features, the technical effect of multi-dimensional dynamic adaptation to data changes and improving the accuracy and practicality of data evaluation is achieved; by calculating the information quantification index in multiple dimensions, the dynamic optimization and adaptive adjustment of the information quantification index are achieved, which improves the scientific nature and efficiency of warehouse management decisions; using stream processing technology, real-time collection, processing and analysis of data further improves the timeliness of warehouse management decisions. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1 This is a schematic diagram of the overall process of an intelligent logistics warehousing management method in an embodiment of the present invention. DETAILED DESCRIPTION

[0031] To facilitate understanding of the present invention, the present application will be described more comprehensively below with reference to the relevant drawings; the drawings show preferred embodiments of the present invention, but the present invention can be implemented in many different forms and is not limited to the embodiments described herein; on the contrary, the purpose of providing these embodiments is to enable a more thorough and comprehensive understanding of the disclosed content of the present invention.

[0032] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this invention pertains; the terms used herein in the specification of the present invention are for the purpose of describing specific embodiments only and are not intended to limit the present invention; the term "and / or" used herein includes any and all combinations of one or more of the associated listed items.

[0033] Example 1: Figure 1 As shown, an intelligent logistics warehousing management method includes:

[0034] S100: Acquire an original data set, perform a shared information quantitative analysis on the original data set to obtain an information quantification index, and perform a preliminary filtering on the original data set according to the information quantification index to obtain a call data set.

[0035] In some embodiments, to facilitate data sharing, an information sharing platform can be established to share warehouse management information in real time. By communicating with the cloud server, the shared information can be reliably stored in the cloud and analyzed. During the logistics and warehousing management process, within a first time period, the transportation resource utilization and transportation progress information corresponding to different warehousing orders can be extracted through the information sharing platform, with the shared information being sorted by type. This achieves the technical effect of providing basic analytical data for logistics and warehousing capacity management and storage capacity analysis.

[0036] Step S100 also includes: S110: capturing each data item in the data stream in real time to form multiple sub-datasets, which are then fused to form an original data set, and using stream processing technology to perform shared information quantitative analysis on the original data set to form a processed original data set.

[0037] In the prior art, data analysis requires a period of collection and batch analysis after a certain amount of data has accumulated. This results in a certain amount of data delay, which reduces the real-time performance and value. In this application, stream processing technology is used to achieve real-time data collection, processing, and analysis. Data is captured, processed, and analyzed the moment it is generated, without waiting for data accumulation. This greatly reduces the delay in data processing and improves the real-time performance and value of data. In stream processing technology, data streams are usually transmitted and processed through message queues or stream processing platforms, providing efficient data transmission mechanisms, powerful data processing capabilities, and flexible data processing models, enabling stream processing technology to cope with various complex data processing scenarios. Stream processing technology mainly processes real-time data, such as order information, transportation capacity information, and transportation monitoring data. By capturing each data item in the data stream in real time and processing and analyzing it, the processing methods may include data filtering, data conversion, data aggregation, etc., which are set according to actual needs. The result obtained by stream processing technology is a real-time updated information quantification index. The index reflects the real-time changes and trends of the data, providing more timely and accurate information support for warehouse management decisions.

[0038] In some embodiments, the sub-datasets include: an original sub-dataset of order information, an original sub-dataset of transportation capacity information, and an original sub-dataset of transportation monitoring. Specifically, to obtain the original data set, first, different information sources are obtained during the process of logistics and warehousing management, including: order information, transportation capacity information, and transportation monitoring information. The order information includes, but is not limited to, order type, order warehouse, order source, order payment status, etc. The transportation capacity information is resource information for logistics and warehousing companies to manage logistics, transportation, and storage, including, but not limited to, the number of personnel, the number of vehicles, and the number of vehicles available in real time. The transportation monitoring information is cargo transfer information obtained by monitoring the process of logistics and transportation. By collecting the above information in real time or setting a certain time period for collection, the original data set is the data set generated during the process of logistics and warehousing management and cargo flow, collected in real time or at a fixed time period, including the original sub-dataset of order information, the original sub-dataset of transportation capacity information, and the original sub-dataset of transportation monitoring.

[0039] Step S100 also includes: S120: extracting multi-dimensional data features from the processed original data set and analyzing to obtain corresponding eigenvalues, and performing weighted summation on the eigenvalues ​​to obtain an information quantification index.

