Small warehouse cargo management method and system based on artificial intelligence

Abstract

The present invention relates to the field of warehouse goods management, and in particular to a small-scale warehouse goods management method and system based on artificial intelligence, including collecting data information of goods and storage space according to sensors and performing data preprocessing, establishing a neural network model for detecting abnormal inventory of goods, and obtaining abnormal results of the abnormal inventory of goods; setting an inventory risk coefficient according to the output result of the neural network model for detecting abnormal inventory of goods, and judging whether to enter a first-level early warning mode; calculating safe storage supervision parameters according to the inventory turnover rate and the inventory risk coefficient, and judging whether to start a second-level early warning mode; if the second-level early warning mode is not started, combining the judgment of the comparison result of the safe storage supervision coefficient, establishing an adaptive control parameter optimization model, and realizing intelligent small-scale warehouse goods management.

Description

Technical Field

[0001] The present invention relates to the field of warehouse cargo management, and in particular to a small-scale warehouse cargo management method and system based on artificial intelligence. Background Art

[0002] With the rapid development of e-commerce and the expansion of corporate production scale, enterprises have to cope with the changes in the development trend of the new era. The importance of warehouse management in the logistics supply chain has become increasingly prominent. For small warehouses, traditional cargo management methods have many disadvantages; for example, manual inventory of goods is inefficient and prone to errors, resulting in inaccurate inventory data; it is difficult to monitor the status of goods in real time, such as shelf life, damage, etc., which may cause waste or loss of goods. In addition, traditional methods lack accuracy in predicting cargo demand and cannot adjust inventory strategies in a timely manner according to market changes.

[0003] Due to the continuous development of artificial intelligence, it has also been of great help to the management of small warehouse goods, but the existing technology still has the following problems: insufficient grasp of abnormal situations in cargo inventory information, which can easily lead to additional costs due to abnormal situations; the risk situation cannot be clearly grasped, and cargo warehouse management personnel lack the ability to perceive potential problems, and the division of early warning modes is unclear, which can easily lead to unreasonable resource allocation and slow and incomplete problem solving; at the same time, there is no real-time adjustment and optimization of control parameters, which makes the warehouse cargo management system unable to further adapt to actual needs and reduces the efficiency of warehouse cargo management.

[0004] Therefore, there is a need for a small warehouse cargo management method and system based on artificial intelligence. Summary of the invention

[0005] The artificial intelligence-based small-scale warehouse cargo management method and system provided by the present invention aims to improve the efficiency, accuracy and safety of warehouse cargo management to cope with the rapidly changing demands and challenges in the modern business environment.

[0006] The technical solution of the present invention is specifically as follows:

[0007] The small warehouse cargo management method based on artificial intelligence includes the following steps:

[0008] Step S1. Collect and pre-process data information about goods and storage space based on sensors, establish a neural network model for abnormal inventory detection, and obtain abnormal inventory results;

[0009] Step S2. According to the output result of the neural network model for detecting abnormal inventory of goods, set the inventory risk coefficient and determine whether to enter the first-level warning mode;

[0010] Step S3. Calculate the safe storage supervision parameters according to the inventory turnover rate and inventory risk factor, and determine whether to start the secondary warning mode;

[0011] Step S4. If the secondary warning mode is not activated, an adaptive control parameter optimization model is established based on the judgment of the comparison results of the safe warehousing supervision coefficient to realize intelligent small-scale warehousing cargo management.

[0012] Further, step S1 specifically includes:

[0013] Obtain historical data information of stored goods, and use the obtained data information related to stored goods and storage space as training samples. The cargo inventory anomaly detection neural network includes an input layer, a comprehensive evaluation layer, anomaly detection layer, and an output layer;

[0014] In the anomaly detection layer,

[0015] , in, represents the input of the anomaly detection layer; Represents the output of the comprehensive analysis layer; Represents the connection weight between the comprehensive evaluation layer and the anomaly detection layer; represents the bias of the anomaly detection layer; represents the output of the anomaly detection layer; represents the learning factor; represents the activation function; Indicates the abnormal coefficient of goods inventory; Represents the credibility coefficient in the anomaly detection process; Indicates the set judgment threshold.

