Electric power material checking equipment scheduling planning method and system

Abstract

The invention provides an electric power material checking equipment scheduling planning method and system, and belongs to the field of electric power material warehouse management. The method comprises the steps of obtaining real-time state information of a current reservoir area through a digital twinborn model in response to a checking instruction; based on the real-time state information, identifying the features of the to-be-checked warehouse area; calculating the matching degree between the reservoir area features and the inventory device capability portrait; dynamically selecting at least one target checking device from the checking devices based on the matching degree, and generating a checking task instruction for the at least one target checking device; and scheduling the at least one target inventory device to execute the inventory task instruction, and receiving inventory data returned by the target inventory device. According to the invention, intelligent scheduling and efficient cooperation of the electric power material checking equipment can be realized, the checking accuracy and the operation efficiency are significantly improved, and the method is suitable for material checking scenes of various electric power warehouses and different types of warehouse areas.

Description

Technical Field

[0001] This invention belongs to the field of power material storage management technology, and in particular relates to a method and system for scheduling and planning power material inventory equipment. Background Technology

[0002] The statements in this section are merely background information related to the present invention and do not necessarily constitute prior art.

[0003] Power supply warehousing is a crucial link in ensuring the stable operation of the power grid. The diverse types of materials, their high value, and complex layout place extremely high demands on the accuracy and efficiency of inventory checks. Traditional power supply inventory checks primarily rely on manual labor, with workers entering the storage area carrying documents or terminal equipment to count and record each item. This method is not only inefficient and labor-intensive, but also highly susceptible to errors and omissions due to human fatigue, negligence, or environmental factors, making it difficult to meet the requirements of modern lean management of power supplies.

[0004] To improve inventory efficiency and accuracy, the industry has begun to introduce automated inventory devices, such as Automated Guided Vehicles (AGVs), inventory robots, and inventory drones. These devices utilize technologies such as Radio Frequency Identification (RFID), computer vision, and laser ranging to automatically or semi-automatically collect material information. However, existing inventory systems using these automated devices typically employ rigid and inefficient scheduling methods. Common practices include assigning tasks using fixed, pre-defined rules, such as simply dividing responsibility areas according to warehouse area numbers (e.g., AGVs 1-3 are responsible for area A), or assigning fixed work areas to specific types of devices.

[0005] This static scheduling method has significant drawbacks: First, it fails to fully consider the matching relationship between the specific capabilities of different inventory counting devices and the specific characteristics of different warehouse areas. For example, in high-bay automated warehouses with rack heights exceeding 10 meters, AGV robots, which mainly rely on ground movement, cannot effectively count inventory at high-level locations; while in dense storage areas with narrow aisles and many obstacles, the mobility of drones is severely limited. Second, this method lacks adaptability to dynamic changes in the warehouse. The operating environment within a warehouse is constantly changing; temporary aisle blockages caused by forklift operations, changes in lighting conditions, and fluctuations in network signals can all affect the operational effectiveness of specific inventory counting devices, and fixed scheduling rules cannot respond to these real-time changes.

[0006] Therefore, existing technologies essentially treat heterogeneous warehouse environments and inventory devices with different functions as homogeneous objects, which makes it impossible to give full play to the advantages of various devices and makes it difficult to achieve the optimal balance between inventory accuracy and efficiency in complex scenarios. Summary of the Invention

[0007] To overcome the shortcomings of the existing technology, this invention provides a method and system for scheduling and planning power material inventory equipment. By constructing a digital twin model, device capability profile, and warehouse feature vector, it achieves dynamic matching and collaborative scheduling of multi-modal devices, thereby improving inventory accuracy and operational efficiency.

[0008] To achieve the above objectives, one or more embodiments of the present invention provide the following technical solutions: The first aspect of this invention provides a method for power material inventory and equipment scheduling planning; A method for scheduling and planning power equipment inventory includes: In response to inventory commands, the system obtains real-time status information of the current warehouse area through a digital twin model. Based on the real-time status information, identify the characteristics of the warehouse area to be inventoried; The characteristics of the warehouse area are matched with the pre-established capability profiles of multiple inventory devices, and the matching degree is calculated. Based on the matching degree, at least one target inventory device is dynamically selected from the plurality of inventory devices, and an inventory task instruction is generated for the at least one target inventory device; The system schedules at least one target inventory device to execute the inventory task instruction and receives the inventory data returned by it.

