Intelligent warehousing automatic inventory management system and method based on Internet of Things

Abstract

The invention discloses an intelligent warehousing automatic inventory management system and method based on the Internet of Things, and belongs to the technical field of inventory management, and the system comprises a short-time state jump existence information analysis module, a short-time state jump associated information judgment module, a first adaptation scheme analysis module and a second adaptation scheme analysis module. By monitoring the storage shelf state, capturing potential vibration signals in storage, accurately distinguishing shelf structure vibration and non-structure vibration, avoiding misjudgment, improving monitoring accuracy, aiming at the shelf structure vibration, the first adaptation scheme analysis module is combined with historical vibration characteristics to realize dynamic time sequence adjustment and reduce false alarms, and aiming at the non-structure vibration, the method is simple and convenient to operate. According to the method, the reliability and the direction consistency of article change are evaluated, the actual change condition of the article is judged, then a targeted adaptation strategy is adopted, accurate collection and timely response of inventory change information are ensured, the intelligent level and the reliability of warehouse inventory management are improved, and the inventory checking efficiency and the accuracy are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of inventory management, and in particular to an intelligent warehousing automated inventory management system and method based on the Internet of Things. Background Art

[0002] With the continuous development of industrial automation and information technology, IoT-based warehouse management systems are increasingly being used for the storage, sorting, and inbound and outbound management of industrial materials such as machinery and electronics. By deploying sensors, actuator terminals, and communication devices within the warehouse environment, the system can perceive the material's in-place status, environmental conditions, and operational behavior in real time, enabling dynamic updates of inventory information and remote scheduling and control.

[0003] In existing technologies, identifying the status of stored materials typically relies on the coordinated use of multiple sensing devices. For example, laser ranging sensors are used to determine whether the goods are in a designated location; pressure sensors or weight modules are used to detect the physical load exerted by the material in place; image acquisition and recognition technologies are used to monitor changes in storage locations, material handling movements, or occlusions; and RFID and QR code recognition technologies are used to track the unique identification and location information of materials. Furthermore, supporting software systems can store, parse, and analyze the data collected by the sensors for use in material inbound and outbound records, inventory ledger maintenance, equipment task scheduling, and status monitoring. The system can be combined with an edge computing gateway or cloud platform to process data in real time, supporting local feedback or the issuance of remote control commands, thereby achieving automated warehouse operation management.

[0004] For example, the Chinese invention patent with announcement number: CN115249137B discloses a material intelligent warehouse management system, which includes a management server, a collection module, a calculation module, and a communication module. The management server can be used to display material information or input material information. The material information includes but is not limited to material category and material inventory. The management server sends a signal to the collection module through the communication module. The collection module starts to collect information about the material tray and transmits the collected information to the calculation module through the communication module. The calculation module performs logical operations based on the information collected by the collection module.

[0005] For example, the Chinese invention patent with the announcement number CN118798784B discloses an intelligent inbound and outbound management system and method for a three-dimensional warehouse, which includes a cargo weighing module, a space monitoring module, a space screening module, a load-bearing monitoring module, a load-bearing analysis module, a scheduling terminal and a tallying terminal. The cargo weighing module is used to weigh and measure the specifications of the goods scheduled to be stored, the space monitoring module is used to monitor the storage area, the space screening module is used to screen the storage space that matches the goods to be stored, the scheduling terminal is used to schedule transportation equipment to complete the cargo storage operation, the load-bearing monitoring module is used to monitor the weight distribution of the stacked goods in each storage space, the load-bearing analysis module is used to analyze the center of gravity of the stacked goods in the storage space, and the tallying terminal is used to adjust the placement of the stacked goods.

[0006] The above technology has at least the following technical problems:

[0007] The current warehouse management system focuses on the basic entry and exit of materials, the recording and management of inventory quantities, and the optimization of warehouse space utilization. In the process of inventory status perception, the system mostly uses laser ranging or pressure sensors to determine whether the material is in place, and regards each status change as a valid entry and exit operation. However, in actual operation, it may be affected by factors such as slight jitter, sensor drift or equipment vibration, causing invalid state flips, causing the system to misjudge the actual movement of materials, frequently refresh inventory ledgers, cause frequent abnormal inventory records, and inaccurate material status identification, thereby affecting the reliability of inventory data, and then interfering with subsequent entry and exit scheduling logic, and may even trigger erroneous instructions or error abnormality warnings, reducing system stability. Summary of the Invention

[0008] In order to solve the above technical problems existing in the prior art, the embodiments of the present invention provide an intelligent warehouse automation inventory management system and method based on the Internet of Things. The technical solution is as follows:

[0009] On the one hand, it provides an intelligent warehouse automation inventory management system based on the Internet of Things, including:

[0010] The short-term state jump existence information analysis module is used to monitor each shelf in the warehouse, analyze the short-term state jump existence information, and record the shelf with short-term state jump as the target shelf.

[0011] The short-term state jump correlation information determination module is used to analyze the vibration-jump correlation characteristic factor of the target shelf within a preset monitoring window and determine the short-term state jump correlation information of the target shelf.

[0012] The first adaptation solution analysis module is used to analyze the first adaptation solution in combination with the historical vibration-jump correlation characteristic factor of the target shelf when the short-term state jump correlation information of the target shelf is shelf structure vibration.

[0013] The second adaptation scheme analysis module is used to analyze the credibility index of the target shelf's item changes when the short-term state jump associated information of the target shelf is non-shelf structure vibration, and simultaneously analyze the number of consistency in the direction of item changes on the target shelf, thereby extracting the credibility constraint factor, and analyzing the second adaptation scheme in combination with the credibility index of the target shelf's item changes.

[0014] On the other hand, an intelligent warehousing automated inventory management method based on the Internet of Things is provided, comprising the following steps:

[0015] Monitor each shelf in the warehouse, analyze the existence of short-term state jump information, and record the shelves with short-term state jumps as target shelves.

[0016] Within the preset monitoring window, the vibration-jump correlation characteristic factors of the target shelf are analyzed to determine the short-term state jump correlation information of the target shelf.

[0017] When the short-term state jump associated information of the target shelf is shelf structure vibration, the first adaptation solution is analyzed in combination with the historical vibration-jump associated characteristic factors of the target shelf.

[0018] When the short-term state jump associated information of the target shelf is non-shelf structure vibration, the credibility index of the item change of the target shelf is analyzed, and the consistency of the direction of the item change of the target shelf is simultaneously analyzed to extract the credibility constraint factor. The second adaptation plan is analyzed in combination with the credibility index of the item change of the target shelf.