[0016] Further, step S2 specifically includes:

[0017] Set the inventory risk factor to , in, Indicates The inventory risk coefficient of this type of goods is Class of goods; Indicates The weight coefficient corresponding to the type of goods.

[0018] Further, step S2 specifically includes:

[0019] Define the first inventory risk factor comparison parameter , the inventory risk factor Parameters for comparison with the first inventory risk factor Perform a comparison and determine whether to start the first-level warning mode based on the comparison results. At the same time, set the manual replenishment frequency to .

[0020] Further, step S2 specifically includes:

[0021] if , it means that the inventory of warehouse goods exceeds the standard range and it is necessary to activate the first-level warning mode; define the first manual replenishment frequency as ;

[0022] if , it means that the warehouse inventory is within the normal range, and then enter the second supervision module; define the first manual replenishment frequency as ,in, Standard manual replenishment frequency.

[0023] Further, step S3 specifically includes:

[0024] in, Indicates safe storage supervision parameters; represents the constant adjustment coefficient; , They represent weight coefficients, corresponding to inventory turnover rate and inventory risk coefficient respectively; Indicated in The warehouse efficiency feedback value at each moment; Represents the feedback control coefficient at different times.

[0025] Further, step S3 specifically includes:

[0026] The preset safety storage factor is , calculate safe storage supervision parameters With the preset safety storage factor The difference , ; At the same time, set the first comprehensive safety storage supervision parameters and the second comprehensive safety storage supervision parameters ,and , respectively and and A comparison is made, and based on the comparison results, it is determined whether to activate the secondary warning mode, and the frequency of manual replenishment is adjusted.

[0027] Small warehouse cargo management system based on artificial intelligence, including the following:

[0028] Information collection and processing module, cargo inventory anomaly detection module, early warning module, inventory risk assessment module, safe warehousing supervision module, manual replenishment frequency adjustment module, and management and control optimization module;

[0029] The early warning module includes a first early warning unit and a second early warning unit;

[0030] The information collection and processing module is used to collect various data on stored goods and space, and process and integrate these data to provide input for subsequent modules;

[0031] The cargo inventory anomaly detection module is used to monitor and detect anomalies in cargo inventory, identify problems in a timely manner and take measures;

[0032] The early warning module generates early warning information based on the abnormal detection results and the preset rules of inventory risk factors and safe storage supervision parameters to remind managers to pay attention to potential problems or risks;

[0033] The first early warning unit is used to compare the inventory risk coefficient with the first inventory risk coefficient comparison parameter, and determine whether to enter the first-level early warning mode according to the comparison result;

[0034] The second early warning unit is used to compare the difference between the safety storage supervision parameter and the preset safety storage coefficient according to the first comprehensive safety storage supervision parameter and the second comprehensive safety storage supervision parameter, and determine whether to start the second-level early warning mode according to the comparison result;

[0035] Inventory risk assessment module, which is used to evaluate and analyze inventory risks, combining inventory data and historical information to quantify risk levels;

[0036] The safe storage supervision module is used to calculate safe storage supervision parameters based on parameters such as inventory turnover rate and inventory risk factor, and guide managers to formulate safe storage strategies;

[0037] Manual replenishment frequency adjustment module, which automatically or semi-automatically adjusts the replenishment frequency based on the data information obtained from the calculation of the stored goods, optimizes inventory management and reduces inventory costs;

[0038] The management and control optimization module comprehensively considers inventory information, risk assessment, and replenishment frequency factors to optimize and adjust the warehouse management process to improve efficiency and reduce risks.

[0039] Beneficial effects: 1. The present invention establishes a neural network model for detecting abnormal inventory of goods, which can monitor the status of goods in real time, detect abnormal situations in time, and help reduce losses and improve safety; automatically identify and detect abnormal situations in goods inventory, reduce human errors and missed detections, improve detection efficiency and accuracy, reduce manual intervention, improve management efficiency, and reduce additional costs caused by abnormal situations; through the results of abnormal detection, the inventory management strategy can be better optimized to avoid overstocking or out-of-stock situations, improve inventory turnover, and reduce inventory costs.

