Intelligent stereoscopic warehouse inventory data synchronization method and device and computer program product

Abstract

The invention discloses an intelligent stereoscopic warehouse inventory data synchronization method and device and a computer program product, and the method comprises the steps: collecting multi-source data of an intelligent stereoscopic warehouse, and constructing a multivariate data set; embedding the multivariate data set into a nonlinear mapping space, and constructing an embedded state vector for expressing inventory behaviors; a scheduling weight evaluation function is constructed based on the embedded state vector and historical error feedback, the scheduling weight of the inventory operation is calculated through the scheduling weight evaluation function, a decision is made on the synchronization mode of the inventory operation according to the scheduling weight, and the synchronization mode comprises instant synchronization, delay synchronization or merging synchronization; and based on the scheduling weight and historical error feedback, dynamically correcting the response tension coefficient of each dimension in the embedded state vector, and applying the corrected response tension coefficient to subsequent embedded state vector construction to form a feedback closed loop. According to the invention, a powerful guarantee is provided for efficient, accurate and stable operation of the intelligent warehousing system.

Description

Technical Field

[0001] This invention relates to the field of intelligent warehousing and logistics automation technology, specifically to a method, device, and computer program product for synchronizing inventory data in an intelligent automated warehouse. Background Technology

[0002] With the rapid development of industrial automation and intelligent manufacturing, intelligent automated warehouses have become a core component of modern logistics systems. Their core function is to efficiently handle diverse, high-frequency, and flexible inbound and outbound operations. To achieve the goals of multi-system collaborative operation, precise data flow control, and efficient scheduling, intelligent automated warehouses must not only achieve automated handling and precise storage at the physical level, but also build a real-time perception, precise synchronization, and dynamic feedback mechanism for inventory status at the information level.

[0003] However, the inventory data synchronization process involves interface interactions between multiple heterogeneous systems such as WCS (Warehouse Control System), ERP (Enterprise Resource Planning System), and MES (Manufacturing Execution System), making the data chain extremely complex. During this process, any processing delay, instruction conflict, or feedback lag at any node can directly disrupt the consistency of inventory data, thereby affecting the accuracy of business execution. Summary of the Invention

[0004] The technical problem to be solved by the embodiments of the present invention is to provide a method, device and computer program product for synchronizing inventory data in an intelligent automated warehouse, so as to improve the real-time response capability and status recognition capability of inventory data synchronization in an intelligent automated warehouse, and ensure the high reliability operation of the intelligent automated warehouse.

[0005] To address the aforementioned technical problems, this invention provides a method for synchronizing inventory data in an intelligent automated warehouse, comprising: Step S1: Collect multi-source data from the intelligent automated warehouse and construct a multi-dimensional data set; Step S2: Embed the multivariate data set into a nonlinear mapping space to construct an embedded state vector for expressing inventory behavior; Step S3: Construct a scheduling weight evaluation function based on the embedded state vector and historical error feedback; calculate the scheduling weight of inventory operations using the scheduling weight evaluation function; and make a decision on the synchronization method of inventory operations based on the scheduling weight. The synchronization method includes instant synchronization, delayed synchronization, or merged synchronization. Step S4: Based on the scheduling weight and historical error feedback, dynamically correct the response tension coefficients of each dimension in the embedded state vector, and use the corrected response tension coefficients for subsequent embedded state vector construction to form a feedback closed loop.

[0006] Preferably, the multi-source data collected in step S1 includes the three-dimensional location coordinates of the storage location, the quantity of materials entering and leaving, the operation type, and the event timestamp. The multi-source data set is represented as follows: ,in, The three-dimensional coordinates of the storage location; Indicate quantity; Indicates the operation type; This is the timestamp of the event.

[0007] Preferably, the formula for constructing the embedded state vector in step S2 is:

[0008]

[0009] in, It is the current moment. The embedded state vector; It is the number of dimensions of the embedded state vector. ; yes The first in Each dimension has a component, representing the time interval. The sub-embedding vector is at the 1st Response results in each dimension; It is the first The response tension coefficient in each dimension; It is a moment The event state functions, each Sourced from multivariate datasets ; It is the frequency perturbation coefficient, representing the first... The embedding state of the first dimension is related to the second dimension. The time response frequency of event states in each dimension; It is the phase offset parameter, representing the embedding state of the m-th dimension relative to the... Time response lag or offset angle in each dimension; It is a time-perturbation transformation of the event state.