[0019] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0020] 1. The intelligent warehouse automation inventory management system and method based on the Internet of Things provided by the present invention can monitor the status of warehouse shelves in real time through the short-term state jump information analysis module, quickly identify the target shelves with abnormal jumps, and effectively capture potential vibration or item change signals in the warehouse. Through the short-term state jump associated information judgment module, it can accurately distinguish between shelf structural vibration and non-structural vibration, avoid misjudgment, and improve monitoring accuracy. For shelf structural vibration, the first adaptation scheme analysis module combines historical vibration characteristics to achieve dynamic timing adjustment, reduce the sampling frequency or extend the jump confirmation window, and reduce false alarms caused by environmental vibration. For non-structural vibration, the credibility and direction consistency of item changes are evaluated, and the actual changes of items are determined. Then, an adaptation strategy of updating credible jump records, generating early warning prompts, or executing confirmation processes is adopted to ensure accurate collection and timely response of inventory change information. The intelligence level and reliability of warehouse inventory management are improved, and the efficiency and accuracy of inventory counting are improved.

[0021] 2. The present invention can accurately distinguish between shelf structural vibration and non-structural vibration by determining the relevant information of short-term state jumps of the target shelf, avoid false alarms and missed alarms caused by vibration or external interference, and combine historical vibration characteristics and real-time monitoring data to dynamically adjust monitoring parameters, thereby improving the system's response sensitivity and stability to abnormal jumps. At the same time, through multi-dimensional item change credibility indicators and directional consistency analysis, the actual changes in inventory items can be scientifically judged, and accurate perception and management of inventory status can be achieved, significantly improving the accuracy, real-time nature and reliability of warehouse automation inventory management.

[0022] 3. By analyzing the first adaptation scheme, the present invention can combine the historical vibration-jump correlation characteristics of the target shelf, dynamically adjust the monitoring timing parameters, suppress the misjudgment of short-term state jumps caused by the vibration of the shelf structure, and improve the stability and accuracy of the monitoring system. At the same time, through difference processing and weighted average methods, it can achieve intelligent response to abnormal vibrations, ensuring that the system can still maintain efficient and reliable status monitoring capabilities in complex environments, thereby optimizing the warehouse management process and reducing equipment maintenance costs.

[0023] 4. By analyzing the second adaptation scheme, the present invention can accurately evaluate the authenticity and credibility of item changes based on the number of consistent item change directions and the credibility constraint factor on the target shelf. By setting multi-level thresholds, it can achieve classified processing of different change situations, including updating trusted jump records, generating early warning prompt information and executing confirmation processes, to prevent false alarms and omissions, and ensure the accurate collection and timely response of inventory change information; at the same time, through the repeated confirmation mechanism and weighted verification, it enhances the reliability of the system's judgment on abnormal item changes, and improves the intelligence level and operational safety of warehouse automation inventory management. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0025] Figure 1 This is a structural diagram of an intelligent warehousing automation inventory management system based on the Internet of Things provided by an embodiment of the present invention.

[0026] Figure 2 This is a flow chart of an intelligent warehousing automated inventory management method based on the Internet of Things provided by an embodiment of the present invention.

[0027] Figure 3 This is a flow chart of vibration jump correlation determination involved in an embodiment of the present invention.

[0028] Figure 4 This is a flowchart of item change credibility judgment and jump processing involved in an embodiment of the present invention.

[0029] Figure 5 This is the homepage of the intelligent warehouse management system involved in the embodiment of the present invention.

[0030] Figure 6 This is a diagram of the inventory management interface of the intelligent warehouse management system involved in an embodiment of the present invention.

[0031] Figure 7 This is a diagram of the shelf abnormality monitoring interface of the intelligent warehouse management system involved in an embodiment of the present invention.

[0032] Figure 8 This is a continuation of the shelf abnormality monitoring interface of the intelligent warehouse management system involved in an embodiment of the present invention. DETAILED DESCRIPTION

[0033] The technical solution of the present invention is described below in conjunction with the accompanying drawings.

[0034] In the embodiments of the present invention, words such as "exemplarily" and "for example" are used to indicate examples, illustrations, or explanations. Any embodiment or design described as an "exemplary" in the present invention should not be construed as being preferred or advantageous over other embodiments or designs. Rather, the use of the word "exemplary" is intended to present concepts in a concrete manner. Furthermore, in the embodiments of the present invention, "and / or" can mean both or either of the two.

[0035] In the embodiments of the present invention, the terms "image" and "picture" may sometimes be used interchangeably. It should be noted that, when the distinction is not emphasized, the meanings they convey are the same. The terms "of," "corresponding," and "corresponding" may sometimes be used interchangeably. It should be noted that, when the distinction is not emphasized, the meanings they convey are the same.

[0036] In the embodiments of the present invention, sometimes a subscript such as W1 may be written as a non-subscript such as W1. When the difference is not emphasized, the meanings to be expressed are the same.

[0037] In order to make the technical problems, technical solutions and advantages to be solved by the present invention clearer, a detailed description will be given below with reference to the accompanying drawings and specific embodiments.

[0038] The embodiment of the present invention provides an intelligent warehouse automation inventory management system based on the Internet of Things, such as Figure 1The schematic structural diagram of the intelligent warehousing automation inventory management system based on the Internet of Things shown includes: a short-term state jump existence information analysis module, a short-term state jump related information determination module, a first adaptation solution analysis module and a second adaptation solution analysis module.

[0039] It should be noted that the analysis and processing involved in the following solutions are all based on the background of short-term state jumps. They only identify and judge state change behaviors that are of short duration and may be caused by abnormal factors. The system will simultaneously record and manage normal inbound and outbound operations.

[0040] like Figure 7 and Figure 8 The following are respectively a diagram of an abnormal shelf monitoring interface of an intelligent warehouse management system according to an embodiment of the present invention and a continuation diagram of an abnormal shelf monitoring interface of an intelligent warehouse management system according to an embodiment of the present invention. Figure 7 Monitor and visualize the abnormal status of each shelf in the current warehouse, and display the abnormal alarm information of the shelf simultaneously. Figure 7 The shelf in the Figure 8 , displays the basic information of the clicked shelf.

[0041] The short-term state jump existence information analysis module is used to monitor each shelf in the warehouse, analyze the short-term state jump existence information, and record the shelf with short-term state jump as the target shelf.

[0042] Furthermore, the information about the existence of short-term state transitions is analyzed and the acquisition process is as follows:

[0043] Within the preset time window, obtain the number of short-term state jumps of each shelf in the warehouse.

[0044] Short-term state jump refers to the state change behavior in which the state of the shelf switches repeatedly within the continuous monitoring time window, and the state duration after each switch is less than the preset jump confirmation time window.

[0045] It should be explained that within the preset time window, the system continuously collects the status of goods in place through the status detection sensors deployed on each shelf, identifies the status change behavior (that is, the switch between goods in place and out of stock), and determines the duration of the new status after each switch. When the duration after a certain status switch is less than the preset jump confirmation time window, it is recorded as a short-term status jump. The system counts the number of jumps within the time window based on this as a quantitative basis for the short-term status jump behavior of the shelf.