[0040] 2. The present invention can help the warehouse cargo management system provide early warnings before risks occur by setting inventory risk coefficients and triggering the first-level early warning mode, thereby improving managers' perception of potential problems and reducing losses; by timely entering the first-level early warning mode, managers can take quick action to avoid the deterioration of abnormal inventory conditions, thereby reducing cargo losses and other potential risks. At the same time, they can also adjust resource allocation according to the situation and take corresponding measures to deal with risks, such as strengthening supervision, speeding up replenishment, etc., to optimize warehouse management; the setting of the first-level early warning mode enables the system to respond quickly to abnormal situations, accelerate the speed of problem solving, and avoid the expansion of losses due to untimely response.

[0041] 3. The present invention combines inventory turnover rate and inventory risk coefficient to calculate safe storage supervision parameters, which can achieve a comprehensive assessment of storage risks and more accurately judge the safety and stability of storage conditions; supervision based on safe storage supervision parameters can achieve refined management of the storage environment, improve the accuracy and pertinence of management, and reduce risk loopholes; on the basis of the first-level early warning mode, by starting the second-level early warning mode, reactions and decisions can be made more quickly, accelerating the problem-solving process, and the system can make preventive responses before risks occur, reduce losses caused by potential risks, and improve safety and stability.

[0042] 4. The present invention can adjust parameters according to real-time storage conditions and regulatory requirements by establishing an adaptive control parameter optimization model, making management more flexible and accurate; reducing the need for human intervention, reducing management costs, and improving management efficiency; at the same time, the model can continuously learn and optimize parameters, gradually improve management levels, and continuously improve storage management strategies to make them more adaptable to actual needs. Intelligent management models help to promptly identify potential risks and make corresponding adjustments, reduce the possibility of losses, improve storage safety and management efficiency, reduce resource waste, optimize storage processes, and improve overall operational efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 It is a flow chart of the small-scale warehouse cargo management method based on artificial intelligence of the present invention;

[0044] Figure 2 This is a module diagram of the small warehouse cargo management system based on artificial intelligence of the present invention;

[0045] Figure 3 It is a schematic diagram of the early warning module of the present invention. DETAILED DESCRIPTION

[0046] In order to better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods. It should also be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0047] Refer to the attached Figure 1 , this embodiment provides a small warehouse cargo management method based on artificial intelligence, comprising the following steps:

[0048] S1. Based on the data information of goods and storage space collected by sensors and data preprocessing, a neural network model for detecting abnormal inventory of goods is established to obtain abnormal inventory results of goods.

[0049] Use IoT sensors to collect information about goods. Install sensors on the packaging or storage location of each product. Sensor types include but are not limited to radio frequency identification (RFID) tags, weight sensors, temperature and humidity sensors, etc. Specifically, RFID tags are used to identify the unique identification of goods, such as product numbers, batches, and other information; weight sensors can monitor the weight changes of goods in real time to determine whether there are missing or abnormal increases in goods; temperature and humidity sensors are used to monitor whether the storage environment of goods that have requirements for environmental conditions, such as food and medicine, is suitable. The collected goods information is transmitted to the database of the warehouse management system through wireless communication networks, such as Wi-Fi, Bluetooth, or ZigBee, to realize digital storage of goods information.

[0050] Then, the obtained cargo-related data information is preprocessed through existing technologies. In cargo management, scanning errors and data loss may occur, which require data cleaning, feature selection, data standardization and other methods to handle;

[0051] Establish a cargo inventory anomaly detection neural network model, obtain the historical data information of the stored cargo, and use the obtained data information related to the stored cargo as training samples as the input of the cargo inventory anomaly detection neural network model. After multiple trainings, the cargo inventory anomaly detection neural network model can output a real-time cargo inventory anomaly detection neural network model. The trained cargo inventory anomaly detection neural network includes an input layer, a comprehensive evaluation layer, anomaly detection layer, and an output layer.