[0040] In some embodiments, the multidimensional data features include data real-time, data integrity, data importance and data transmission; the data real-time reflects the update frequency and timeliness of the data; the data integrity measures the completeness and accuracy of the data; the data importance assessment includes the credibility and reliability of the data provider and the criticality of the data; the data transmission refers to the ease of data transmission. The larger the amount of data and the larger the data flow, the more difficult the transmission; when transmitting data, all features of the multidimensional data features should be considered comprehensively, rather than considering a single feature. When pre-setting weight values ​​for different data features, they should be set according to actual conditions or historical data experience. Generally, the weight value of data importance should be set to the maximum to ensure that important data can be shared first.

[0041] In some embodiments, there are two ways to obtain the information quantization index. The first way is to regard the original data set as a whole for calculation to obtain an information quantization index for subsequent processing. This is suitable for situations where the data volume is small and the data is easy to distinguish; the second way is to regard each sub-data set in the original data set as a whole, calculate the information quantization index separately, and perform subsequent processing. Compared with the first way, the complexity of the calculation is increased, but in the subsequent processing process, especially when data greater than the quantization index threshold appears, it is easy to find the corresponding data for reprocessing; in actual applications, dynamic adjustment is required based on the size of the overall data volume and actual conditions, and this application does not make specific restrictions here.

[0042] The step S100 further includes: S130: presetting a quantization index threshold, marking data corresponding to an information quantization index less than the quantization index threshold as callable data;

[0043] The data corresponding to the information quantization index not less than the quantization index threshold is filtered, and the information quantization index of the filtered data is recalculated. If it is less than the quantization index threshold, it is marked as callable data; if it is not less than the quantization index threshold, it is discarded.

[0044] In some embodiments, the quantitative index threshold is pre-set based on historical experimental data to measure the comprehensive characteristics of the data, ensuring the importance and transferability of the data. If the threshold is not less than the quantitative index threshold, it indicates that the amount of data corresponding to the information quantitative index is too large and needs to be filtered. Specifically, multiple filtering indicators are pre-set, including a data status indicator, a data value indicator, a data duplication indicator, and a data timeliness indicator. The matrix indicator model is generated based on the data status indicator, data value indicator, data duplication indicator, and data timeliness indicator. The matrix indicator model is a functional model for identifying and filtering data, and is constructed and generated using multiple indicators. The multiple filtering indicators are multiple dimensions for evaluating data during the data screening and elimination process, including a data status indicator, a data value indicator, a data duplication indicator, and a data timeliness indicator. The data status indicator indicates whether the data is currently being executed. If not, it can be temporarily not shared. If it is, it needs to be shared in real time. Thus, data is filtered based on sharing priority. The data value index analyzes the value of data to warehouse management, including its contribution to data warehousing. The data's usage value is assessed based on the data value index. The data duplication index evaluates the data's sharing history. If data has been shared before, it is no longer shared. If it has not been shared, it needs to be uploaded and shared promptly. The data timeliness index assesses the timeliness of data, including data validity. This assesses whether the data has exceeded its usage time limit. For example, yesterday's warehouse management plan data is no longer relevant to today's warehouse management, and today's warehouse management needs to be rescheduled based on today's order status and transportation resources. The matrix index model is a 2x2 matrix. Preferably, the data status index and data value index are located in the first row of the matrix, and the data duplication index and data timeliness index are located in the second row. Furthermore, data is identified and filtered based on the matrix index model. Data that does not meet the index is removed from the dataset, and the information quantification index of the filtered data is recalculated. If the information quantification index is less than the threshold, the data is marked as callable; if it is not less than the threshold, the data is discarded.

[0045] The technical solutions in the above embodiments of the present application have at least the following technical effects or advantages:

[0046] This application achieves the technical effect of multi-dimensional dynamic adaptation to data changes and improving the accuracy and practicality of data evaluation by adding multi-dimensional data features; through multi-dimensional calculation of information quantification index, dynamic optimization and adaptive adjustment of information quantification index are achieved, thereby improving the scientific nature and efficiency of warehouse management decisions; using stream processing technology, real-time collection, processing and analysis of data further improves the timeliness of warehouse management decisions.

[0047] Example 2: In Example 1, by using stream processing technology and adding multi-dimensional data features, the technical effect of multi-dimensional dynamic adaptation to data changes and improving the accuracy and practicality of data evaluation is achieved. However, it is still inevitable to transmit a large amount of data information during data transmission, which affects the data transmission efficiency. This example makes further improvements on the basis of the above example.