[0010] Preferably, the event state function Specifically, it includes: This indicates spatial location information; , indicating the number of operations; This indicates the impact of the operation direction; outbound shipments are negative. This indicates the impact of cargo location density; , which represents the offset within minutes of the current event.

[0011] Preferably, the expression for the scheduling weight evaluation function in step S3 is:

[0012]

[0013] in, It is the current moment. The scheduling weight; It is the temperature control coefficient for scheduling; It is a composite evaluation function that aggregates the weighted sum of the current embedded state and the previous round of feedback state; It is the intelligent warehouse system at a specific time point. The error feedback vector, It is the feedback delay time parameter; This indicates the feedback nonlinear amplification power factor; It is the first The feedback response weights of each dimension represent the degree of influence of the current dimension state on the scheduling weights.

[0014] Preferably, the scheduling temperature control coefficient Adjust dynamically based on system load; reduce when system load is high. To suppress excessive event concentration, increase when system load is low. To improve response speed.

[0015] Preferably, the update formula for the response tension coefficient in step S4 is:

[0016] in, It is the first The values ​​of the response tension coefficients in each dimension after the current cycle update are used to calculate the embedded state vector in the next round. Input; It is the feedback learning rate, which represents the strength of the response of the feedback error to the adjustment of the response tension coefficient; The scheduling weight at the current moment Compared with the average scheduling within the current time window The deviation between them Indicates from arrive The average scheduling weight; It is the first The absolute value of the feedback error in the current dimension reflects the current scheduling cycle. The strength of the error in each dimension; It is a power exponent; It is a fuzzy error evaluation function used to evaluate inventory feedback errors. Introduced into feedback regulation.

[0017] Preferably, step S3 further includes: generating a standardized inventory update instruction based on the scheduling weight, and asynchronously sending it to the system interface via a message bus, wherein the sending form includes a REST API or a message queue.

[0018] The present invention also provides an intelligent automated warehouse inventory data synchronization device, comprising: One or more processors; Memory; One or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the one or more processors, and the one or more applications are configured to perform the intelligent automated warehouse inventory data synchronization method.

[0019] The present invention also provides a computer program product, including computer instructions that instruct a computer device to perform an operation corresponding to the method.

[0020] The implementation of this invention has the following beneficial effects: By embedding multi-source data such as three-dimensional spatial information of storage locations, material quantity, operation type, and timestamps into a multi-dimensional nonlinear mapping space, this invention constructs an embedded state vector with disturbance response and time sensitivity characteristics. This overcomes the limitations of linear processing of a single instruction in traditional synchronization mechanisms, enabling more precise capture of differences in the operational states of different storage locations and forming a high-dimensional state feature expression. This significantly improves the scheduling system's sensitivity to local changes and its adaptive control level. Simultaneously, the scheduling weight evaluation function constructed based on the embedded state vector and historical error feedback can dynamically integrate the current state with previous scheduling error information, real-time correcting scheduling priorities and delay strategies. This significantly improves the rationality of scheduling behavior and resource utilization efficiency, effectively reducing system deviations and anomalies such as incorrect or missed material issuance caused by asynchronous updates of inventory data. Furthermore, the dynamic correction mechanism of the response tension coefficient can adjust the nonlinear sensitivity of the state mapping in real time according to error fluctuations, allowing the state expression model to continuously evolve during long-term operation. This adapts to dynamic changes in inventory structure, business rhythm, and environmental load, ensuring the system has high adaptability and long-term stability, providing a strong guarantee for the efficient, accurate, and stable operation of intelligent warehousing systems. Attached Figure Description

[0021] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0022] Figure 1 This is a flowchart illustrating a method for synchronizing inventory data in an intelligent automated warehouse, according to an embodiment of the present invention. Detailed Implementation

[0023] The following description of the embodiments is taken with reference to the accompanying drawings, which illustrate specific embodiments in which the invention can be implemented.