[0052] Set the data information related to the stored goods feature data. In the model, the input layer and the comprehensive evaluation layer are connected through a fully connected network to pass the feature information to the comprehensive evaluation layer. The specific process is as follows:

[0053] , in, Represents the input of the comprehensive analysis layer; Represents the connection weight between the input layer and the comprehensive evaluation layer; Indicates the bias of the comprehensive evaluation layer; Represents the output of the comprehensive analysis layer; Indicates the input Features, ; represents the time attenuation coefficient; represents the weight adjustment coefficient; represents the learning factor; Indicates the length of recorded time for the circulation of goods in the storage space; Indicates storage space in Temperature changes; Indicates the critical value of the temperature in the storage space; Vibration frequency parameters representing the average storage time of different types of goods; Indicates The purchase volume of such goods.

[0054] In the anomaly detection layer, anomalies in the inventory of goods are detected. The specific process is as follows:

[0055] , in, represents the input of the anomaly detection layer; Represents the connection weight between the comprehensive evaluation layer and the anomaly detection layer; represents the bias of the anomaly detection layer; represents the output of the anomaly detection layer; represents the learning factor; represents the activation function; Indicates the abnormal coefficient of goods inventory; Represents the credibility coefficient in the anomaly detection process; Indicates the judgment threshold that is set based on expert experience and experimental data.

[0056] In the output layer, the abnormal probability results of different categories are output. The specific process is as follows:

[0057] in, represents the output of the output layer, i.e. The probability of abnormal inventory of goods of the same category; represents the weight of the output layer; represents the bias of the output layer; represents the statistical coefficient of abnormal probability; Indicates the cargo inventory anomaly detection model for The feature weight of the cargo anomaly, that is, the degree of anomaly contribution.

[0058] The present invention establishes a neural network model for detecting abnormalities in cargo inventory, which can monitor the cargo situation in real time, discover abnormalities in time, and help reduce losses and improve safety; automatically identify and detect abnormalities in cargo inventory, reduce human errors and missed detections, improve detection efficiency and accuracy, reduce manual intervention, improve management efficiency, and reduce additional costs caused by abnormal situations; through the abnormality detection results, the inventory management strategy can be better optimized, overstocking or out-of-stock situations can be avoided, inventory turnover can be improved, and inventory costs can be reduced.

[0059] S2. According to the output results of the neural network model for detecting abnormal inventory of goods, set the inventory risk coefficient and determine whether to enter the first-level warning mode.

[0060] , in, Indicates The inventory risk coefficient of this type of goods is Class of goods; It represents the proportionality coefficient, which is used to express the risk sensitivity; Indicates The value of the goods; Indicates the reference value of goods, for example, the average value of stored goods; Indicates The weight coefficient corresponding to the type of goods.

[0061] Define the first inventory risk factor comparison parameter , the inventory risk factor Parameters for comparison with the first inventory risk factor Perform a comparison and determine whether to start the first-level warning mode based on the comparison results. At the same time, set the manual replenishment frequency to , the specific process is as follows:

[0062] if , it means that the inventory of warehouse goods exceeds the standard range and it is necessary to activate the first-level warning mode; define the first manual replenishment frequency as ;

[0063] if , it means that the warehouse inventory is within the normal range, and then enter the second supervision module; define the first manual replenishment frequency as ,in, Standard manual replenishment frequency.

[0064] The present invention can help the warehouse cargo management system provide early warnings before risks occur by setting inventory risk coefficients and triggering a first-level early warning mode, thereby improving managers' perception of potential problems and reducing losses. By timely entering the first-level early warning mode, managers can take quick actions to avoid the deterioration of abnormal inventory conditions, thereby reducing cargo losses and other potential risks. At the same time, they can also adjust resource allocation according to the situation and take corresponding measures to deal with risks, such as strengthening supervision, speeding up replenishment, etc., to optimize warehouse management. The setting of the first-level early warning mode enables the system to respond quickly to abnormal situations, accelerate the speed of problem solving, and avoid the expansion of losses due to untimely response.