[0048] S200: Generate a basic database, identify the basic data and corresponding multi-level identification codes in the called data set based on the basic database, mark the remaining data in the called data set as identification data, and form a shared data set with the multi-level identification codes and identification data; share data based on the shared data set to generate a warehouse management decision result.

[0049] In step S200, a basic database is generated, including: obtaining a historical shared data set, classifying the data in the historical shared data set into basic data and identification data; setting a unique multi-level identification code for each basic data, storing the basic data and the unique multi-level identification code in the database to form a basic database, and the correspondence between the basic data and the identification data is one-to-many.

[0050] In some embodiments, basic data refers to data that can be used over time, i.e., data that can be used in a single sub-dataset or multiple sub-datasets. Identification data refers to data that cannot be used over time and needs to be updated each time. Different sub-datasets correspond to different basic data and identification data. For example, in the original sub-dataset of order information, basic data includes: order type description (e.g., "regular order," "expedited order"), order source category (e.g., "e-commerce platform," "offline store"), etc.; identification data includes: order number, specific order time, order payment status, etc. In the original sub-dataset of transportation information, basic data includes: vehicle type description (e.g., "truck," "refrigerated truck"), personnel position description (e.g., "driver," "loader"), etc.; identification data includes: real-time vehicle number, personnel current status (e.g., "on duty," "resting"), etc. In the original sub-dataset of transportation monitoring, basic data includes: transportation status description (e.g., "in transit," "arrived"), etc.; identification data includes: real-time location of goods, records of abnormal events during transportation, etc.

[0051] In some embodiments, the same basic database is stored in both the data receiving and data sharing administrators. A unique multi-level identification code is assigned to each piece of basic data in the basic database. When sharing data, the corresponding multi-level identification code is found in the basic database based on the acquired basic data. The multi-level identification code and identification data are then shared. The recipient searches for the corresponding basic data based on the multi-level identification code, thereby reducing the amount of data shared. Upon receiving the data, the recipient first parses the multi-level identification code, searches for the corresponding basic data in the basic database based on the multi-level identification code, and combines the basic data with the identification data to restore the complete shared data set.

[0052] In this embodiment, by transmitting only the identification code and identification data, the amount of data transmitted is greatly reduced and the data transmission efficiency is improved; the recipient can flexibly search and combine data according to the identification code, adapting to the data requirements in different scenarios; the update and maintenance mechanism of the basic database can easily cope with the emergence and changes of new data items, enhance scalability, and improve adaptability to complex environments.

[0053] By classifying the data in the historical shared data set into basic data and identification data, and setting a unique multi-level identification code for each basic data, only the multi-level identification code and identification data are transmitted, and the recipient searches for the corresponding basic data in the basic database according to the multi-level identification code.

[0054] This technical approach greatly reduces the amount of data that needs to be transmitted, because only the identification code and a small amount of identification data need to be transmitted, rather than the complete basic data.

[0055] The technical solutions in the above embodiments of the present application have at least the following technical effects or advantages:

[0056] This application greatly reduces the amount of data transmitted by only transmitting identification codes and identification data, thereby improving the efficiency of data transmission and sharing; flexibly searches and combines data according to identification codes, adapts to data needs in different scenarios, easily responds to the emergence and changes of new data items, enhances scalability, and achieves the effect of improving adaptability to complex environments.

[0057] Embodiment 3: This embodiment makes further improvements based on the above embodiment.

[0058] The basic data includes first basic data and second basic data, the first basic data refers to basic data whose data update frequency is not greater than a preset first frequency threshold, and the second basic data is identification data that meets a preset condition.

[0059] The preset conditions are set as: presetting a monitoring period, obtaining all identification data transmitted within the monitoring period, calculating the transmission frequency of different identification data, presetting a second frequency threshold, and marking the identification data corresponding to the transmission frequency greater than the second frequency threshold as second basic data.

[0060] The multi-level identification code includes a header and a tail, the header corresponds to the first basic data, and the tail corresponds to the second basic data.

[0061] In some embodiments, the data update frequency refers to the number of times a data item changes within a unit of time. For the first basic data, its update frequency is low and remains stable; the transmission frequency refers to the number of times a certain identification data is transmitted within a monitoring period, which is used to measure the activity of the identification data in data sharing. For each identification data, the total number of times it is transmitted within the monitoring period is counted, and the number of transmissions is divided by the length of the monitoring period (such as days or weeks) to obtain the transmission frequency.

