Wood storage management system and method based on artificial intelligence

Abstract

The invention discloses a wood warehouse management system and method based on artificial intelligence, and relates to the field of wood warehouse management, and the system comprises an image collection module, a preliminary analysis module and a management control module. The method obtains the actual storage amount corresponding to each type of wood in the wood warehouse, provides an effective data basis for the subsequent wood warehouse management, indirectly improves the accuracy and effectiveness of the wood warehouse management, and improves the accuracy and effectiveness of the wood warehouse management through the historical transaction records in the wood warehouse. And periodic analysis is carried out and scientific analysis is carried out in combination with wood storage data in the wood warehouse, so that a wood transaction management control result corresponding to the wood warehouse is obtained, the storage efficiency and economic benefits of the wood warehouse are effectively improved, and the development of the wood storage industry is promoted.

Description

Technical Field

[0001] The present application relates to the field of timber storage management, and in particular to a timber storage management system based on artificial intelligence. Background Art

[0002] As market demand changes and inventory is dynamically updated, intelligent warehousing systems can monitor warehouse storage conditions in real time and automatically adjust storage strategies based on actual needs to ensure efficient space utilization. Intelligent warehouse management systems can collect and store large amounts of timber storage data, including inbound and outbound records, inventory levels, and environmental parameters. Through in-depth analysis and mining of this data, companies can understand timber sales trends, inventory turnover rates, customer demand, and other information, providing a scientific basis for their production, sales, and procurement decisions. However, existing technologies still have the following shortcomings: Existing technologies lack scientific inventory planning and management methods for timber storage management, resulting in frequent timber inventory backlogs or shortages. Inventory backlogs will occupy a large amount of capital and storage space, increasing the company's operating costs. These problems have seriously affected the turnover efficiency and economic benefits of timber storage management, and restricted the development of the timber storage industry. Summary of the Invention

[0003] The purpose of the present invention is to provide a timber storage management system and method based on artificial intelligence to solve the problems raised in the above background technology.

[0004] To achieve the above objectives, the present invention provides the following technical solutions: a timber storage management system based on artificial intelligence, comprising: Image acquisition module: used to collect data on the storage status of the target timber warehouse and obtain the storage image set corresponding to the target timber warehouse; Preliminary analysis module: used to analyze the storage image set corresponding to the target timber warehouse and obtain the storage data corresponding to the target timber warehouse; Management control module: used to obtain the historical timber transaction data corresponding to the target timber warehouse and the storage management data corresponding to various types of timber, and conduct system analysis in combination with the storage data corresponding to the target timber warehouse to obtain the timber transaction management control results corresponding to the target timber warehouse.