[0024] Please refer to Figure 1 As shown, Embodiment 1 of the present invention provides a method for synchronizing inventory data in an intelligent automated warehouse, comprising: Step S1: Collect multi-source data from the intelligent automated warehouse and construct a multi-dimensional data set; Step S2: Embed the multivariate data set into a nonlinear mapping space to construct an embedded state vector for expressing inventory behavior; Step S3: Construct a scheduling weight evaluation function based on the embedded state vector and historical error feedback; calculate the scheduling weight of inventory operations using the scheduling weight evaluation function; and make a decision on the synchronization method of inventory operations based on the scheduling weight. The synchronization method includes instant synchronization, delayed synchronization, or merged synchronization. Step S4: Based on the scheduling weight and historical error feedback, dynamically correct the response tension coefficients of each dimension in the embedded state vector, and use the corrected response tension coefficients for subsequent embedded state vector construction to form a feedback closed loop.

[0025] Specifically, in step S1, multi-source data is collected to capture real-time location and operation status information in the intelligent automated warehouse, including: three-dimensional location coordinates of the shelves, used to construct spatial embedding vectors; material entry and exit quantities, used to dynamically adjust mapping intensity and scheduling thresholds; operation type, identifying whether the current event is an inbound or outbound action; and event timestamps, providing a reference benchmark for all time transformations, disturbance frequency functions, and feedback delay windows. All collected data undergoes preliminary normalization processing locally at the edge control node to construct a multi-source data set.

[0026] During the preprocessing stage, uniform encoding is used to form multi-dimensional data groups. ,in, The three-dimensional coordinates of the storage location; Indicate quantity; Indicates the operation type; The timestamp (in seconds) of the event.

[0027] Step S2 embeds the constructed multi-data set into a nonlinear mapping space to form an embedded state vector with disturbance response and time sensitivity characteristics, which is used to express complex inventory behavior; that is, the linear structure of the storage space + operation state data is projected into a highly nonlinear abstract space, so that the subsequent scheduling weights no longer present a direct linear response, but are sensitive to asymmetric distribution, temporal coupling and operation conflicts.

[0028] Specifically, to achieve refined responses to different combinations of storage location and operational states, a mathematical function is constructed to nonlinearly embed storage location space, operational information, and temporal state into a multidimensional scheduling evaluation vector, using multivariate data sets. Based on this, a set of event state functions are derived. This represents the different physical characteristics of an event at the current moment, such as spatial density, operational direction intensity, and material quantity. For each embedded dimension... By dynamically perturbing the input state function using a set of frequency perturbation coefficients and phase offset parameters, and then combining power transform and logarithmic compression, the first... The embedded response, where all dimensions are embedded, forms an embedded state vector. Its construction path reflects a series of mathematical transformation mechanisms, including frequency interference, multi-level nesting, and nonlinear scaling, thereby constructing an evaluation basis vector with nonlinear response capability and strong feedback sensitivity to scheduling behavior. The formula for the embedded state vector is:

[0029]

[0030] in, It is the current moment. The embedded state vector is a A dimensional vector represents the high-dimensional state mapping result of an event. yes The first in Each dimension has a component, representing the time interval. The sub-embedding vector is at the 1st Response results in each dimension; It is the number of dimensions of the embedded state vector; It is the first The response tension coefficient of each dimension is used to control the response capability of the current dimension to the intensity of disturbance. The larger the value, the more nonlinear the output. It is a moment The event state function, with dimensions of Each item corresponds to a state type, and each Sourced from multivariate datasets Specifically: Indicates spatial location information; Indicates the number of operations; This indicates the impact of the operation direction (negative for outbound shipments); Indicates the impact of cargo location density; This represents the offset within minutes of the current event, used for periodic perturbations; the rest... It can be extended to environmental variables such as system temperature and equipment status; It is the frequency perturbation coefficient, representing the first... The embedding state of the first dimension is related to the second dimension. The time response frequency of event states in each dimension; It is the phase offset parameter, representing the embedding state of the m-th dimension relative to the... Time response lag or offset angle in each dimension; It is a temporal perturbation transformation of the event state, making It exhibits temporal instability and frequency response variation, enhancing the non-stationarity of the mapping.

[0031] In step S3, a scheduling weight evaluation function is constructed based on the embedded state vector and historical feedback state. By integrating the current state and error information, the priority of each inventory operation is dynamically calculated, enabling decisions on delaying, merging, or instant synchronization of inventory events, thus making the system scheduling timely and stable.