[0062] In some embodiments, the first frequency threshold and the second frequency threshold are both pre-set according to actual conditions and historical data. For example, the setting of the first frequency threshold: according to the business characteristics of warehousing and logistics management, the historical update records of various basic data are analyzed. For data items that are stable for a long time or change very little, a lower first frequency threshold is set (such as no more than 1 update per month); for data items that occasionally need to be updated, a slightly higher first frequency threshold is set (such as no more than 1 update per quarter). Setting of the second frequency threshold: pre-set a monitoring period, such as one month or one quarter, collect the transmission records of all identification data within the monitoring period, analyze the transmission records, calculate the transmission frequency of each identification data, and set the second frequency threshold according to business needs and data analysis results. For example, for a customer ID, if a customer appears far more times than other customers during the monitoring period and has an important impact on the business, its transmission frequency can be set to the second frequency threshold. Specific adjustments need to be made according to actual conditions, and this application does not impose specific restrictions here.

[0063] In some embodiments, when calling a data set for identification judgment, it is first determined whether the first basic data exists. If so, continue to search to see whether the second basic data exists. If both exist, a multi-level identification code is generated, and the multi-level identification code and identification data are shared; the head of the multi-level identification code is used to uniquely identify the first basic data, and the tail is used to identify the category / attribute of the second basic data or specific identification data, so as to facilitate efficient transmission and accurate search when sharing data.

[0064] For example, for order information: the order type description, order source category, etc. are used as the first basic data, and the frequently appearing specific order number or customer ID (if exceeding the threshold) is promoted to the second basic data; for capacity information: the vehicle type description and personnel position description are used as the first basic data, and the commonly used vehicle number or personnel ID (if exceeding the threshold) is promoted to the second basic data; for transportation monitoring: the transportation status description is used as the first basic data, and the identification of the specific transportation route (if exceeding the threshold) is promoted to the second basic data.

[0065] Consider the following data items in logistics and warehousing management: Order information: Order type description (e.g., "regular order"), order source category (e.g., "e-commerce platform"), order number, customer ID, and order time. Transport capacity information: Vehicle type description (e.g., "truck"), personnel position description (e.g., "driver"), vehicle number, personnel ID, and personnel status.

[0066] The initial division is:

[0067] First basic data: order type description, order source category, vehicle type description, and personnel position description.

[0068] Identification data: order number, customer ID, specific order time, vehicle number, personnel ID, personnel current status.

[0069] After statistical analysis of subsequent identification data, it was found that orders of a certain customer ID (such as "Customer A") appeared frequently, exceeding the first threshold; it was found that a certain vehicle number (such as "Vehicle 123") appeared frequently in the transportation information, exceeding the first threshold.

[0070] "Customer A" is promoted to the second basic data (customer category); "Vehicle 123" is promoted to the second basic data (vehicle category).

[0071] The multi-level identification code for the order type description "normal order" ends with "01"; the multi-level identification code for the customer category "customer A" ends with "A01".

[0072] The multi-level identification code for the vehicle type description "truck" ends with "V01"; the multi-level identification code for the vehicle category "vehicle 123" ends with "V123".

[0073] The sender transmits: multi-level identification code "01A01" (normal order - customer A), specific order time, and other relevant identification data.

[0074] Recipient analysis: Search for the first basic data "Ordinary Order" based on "01" and search or confirm the second basic data "Customer A" based on "A01".

[0075] Combined restoration: Combine "normal order", "customer A" with the specific order time and other identification data to form complete order information.

[0076] The specific implementation process is as follows: Collect historical shared data sets and classify the data, initially dividing it into first basic data and identification data. Based on the data update frequency, determine the first basic data items and assign unique multi-level identification headers to them. Establish a basic database to store the first basic data and their corresponding multi-level identification headers. Set a monitoring period, such as one month. During this monitoring period, record the transmission of all identification data and calculate the transmission frequency of each identification data item using the same method as described in the above design. Set a second frequency threshold and mark identification data items with a transmission frequency exceeding this threshold as second basic data. Assign a multi-level identification code tail to the second basic data and combine it with the corresponding header to form a complete multi-level identification code.