[0046] Extract the short-term state transition count threshold preset in the database.

[0047] If the number of short-term state transitions of a certain shelf is less than the short-term state transition number threshold, the short-term state transition existence information of the shelf is recorded as no short-term state transition.

[0048] If the number of short-term state transitions for a shelf is less than the short-term state transition threshold, it indicates that the shelf has experienced few state changes within the current monitoring window and has not frequently switched from "in-place to empty." This indicates that the shelf's overall state is stable and exhibits no abnormal transition characteristics. Therefore, the system marks the presence of short-term state transitions for that shelf as "no short-term state transitions," eliminating the need to proceed to the subsequent transition cause determination and adaptation analysis phase.

[0049] If the number of short-term state transitions of a shelf is greater than or equal to the short-term state transition threshold, the short-term state transition existence information of the shelf is recorded as the existence of a short-term state transition.

[0050] If the number of short-term state transitions for a shelf is greater than or equal to the short-term state transition threshold, it indicates that the shelf has experienced multiple "in-place-to-vacant" state transitions within the current monitoring window, showing a trend of repeated transitions within a short period of time. This may be affected by factors such as structural vibration, physical disturbances, or sensor fluctuations, and there is a risk of state instability. In this case, the system marks the shelf's short-term state transition information as "short-term state transition exists" and selects the shelf as the target shelf, proceeding to the next step of the transition correlation analysis process.

[0051] The short-term state jump correlation information determination module is used to analyze the vibration-jump correlation characteristic factor of the target shelf within a preset monitoring window and determine the short-term state jump correlation information of the target shelf.

[0052] like Figure 3 The figure shows a flow chart for determining vibration jump correlation, according to an embodiment of the present invention. This process is used to determine whether a target shelf's jump is caused by structural vibration. The system first collects vibration-related characteristic parameters, calculates a vibration-jump correlation characteristic factor, and compares it with a preset verification factor. If the threshold is exceeded, it is determined to be structural vibration and the jump is intercepted. If not, the subsequent trusted jump analysis process begins.

[0053] Furthermore, the short-term state transition associated information of the target shelf is determined. The determination process is as follows:

[0054] In a preset monitoring window, a set of vibration-jump correlation characteristic parameters of the target shelf is collected, and the vibration-jump correlation characteristic factor of the target shelf is obtained by analysis.

[0055] Extract the vibration-jump correlation feature verification factors preset in the warehouse database.

[0056] When the vibration-jump correlation characteristic factor of the target shelf exceeds the vibration-jump correlation characteristic verification factor, the determination result of the short-term state jump correlation information of the target shelf is recorded as the shelf structure vibration, and an interception jump control instruction is generated.

[0057] If the target shelf's vibration-jump correlation characteristic factor exceeds the vibration-jump correlation characteristic verification factor, it indicates that the shelf's short-term state jump is strongly correlated with the shelf's structural vibration and is likely caused by the shelf's structural vibration. The system then identifies the target shelf's short-term state jump as structural vibration and generates a jump intercept control instruction to prevent jump information caused by structural vibration from interfering with inventory management accuracy.

[0058] When the vibration-jump correlation characteristic factor of the target shelf does not exceed the vibration-jump correlation characteristic verification factor, the determination result of the short-term state jump correlation information of the target shelf is recorded as non-shelf structure vibration.

[0059] If the target shelf's vibration-jump correlation characteristic factor does not exceed the vibration-jump correlation characteristic verification factor, this indicates that the shelf's short-term state jump is only weakly correlated with the shelf's structural vibration and is not caused by the shelf's inherent structural vibration. Therefore, the system records the target shelf's short-term state jump correlation information as non-shelf structural vibration and will subsequently analyze the cause of the jump from other perspectives, such as item movement.

[0060] Furthermore, the vibration-jump correlation characteristic factor of the target shelf is analyzed in the following specific process:

[0061] The vibration-jump correlation characteristic parameter set of the target shelf includes the vibration amplitude peak proportional factor, the jump-vibration main frequency matching proportional factor, and the jump-vibration time sequence coupling proportional factor.

[0062] In this embodiment, the peak vibration amplitude refers to the maximum peak value of the target shelf's structural vibration amplitude within a short time window before and after the transition, and is used to quantify the vibration intensity during the transition. A triaxial accelerometer installed on the shelf structure collects vibration data in real time. A symmetrical short-term analysis window (pre-defined in the warehouse database) is defined before and after the transition, and the peak displacement within this time window is extracted as the peak vibration amplitude.

[0063] The jump-to-vibration frequency matching degree indicates the similarity between the jump event period and the shelf's vibration frequency, quantifying the frequency-domain coupling between the two. Fourier transform or wavelet analysis is performed on the time interval sequence of multiple consecutive jump events to extract the jump frequency components. Simultaneously, spectrum analysis is performed on the vibration sensor signal to extract the vibration frequency. The matching degree formula (cosine similarity is used in this example) is used to calculate the frequency matching degree.

[0064] The transition-vibration timing coupling refers to the distribution of the time difference between the occurrence of a transition event and the local peak of the vibration waveform, measuring the degree of synchronization between the two on the time axis. The trigger timestamp of each transition event is recorded, and the timestamp of the most recent vibration peak in the vibration sensor signal is extracted. The time difference between the two is calculated as the numerical result of the transition-vibration timing coupling.

[0065] The peak vibration amplitude, the degree of matching between the jump and the dominant vibration frequency, and the degree of coupling between the jump and the timing of the vibration exhibit a synergistic response relationship in the analysis. When any one of these parameters changes significantly, the others typically exhibit a corresponding trend of linked changes. For example, when the peak vibration amplitude increases significantly, if the jump is caused by this vibration, the matching degree between the jump frequency and the dominant vibration frequency often increases, and the jump time is closer to the vibration peak time, thereby simultaneously improving the dominant frequency matching and the timing coupling. Conversely, if the vibration amplitude changes significantly but the dominant frequency matching and timing coupling do not increase simultaneously, it indicates that the vibration is likely an occasional shock and has a weak correlation with the jump.

[0066] The reference vibration amplitude peak value, reference jump-vibration main frequency matching degree and reference jump-vibration timing coupling degree stored in the database are extracted.

[0067] The vibration amplitude peak proportional factor is the numerical result of dividing the vibration amplitude peak by the reference vibration amplitude peak, the jump-vibration main frequency matching proportional factor is the numerical result of dividing the jump-vibration main frequency matching by the reference jump-vibration main frequency matching, and the jump-vibration timing coupling proportional factor is the numerical result of dividing the jump-vibration timing coupling by the reference jump-vibration timing coupling.

[0068] The weighted measurement factors of the vibration amplitude peak proportional factor, the weighted measurement factors of the jump-vibration main frequency matching proportional factor and the weighted measurement factors of the jump-vibration timing coupling proportional factor preset in the database are extracted.