[0009] As a further technical solution, the real-time status information of the storage area includes equipment status, inventory status, and environmental status.

[0010] As a further technical solution, obtaining the real-time status information of the current storage area through a digital twin model includes: Receive real-time environmental data uploaded by IoT sensor nodes deployed in a physical warehouse; Receives its own status data and local sensing data uploaded from each inventory device; Obtain the latest inventory master data from the warehouse management system; The real-time environmental data, the self-state and local perception data, and the inventory master data are synchronized to the corresponding data layer in the digital twin model to generate the current real-time status of the warehouse area.

[0011] As a further technical solution, based on the real-time status information, the characteristics of the warehouse area to be inventoried are identified, including: Feature extraction is performed on the real-time status information in the digital twin model to construct a multi-dimensional feature vector to characterize the warehouse area to be inventoried; wherein, the multi-dimensional feature vector includes a spatial geometric feature vector, a stored material feature vector, and a dynamic environment feature vector.

[0012] As a further technical solution, the characteristics of the warehouse area are matched with the pre-established capability profiles of multiple inventory devices, and the matching degree is calculated, including: The quantitative indicators in the reservoir feature vector are normalized, and the scoring vector in the device capability profile is standardized. Establish a mapping relationship between the characteristics of the storage area and the capabilities of the equipment, and dynamically allocate the weights of each associated dimension according to the current inventory target; For each set of associated dimensions, calculate the single-dimensional matching sub-score. Based on the matching degree calculation function, multiply each single-dimensional matching sub-score by its corresponding weight and sum them to obtain the comprehensive matching degree between each device and the current storage area, and sort them according to the comprehensive matching degree.

[0013] As a further technical solution, based on the matching degree, at least one target inventory device is dynamically selected from the plurality of inventory devices, and an inventory task instruction is generated for the at least one target inventory device, including: From the candidate devices ranked by matching degree, a secondary screening is performed based on the real-time status of the devices to select one or more target inventory devices and determine a collaborative strategy, which includes: Independent working strategy: Select the single inventory counting device with the highest matching score to execute the task independently; Master-slave collaboration strategy: Select the device with the highest matching score as the master device, and select devices with high scores in one or more complementary capability dimensions as slave devices for collaboration; Peer-to-peer collaborative strategy: Divide a large, homogeneous warehouse area into several sub-regions, and use multiple inventory counting devices of the same or different types to work in parallel. Based on the matching degree of the inventory counting devices in the sub-regions, assign the corresponding optimal device to each sub-region.

[0014] As a further technical solution, after receiving the returned inventory data, data fusion and conflict resolution steps are also included: When there are conflicting inventory count results for the same storage location from different inventory counting devices, a confidence assessment is initiated. Based on the inherent accuracy of the device, real-time environmental factors, and data characteristics, a dynamic confidence score is calculated for each conflicting inventory result. Based on the dynamic confidence score, perform operations such as automatic acceptance, scheduling a third-party device for review, or submitting for manual review.

[0015] The second aspect of this invention provides a power material inventory and equipment scheduling planning system.

[0016] A power material inventory and equipment scheduling planning system includes: The status information acquisition module is configured to: in response to inventory commands, acquire the real-time status information of the current warehouse area through a digital twin model; The feature recognition module is configured to: identify the features of the warehouse area to be inventoried based on the real-time status information; The matching degree calculation module is configured to: match the features of the warehouse area with the pre-established capability profiles of multiple inventory devices, and calculate the matching degree; The task scheduling and instruction generation module is configured to: dynamically select at least one target inventory device from the plurality of inventory devices based on the matching degree, and generate inventory task instructions for the at least one target inventory device; The task execution module is configured to: schedule the at least one target inventory device to execute the inventory task instruction, and receive the inventory data returned by it.

[0017] A third aspect of the present invention provides a computer-readable storage medium having a program stored thereon, which, when executed by a processor, implements the steps of the power material inventory equipment scheduling and planning method described in the first aspect of the present invention.

[0018] A fourth aspect of the present invention provides an electronic device, including a memory, a processor, and a program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps in the power material inventory equipment scheduling and planning method described in the first aspect of the present invention.

[0019] The above one or more technical solutions have the following beneficial effects: This invention introduces a dynamic intelligent matching mechanism based on capability profiles and warehouse area characteristics, enabling the allocation of appropriate inventory devices to each micro-area, thus ensuring the applicability and efficiency of the operation from the outset. More importantly, by introducing a cross-device inventory data fusion and confidence assessment mechanism, it can intelligently handle multi-source data conflicts, automatically accept high-confidence results or trigger manual verification, constructing multiple lines of defense to ensure the highest accuracy and greatly reducing the risk of incorrect or missed inventory checks.