[0065] S3. Based on inventory turnover rate and inventory risk factor Calculate safe storage supervision parameters , determine whether to activate the secondary warning mode based on the safety warehousing supervision parameters.

[0066] In the embodiment of the present invention, a high inventory turnover rate generally indicates a fast turnover of goods and a high efficiency of warehouse goods management; a low inventory turnover rate may indicate a backlog of goods or poor sales; calculating the inventory turnover rate , the specific process is as follows:

[0067] in, represents the constant adjustment coefficient; , They represent weight coefficients, corresponding to inventory turnover rate and inventory risk coefficient respectively; Indicated in The warehouse efficiency feedback value at each moment; Represents the feedback control coefficient at different times.

[0068] The preset safety storage factor is , calculate safe storage supervision parameters With the preset safety storage factor The difference , ; At the same time, set the first comprehensive safety storage supervision parameters and the second comprehensive safety storage supervision parameters ,and , respectively and and The comparison is performed, and based on the comparison results, it is determined whether to start the secondary warning mode, and the manual replenishment frequency is adjusted. The specific process is as follows:

[0069] if , then adjust the manual replenishment frequency to ;

[0070] if , then adjust the manual replenishment frequency to ;

[0071] if , then adjust the manual replenishment frequency to , and start the second early warning mode at the same time;

[0072] in, Indicates the first manual replenishment adjustment frequency compensation parameter, Indicates the second manual replenishment adjustment frequency compensation parameter, Indicates the third manual replenishment adjustment frequency compensation parameter.

[0073] The present invention calculates safe warehousing supervision parameters in combination with inventory turnover rate and inventory risk coefficient, which can realize comprehensive evaluation of warehousing risks and more accurately judge the safety and stability of warehousing conditions; supervision based on safe warehousing supervision parameters can realize refined management of the warehousing environment, improve the accuracy and pertinence of management, and reduce risk loopholes; on the basis of the first-level early warning mode, by starting the second-level early warning mode, reactions and decisions can be made more quickly, the problem-solving process can be accelerated, and the system can make preventive responses before risks occur, reduce losses caused by potential risks, and improve safety and stability.

[0074] S4. If the secondary warning mode is not activated, an adaptive control parameter optimization model is established based on the comparison results of the safe warehousing supervision coefficient to realize intelligent small-scale warehousing cargo management.

[0075] Establish an adaptive control optimization model. The specific process is as follows:

[0076] in, Represents the output of the adaptive management and control optimization model; Represents the control coefficient, which is used to control the stability of the optimization process; Indicates Expected loss of value of such goods; Indicates the balance coefficient, which is used to balance the impact of various key parameters in the control process; Indicates the total amount of control parameters; Indicates Control variable parameter value; Indicates Decision bias for each parameter value; Indicates The baseline parameter of a control variable.

[0077] Through the output of the adaptive management and control optimization model, the currently relatively normal storage goods are managed and controlled, the intelligence and safety of small storage goods are improved, and the management efficiency is maximized at the same time.

[0078] The present invention can adjust parameters according to real-time storage conditions and regulatory requirements by establishing an adaptive control parameter optimization model, making management more flexible and accurate; reducing the need for human intervention, reducing management costs, and improving management efficiency; at the same time, the model can continuously learn and optimize parameters, gradually improve management levels, and continuously improve storage management strategies to make them more adaptable to actual needs. Intelligent management models help to timely discover potential risks and make corresponding adjustments, reduce the possibility of losses, improve storage safety and management efficiency, reduce resource waste, optimize storage processes, and improve overall operational efficiency.