[0069] It should be noted that to achieve weighted fusion of the vibration-jump characteristic factors of the target shelf, multiple mapping relationships are pre-established in the database, associating different jump characterization parameters with their corresponding weighted measurement factors. These mapping relationships are stored in a structured data table (e.g., a weighted configuration table), which records the weighted measurement factors corresponding to the vibration amplitude peak scale factor, the jump-to-vibration main frequency matching scale factor, and the jump-to-vibration timing coupling scale factor. This weighted configuration table is combined with actual vibration monitoring data and historical jump sample data through associative queries to construct a complete vibration-jump coupling evaluation system. Based on this evaluation system, the system directly extracts the weighted measurement factors of each scale factor that matches the current jump state of the target shelf from the database for subsequent characteristic factor fusion calculations. The value range of each weighted measurement factor is limited to 0 to 1, and the sum of the three is 1, ensuring normalization and physical consistency of the multi-factor coupling analysis results.

[0070] The vibration amplitude peak proportional factor, the jump-vibration main frequency matching proportional factor and the jump-vibration timing coupling proportional factor are weightedly coupled by the weighted measurement factors preset in the warehouse database to obtain the vibration-jump correlation characteristic factor of the target shelf.

[0071] The vibration-jump correlation characteristic factors of the target shelf are the vibration amplitude peak proportional factor, the jump-vibration main frequency matching proportional factor and the jump-vibration timing coupling proportional factor, which jointly quantitatively represent the vibration-jump correlation degree of the target shelf.

[0072] In a specific embodiment, the vibration-jump correlation characteristic factor of the target shelf is specifically expressed as follows:

[0073] ,

[0074] Among them, A is the vibration-jump correlation characteristic factor of the target shelf, a is the vibration amplitude peak proportional factor, b is the jump-vibration main frequency matching proportional factor, c is the jump-vibration timing coupling proportional factor, x1 is the weighted measurement factor of the vibration amplitude peak proportional factor, x2 is the weighted measurement factor of the jump-vibration main frequency matching proportional factor, and x3 is the weighted measurement factor of the jump-vibration timing coupling proportional factor.

[0075] The first adaptation solution analysis module is used to analyze the first adaptation solution in combination with the historical vibration-jump correlation characteristic factor of the target shelf when the short-term state jump correlation information of the target shelf is shelf structure vibration.

[0076] Furthermore, the first adaptation solution is analyzed based on the historical vibration-jump correlation characteristic factors of the target shelf. The specific analysis process is as follows:

[0077] The vibration-jump correlation characteristic factor of the target shelf is subtracted from the vibration-jump correlation characteristic verification factor to obtain the vibration-jump correlation characteristic deviation factor.

[0078] It should be explained that the difference processing refers to subtracting the vibration-jump correlation characteristic verification factor from the vibration-jump correlation characteristic factor of the target shelf.

[0079] The number of historical analysis factors is matched by the vibration-jump correlation characteristic deviation factor.

[0080] In this embodiment, a database pre-stores a mapping between the deviation factors of vibration-jump correlation features and the corresponding number of historical analysis factors. This mapping is managed via a structured mapping table (e.g., a historical matching configuration table). During the matching process, the system first extracts the deviation factor of the target shelf's vibration-jump correlation features and uses this deviation factor as a key value to search the mapping table for the corresponding number of historical analysis factors, thereby quickly determining the size of the historical sample required for weighted calculations. This mapping table is constructed based on long-term monitoring data from the warehouse system and a summary of typical vibration jump samples. The values ​​can be adjusted in real time based on the system's dynamic behavior to enhance the representativeness and accuracy of subsequent feature fusion analysis.

[0081] It should be noted that a larger deviation factor for the vibration-jump correlation characteristic indicates a greater degree of deviation between the target shelf's current vibration jump state and the system's set standard, indicating a more pronounced structural anomaly. To improve the stability and robustness of the analysis results, the system automatically expands the analysis reference dimension, extracting a greater number of corresponding historical analysis factors. This allows for the integration of a richer set of historical data samples for feature trend identification and behavioral pattern comparison, enhancing the accuracy and confidence of jump correlation judgments.

[0082] Based on the number of historical analysis factors, each historical vibration-jump correlation characteristic factor is extracted from the warehouse database. Combined with the vibration-jump correlation characteristic factor analysis of the target shelf, the vibration-jump correlation characteristic weighted average factor of the target shelf is obtained.

[0083] In this embodiment, assuming that the number of historical analysis factors is M, the vibration-jump correlation characteristic factors corresponding to the target shelf for the previous M times are extracted from the warehouse database and recorded as each historical vibration-jump correlation characteristic factor. The historical vibration-jump correlation characteristic factors and the vibration-jump correlation characteristic factors of the target shelf are comprehensively recorded as each vibration-jump correlation characteristic factor to be processed. A weighted average analysis is performed based on the weighted rules pre-set in the warehouse database to obtain the weighted average factor of the vibration-jump correlation characteristics of the target shelf.

[0084] It should be added that, in this embodiment, the weighting rule is a time-decay weighting rule, that is, the closer the vibration-jump correlation characteristic factor is to the current moment, the higher its weight is, and the earlier the historical factor occurs, the lower its weight is.

[0085] It should also be noted that in specific embodiments, different weighting rules can be selected for feature factor fusion processing based on different application scenarios, jump behavior types, data stability requirements, and historical data validity. For example, linear weighting, sliding average, confidence-driven weighting, etc. can all be configured and adjusted according to system requirements. Therefore, the time-decay weighting rule adopted in this embodiment is only one of the preferred examples and does not limit the implementation method of the present invention.

[0086] When the weighted average factor of the vibration-jump correlation feature of the target shelf exceeds the vibration-jump correlation feature verification factor, the first adaptation solution is recorded as executing timing adjustment.

[0087] If the weighted average factor of the vibration-jump correlation feature of the target shelf exceeds the vibration-jump correlation feature verification factor, it means that the weighted average result calculated by combining historical data with current data shows that the degree of correlation between the vibration and jump of the shelf has exceeded the preset reasonable range, and there are persistent or significant structural vibration-related problems. It is necessary to optimize the monitoring and judgment of the shelf status by performing timing adjustments (such as adjusting the sampling frequency, adding a jump confirmation time window, etc.) to reduce the impact of abnormalities.

[0088] Timing adjustment, the specific execution process is as follows:

[0089] The weighted average deviation factor of the vibration-jump correlation feature of the target shelf is obtained by performing difference processing on the weighted average factor of the vibration-jump correlation feature and the verification factor of the vibration-jump correlation feature.

[0090] Difference processing refers to subtracting the vibration-jump correlation feature verification factor from the weighted average factor of the vibration-jump correlation feature of the target shelf.

[0091] The timing adjustment set is matched from the warehouse database based on the weighted average deviation factor of the vibration-jump correlation feature.