[0020] This invention, based on a digital twin-based multimodal device collaborative scheduling model, achieves macro-level decomposition and micro-level assignment of inventory tasks. This enables heterogeneous devices such as drones, AGVs, and personnel wearing AR glasses to operate in parallel and collaboratively, overcoming the functional limitations of single-type devices. It ensures the entire scheduling process is dynamic and real-time, responding to changes in the warehouse area and avoiding resource idleness or bottleneck waiting under traditional fixed-rule scheduling, thus significantly improving operational efficiency. This invention makes dynamic decisions based on real-time perception of the dynamic environmental characteristics of the warehouse area and the real-time status of the devices. When the environment changes, the system can automatically adjust the scheduling strategy and matching weights; for example, prioritizing drones in scenarios requiring efficiency and prioritizing personnel in scenarios requiring accuracy. This allows the system to flexibly adapt to various complex and changing actual warehousing operation environments.

[0021] Advantages of additional aspects of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. Attached Figure Description

[0022] The accompanying drawings, which form part of this invention, are used to provide a further understanding of the invention. The illustrative embodiments of the invention and their descriptions are used to explain the invention and do not constitute an improper limitation of the invention.

[0023] Figure 1 This is a flowchart of the method in the first embodiment.

[0024] Figure 2 This is a system structure diagram of the second embodiment. Detailed Implementation

[0025] It should be noted that the following detailed descriptions are exemplary and intended to provide further illustration of the invention. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0026] It should be noted that the terminology used herein is for the purpose of describing particular implementations only and is not intended to limit the exemplary implementations of the present invention.

[0027] Where there is no conflict, the embodiments and features in the embodiments of the present invention can be combined with each other.

[0028] Example 1 This embodiment discloses a method for scheduling and planning equipment for power material inventory. By constructing a multimodal device collaborative scheduling model based on digital twins, a dynamic intelligent matching mechanism between capability profiles and warehouse characteristics is established. Combined with cross-device inventory data fusion and a confidence assessment system, it achieves precise adaptation of inventory equipment to warehouses, efficient collaborative operation, and high accuracy verification of inventory results. This solves the technical problems of lack of specificity, poor adaptability, and insufficient inventory accuracy in existing power material inventory methods, significantly improving the intelligence level and operational efficiency of power material inventory. It is applicable to material inventory scenarios in various power warehouses and different types of warehouses.

[0029] Specifically, such as Figure 1 As shown, a method for scheduling and planning power material inventory equipment includes: Step S1: In response to the inventory command, obtain the real-time status information of the current warehouse area through the digital twin model.

[0030] When an inventory count instruction is received, the real-time status acquisition process of the digital twin is triggered. Through the data interface and connection layer, three types of real-time data are received simultaneously: real-time environmental data, inventory master data, and its own status data and local perception data.

[0031] For real-time environmental data, a sensor network deployed in the warehouse area collects information such as real-time light intensity, ambient temperature, and network signal strength; LiDAR or visual monitoring equipment identifies the location and movement trajectory of dynamic obstacles. For equipment status data and local perception data, the control systems of inventory devices such as AGVs, drones, and AR glasses obtain the current location, remaining battery power, health status, and current task progress of the equipment; local perception data includes images, RFID signals, or laser point cloud data collected by sensors on the devices. For inventory status data, the latest inventory records for the target warehouse area are obtained from the warehouse management system (WMS), including the current book quantity, specifications, inbound time, and estimated outbound time of materials at each location. Simultaneously, real-time material identification data uploaded by RFID readers and cameras is received to form the basis for comparing inventory records with physical inventory.

[0032] The collected real-time environmental data, self-status and local perception data, and inventory master data are preprocessed to remove outliers. The processed real-time status data is written into the dynamic data pool of the digital twin, updating the display status of the corresponding entity in the 3D physical model. At the same time, a real-time status dashboard is generated to intuitively display the equipment operation rate, environmental compliance rate, and inventory discrepancy warning number of the target warehouse area, providing visual decision support for the dynamic scheduling engine.

[0033] Step S2: Based on the real-time status information, identify the characteristics of the warehouse area to be inventoried.