[0005] In the preferred embodiment of this solution, the specific implementation of the image acquisition module is as follows: Establishing a data storage relationship between the image acquisition module and the database, and extracting the storage block heap model corresponding to the combination of each storage block heap size and storage mode stored in the database; By collecting images of the target timber warehouse using each image collection device preset in the target timber warehouse, a monitoring image corresponding to each image collection device is obtained, and a comprehensive image set corresponding to the target timber warehouse is established based on the monitoring images corresponding to each image collection device; Obtain data collection points and record them as data collection points; Obtain the relative position coordinates, relative image acquisition viewing angle, and device number of each image acquisition device corresponding to the target timber warehouse; A three-dimensional stereo model corresponding to the target timber warehouse is established using the omnidirectional image set corresponding to the target timber warehouse. The three-dimensional stereo model corresponding to the target timber warehouse is matched with the storage block stack models corresponding to the size and storage method combinations of each storage block stack to obtain the storage block stacks corresponding to the target timber warehouse and the relative position coordinates of each storage block stack. The relative position coordinates corresponding to each storage block stack are matched with the relative position coordinates and relative image acquisition viewing angles corresponding to each image acquisition device to obtain the image acquisition devices corresponding to each storage block stack. The monitoring images corresponding to each image acquisition device are screened and obtained, and the monitoring images of each image acquisition device corresponding to each storage block stack are recorded as the storage image set corresponding to the target timber warehouse. In the preferred embodiment of this solution, the specific implementation of the preliminary analysis module is as follows: Establish a data extraction relationship between the preliminary analysis module and the database to extract the color data, texture data and annual ring feature data corresponding to various types of wood stored in the database; performing information extraction on monitoring images of each image acquisition device corresponding to each storage block stack to obtain color data, texture data, and growth ring feature data of the monitoring images of each image acquisition device corresponding to each storage block stack, wherein the color data, texture data, and growth ring feature data of the monitoring images refer to the color data, texture data, and growth ring feature data of the wood in the storage block stack corresponding to the monitoring image, wherein the color data includes hue and hue saturation, the texture data includes texture direction, texture thickness, and texture pattern, and the growth ring features include growth ring clarity, growth ring width, and growth ring shape; Matching the color data, texture data, and growth ring feature data corresponding to each type of wood with the color data, texture data, and growth ring feature data of each image acquisition device to obtain the wood type corresponding to each image acquisition device; performing statistical calculations on the wood types corresponding to each image acquisition device in each storage block pile to obtain the percentage of each type of wood corresponding to each storage block pile; screening the wood type with the highest percentage corresponding to each storage block pile; recording the wood type with the highest percentage as the wood type corresponding to each storage block pile; and statistically obtaining the wood type corresponding to each storage block pile in the target wood warehouse; Extracting the wood storage density corresponding to each storage method stored in the database; Obtaining a storage block pile model and a storage method corresponding to each storage block pile in the target wood warehouse, and obtaining a wood storage density corresponding to each storage block pile in the target wood warehouse through screening using the storage method corresponding to each storage block pile in the target wood warehouse; Obtaining a model scaling ratio of the three-dimensional model corresponding to the target timber warehouse, performing model recognition on the storage block pile models corresponding to each storage block pile based on the model scaling ratio of the three-dimensional model corresponding to the target timber warehouse, and obtaining the storage block pile model volume corresponding to each storage block pile; Data calculation is performed based on the wood storage density and the model volume of the storage block pile corresponding to each storage block pile in the target wood warehouse to obtain the wood storage volume corresponding to each storage block pile in the target wood warehouse; statistics are performed based on the wood types corresponding to each storage block pile to obtain the wood storage volume corresponding to each wood type in the target wood warehouse; and the wood storage volume corresponding to each wood type in the target wood warehouse is recorded as the storage data corresponding to the target wood warehouse; The percentage of each type of wood corresponding to each storage block stack refers to the percentage of each type of wood corresponding to each storage block stack in the total number of image acquisition devices obtained by counting and analyzing the types of wood corresponding to each storage block stack; The wood storage density refers to the storage capacity of wood per unit volume.

[0006] In the preferred embodiment of this solution, the specific implementation of the management control module is as follows: Obtaining historical timber transaction data and timber management data corresponding to the target timber warehouse, wherein the historical timber transaction data includes the timber type, transaction price, transaction quantity, and transaction time corresponding to each timber transaction; performing data statistics on the historical timber transaction data corresponding to the target timber warehouse to obtain the transaction quantity, transaction price, and transaction time corresponding to each timber type; and obtaining the average transaction price and storage duration corresponding to each timber type in the target timber warehouse; The timber management data corresponding to the target timber warehouse includes a timber storage loss rate variation curve corresponding to various types of timber and storage time; According to the transaction quantity, transaction price and transaction time point of each timber transaction of the same type of timber, a transaction learning model corresponding to each type of timber is established, wherein the transaction learning model includes a transaction quantity change curve and a transaction price change curve. The transaction quantity change curve and the transaction price change curve contain each rising sub-curve and each falling sub-curve. The initial time point and the end time point corresponding to each rising sub-curve and each falling sub-curve are obtained. The curve periodicity analysis is performed based on the initial time point and the end time point corresponding to each rising sub-curve and each falling sub-curve to obtain the curve change period of the transaction quantity and transaction price corresponding to each type of timber. By comparing the data collection point with various Perform periodic matching on the curve change cycles of transaction quantities and transaction prices corresponding to different types of wood, obtain the relative position of the data collection point in the curve change cycle and the change curve of the remaining cycle, record the change curve of the remaining cycle as the remaining change curve, screen and obtain the remaining change curves corresponding to the transaction prices and transaction quantities of various types of wood, perform data analysis on the average transaction price corresponding to each type of wood in the target wood warehouse and the remaining change curve corresponding to the transaction price, obtain the transaction price change curves of each segment above the average transaction price in the remaining change curve corresponding to the transaction price, and screen and obtain the transaction price change curves of each segment corresponding to each type of wood; Based on the transaction change curves for each segment corresponding to each type of wood, the timber storage loss rate change curves for each type of wood and storage time, and the average transaction price and storage time corresponding to each type of wood, a data model was established and data analysis was performed to obtain the transaction index at each time point in the transaction change curves for each segment, which was recorded as the transaction index for each type of wood at each time point; Compare the transaction index of each type of wood at each time point with a preset transaction index threshold, select the time points with a transaction index greater than the transaction index threshold, record the time points with a transaction index greater than the transaction index threshold as recommended transaction time points, and arrange the recommended transaction time points in order of size to obtain a transaction recommendation queue corresponding to each type of wood; According to the residual change curves corresponding to the recommended transaction time points and the transaction quantities of various types of wood in the transaction recommendation queue corresponding to various types of wood, the transaction quantities corresponding to the recommended transaction time points of various types of wood are obtained; The timber storage volume corresponding to each timber type in the target timber warehouse is traded and allocated according to the arrangement order of the recommended transaction time points in the transaction recommendation queues corresponding to the various timber types, and the timber transaction data of each allocated recommended transaction time point and each allocated recommended transaction time point in the transaction recommendation queues corresponding to the various timber types are obtained. The timber transaction management and control results of each allocated recommended transaction time point and each allocated recommended transaction time point in the transaction recommendation queues corresponding to the various timber types are recorded as the timber transaction management and control results corresponding to the target timber warehouse.