[0077] When sharing data, the sender converts the basic data into a multi-level identification code based on the basic database, and only transmits the multi-level identification code and the remaining identification data. After receiving the data, the receiver first parses the multi-level identification code and searches the basic database for the corresponding first basic data based on the header. If the multi-level identification code contains a tail, it searches or confirms the second basic data based on the tail. The first basic data, the second basic data (if any), and the identification data are combined to restore the complete shared data set.

[0078] The basic database is dynamically updated and reviewed and adjusted regularly (e.g. quarterly) or as needed. The second basic data items and multi-level identification code system are updated based on the transmission frequency data within the new monitoring cycle to ensure the efficiency and accuracy of data sharing.

[0079] The technical solutions in the above embodiments of the present application have at least the following technical effects or advantages:

[0080] This application further reduces the amount of identification data by dividing the basic data into first basic data and second basic data, thereby achieving the effect of further improving the accuracy and efficiency of data sharing.

[0081] Embodiment 4: This embodiment makes further improvements based on the above embodiment.

[0082] In step S200, the warehouse management decision result includes the current warehouse task decision result and the warehouse task prediction result of the next monitoring cycle. The current warehouse task decision result is obtained based on the shared data set; the warehouse task prediction result of the next monitoring cycle is obtained, including: obtaining the second basic data within multiple monitoring cycles and marking it as analysis data, identifying the dynamic change factors in the warehouse logistics, and constructing a prediction model based on the analysis data and the analysis results of the dynamic change factors, thereby generating the warehouse task prediction result of the next monitoring cycle.

[0083] In some embodiments, the second basic data obtained within multiple monitoring cycles is marked as analysis data. The length of the obtained data needs to be set according to the actual situation. It can be 5 monitoring cycles, 10 monitoring cycles, etc. This application does not impose specific restrictions here. The second basic data is screened out from a large amount of identification data and represents those data items that appear frequently and have an important impact on the business. Therefore, using the second basic data as analysis data can greatly reduce the amount of data and improve the efficiency of data processing and analysis.

[0084] Since the second basic data includes those factors that have a significant impact on warehousing and logistics tasks and change frequently, using this data as analytical data for the prediction model can more accurately capture the dynamic changes in warehousing and logistics, thereby improving the accuracy of the prediction model.

[0085] The selection of the second base data is based on actual data transmission frequency and business needs, making it highly adaptable. As the business evolves and data changes, the second base data can be updated by adjusting the frequency threshold, ensuring that the prediction model always makes predictions based on the most relevant and important data.

[0086] As the business develops and data changes, the second basic data can be updated by adjusting the frequency threshold to ensure that the forecasting model always makes predictions based on the most relevant and important data, thereby continuously optimizing the warehouse management decision-making process.

[0087] In some embodiments, identifying dynamic change factors in warehousing and logistics includes: using association rule mining technology to perform data mining on analytical data and converting the analytical data into numerical data; generating frequent item sets using a layer-by-layer search method, setting minimum support and minimum confidence, and constructing an association rule mining model; inputting numerical data into the association rule mining model to obtain frequent item sets and association rules, and then identifying dynamic change factors in warehousing and logistics and the relationship between dynamic change factors; specifically, the dynamic change factors include but are not limited to: transport vehicle scheduling, cargo scheduling and transportation date.

[0088] The transport vehicle scheduling data includes the vehicle's departure time, arrival time, route and cargo capacity, etc. The cargo scheduling data includes the cargo's warehousing time, outbound time, storage location, cargo type and cargo demand, etc. The transportation date refers to the arrival date agreed in advance by the logistics department.

[0089] Specifically, the minimum support represents the minimum frequency at which an itemset appears in a dataset. Lower support yields more frequent itemsets, but may contain noisy data. The minimum confidence represents the credibility of an association rule. Higher confidence indicates a more reliable rule.

[0090] In some embodiments, building an association rule mining model requires selecting an association rule mining algorithm. Here, the Apriori algorithm is selected to generate frequent item sets by searching layer by layer. The initial minimum support is set to 0.2 and the minimum confidence is set to 0.7. Based on the initial parameters and the association rule mining algorithm, an association rule mining model is constructed, and the analysis data is input to obtain the corresponding frequent item sets and association rules. The model results are evaluated, and valuable association rules are screened out to identify the dynamic change factors in warehousing and logistics and the relationship between the dynamic change factors.