[0034] First, establish a mapping between real-time status data and feature dimensions. Retrieve three types of real-time data from the dynamic data pool of the digital twin: real-time environmental data, inventory master data, and its own status data and local perception data for the warehouse area to be inventoried. Then, associate each type of data with three preset feature dimensions: spatial geometry, stored materials, and dynamic environment, forming the data foundation for feature extraction.

[0035] Secondly, static basic features and dynamic real-time features are extracted in layers. Static basic features are extracted from the associated spatial geometric data and material basic data, such as determining the average height of the warehouse area and the width of the storage location based on the measurement values ​​of the 3D model; and material value level and label type are read from the master data of the warehouse management system. Once these features are extracted, they remain stable if the physical structure of the warehouse area and the storage attributes of the materials have not changed. Dynamic real-time features are extracted from real-time environmental data and material dynamic data, such as determining the real-time light intensity based on the real-time values ​​of the photosensitive sensor, calculating the forklift operation frequency by the frequency of forklift position changes per unit time, and determining the network signal strength based on the RSSI value returned by the network signal probe. The above features are updated in real time to ensure that they reflect the real-time status of the warehouse area.

[0036] Finally, the extracted features are quantified and standardized. Non-numerical features such as label type and channel type are converted into discrete values; numerical features such as height and illumination are normalized to the [0,1] interval according to a preset range; dynamic features are corrected by combining historical inventory data, ultimately forming a standardized warehouse area feature vector with three levels of dimensions: macro, meso, and micro, used for device matching. For example, the macro dimension mainly refers to the warehouse area level, which is a large-scale division based on the function and physical structure of the warehouse. The feature vector includes: [Area type: outdoor flat area, average height: 2m, aisle type: spacious, label type: RFID, environment: susceptible to weather]. The meso dimension mainly refers to the shelving group or aisle level, which is a division within the same warehouse area based on shelving arrangement and aisle attributes. In a high-bay automated warehouse: [Sub-area: Area A, 1-10 rows of shelving, height: 18m, aisle: narrow aisle, network signal: medium, forklift frequency: high]. At the micro level, referring to the storage location level, each storage location is an independent decision-making unit. A high-value storage location: [Storage Location ID: P001-A-01, Height: 16.5m, Width: 1.2m, Value Level: High, Turnover Rate: Low, Tag Type: RFID, Real-time Illumination: Insufficient, Historical Inventory Confidence: 0.7].

[0037] Step S3 involves matching the warehouse area features with pre-established capability profiles of multiple inventory devices and calculating the matching degree. The capability profile translates the physical capabilities of the inventory devices into a unified language that computers can understand and calculate, serving as the cornerstone for intelligent scheduling and optimal matching. Essentially, it assigns each inventory device a unified, quantifiable score to precisely express its capabilities across different dimensions. This ensures the most suitable inventory device performs the appropriate task, thereby achieving the highest inventory accuracy and efficiency. The profile consists of multiple evaluation dimensions and quantified scores for each dimension. Examples include planar movement speed, vertical operation capability, data acquisition accuracy, and endurance.

[0038] The quantitative indicators such as height, light intensity, and forklift operation frequency in the reservoir area feature vector are normalized, and the scoring vector in the equipment capability profile is standardized to ensure that the reservoir area features and equipment capabilities are comparable in the same numerical dimension.

[0039] Establish a mapping relationship between the characteristics of the storage area and the capabilities of the equipment, and dynamically allocate the weights of each associated dimension according to the current inventory target.

[0040] For each set of association dimensions, calculate the single-dimensional matching sub-score. Based on the matching degree calculation function The scores of each single-dimensional matching sub-score are multiplied by their corresponding weights and then summed to obtain the overall matching degree between each device and the current warehouse area; all inventory devices participating in the matching are sorted from high to low according to their overall matching degree.

[0041] Step S4: Based on the matching degree, dynamically select at least one target inventory device from the plurality of inventory devices, and generate an inventory task instruction for the at least one target inventory device.

[0042] From the candidate devices ranked by matching degree, a second screening is performed based on the real-time status of the devices synchronized by the digital twin: devices with remaining battery power below 20%, fault codes, or current task load exceeding 80% are eliminated. For the remaining candidate devices after screening, a comprehensive priority score is calculated based on the matching degree score and the real-time availability score, and the final candidate sequence is determined according to the comprehensive priority score from high to low.

[0043] If the inventory area is of a simple type, the device with the highest comprehensive priority score is selected from the final candidate sequence as the sole target device, and an independent working strategy is adopted.