[0079] Refer to the attached Figure 2 This embodiment provides a small warehouse cargo management system based on artificial intelligence, including the following contents:

[0080] Information collection and processing module, cargo inventory anomaly detection module, early warning module, inventory risk assessment module, safe warehousing supervision module, manual replenishment frequency adjustment module, and management and control optimization module;

[0081] The early warning module includes a first early warning unit and a second early warning unit;

[0082] The information collection and processing module is used to collect various data on the stored goods and space, such as goods in and out of the warehouse, inventory, temperature and humidity, etc., and process and integrate these data to provide input for subsequent modules;

[0083] Cargo inventory anomaly detection module monitors and detects anomalies in cargo inventory, helping to identify problems and take measures in a timely manner;

[0084] The early warning module generates early warning information based on the abnormal detection results and the preset rules of inventory risk factors and safe storage supervision parameters to remind managers to pay attention to potential problems or risks so that they can be dealt with in a timely manner;

[0085] The first early warning unit is used to compare the inventory risk coefficient with the first inventory risk coefficient comparison parameter, and determine whether to enter the first-level early warning mode according to the comparison result;

[0086] The second early warning unit is used to compare the difference between the safety storage supervision parameter and the preset safety storage coefficient according to the first comprehensive safety storage supervision parameter and the second comprehensive safety storage supervision parameter, and determine whether to start the second-level early warning mode according to the comparison result;

[0087] Inventory risk assessment module, which is used to evaluate and analyze inventory risks, combine inventory data and historical information, quantify risk levels, and help managers better understand inventory status;

[0088] The safe storage supervision module is used to calculate safe storage supervision parameters based on parameters such as inventory turnover rate and inventory risk factor, and guide managers to formulate safe storage strategies;

[0089] Manual replenishment frequency adjustment module, which automatically or semi-automatically adjusts the replenishment frequency based on the data information obtained from the calculation of the stored goods, optimizes inventory management and reduces inventory costs;

[0090] The management and control optimization module comprehensively considers factors such as inventory information, risk assessment, replenishment frequency, etc., optimizes and adjusts the warehouse management process to improve efficiency and reduce risks.

[0091] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0092] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0093] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0094] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0095] The above contents are only for explaining the technical idea of ​​the present invention and cannot be used to limit the protection scope of the present invention. Any changes made on the basis of the technical solution in accordance with the technical idea proposed by the present invention shall fall within the protection scope of the claims of the present invention.

Claims

1. A small warehouse cargo management method based on artificial intelligence, characterized in that: The following steps are involved: Step S1. According to the data information of goods and storage space collected by sensors and preprocessed, a neural network model for detecting abnormal inventory of goods is established to obtain abnormal inventory results of goods; and the probability results of abnormalities of different types are output: in, represents the output of the output layer, i.e. The probability of abnormal inventory of goods of the same category; represents the output of the anomaly detection layer; represents the weight of the output layer; represents the bias of the output layer; represents the statistical coefficient of abnormal probability; Indicates the cargo inventory anomaly detection model for The characteristic weight of the cargo anomaly, i.e. the degree of anomaly contribution; Step S2. According to the output results of the neural network model for detecting abnormal inventory of goods, the inventory risk coefficient is set to determine whether to enter the first-level warning mode, and the manual replenishment frequency is set; Set the inventory risk factor to , in, Indicates The inventory risk coefficient of this type of goods is Class of goods; Indicates Weight coefficient corresponding to the type of goods; Step S3. Calculate the safe storage supervision parameters according to the inventory turnover rate and inventory risk factor, and determine whether to start the secondary warning mode; in, Indicates safe storage supervision parameters; represents the constant adjustment coefficient; , They represent weight coefficients, corresponding to inventory turnover rate and inventory risk coefficient respectively; Indicated in The warehouse efficiency feedback value at each moment; Represents the feedback control coefficient at different times; Set up the first comprehensive safety warehousing supervision parameters and the second comprehensive safety storage supervision parameters ,and , respectively and and Compare and decide whether to start the secondary warning mode according to the comparison results, and adjust the manual replenishment frequency; Step S4. If the secondary warning mode is not activated, an adaptive control parameter optimization model is established based on the comparison results of the safety storage supervision coefficient to realize intelligent small storage cargo management; in, Represents the output of the adaptive management and control optimization model; represents the control coefficient; represents the adjusted manual replenishment frequency; Indicates Expected loss of value of such goods; Indicates the balance coefficient, which is used to balance the impact of various key parameters in the control process; Indicates the total amount of control parameters; Indicates Control variable parameter value; Indicates Decision bias for each parameter value; Indicates The baseline parameter of a control variable.