[0032] Specifically, based on the embedded state vector, an evaluation method is constructed to determine whether event delay, merging, or preprocessing should be performed in the current state. This method can simultaneously receive the current embedded state vector and historical scheduling feedback, outputting scheduling weights that represent the driving strength of scheduling behavior. The composite evaluation function is defined as a weighted nonlinear power sum of the products of the current embedded state vector and the historical feedback vector in each dimension. The feedback term originates from the error record of the previous cycle, giving the composite evaluation function historical sensitivity. Control factors are used to amplify or suppress the influence of different state dimensions on the feedback term. The final calculated composite evaluation function value is then passed to a Sigmoid function to output the scheduling weights, with a value of [value missing]. The closer the value is to 1, the higher the scheduling priority after combining the current state and feedback; the closer it is to 0, the more acceptable the event is to be delayed or merged. The scheduling weight function takes the following form:

[0033]

[0034] in, It is the current moment. The scheduling weight indicates whether to perform a scheduling operation on the current event; the closer it is to 1, the higher the priority. It is the temperature control coefficient that controls the response speed of the intelligent automated warehouse system to the current state and feedback intensity; It is a composite evaluation function that aggregates the weighted sum of the current embedded state and the feedback state from the previous round. The larger the value, the stronger the importance of the current event to the scheduling system. It is the intelligent warehouse system at a specific time point. The error feedback vector represents the error estimate between the system scheduling result and the actual execution result in the previous one or more preceding scheduling cycles. Each component in Corresponding embedded state vector Error signals of the same dimension in the middle, It is a feedback delay time parameter used to synchronize the data acquisition and processing delays between multiple systems; This represents the feedback nonlinear amplification power factor, used to enhance the influence of strong feedback in scheduling and avoid linear decay. It is the first The feedback response weights for each dimension represent the influence of the current dimension's state on the scheduling weights. These weights are estimated through system training or field experience, for example, they can be calculated from the feature contribution of a decision tree. (Schedule temperature control coefficient) This indicates the "execution sensitivity" of the entire system in the current scheduling cycle. When the system load is high (e.g., the number of device scheduling threads reaches its limit), it indicates the sensitivity of the system. Automatically reduce to suppress excessive event concentration, otherwise increase to improve system response.

[0035] Step S4 will dynamically adjust the response tension coefficients of each dimension of the state based on the scheduling weight and historical error feedback, so as to achieve adaptive optimization of state modeling. The adjusted response tension coefficients will be used for the state expression and scheduling evaluation in the next cycle, thereby forming a feedback closed loop and driving the intelligent warehouse system to continuously optimize the inventory synchronization accuracy and scheduling efficiency.

[0036] The output value of the scheduling weight function in the current period is not only used to control the synchronous scheduling decision of inventory status, but also serves as one of the feedback factors to participate in the dynamic correction of the response tension coefficients of each dimension in the embedded state vector. Each dimension's response tension coefficient controls the projection intensity of the embedded state vector onto the current dimension's state, directly affecting the nonlinear disturbance amplitude of the state embedding vector. During the operation of the intelligent automated warehouse system, if the inventory status of a certain dimension continuously causes a large data synchronization deviation over multiple periods, it is necessary to improve the tension response capability of the current dimension to enhance the sensitivity of the embedded state vector to the current state. Therefore, a nonlinear update function based on the weight calculation of historical scheduling weight deviation and feedback error is defined to achieve automatic dynamic adjustment of the response tension coefficients. The update function is as follows:

[0037] in, It is the first The values ​​of the response tension coefficients in each dimension after the current cycle update are used to calculate the embedded state vector in the next round. Input; It is the feedback learning rate, which represents the strength of the response of the feedback error to the adjustment of the response tension coefficient; The scheduling weight at the current moment Compared with the average scheduling within the current time window The deviation between them Indicates from arrive The average scheduling weight can be calculated using a sliding window in practice. It is the first The absolute value of the feedback error in the current dimension reflects the current scheduling cycle. The strength of the error in each dimension; It is a power exponent, used to enhance the adjustment range in the large error range and avoid excessive amplification of small error disturbances; It is a fuzzy error evaluation function used to evaluate inventory feedback errors. Feedback adjustment is introduced, but mathematical anomalies are avoided when the error is zero, while the rate of error input growth is controlled. The above update process is executed at the end of each scheduling cycle, ensuring that the embedded state vector continuously and adaptively adjusts based on historical behavior, thereby continuously optimizing the state representation capability and the accuracy of system anomaly recognition.