[0044] If the storage area is complex (such as a high-bay automated warehouse or a high-value material storage area), or if a single device cannot cover all storage locations, a master-slave collaboration strategy is adopted. The device with the highest matching score is selected as the master device, and devices with high scores in one or more complementary capability dimensions are selected as slave devices for collaboration.

[0045] The large, homogeneous warehouse area is divided into several sub-regions. A peer-to-peer collaborative strategy is adopted to select multiple inventory counting devices of the same or different types to work in parallel. Based on the matching degree of the inventory counting devices in the sub-regions, the corresponding optimal device is assigned to each sub-region.

[0046] For the target device and the defined collaboration mode, the micro-level storage location task is broken down according to device capabilities and collaboration rules, and structured task instructions are generated. The instructions include: target device ID, task type, storage location list, route planning parameters, data collection requirements, and instruction effective time. The generated instructions are sent to the target device through the data interface and connection layer of the digital twin, and the task instructions are adapted to the communication protocol according to the device type. At the same time, the storage location and device path corresponding to the task instructions are marked in the 3D model of the digital twin, realizing the visual tracking of instructions.

[0047] Step S5: Schedule the at least one target inventory device to execute the inventory task instruction and receive the inventory data returned by it.

[0048] The device transmits inventory data back to the digital twin in real time and updates the dynamic data pool. When inventory results from different inventory devices for the same storage location conflict, a confidence assessment is initiated. Based on the inherent accuracy of the device, real-time environmental factors, and data characteristics, a dynamic confidence score is calculated for each conflicting inventory result. Based on the dynamic confidence score, perform operations such as automatic acceptance, scheduling a third-party device for review, or submitting for manual review.

[0049] Example 2 This embodiment discloses a power material inventory equipment scheduling and planning system; like Figure 2 As shown, a power material inventory and equipment scheduling planning system includes: The status information acquisition module is configured to: in response to inventory commands, acquire the real-time status information of the current warehouse area through a digital twin model; The feature recognition module is configured to: identify the features of the warehouse area to be inventoried based on the real-time status information; The matching degree calculation module is configured to: match the features of the warehouse area with the pre-established capability profiles of multiple inventory devices, and calculate the matching degree; The task scheduling and instruction generation module is configured to: dynamically select at least one target inventory device from the plurality of inventory devices based on the matching degree, and generate inventory task instructions for the at least one target inventory device; The task execution module is configured to: schedule the at least one target inventory device to execute the inventory task instruction, and receive the inventory data returned by it.

[0050] Example 3 The purpose of this embodiment is to provide a computer-readable storage medium.

[0051] A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps in the power material inventory equipment scheduling planning method as described in Example 1.

[0052] Example 4 The purpose of this embodiment is to provide an electronic device.

[0053] An electronic device includes a memory, a processor, and a program stored in the memory and executable on the processor. When the processor executes the program, it implements the steps in the power material inventory equipment scheduling and planning method as described in Embodiment 1.

[0054] The steps and methods involved in the apparatuses of Embodiments 2, 3, and 4 above correspond to those in Embodiment 1. For specific implementation details, please refer to the relevant description section of Embodiment 1. The term "computer-readable storage medium" should be understood as a single medium or multiple media including one or more instruction sets; it should also be understood as including any medium capable of storing, encoding, or carrying an instruction set for execution by a processor and enabling the processor to perform any of the methods in this invention.

[0055] Those skilled in the art will understand that the modules or steps of the present invention described above can be implemented using general-purpose computer devices. Optionally, they can be implemented using computer-executable program code, thereby allowing them to be stored in a storage device for execution by a computer device, or they can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. The present invention is not limited to any particular combination of hardware and software.

[0056] While the specific embodiments of the present invention have been described above in conjunction with the accompanying drawings, this is not intended to limit the scope of protection of the present invention. Those skilled in the art should understand that various modifications or variations that can be made by those skilled in the art without creative effort based on the technical solutions of the present invention are still within the scope of protection of the present invention.

Claims

1. A power asset inventory device dispatch planning method, characterized by, The method comprises the following steps: In response to the inventory instruction, the real-time state information of the current warehouse area is obtained through the digital twin model; Based on the real-time state information, the warehouse area characteristics of the warehouse area to be inventoried are identified; The warehouse area characteristics are matched with the pre-established capability profiles of multiple inventory devices, and the matching degree is calculated; Based on the matching degree, at least one target inventory device is dynamically selected from the multiple inventory devices, and an inventory task instruction is generated for the at least one target inventory device; The at least one target inventory device is dispatched to execute the inventory task instruction, and the returned inventory data is received.