[0092] In this embodiment, a mapping relationship between the weighted average deviation factor of the vibration-jump correlation feature and the corresponding timing adjustment set is pre-established in the database. This mapping relationship is centrally managed through a structured mapping table (e.g., a timing adjustment configuration table). During the matching process, the system first extracts the weighted average deviation factor of the vibration-jump correlation feature of the target shelf and uses it as a key value to query the mapping table for the corresponding timing adjustment set, including the sampling frequency reduction value and the jump confirmation time window supplement value. This mapping table is established based on a large number of historical vibration jump events and their adjustment effects. The parameters support dynamic update to ensure that the selected adjustment strategy can achieve accurate and efficient timing control optimization for different deviation levels.

[0093] The timing adjustment set includes a sampling frequency reduction value and a transition confirmation time window supplement value.

[0094] The timing adjustment of the target shelf is performed based on the timing adjustment set, specifically: the current sampling frequency and the current jump confirmation time window are extracted from the system program log, the sum of the current sampling frequency and the sampling frequency reduction value is used as the execution sampling frequency, and the sum of the current jump confirmation time window and the jump confirmation time window supplement value is used as the execution jump confirmation time window.

[0095] It should be added that, in a specific embodiment, if the execution sampling frequency obtained by analysis is lower than the minimum allowable sampling frequency preset in the warehouse database, it is executed at the minimum allowable sampling frequency. Similarly, if the execution jump confirmation time window obtained by analysis is higher than the maximum allowable jump confirmation time window preset in the warehouse database, it is executed at the maximum allowable jump confirmation time window.

[0096] When the weighted average factor of the vibration-jump correlation feature of the target shelf does not exceed the vibration-jump correlation feature verification factor, the first adaptation solution is recorded as generating prompt information.

[0097] If the weighted average factor of the target shelf's vibration-jump correlation characteristic does not exceed the vibration-jump correlation characteristic verification factor, this indicates that the correlation level, based on the historical and current vibration-jump correlation data, is within the preset reasonable range and has not yet reached the level that requires timing adjustment. At this point, the first adaptation solution is recorded as generating a prompt message to remind relevant personnel to pay attention to the shelf's status so that they can be aware of potential changes in a timely manner. However, no immediate adjustment is required.

[0098] The second adaptation scheme analysis module is used to analyze the credibility index of the target shelf's item changes when the short-term state jump associated information of the target shelf is non-shelf structure vibration, and simultaneously analyze the number of consistency in the direction of item changes on the target shelf, thereby extracting the credibility constraint factor, and analyzing the second adaptation scheme in combination with the credibility index of the target shelf's item changes.

[0099] like Figure 4 As shown, this is a flowchart of the credibility judgment and jump processing of item changes involved in an embodiment of the present invention. The process collects the pressure, distance and weight changes of the target shelf, calculates the credibility index and directional consistency quantity of the item change, matches the credibility constraint factor, and comprehensively generates the item change credibility constraint index. Based on the comparison results of the index with the preset first and second thresholds, the system executes different processing strategies such as updating the credibility jump record, generating an early warning prompt or entering the confirmation process.

[0100] Furthermore, the reliability index of the item changes on the target shelf is analyzed. The analysis process is as follows:

[0101] Collect the parameters representing item changes on the target shelf and analyze the factors representing item changes on the target shelf.

[0102] The parameters representing the item change of the target shelf include the pressure change amplitude, distance change amplitude, and weight change amplitude of the target shelf.

[0103] In this embodiment, the pressure amplitude reflects the degree of disturbance to the stress state of the shelf or structure caused by the entry and exit of items. Pressure sensors installed on the shelf floor or load-bearing unit capture real-time pressure change data. Combined with the pre- and post-change comparison analysis window set in the warehouse database, the maximum pressure change within that time period is extracted as the pressure amplitude.

[0104] The distance change amplitude is obtained in real time by a laser ranging or ultrasonic sensor installed directly above or in front of the shelf to obtain the distance value between the surface of the object and the sensor. The difference in distance before and after the jump is the distance change amplitude.

[0105] Weight variation, measured by the overall mass change of items, is captured by the weighing module within the shelf, reflecting the direct impact of actual inbound / outbound operations on the load. Weight data is collected by a high-precision weighing unit (such as a strain gauge or electromagnetic force compensation type).

[0106] The item variation characterization factors of the target shelf include the pressure variation proportional coefficient, the distance variation proportional coefficient, and the weight variation proportional coefficient of the target shelf.

[0107] The reference pressure change amplitude, reference distance change amplitude, and reference weight change amplitude stored in the database are extracted.

[0108] The pressure change amplitude proportional coefficient is the numerical result of dividing the pressure change amplitude by the reference pressure change amplitude, the distance change amplitude proportional coefficient is the numerical result of dividing the distance change amplitude by the reference distance change amplitude, and the weight change amplitude proportional coefficient is the numerical result of dividing the weight change amplitude by the reference weight change amplitude.

[0109] The target shelf's item change credibility index is obtained by weighted coupling processing of the target shelf's pressure change amplitude proportional coefficient, distance change amplitude proportional coefficient, and weight change amplitude proportional coefficient using the weighted measurement coefficients preset in the warehouse database.

[0110] The weighted measurement coefficients of the pressure variation proportional coefficient, the distance variation proportional coefficient and the weighted measurement coefficient of the weight variation proportional coefficient preset in the database are extracted.

[0111] To achieve weighted fusion of item change credibility indicators, multiple mapping relationships are pre-established in the database, associating different change representation parameters with their corresponding weighted measurement coefficients. These mapping relationships are managed in structured data tables (such as a credibility weighted configuration table), which records the weighted measurement coefficients corresponding to the pressure change amplitude proportional coefficient, the distance change amplitude proportional coefficient, and the weight change amplitude proportional coefficient. This configuration table is combined with a large number of measured in-and-out samples and false trigger event samples in the warehouse environment through associative queries to construct a complete credibility assessment model. Based on this model, the system extracts weighted measurement coefficients from the database that match the current status change characteristics of the target shelf items. These are used in the subsequent fusion calculation of credibility indicators. The value range of each weighted measurement coefficient is limited to 0 to 1, and the sum of the three is 1. This ensures the normalization of the multi-factor comprehensive credibility analysis results and the physical rationality of the relative weights.

[0112] The target shelf item change credibility index is a quantitative representation of the impact of the target shelf's pressure change amplitude proportional coefficient, distance change amplitude proportional coefficient, and weight change amplitude proportional coefficient on the credibility of the target shelf's short-term state jump.

[0113] In a specific embodiment, the reliability index of the item change of the target shelf is specifically expressed as:

[0114] ,

[0115] Among them, B is the credibility index of the item change of the target shelf, d is the pressure change amplitude proportional coefficient, f is the distance change amplitude proportional coefficient, g is the weight change amplitude proportional coefficient, y1 is the weighted measurement coefficient of the pressure change amplitude proportional coefficient, y2 is the weighted measurement coefficient of the distance change amplitude proportional coefficient, and y3 is the weighted measurement coefficient of the weight change amplitude proportional coefficient.