[0007] To achieve the above objectives, the present invention further provides the following technical solution: a timber storage management method based on artificial intelligence, comprising the following steps: Collect data on the storage status of the target timber warehouse and obtain a storage image set corresponding to the target timber warehouse; Analyze the stored image set corresponding to the target wood warehouse to obtain the storage data corresponding to the target wood warehouse; The historical timber transaction data corresponding to the target timber warehouse and the storage management data corresponding to various types of timber are obtained, and the storage data corresponding to the target timber warehouse are combined for system analysis to obtain the timber transaction management control results corresponding to the target timber warehouse.

[0008] Compared with the prior art, the present invention has the following beneficial effects: The present invention obtains the actual storage quantity of various types of wood in the wood warehouse by scientifically detecting and analyzing the wood storage status in the wood warehouse, providing an effective data basis for subsequent wood storage management, and indirectly improving the accuracy and effectiveness of wood storage management; The present invention obtains the timber transaction management and control results corresponding to the timber warehouse by periodically analyzing the historical transaction records in the timber warehouse and combining them with the timber storage data in the timber warehouse for scientific analysis, thereby effectively improving the storage efficiency and economic benefits of the timber warehouse and promoting the development of the timber storage industry. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] The present invention is further described with reference to the accompanying drawings. However, the embodiments in the accompanying drawings do not constitute any limitation to the present invention. A person skilled in the art can obtain other drawings based on the following drawings without creative effort.

[0010] Figure 1 This is a schematic diagram of module connections according to an embodiment of the present invention.

[0011] Figure 2 This is a schematic diagram of the connection steps of an embodiment of the present invention. DETAILED DESCRIPTION