2. The small-scale warehouse cargo management method based on artificial intelligence according to claim 1 is characterized in that: The step S1 specifically includes: Obtain historical data information of stored goods, and use the obtained data information related to stored goods and storage space as training samples. The cargo inventory anomaly detection neural network includes an input layer, a comprehensive evaluation layer, anomaly detection layer, and an output layer; In the anomaly detection layer, , in, represents the input of the anomaly detection layer; Represents the output of the comprehensive evaluation layer; Represents the connection weight between the comprehensive evaluation layer and the anomaly detection layer; represents the bias of the anomaly detection layer; represents the output of the anomaly detection layer; represents the learning factor; represents the activation function; Indicates the abnormal coefficient of goods inventory; Represents the credibility coefficient in the anomaly detection process; Indicates the set judgment threshold.

3. The small-scale warehouse cargo management method based on artificial intelligence according to claim 1 is characterized in that: The step S2 specifically includes: Define the first inventory risk factor comparison parameter , the inventory risk factor Parameters for comparison with the first inventory risk factor Carry out a comparison and determine whether to activate the first-level warning mode based on the comparison results.

4. The small-scale warehouse cargo management method based on artificial intelligence according to claim 3 is characterized in that: The step S2 specifically includes: if , it means that the inventory of warehouse goods exceeds the standard range and it is necessary to activate the first-level warning mode; define the first manual replenishment frequency as ; if , it means that the warehouse inventory is within the normal range, and then enter the second supervision module; define the first manual replenishment frequency as ,in, Standard manual replenishment frequency.

5. The small-scale warehouse cargo management method based on artificial intelligence according to claim 1 is characterized in that: The step S3 specifically includes: The preset safety storage factor is , calculate safe storage supervision parameters With the preset safety storage factor The difference , ; if , then adjust the manual replenishment frequency to ; if , then adjust the manual replenishment frequency to ; if , then adjust the manual replenishment frequency to , and start the second early warning mode at the same time; in, Indicates the first manual replenishment adjustment frequency compensation parameter, Indicates the second manual replenishment adjustment frequency compensation parameter, Indicates the third manual replenishment adjustment frequency compensation parameter.

6. A small-scale warehouse cargo management system based on artificial intelligence, applied to the small-scale warehouse cargo management method based on artificial intelligence as claimed in claim 1, characterized in that: Includes the following: Information collection and processing module, cargo inventory anomaly detection module, early warning module, inventory risk assessment module, safe warehousing supervision module, manual replenishment frequency adjustment module, and management and control optimization module; The early warning module includes a first early warning unit and a second early warning unit; The information collection and processing module is used to collect various data on stored goods and space, and process and integrate these data to provide input for subsequent modules; The cargo inventory anomaly detection module is used to monitor and detect anomalies in cargo inventory, identify problems in a timely manner and take measures; The early warning module generates early warning information based on the abnormal detection results and the preset rules of inventory risk coefficient and safe storage supervision parameters to remind managers to pay attention to potential problems or risks; The first early warning unit is used to compare the inventory risk coefficient with the first inventory risk coefficient comparison parameter, and determine whether to enter the first-level early warning mode according to the comparison result; The second early warning unit is used to compare the difference between the safety storage supervision parameter and the preset safety storage coefficient according to the first comprehensive safety storage supervision parameter and the second comprehensive safety storage supervision parameter, and determine whether to start the secondary early warning mode according to the comparison result; The inventory risk assessment module is used to assess and analyze inventory risks and quantify risk levels by combining inventory data and historical information; The safe storage supervision module is used to calculate safe storage supervision parameters based on parameters such as inventory turnover rate and inventory risk factor, and guide managers to formulate safe storage strategies; The manual replenishment frequency adjustment module automatically or semi-automatically adjusts the replenishment frequency according to the data information obtained by calculation related to the stored goods, thereby optimizing inventory management and reducing inventory costs; The management and control optimization module comprehensively considers inventory information, risk assessment, and replenishment frequency factors to optimize and adjust the warehouse management process to improve efficiency and reduce risks.

Images