[0116] Furthermore, we analyze the consistency of the change direction of items on the target shelf. The specific analysis process is as follows:

[0117] Set the condition tags, including the first condition, the second condition, and the third condition.

[0118] The state where the parameter change amplitude is positive is recorded as satisfying the first condition, the state where the parameter change amplitude is negative is recorded as satisfying the second condition, and the state where the parameter change amplitude is zero is recorded as satisfying the third condition.

[0119] Analyze the condition labels of the target shelf's item change characterization parameters, count the number of items that meet each condition, and use the number corresponding to the condition that meets the most conditions as the consistency number of item change directions for the target shelf.

[0120] In a specific embodiment, the pressure change amplitude in the item change characterization parameters of a certain target shelf is positive, satisfying the first condition, the distance change amplitude is negative, satisfying the second condition, and the weight change amplitude is negative, satisfying the second condition. After statistics, the number of items that meet the first condition is 1, the number that meet the second condition is 2, and the number that meet the third condition is 0. Therefore, the number of item change direction consistency of the target shelf is 2.

[0121] It should be added that if in a specific embodiment, the item change characterization parameters of a target shelf happen to have the following situation: the number that meets the first condition is 1, the number that meets the second condition is 1, and the number that meets the third condition is 1, a prompt message is directly generated without subsequent processing.

[0122] Further, the second adaptation solution is analyzed. The specific analysis process is as follows:

[0123] The credibility constraint factor is matched based on the consistency of the quantity of item change directions on the target shelf.

[0124] In this embodiment, a mapping relationship between the number of consistent item change directions and corresponding credibility constraint factors is pre-established in the database. This mapping relationship is managed via a structured mapping table (e.g., a credibility constraint configuration table). During the matching process, the system first obtains the number of consistent item change directions on the target shelf. Using this number as a key, it searches the mapping table for the corresponding credibility constraint factor, thereby implementing a quantitative constraint on the credibility of item change behavior. This mapping table is constructed based on historical item change data and empirical rules, and the values ​​can be dynamically adjusted based on actual application scenarios to ensure accuracy and flexibility in credibility determination.

[0125] It's important to note that the greater the number of consistent item change directions on the target shelf, the stronger the consistency of the parameter change directions in the current jump event, indicating a higher likelihood of a credible change. To improve the accuracy of credible jump determinations, the corresponding extracted credibility constraint factor is also increased, thereby strengthening the decision weight of credible determinations in multi-parameter consistency scenarios.

[0126] The credibility constraint index of the target shelf's item change is analyzed based on the credibility constraint factor and the target shelf's item change credibility index.

[0127] In this embodiment, the target shelf item change credibility constraint index is a numerical result of the product of the credibility constraint factor and the target shelf item change credibility index.

[0128] The first threshold value of the item change credibility constraint index and the second threshold value of the item change credibility constraint index stored in the warehouse database are extracted.

[0129] It should be explained that the first threshold value of the item change credibility constraint index is greater than the second threshold value of the item change credibility constraint index.

[0130] If the item change credibility constraint index of the target shelf is greater than or equal to the first threshold of the item change credibility constraint index, the second adaptation solution is recorded as updating the credibility jump record.

[0131] If the target shelf's item change credibility constraint index is greater than or equal to the first threshold, the shelf's item change, after adjustment by the credibility constraint factor, has reached a high level of credibility, confirming that the item change is authentic and valid. Therefore, the system records the second adaptation solution as an updated credibility transition record to reflect the actual item change status on the shelf.

[0132] If the item change credibility constraint index of the target shelf is less than or equal to the second threshold value of the item change credibility constraint index, the second adaptation solution is recorded as generating early warning prompt information.

[0133] If the target shelf's item change credibility constraint index is less than or equal to the second threshold, the credibility of the shelf's item change is extremely low, and the item change is likely caused by a misjudgment or abnormal interference. The system then generates a warning message for the second adaptation solution, alerting relevant personnel to investigate and resolve any potential issues.

[0134] If the item change credibility constraint index of the target shelf is less than the first threshold of the item change credibility constraint index and greater than the second threshold of the item change credibility constraint index, the second adaptation solution is recorded as the execution confirmation process.

[0135] If the target shelf's item change credibility constraint index is less than the first threshold and greater than the second threshold, the credibility of the shelf's item change is moderate. The authenticity of the change cannot be fully confirmed, nor can it be directly determined as a false positive or anomaly. Therefore, the system marks the second adaptation solution as the execution confirmation process, and through further repeated analysis and verification, it ultimately confirms the authenticity of the item change.

[0136] Furthermore, the confirmation process is executed. The specific execution process is as follows:

[0137] The item change credibility constraint index of the target shelf is subjected to difference processing with the second threshold value of the item change credibility constraint index to obtain the item change credibility constraint deviation index of the target shelf.

[0138] It should be explained that the difference processing refers to subtracting the second threshold value of the item change credibility constraint index from the item change credibility constraint index of the target shelf.

[0139] The confirmation cycle number is extracted from the warehouse database through the credibility constraint deviation index of the item change of the target shelf.

[0140] In this embodiment, a mapping relationship between item change credibility constraint deviation indicators and confirmation cycle times is pre-established in the warehouse database. This mapping relationship is managed in the form of a structured mapping table (e.g., a confirmation cycle configuration table). During the matching process, the system first calculates the item change credibility constraint deviation indicator for the target shelf. Using this deviation indicator as a query key, it retrieves the corresponding confirmation cycle number from the mapping table to determine the time window required for repeated verification. This mapping table is set based on historical verification data and operational experience, and supports dynamic adjustment to ensure the scientific and effective nature of the confirmation process.

[0141] It should be noted that a larger deviation index indicates a higher level of credibility constraint deviation for item changes on the target shelf, which generally indicates a higher degree of unreliability for the current jump event. To improve system response efficiency and avoid over-verification, the corresponding number of extracted confirmation cycles will be smaller.

[0142] The item change credibility constraint index of the target shelf is repeatedly analyzed based on the number of confirmation cycles to obtain the item change credibility constraint index.

[0143] In a specific embodiment, assuming that the number of confirmation cycles extracted from the warehouse database is N times, then in each of the subsequent N cycles, the above-mentioned item change credibility constraint index analysis steps are repeated to obtain the item change credibility constraint index of the target shelf corresponding to each cycle, and the item change credibility constraint index of the target shelf corresponding to each cycle is marked as each item change credibility constraint index.

[0144] The item change credibility constraint verification index of the target shelf is obtained by performing a weighted average based on the item change credibility constraint index of each item and the item change credibility constraint index of the target shelf.