2. The method of claim 1, wherein, The real-time state information of the warehouse area includes device state, inventory state and environment state.

3. The method of claim 1, wherein, The real-time state information of the warehouse area is obtained through the digital twin model, which comprises the following steps: Real-time environment data uploaded by Internet of Things sensor nodes deployed in the physical warehouse is received; Self-state data and local perception data uploaded by each inventory device are received; The latest inventory master data is obtained from the warehouse management system; The real-time environment data, self-state and local perception data, and inventory master data are synchronized to the corresponding data layer in the digital twin model to generate the real-time state of the current warehouse area.

4. The method of claim 1, wherein, Based on the real-time state information, the warehouse area characteristics of the warehouse area to be inventoried are identified, which comprises the following steps: Feature extraction is performed on the real-time state information in the digital twin model to construct a multi-dimensional feature vector for representing the warehouse area to be inventoried; wherein the multi-dimensional feature vector includes a spatial geometric feature vector, a stored material feature vector, and a dynamic environment feature vector.

5. The method of claim 1, wherein, The warehouse area characteristics are matched with the pre-established capability profiles of multiple inventory devices, and the matching degree is calculated, which comprises the following steps: The quantitative indicators in the warehouse area feature vector are normalized, and the scoring vectors in the device capability profile are standardized; An associated mapping relationship between the warehouse area feature dimensions and the device capability dimensions is established, and the weights of each associated dimension are dynamically allocated according to the current inventory target; For each group of associated dimensions, a single-dimensional matching sub-score is calculated, and the sum of the product of each single-dimensional matching sub-score and the corresponding weight is obtained according to the matching degree calculation function to obtain the comprehensive matching degree of each device with the current warehouse area, and the devices are sorted according to the comprehensive matching degree.

6. The method of claim 1, wherein, Based on the matching degree, at least one target inventory device is dynamically selected from the multiple inventory devices, and an inventory task instruction is generated for the at least one target inventory device, which comprises the following steps: From the candidate devices sorted by matching degree, a secondary screening is performed in combination with the real-time state of the devices to select one or more target inventory devices and determine a collaboration strategy, the collaboration strategy comprising: Independent working strategy: selecting a single inventory device with the highest matching degree score to independently execute the task; Master-slave collaboration strategy: selecting the device with the highest matching degree score as the master device, and selecting devices with high scores in one or more complementary capability dimensions as the slave devices for collaboration; Peer collaboration strategy: dividing a large area and homogeneous warehouse area into several sub-areas, using multiple same-type or different-type inventory devices to work in parallel, and assigning the optimal device to each sub-area according to the matching degree of the inventory device in the sub-area.

7. The method of claim 1, wherein, After receiving the returned inventory data, a data fusion and conflict processing step is further included: When there is a conflict in the inventory results of the same storage location from different inventory devices, a confidence assessment is initiated; Based on the inherent accuracy of the device, real-time environmental factors and data characteristics, a dynamic confidence score is calculated for each conflicting inventory result; According to the dynamic confidence score, automatic acceptance, dispatching of third-party device review or submission of manual review operations are performed.

8. A power asset inventory device dispatch planning system, characterized by, Comprise: A state information acquisition module configured to acquire real-time state information of the current warehouse area through a digital twin model in response to an inventory instruction; A feature recognition module configured to identify the warehouse area features of the warehouse area to be inventoried based on the real-time state information; A matching degree calculation module configured to match the warehouse area features with the pre-established ability profiles of a plurality of inventory devices and calculate the matching degree; A task scheduling and instruction generation module configured to dynamically select at least one target inventory device from the plurality of inventory devices based on the matching degree and generate an inventory task instruction for the at least one target inventory device; A task execution module configured to schedule the at least one target inventory device to execute the inventory task instruction and receive the returned inventory data.

9. A computer-readable storage medium having stored thereon a program, characterized in that, The program is executed by the processor to realize the steps in the power material inventory device scheduling planning method of any one of claims 1-7.

10. An electronic device comprising a memory, a processor, and a program stored on the memory and executable on the processor, characterized in that, The processor executes the program to realize the steps in the power material inventory device scheduling planning method of any one of claims 1-7.

Images