[0012] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0013] See also Figure 1 ,The present invention provides a timber storage management system based on artificial intelligence, which includes an image acquisition module, a preliminary analysis module and a management control module; The image acquisition module is connected to the preliminary analysis module, and the preliminary analysis module is connected to the management and control module; The image acquisition module is used to collect data on the storage status of the target timber warehouse and obtain a storage image set corresponding to the target timber warehouse; Furthermore, the specific execution mode of the image acquisition module is as follows: Establishing a data storage relationship between the image acquisition module and the database, and extracting the storage block heap model corresponding to the combination of each storage block heap size and storage mode stored in the database; By collecting images of the target timber warehouse using each image collection device preset in the target timber warehouse, a monitoring image corresponding to each image collection device is obtained, and a comprehensive image set corresponding to the target timber warehouse is established based on the monitoring images corresponding to each image collection device; Obtain data collection points and record them as data collection points; Obtain the relative position coordinates, relative image acquisition viewing angle, and device number of each image acquisition device corresponding to the target timber warehouse; A three-dimensional stereo model corresponding to the target timber warehouse is established using the omnidirectional image set corresponding to the target timber warehouse. The three-dimensional stereo model corresponding to the target timber warehouse is matched with the storage block stack models corresponding to the size and storage method combinations of each storage block stack to obtain the storage block stacks corresponding to the target timber warehouse and the relative position coordinates of each storage block stack. The relative position coordinates corresponding to each storage block stack are matched with the relative position coordinates and relative image acquisition viewing angles corresponding to each image acquisition device to obtain the image acquisition devices corresponding to each storage block stack. The monitoring images corresponding to each image acquisition device are screened and obtained, and the monitoring images of each image acquisition device corresponding to each storage block stack are recorded as the storage image set corresponding to the target timber warehouse. The preliminary analysis module is used to analyze the storage image set corresponding to the target timber warehouse to obtain the storage data corresponding to the target timber warehouse; Furthermore, the specific execution method of the preliminary analysis module is as follows: Establish a data extraction relationship between the preliminary analysis module and the database to extract the color data, texture data and annual ring feature data corresponding to various types of wood stored in the database; performing information extraction on monitoring images of each image acquisition device corresponding to each storage block stack to obtain color data, texture data, and growth ring feature data of the monitoring images of each image acquisition device corresponding to each storage block stack, wherein the color data, texture data, and growth ring feature data of the monitoring images refer to the color data, texture data, and growth ring feature data of the wood in the storage block stack corresponding to the monitoring image, wherein the color data includes hue and hue saturation, the texture data includes texture direction, texture thickness, and texture pattern, and the growth ring features include growth ring clarity, growth ring width, and growth ring shape; Matching the color data, texture data, and growth ring feature data corresponding to each type of wood with the color data, texture data, and growth ring feature data of each image acquisition device to obtain the wood type corresponding to each image acquisition device; performing statistical calculations on the wood types corresponding to each image acquisition device in each storage block pile to obtain the percentage of each type of wood corresponding to each storage block pile; screening the wood type with the highest percentage corresponding to each storage block pile; recording the wood type with the highest percentage as the wood type corresponding to each storage block pile; and statistically obtaining the wood type corresponding to each storage block pile in the target wood warehouse; Extracting the wood storage density corresponding to each storage method stored in the database; Obtaining a storage block pile model and a storage method corresponding to each storage block pile in the target wood warehouse, and obtaining a wood storage density corresponding to each storage block pile in the target wood warehouse through screening using the storage method corresponding to each storage block pile in the target wood warehouse; Obtaining a model scaling ratio of the three-dimensional model corresponding to the target timber warehouse, performing model recognition on the storage block pile models corresponding to each storage block pile based on the model scaling ratio of the three-dimensional model corresponding to the target timber warehouse, and obtaining the storage block pile model volume corresponding to each storage block pile; Data calculation is performed based on the wood storage density and the model volume of the storage block pile corresponding to each storage block pile in the target wood warehouse to obtain the wood storage volume corresponding to each storage block pile in the target wood warehouse; statistics are performed based on the wood types corresponding to each storage block pile to obtain the wood storage volume corresponding to each wood type in the target wood warehouse; and the wood storage volume corresponding to each wood type in the target wood warehouse is recorded as the storage data corresponding to the target wood warehouse; The percentage of each type of wood corresponding to each storage block stack refers to the percentage of each type of wood corresponding to each storage block stack in the total number of image acquisition devices obtained by counting and analyzing the types of wood corresponding to each storage block stack; The wood storage density refers to the storage capacity of wood per unit volume.

[0014] Management control module: used to obtain the historical timber transaction data corresponding to the target timber warehouse and the storage management data corresponding to various types of timber, and conduct system analysis in combination with the storage data corresponding to the target timber warehouse to obtain the timber transaction management control results corresponding to the target timber warehouse.