[0145] If the item change credibility constraint verification index of the target shelf is greater than or equal to the first threshold of the item change credibility constraint index, it is recorded as a credible jump and the record is updated.

[0146] If the target shelf's item change credibility constraint verification index is greater than or equal to the first threshold, it indicates that after repeated analysis and weighted average verification, the shelf's item change has been confirmed to have a sufficiently high degree of credibility and is a valid item change. Therefore, the system records this as a credible jump and updates the relevant records to accurately reflect the shelf's actual inventory change status.

[0147] If the item change credibility constraint verification index of the target shelf is less than the first threshold value of the item change credibility constraint index, an early warning prompt message is generated.

[0148] If the target shelf's item change credibility constraint verification index is less than the first threshold, this indicates that even after repeated analysis and weighted average verification, the shelf's item changes are still not sufficiently reliable and cannot be verified as genuine. The system then generates a warning message to remind relevant personnel to further verify the shelf's item changes to avoid erroneous records that could impact inventory management accuracy.

[0149] like Figure 5 As shown, it is the homepage of the intelligent warehouse management system involved in the embodiment of the present invention, which visually displays the overall status of the current warehouse, including inbound and outbound records, shelf distribution and remaining space, warehouse inventory analysis and inventory value.

[0150] like Figure 6 As shown, it is an inventory management interface diagram of the intelligent warehouse management system involved in an embodiment of the present invention, which visually displays the current system storage list and inventory warning.

[0151] like Figure 2 The flowchart of the method for automated inventory management of intelligent warehousing based on the Internet of Things is shown, which provides a method for automated inventory management of intelligent warehousing based on the Internet of Things. The method includes:

[0152] Monitor each shelf in the warehouse, analyze the existence of short-term state jump information, and record the shelves with short-term state jumps as target shelves.

[0153] Within the preset monitoring window, the vibration-jump correlation characteristic factors of the target shelf are analyzed to determine the short-term state jump correlation information of the target shelf.

[0154] When the short-term state jump associated information of the target shelf is shelf structure vibration, the first adaptation solution is analyzed in combination with the historical vibration-jump associated characteristic factors of the target shelf.

[0155] When the short-term state jump associated information of the target shelf is non-shelf structure vibration, the credibility index of the item change of the target shelf is analyzed, and the consistency of the direction of the item change of the target shelf is simultaneously analyzed to extract the credibility constraint factor. The second adaptation plan is analyzed in combination with the credibility index of the item change of the target shelf.

[0156] The above embodiments can be implemented in whole or in part via software, hardware (e.g., circuits), firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product comprises one or more computer instructions or computer programs. When loaded or executed on a computer, the processes or functions described in accordance with the embodiments of the present invention are fully or partially performed. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired means (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium accessible by a computer or a data storage device such as a server or data center that contains a collection of one or more available media. The available medium can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., DVDs), or semiconductor media. The semiconductor media can be a solid-state drive.

[0157] It should be understood that the term "and / or" as used herein simply describes a relationship between associated objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A alone, A and B together, or B alone. A and B can be singular or plural. Furthermore, the character " / " as used herein generally indicates an "or" relationship between the associated objects, but it may also indicate an "and / or" relationship. For specific understanding, please refer to the context.

[0158] In this disclosure, "at least one" means one or more, and "plurality" means two or more. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, "at least one of a, b, or c" can mean: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or plural.

[0159] It should be understood that in various embodiments of the present invention, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0160] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present invention.

[0161] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described equipment, devices and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0162] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0163] If the functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, or the portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage media include various media that can store program code, such as USB flash drives, mobile hard drives, read-only memories (ROM), random access memories (RAM), magnetic disks, or optical disks.

[0164] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any modifications or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present invention should be included in the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be based on the scope of protection of the claims.

Claims

1. The intelligent warehouse automation inventory management system based on the Internet of Things is characterized by: The system comprises: The short-term state jump existence information analysis module is used to monitor each shelf in the warehouse, analyze the short-term state jump existence information, and record the shelf with short-term state jump as the target shelf; A short-term state jump correlation information determination module is used to analyze the vibration-jump correlation characteristic factor of the target shelf within a preset monitoring window and determine the short-term state jump correlation information of the target shelf; A first adaptation solution analysis module is configured to analyze a first adaptation solution based on a historical vibration-jump correlation characteristic factor of the target shelf when the short-term state jump correlation information of the target shelf is shelf structure vibration; The second adaptation scheme analysis module is used to analyze the credibility index of the target shelf's item changes when the short-term state jump associated information of the target shelf is non-shelf structure vibration, and simultaneously analyze the number of consistency in the direction of item changes on the target shelf, thereby extracting the credibility constraint factor, and analyzing the second adaptation scheme in combination with the credibility index of the target shelf's item changes.

2. The intelligent warehouse automation inventory management system based on the Internet of Things according to claim 1 is characterized in that: The analysis of the short-term state jump information is as follows: Within a preset time window, obtain the number of short-term state transitions of each shelf in the warehouse; The short-term state jump refers to the state change behavior in which the state of the shelf switches repeatedly within the continuous monitoring time window, and the state duration after each switch is less than the preset jump confirmation time window; Extracting the short-term state transition count threshold preset in the database; If the number of short-term state transitions of a shelf is less than the short-term state transition threshold, the short-term state transition information of the shelf is recorded as no short-term state transition. If the number of short-term state transitions of a shelf is greater than or equal to the short-term state transition threshold, the short-term state transition existence information of the shelf is recorded as the existence of a short-term state transition.

3. The intelligent warehouse automation inventory management system based on the Internet of Things according to claim 1 is characterized in that: The determination process of the target shelf short-term state jump associated information is as follows: In a preset monitoring window, a set of vibration-jump correlation characteristic parameters of the target shelf is collected, and the vibration-jump correlation characteristic factor of the target shelf is obtained by analysis; Extract the vibration-jump correlation feature verification factors preset in the storage database; When the vibration-jump correlation characteristic factor of the target shelf exceeds the vibration-jump correlation characteristic verification factor, the determination result of the short-term state jump correlation information of the target shelf is recorded as the shelf structure vibration, and an interception jump control instruction is generated; When the vibration-jump correlation characteristic factor of the target shelf does not exceed the vibration-jump correlation characteristic verification factor, the determination result of the short-term state jump correlation information of the target shelf is recorded as non-shelf structure vibration.

4. The intelligent warehouse automation inventory management system based on the Internet of Things according to claim 3 is characterized in that: The specific analysis process of the vibration-jump correlation characteristic factor of the target shelf is as follows: The vibration-jump associated characteristic parameter set of the target shelf includes a vibration amplitude peak proportional factor, a jump-vibration main frequency matching proportional factor, and a jump-vibration timing coupling proportional factor; The vibration amplitude peak proportional factor, the jump-vibration main frequency matching proportional factor, and the jump-vibration timing coupling proportional factor are weightedly coupled using the weighted measurement factors preset in the warehouse database to obtain the vibration-jump correlation characteristic factor of the target shelf. The vibration-jump correlation characteristic factor of the target shelf is a quantitative representation of the vibration-jump correlation degree of the target shelf, which is a combination of the vibration amplitude peak proportional factor, the jump-vibration main frequency matching proportional factor and the jump-vibration timing coupling proportional factor.