[0091] In some embodiments, a prediction model is constructed based on the analysis data and the analysis results of the dynamic change factors, including: preprocessing the analysis data to obtain processed analysis data, dividing the processed analysis data into a training set and a validation set, using a time series model as a base model, training the time series model using the training set to obtain an initial model, and validating and optimizing the initial model based on the validation set to obtain a prediction model; using the prediction model to predict the dynamic change factors within the next monitoring cycle, thereby obtaining a prediction result for the warehousing task for the next monitoring cycle. Based on the prediction results, the transportation vehicle scheduling and cargo scheduling plans are adjusted to address the possible impact of date restrictions.

[0092] For example, a logistics company needs to predict the number of transport vehicle dispatches within the next monitoring cycle (one month) to ensure appropriate vehicle and personnel arrangements. Secondary basic data from the past 12 monitoring cycles (one year) is collected to identify dynamic factors. Using transport vehicle dispatch data as an example, daily vehicle dispatch volumes are calculated. Data is preprocessed to remove outliers and missing values ​​and normalize. A forecasting model is used to analyze whether there is significant autocorrelation and seasonality. The analysis indicates that the number of transport vehicle dispatches within the next monitoring cycle will initially increase and then decrease, necessitating additional vehicles and personnel during peak periods. Based on the forecast results, a transport vehicle dispatch plan is developed to ensure sufficient vehicles and personnel during peak periods. The discrepancy between actual dispatch volumes and forecast volumes is monitored in real time, allowing timely adjustments to the plan to address unexpected situations. The model's forecasting performance is regularly evaluated, and it is iteratively optimized based on actual needs.

[0093] In some embodiments, a prediction model is constructed. Specifically, secondary basic data from multiple past monitoring periods (e.g., the past year, a total of 12 monitoring periods) is collected. This data should cover key information such as transport vehicle scheduling, cargo scheduling, and transportation dates. Outliers (e.g., unreasonable departure times, arrival times, cargo demand, etc.) and missing values ​​are removed. For missing values, interpolation, leading value filling, and trailing value filling methods can be used to convert non-numeric data (e.g., cargo type) into numeric data. For example, one-hot encoding can be used to convert cargo type into a binary vector, and numeric data can be normalized to bring the data to a consistent level for easier model training. Based on the association rule mining results, dynamically changing factors such as transport vehicle scheduling, cargo scheduling, and transportation dates are identified. The preprocessed analysis data is divided into a training set and a validation set. The training set is used to train the model, and the validation set is used to evaluate model performance. Based on the data characteristics and prediction requirements, an appropriate time series model, such as the ARIMA model, SARIMA model, or Holt-Winters model, is selected. The selected time series model is trained using the training set. During the training process, the model parameters need to be adjusted. The trained model is validated using the validation set to evaluate the model's prediction accuracy and generalization ability.

[0094] In some embodiments, a trained time series model is used to predict dynamic changing factors in the next monitoring period, such as the dispatch volume of transport vehicles, the dispatch volume of cargo, etc. Based on the prediction results, reasonable transport vehicle scheduling and cargo scheduling plans are formulated. For example, if the prediction results show that the dispatch volume of transport vehicles in the next monitoring period will show a trend of first increasing and then decreasing, then vehicles and personnel arrangements can be increased during peak periods to cope with possible transportation pressure. Monitor the difference between the actual dispatch volume and the predicted volume in real time, and adjust the plan in time to deal with emergencies. For example, if the actual dispatch volume suddenly increases, it may be necessary to temporarily deploy vehicles and personnel to meet transportation needs. Regularly evaluate the model prediction effect, and iteratively optimize the model according to actual needs. As new data is continuously added, the model can be retrained to improve prediction accuracy and generalization ability.

[0095] The technical solutions in the above embodiments of the present application have at least the following technical effects or advantages:

[0096] This application obtains the second basic data within multiple monitoring cycles, combines association rule mining and prediction models, and more accurately captures the dynamic changes in warehousing logistics, thereby improving the accuracy of predictions for warehousing tasks in the next monitoring cycle; by using the second basic data as the data source for predictive analysis, efficient data processing and accurate prediction are achieved, while improving the efficiency and accuracy of warehousing management decisions, and enhancing the adaptability and scalability of the prediction model.

[0097] The foregoing description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Various modifications and variations are readily apparent to those skilled in the art. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present invention shall be included within the scope of protection of the present invention.