[0038] The response tension coefficient obtained from the final update will be immediately used to update the calculation of the embedded state vector for the next cycle, thereby recalculating the embedded state vector of each location-operation unit at the current moment. The embedded state vector will output a new scheduling priority and batching strategy through the scheduling weight function.

[0039] Based on the scheduling weight, it determines whether the inventory operations (inbound or outbound) for the current batch should be executed immediately, delayed, or merged; a standardized inventory update instruction is generated and asynchronously sent to system interfaces such as ERP and MES via the message bus, pushed in the form of REST API or message queue; therefore, The updates directly drive the behavioral decisions of synchronization events, enabling the system to have adaptive scheduling and precise data synchronization capabilities, thereby achieving real-time, accurate, and stable intelligent warehouse inventory data synchronization.

[0040] Corresponding to the intelligent automated warehouse inventory data synchronization method described in Embodiment 1 of the present invention, Embodiment 2 of the present invention also provides an intelligent automated warehouse inventory data synchronization device, comprising: One or more processors; Memory; One or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the one or more processors, and the one or more applications are configured to perform the intelligent automated warehouse inventory data synchronization method described in Embodiment 1 of the present invention.

[0041] Corresponding to the intelligent automated warehouse inventory data synchronization method described in Embodiment 1 of the present invention, Embodiment 3 of the present invention also provides a computer program product, including computer instructions, which instruct a computer device to perform the operation corresponding to the intelligent automated warehouse inventory data synchronization method described in Embodiment 1 of the present invention.

[0042] Preferably, the processor can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor, or the processor can be any conventional processor. The processor is the control center of the device, connecting various parts of the device through various interfaces and lines.

[0043] The memory mainly includes a program storage area and a data storage area. The program storage area can store the operating system, applications required for at least one function, etc., while the data storage area can store related data, etc. Furthermore, the memory can be a high-speed random access memory, or a non-volatile memory, such as a plug-in hard drive, a SmartMedia Card (SMC), a Secure Digital (SD) card, and a Flash Card, or other volatile solid-state storage devices.

[0044] It should be noted that the above-mentioned devices may include, but are not limited to, processors and memory, as will be understood by those skilled in the art.

[0045] As explained above, compared with the prior art, the beneficial effects of this invention are as follows: By embedding multi-source data such as three-dimensional spatial information of the storage location, material quantity, operation type, and timestamp into a multi-dimensional nonlinear mapping space, this invention constructs an embedded state vector with disturbance response and time sensitivity characteristics. This overcomes the limitations of linear processing of a single instruction in traditional synchronization mechanisms, enabling more precise capture of differences in the operation states of different storage locations and forming a high-dimensional state feature expression. This significantly improves the scheduling system's sensitivity to local changes and its adaptive control level. Simultaneously, the scheduling weight evaluation function constructed based on the embedded state vector and historical error feedback can dynamically integrate the current state with previous scheduling error information, real-time correcting scheduling priorities and delay strategies. This significantly improves the rationality of scheduling behavior and resource utilization efficiency, effectively reducing system deviations and anomalies such as incorrect or missed material issuance caused by asynchronous updates of inventory data. Furthermore, the dynamic correction mechanism of the response tension coefficient can adjust the nonlinear sensitivity of the state mapping in real time according to error fluctuations, enabling the state expression model to continuously evolve in long-term operation and adapt to the dynamic changes in inventory structure, business rhythm and environmental load. This ensures that the system has a high degree of adaptability and long-term stability, providing a strong guarantee for the efficient, accurate and stable operation of the intelligent warehousing system.

[0046] The above description is merely a preferred embodiment of the present invention and should not be construed as limiting the scope of the invention. Therefore, any equivalent variations made in accordance with the claims of the present invention are still within the scope of the present invention.