[0015] Furthermore, the specific execution mode of the management control module is as follows: Obtaining historical timber transaction data and timber management data corresponding to the target timber warehouse, wherein the historical timber transaction data includes the timber type, transaction price, transaction quantity, and transaction time corresponding to each timber transaction; performing data statistics on the historical timber transaction data corresponding to the target timber warehouse to obtain the transaction quantity, transaction price, and transaction time corresponding to each timber type; and obtaining the average transaction price and storage duration corresponding to each timber type in the target timber warehouse; The timber management data corresponding to the target timber warehouse includes a timber storage loss rate variation curve corresponding to various types of timber and storage time; According to the transaction quantity, transaction price and transaction time point of each timber transaction of the same type of timber, a transaction learning model corresponding to each type of timber is established, wherein the transaction learning model includes a transaction quantity change curve and a transaction price change curve. The transaction quantity change curve and the transaction price change curve contain each rising sub-curve and each falling sub-curve. The initial time point and the end time point corresponding to each rising sub-curve and each falling sub-curve are obtained. The curve periodicity analysis is performed based on the initial time point and the end time point corresponding to each rising sub-curve and each falling sub-curve to obtain the curve change period of the transaction quantity and transaction price corresponding to each type of timber. By comparing the data collection point with various Perform periodic matching on the curve change cycles of transaction quantities and transaction prices corresponding to different types of wood, obtain the relative position of the data collection point in the curve change cycle and the change curve of the remaining cycle, record the change curve of the remaining cycle as the remaining change curve, screen and obtain the remaining change curves corresponding to the transaction prices and transaction quantities of various types of wood, perform data analysis on the average transaction price corresponding to each type of wood in the target wood warehouse and the remaining change curve corresponding to the transaction price, obtain the transaction price change curves of each segment above the average transaction price in the remaining change curve corresponding to the transaction price, and screen and obtain the transaction price change curves of each segment corresponding to each type of wood; Based on the transaction change curves for each segment corresponding to each type of wood, the timber storage loss rate change curves for each type of wood and storage time, and the average transaction price and storage time corresponding to each type of wood, a data model was established and data analysis was performed to obtain the transaction index at each time point in the transaction change curves for each segment, which was recorded as the transaction index for each type of wood at each time point; The data model is calculated by the formula: , calculate the trading index of various types of wood at each time point ,in Indicates the number of various types of wood, It is represented by the number of each time point in the sub-transaction change curve corresponding to each type of wood. 、 It is represented by the average transaction price and timber storage volume corresponding to each timber type in the target timber warehouse. It is represented by the transaction price at each time point in the sub-transaction change curve of each type of wood. It is expressed as the timber storage loss rate corresponding to each time point in the sub-transaction change curve of each type of timber; The actual storage time of each time point in the sub-transaction change curve corresponding to each wood type is obtained by adding the storage time corresponding to each wood type and the interval between each time point and the data collection point in the sub-transaction change curve. The wood storage loss rate of each time point in the sub-transaction change curve corresponding to each wood type is obtained by filtering the actual storage time of each time point in the sub-transaction change curve corresponding to each wood type. ; Compare the transaction index of each type of wood at each time point with a preset transaction index threshold, select the time points with a transaction index greater than the transaction index threshold, record the time points with a transaction index greater than the transaction index threshold as recommended transaction time points, and arrange the recommended transaction time points in order of size to obtain a transaction recommendation queue corresponding to each type of wood; According to the residual change curves corresponding to the recommended transaction time points and the transaction quantities of various types of wood in the transaction recommendation queue corresponding to various types of wood, the transaction quantities corresponding to the recommended transaction time points of various types of wood are obtained; The timber storage volume corresponding to each timber type in the target timber warehouse is traded and allocated according to the arrangement order of the recommended transaction time points in the transaction recommendation queues corresponding to the various timber types, and the timber transaction data of each allocated recommended transaction time point and each allocated recommended transaction time point in the transaction recommendation queues corresponding to the various timber types are obtained. The timber transaction management and control results of each allocated recommended transaction time point and each allocated recommended transaction time point in the transaction recommendation queues corresponding to the various timber types are recorded as the timber transaction management and control results corresponding to the target timber warehouse.

[0016] See also Figure 2 To achieve the above objectives, the present invention also provides the following technical solution: a timber storage management method based on artificial intelligence, comprising the following steps: Collect data on the storage status of the target timber warehouse and obtain a storage image set corresponding to the target timber warehouse; Analyze the stored image set corresponding to the target wood warehouse to obtain the storage data corresponding to the target wood warehouse; The historical timber transaction data corresponding to the target timber warehouse and the storage management data corresponding to various types of timber are obtained, and the storage data corresponding to the target timber warehouse are combined for system analysis to obtain the timber transaction management control results corresponding to the target timber warehouse.

[0017] The above are all preferred embodiments of the present application, and are not intended to limit the scope of protection of the present application. Therefore, any equivalent changes made based on the structure, shape, and principle of the present application should be included in the scope of protection of the present application.