Claims

1. An intelligent logistics warehousing management method, characterized in that: include: S100: Acquire an original data set, perform a shared information quantitative analysis on the original data set to obtain an information quantification index, and perform a preliminary filtering on the original data set according to the information quantification index to obtain a call data set; S200: Generate a basic database, identify basic data and corresponding multi-level identification codes in the call data set based on the basic database, mark the remaining data in the call data set as identification data, and form a shared data set with the multi-level identification codes and identification data; perform data sharing based on the shared data set to generate a warehouse management decision result; The method comprises obtaining a historical shared data set, classifying the data in the historical shared data set into basic data and identification data; setting a unique multi-level identification code for each basic data, storing the basic data and the unique multi-level identification code in a database, and forming a basic database; wherein the correspondence between the basic data and the identification data is one-to-many; The basic data includes first basic data and second basic data, the first basic data refers to basic data whose data update frequency is not greater than a preset first frequency threshold, and the second basic data is identification data that meets preset conditions; the multi-level identification code includes a header and a tail, the header corresponds to the first basic data, and the tail corresponds to the second basic data.

2. The intelligent logistics warehousing management method according to claim 1, characterized in that: Step S100 also includes: S110: capturing each data item in the data stream in real time to form multiple sub-datasets, which are then fused to form an original data set, and using stream processing technology to perform shared information quantitative analysis on the original data set to form a processed original data set; S120: extracting multi-dimensional data features from the processed original data set and analyzing them to obtain corresponding eigenvalues, performing weighted summation on the eigenvalues ​​to obtain an information quantization index; S130: Pre-set a quantization index threshold, and mark data corresponding to information quantization indexes less than the quantization index threshold as callable data; Filter the data corresponding to the information quantization index that is not less than the quantization index threshold, and recalculate the information quantization index of the filtered data. If it is less than the quantization index threshold, mark it as callable data; if it is not less than the quantization index threshold, discard it; S130: Acquire all callable data to form a call data set.

3. The intelligent logistics warehousing management method according to claim 2, characterized in that: The sub-datasets include: an original sub-dataset of order information, an original sub-dataset of transport capacity information, and an original sub-dataset of transport monitoring; and the multi-dimensional data features include data real-time, data integrity, data importance, and data transmission.

4. The intelligent logistics warehousing management method according to claim 1, characterized in that: The preset conditions are set as: presetting a monitoring period, obtaining all identification data transmitted within the monitoring period, calculating the transmission frequency of different identification data, presetting a second frequency threshold, and marking the identification data corresponding to the transmission frequency greater than the second frequency threshold as second basic data.

5. The intelligent logistics warehousing management method according to claim 1, characterized in that: The warehouse management decision result includes the current warehouse task decision result and the warehouse task prediction result of the next monitoring cycle, and the current warehouse task decision result is obtained based on the shared data set; The second basic data within multiple monitoring cycles is obtained and marked as analysis data, the dynamic change factors in warehousing and logistics are identified, and a prediction model is constructed based on the analysis data and the analysis results of the dynamic change factors, thereby generating the warehousing task prediction results for the next monitoring cycle.

6. The intelligent logistics warehousing management method according to claim 5, characterized in that: Identify dynamic factors in warehouse logistics, including: Use association rule mining technology to mine the analysis data and convert the analysis data into numerical data; use a layer-by-layer search method to generate frequent item sets, set the minimum support and minimum confidence, and build an association rule mining model; Input numerical data into the association rule mining model to obtain frequent item sets and association rules, and then identify the dynamic change factors in warehousing logistics and the relationship between dynamic change factors; The dynamic change factors include transport vehicle scheduling, cargo scheduling and transport date.

7. The intelligent logistics warehousing management method according to claim 5, characterized in that: Based on the analysis data and the analysis results of the dynamic change factors, a prediction model is constructed, including: The analytical data is preprocessed to obtain the processed analytical data, which is then divided into a training set and a validation set. The time series model is used as the basic model, and the training set is used to train the time series model to obtain an initial model. The initial model is validated and optimized based on the validation set to obtain a prediction model. The prediction model is used to predict the dynamic change factors in the next monitoring cycle, thereby obtaining the warehousing task prediction results for the next monitoring cycle.

8. The intelligent logistics warehousing management method according to claim 6, characterized in that: The transport vehicle scheduling includes the vehicle's departure time, arrival time, route and cargo capacity; the cargo scheduling includes the cargo's warehousing time, outbound time, storage location, cargo type and cargo demand; the transport date refers to the arrival date agreed in advance by the logistics department.

Images