5. The intelligent warehouse automation inventory management system based on the Internet of Things according to claim 1 is characterized in that: The first adaptation solution is analyzed by combining the historical vibration-jump correlation characteristic factors of the target shelf. The specific analysis process is as follows: The vibration-jump correlation characteristic factor of the target shelf is subjected to difference processing with the vibration-jump correlation characteristic verification factor to obtain the vibration-jump correlation characteristic deviation factor; Match the number of historical analysis factors by the vibration-jump correlation characteristic deviation factor; Based on the number of historical analysis factors, each historical vibration-jump correlation characteristic factor is extracted from the warehouse database, and the vibration-jump correlation characteristic factor of the target shelf is combined with the analysis of the target shelf's vibration-jump correlation characteristic factor to obtain the target shelf's vibration-jump correlation characteristic weighted average factor; When the weighted average factor of the vibration-jump correlation feature of the target shelf exceeds the vibration-jump correlation feature verification factor, the first adaptation scheme is recorded as executing the timing adjustment; The specific execution process of the timing adjustment is as follows: The weighted average deviation factor of the vibration-jump correlation feature of the target shelf is obtained by performing difference processing on the weighted average factor of the vibration-jump correlation feature and the verification factor of the vibration-jump correlation feature; Matching the timing adjustment set from the storage database based on the weighted average deviation factor of the vibration-jump correlation feature; The timing adjustment set includes a sampling frequency reduction value and a jump confirmation time window supplement value; Execute timing adjustment of the target shelf based on the timing adjustment set; When the weighted average factor of the vibration-jump correlation feature of the target shelf does not exceed the vibration-jump correlation feature verification factor, the first adaptation solution is recorded as generating prompt information.

6. The intelligent warehouse automation inventory management system based on the Internet of Things according to claim 1 is characterized in that: The analysis process of the reliability index of the item change of the target shelf is as follows: Collect the parameters representing the change of items on the target shelf and analyze the factors representing the change of items on the target shelf; The target shelf item change characterization parameters include the target shelf pressure change amplitude, distance change amplitude, and weight change amplitude; The item change characterization factors of the target shelf include a pressure change amplitude proportional coefficient, a distance change amplitude proportional coefficient, and a weight change amplitude proportional coefficient of the target shelf; The target shelf's item change reliability index is obtained by weighted coupling processing of the target shelf's pressure change amplitude proportional coefficient, distance change amplitude proportional coefficient, and weight change amplitude proportional coefficient using the weighted measurement coefficients preset in the warehouse database. The target shelf item change credibility index is a quantitative representation of the impact of the target shelf's pressure change amplitude proportional coefficient, distance change amplitude proportional coefficient, and weight change amplitude proportional coefficient on the target shelf's short-term state jump credibility.

7. The intelligent warehouse automation inventory management system based on the Internet of Things according to claim 6 is characterized in that: The specific analysis process of analyzing the consistency of the change direction of items on the target shelf is as follows: Set condition tags, including the first condition, the second condition, and the third condition; The state where the parameter change amplitude is positive is recorded as satisfying the first condition, the state where the parameter change amplitude is negative is recorded as satisfying the second condition, and the state where the parameter change amplitude is zero is recorded as satisfying the third condition; Analyze the condition labels of the target shelf's item change characterization parameters, count the number of items that meet each condition, and use the number corresponding to the condition that meets the most conditions as the consistency number of item change directions for the target shelf.

8. The intelligent warehouse automation inventory management system based on the Internet of Things according to claim 1 is characterized in that: The analysis of the second adaptation solution is as follows: The credibility constraint factor of the quantity matching based on the consistency of the item change direction of the target shelf; Analyze the item change credibility constraint index of the target shelf according to the credibility constraint factor and the item change credibility index of the target shelf; Extracting a first threshold value of an item change credibility constraint index and a second threshold value of an item change credibility constraint index stored in a storage database; If the item change credibility constraint index of the target shelf is greater than or equal to the first threshold of the item change credibility constraint index, the second adaptation solution is recorded as updating the credibility jump record; If the item change credibility constraint index of the target shelf is less than or equal to the second threshold value of the item change credibility constraint index, the second adaptation solution is recorded as generating early warning prompt information; If the item change credibility constraint index of the target shelf is less than the first threshold of the item change credibility constraint index and greater than the second threshold of the item change credibility constraint index, the second adaptation solution is recorded as the execution confirmation process.

9. The intelligent warehouse automation inventory management system based on the Internet of Things according to claim 8 is characterized in that: The execution confirmation process is specifically executed as follows: Performing a difference process on the item change credibility constraint index of the target shelf and the second threshold value of the item change credibility constraint index to obtain the item change credibility constraint deviation index of the target shelf; The confirmation cycle number is extracted from the warehouse database through the credibility constraint deviation index of the item change of the target shelf; Repeatedly analyze the item change credibility constraint index of the target shelf based on the number of confirmation cycles to obtain the item change credibility constraint index; Based on the weighted average of the item change credibility constraint index of each item and the item change credibility constraint index of the target shelf, the item change credibility constraint verification index of the target shelf is obtained; If the item change credibility constraint verification index of the target shelf is greater than or equal to the first threshold of the item change credibility constraint index, it is recorded as a credible jump and the record is updated; If the item change credibility constraint verification index of the target shelf is less than the first threshold value of the item change credibility constraint index, an early warning prompt message is generated.

10. An intelligent warehouse automation inventory management method based on the Internet of Things, wherein the intelligent warehouse automation inventory management method based on the Internet of Things is used to implement the intelligent warehouse automation inventory management system based on the Internet of Things according to any one of claims 1 to 9, characterized in that: The following steps are involved: Monitor each shelf in the warehouse, analyze the existence of short-term state jump information, and record the shelves with short-term state jumps as target shelves; Within the preset monitoring window, the vibration-jump correlation characteristic factors of the target shelf are analyzed to determine the short-term state jump correlation information of the target shelf; When the short-term state jump associated information of the target shelf is shelf structure vibration, the first adaptation solution is analyzed in combination with the historical vibration-jump associated characteristic factors of the target shelf; When the short-term state jump associated information of the target shelf is non-shelf structure vibration, the credibility index of the item change of the target shelf is analyzed, and the consistency of the direction of the item change of the target shelf is simultaneously analyzed to extract the credibility constraint factor. The second adaptation plan is analyzed in combination with the credibility index of the item change of the target shelf.

Images