Claims

1. A method for synchronizing inventory data in an intelligent automated warehouse, characterized in that, include: Step S1: Collect multi-source data from the intelligent automated warehouse and construct a multi-dimensional data set; Step S2: Embed the multivariate data set into a nonlinear mapping space to construct an embedded state vector for expressing inventory behavior; Step S3: Construct a scheduling weight evaluation function based on the embedded state vector and historical error feedback; calculate the scheduling weight of inventory operations using the scheduling weight evaluation function; and make a decision on the synchronization method of inventory operations based on the scheduling weight. The synchronization method includes instant synchronization, delayed synchronization, or merged synchronization. Step S4: Based on the scheduling weight and historical error feedback, dynamically correct the response tension coefficients of each dimension in the embedded state vector, and use the corrected response tension coefficients for subsequent embedded state vector construction to form a feedback closed loop.

2. The method according to claim 1, characterized in that, The multi-source data collected in step S1 includes the three-dimensional location coordinates of the storage location, the quantity of materials entering and leaving, the operation type, and the event timestamp. This multi-source data set is represented as follows: ,in, The three-dimensional coordinates of the storage location; Indicate quantity; Indicates the operation type; This is the timestamp of the event.

3. The method according to claim 2, characterized in that, The formula for constructing the embedded state vector in step S2 is as follows: in, It is the current moment. The embedded state vector; It is the number of dimensions of the embedded state vector. ; yes The first in Each dimension has a component, representing the time interval. The sub-embedding vector is at the 1st Response results in each dimension; It is the first The response tension coefficient in each dimension; It is a moment The event state functions, each Sourced from multivariate datasets ; It is the frequency perturbation coefficient, representing the first... The embedding state of the first dimension is related to the second dimension. The time response frequency of event states in each dimension; It is the phase offset parameter, representing the embedding state of the m-th dimension relative to the... Time response lag or offset angle in each dimension; It is a time-perturbation transformation of the event state.

4. The method according to claim 3, characterized in that, The event state function Specifically, it includes: This indicates spatial location information; , indicating the number of operations; This indicates the impact of the operation direction; outbound shipments are negative. This indicates the impact of cargo location density; , which represents the offset within minutes of the current event.

5. The method according to claim 3, characterized in that, The expression for the scheduling weight evaluation function in step S3 is: in, It is the current moment. The scheduling weight; It is the temperature control coefficient for scheduling; It is a composite evaluation function that aggregates the weighted sum of the current embedded state and the previous round of feedback state; It is the intelligent warehouse system at a specific time point. The error feedback vector, It is the feedback delay time parameter; This indicates the feedback nonlinear amplification power factor; It is the first The feedback response weights of each dimension represent the degree of influence of the current dimension state on the scheduling weights.

6. The method according to claim 5, characterized in that, The scheduling temperature control coefficient Adjust dynamically based on system load; reduce when system load is high. To suppress excessive event concentration, increase when system load is low. To improve response speed.

7. The method according to claim 1, characterized in that, The update formula for the response tension coefficient in step S4 is as follows: in, It is the first The values ​​of the response tension coefficients in each dimension after the current cycle update are used to calculate the embedded state vector in the next round. Input; It is the feedback learning rate, which represents the strength of the response of the feedback error to the adjustment of the response tension coefficient; The scheduling weight at the current moment Compared with the average scheduling within the current time window The deviation between them Indicates from arrive The average scheduling weight; It is the first The absolute value of the feedback error in the current dimension reflects the current scheduling cycle. The strength of the error in each dimension; It is a power exponent; It is a fuzzy error evaluation function used to evaluate inventory feedback errors. Introduced into feedback regulation.

8. The method according to claim 1, characterized in that, Step S3 further includes: generating a standardized inventory update instruction based on the scheduling weight, and asynchronously sending it to the system interface via a message bus, wherein the sending form includes REST API or message queue.

9. A smart automated warehouse inventory data synchronization device, characterized in that, include: One or more processors; Memory; One or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the one or more processors, the one or more applications being configured to perform the intelligent automated warehouse inventory data synchronization method as described in any one of claims 1 to 8.

10. A computer program product, characterized in that, Includes computer instructions that instruct a computer device to perform an operation corresponding to the method as described in any one of claims 1 to 8.

Images