Claims

1. A timber storage management system based on artificial intelligence, characterized by: include: Image acquisition module: used to collect data on the storage status of the target timber warehouse and obtain the storage image set corresponding to the target timber warehouse; Preliminary analysis module: used to analyze the stored image set corresponding to the target timber warehouse and obtain the storage data corresponding to the target timber warehouse; Management control module: used to obtain the historical timber transaction data corresponding to the target timber warehouse and the storage management data corresponding to various types of timber, and conduct system analysis in combination with the storage data corresponding to the target timber warehouse to obtain the timber transaction management control results corresponding to the target timber warehouse.

2. The artificial intelligence-based timber storage management system according to claim 1, characterized in that: The specific implementation of the image acquisition module is as follows: Establishing a data storage relationship between the image acquisition module and the database, and extracting the storage block heap model corresponding to the combination of each storage block heap size and storage mode stored in the database; By collecting images of the target timber warehouse using each image collection device preset in the target timber warehouse, a monitoring image corresponding to each image collection device is obtained, and a comprehensive image set corresponding to the target timber warehouse is established based on the monitoring images corresponding to each image collection device; Obtain data collection points and record them as data collection points; Obtain the relative position coordinates, relative image acquisition viewing angle, and device number of each image acquisition device corresponding to the target timber warehouse; A three-dimensional stereo model corresponding to the target timber warehouse is established using the omnidirectional image set corresponding to the target timber warehouse. The three-dimensional stereo model corresponding to the target timber warehouse is matched with the storage block stack models corresponding to the size and storage method combinations of each storage block stack to obtain the storage block stacks corresponding to the target timber warehouse and the relative position coordinates of each storage block stack. The relative position coordinates corresponding to each storage block stack are matched with the relative position coordinates and relative image acquisition viewing angles corresponding to each image acquisition device to obtain the image acquisition devices corresponding to each storage block stack. The monitoring images corresponding to each image acquisition device are screened and obtained, and the monitoring images of each image acquisition device corresponding to each storage block stack are recorded as the storage image set corresponding to the target timber warehouse.

3. The artificial intelligence-based timber storage management system according to claim 2, characterized in that: The specific execution method of the preliminary analysis module is as follows: Establish a data extraction relationship between the preliminary analysis module and the database to extract the color data, texture data and annual ring feature data corresponding to various types of wood stored in the database; performing information extraction on monitoring images of each image acquisition device corresponding to each storage block stack to obtain color data, texture data, and growth ring feature data of the monitoring images of each image acquisition device corresponding to each storage block stack, wherein the color data, texture data, and growth ring feature data of the monitoring images refer to the color data, texture data, and growth ring feature data of the wood in the storage block stack corresponding to the monitoring image, wherein the color data includes hue and hue saturation, the texture data includes texture direction, texture thickness, and texture pattern, and the growth ring features include growth ring clarity, growth ring width, and growth ring shape; Matching the color data, texture data, and growth ring feature data corresponding to each type of wood with the color data, texture data, and growth ring feature data of each image acquisition device to obtain the wood type corresponding to each image acquisition device; performing statistical calculations on the wood types corresponding to each image acquisition device in each storage block pile to obtain the percentage of each type of wood corresponding to each storage block pile; screening the wood type with the highest percentage corresponding to each storage block pile; recording the wood type with the highest percentage as the wood type corresponding to each storage block pile; and statistically obtaining the wood type corresponding to each storage block pile in the target wood warehouse; Extracting the wood storage density corresponding to each storage method stored in the database; Obtaining a storage block pile model and a storage method corresponding to each storage block pile in the target wood warehouse, and obtaining a wood storage density corresponding to each storage block pile in the target wood warehouse through screening using the storage method corresponding to each storage block pile in the target wood warehouse; Obtaining a model scaling ratio of the three-dimensional model corresponding to the target timber warehouse, performing model recognition on the storage block pile models corresponding to each storage block pile based on the model scaling ratio of the three-dimensional model corresponding to the target timber warehouse, and obtaining the storage block pile model volume corresponding to each storage block pile; Data calculation is performed based on the wood storage density and the model volume of the storage block pile corresponding to each storage block pile in the target wood warehouse to obtain the wood storage volume corresponding to each storage block pile in the target wood warehouse; statistics are performed based on the wood types corresponding to each storage block pile to obtain the wood storage volume corresponding to each wood type in the target wood warehouse; and the wood storage volume corresponding to each wood type in the target wood warehouse is recorded as the storage data corresponding to the target wood warehouse; The percentage of each type of wood corresponding to each storage block stack refers to the percentage of each type of wood corresponding to each storage block stack in the total number of image acquisition devices obtained by counting and analyzing the types of wood corresponding to each storage block stack; The wood storage density refers to the storage capacity of wood per unit volume.

4. The artificial intelligence-based timber storage management system according to claim 3, characterized in that: The specific implementation of the management control module is as follows: Obtaining historical timber transaction data and timber management data corresponding to the target timber warehouse, wherein the historical timber transaction data includes the timber type, transaction price, transaction quantity, and transaction time corresponding to each timber transaction; performing data statistics on the historical timber transaction data corresponding to the target timber warehouse to obtain the transaction quantity, transaction price, and transaction time corresponding to each timber type; and obtaining the average transaction price and storage duration corresponding to each timber type in the target timber warehouse; The timber management data corresponding to the target timber warehouse includes a timber storage loss rate variation curve corresponding to various types of timber and storage time; According to the transaction quantity, transaction price and transaction time point of each timber transaction of the same type of timber, a transaction learning model corresponding to each type of timber is established, wherein the transaction learning model includes a transaction quantity change curve and a transaction price change curve. The transaction quantity change curve and the transaction price change curve contain each rising sub-curve and each falling sub-curve. The initial time point and the end time point corresponding to each rising sub-curve and each falling sub-curve are obtained. The curve periodicity analysis is performed based on the initial time point and the end time point corresponding to each rising sub-curve and each falling sub-curve to obtain the curve change period of the transaction quantity and transaction price corresponding to each type of timber. By comparing the data collection point with various Perform periodic matching on the curve change cycles of transaction quantities and transaction prices corresponding to different types of wood, obtain the relative position of the data collection point in the curve change cycle and the change curve of the remaining cycle, record the change curve of the remaining cycle as the remaining change curve, screen and obtain the remaining change curves corresponding to the transaction prices and transaction quantities of various types of wood, perform data analysis on the average transaction price corresponding to each type of wood in the target wood warehouse and the remaining change curve corresponding to the transaction price, obtain the transaction price change curves of each segment above the average transaction price in the remaining change curve corresponding to the transaction price, and screen and obtain the transaction price change curves of each segment corresponding to each type of wood; Based on the transaction change curves for each segment corresponding to each type of wood, the timber storage loss rate change curves for each type of wood and storage time, and the average transaction price and storage time corresponding to each type of wood, a data model was established and data analysis was performed to obtain the transaction index at each time point in the transaction change curves for each segment, which was recorded as the transaction index for each type of wood at each time point; Compare the transaction index of each type of wood at each time point with a preset transaction index threshold, select the time points with a transaction index greater than the transaction index threshold, record the time points with a transaction index greater than the transaction index threshold as recommended transaction time points, and arrange the recommended transaction time points in order of size to obtain a transaction recommendation queue corresponding to each type of wood; According to the residual change curves corresponding to the recommended transaction time points and the transaction quantities of various types of wood in the transaction recommendation queue corresponding to various types of wood, the transaction quantities corresponding to the recommended transaction time points of various types of wood are obtained; The timber storage volume corresponding to each timber type in the target timber warehouse is traded and allocated according to the arrangement order of the recommended transaction time points in the transaction recommendation queues corresponding to the various timber types, and the timber transaction data of each allocated recommended transaction time point and each allocated recommended transaction time point in the transaction recommendation queues corresponding to the various timber types are obtained. The timber transaction management and control results of each allocated recommended transaction time point and each allocated recommended transaction time point in the transaction recommendation queues corresponding to the various timber types are recorded as the timber transaction management and control results corresponding to the target timber warehouse.

5. An artificial intelligence-based timber storage management method, applied to the artificial intelligence-based timber storage management system according to any one of claims 1 to 4, characterized in that: include: Collect data on the storage status of the target timber warehouse and obtain a storage image set corresponding to the target timber warehouse; Analyze the stored image set corresponding to the target wood warehouse to obtain the storage data corresponding to the target wood warehouse; The historical timber transaction data corresponding to the target timber warehouse and the storage management data corresponding to various types of timber are obtained, and the storage data corresponding to the target timber warehouse are combined for system analysis to obtain the timber transaction management control results corresponding to the target timber warehouse.

Images