Cargo multimedia information intelligent extraction system and method

Abstract

The invention belongs to the technical field of intelligent logistics, and discloses a cargo multimedia information intelligent extraction system and method, and the method comprises the steps: collecting a cargo picture, a video clip and a text label uploaded by a cargo owner, generating position coordinate binding in combination with an equipment positioning signal, and obtaining a multimedia position set; performing content hierarchical scanning, separating the visual elements and the dynamic sequence to form a hierarchical structure, and obtaining a hierarchical content group; performing cross semantic bridging, and constructing an inter-element association path to obtain an integrated semantic chain; attribute extraction circulation is applied to the integrated semantic chain, cargo specification details and transportation constraint fragments are extracted to establish an attribute set, and a structured attribute set is obtained; based on the binding of the structured attribute set and the position coordinates, generating a driver query sequence, and fusing the driver query sequence into a path-in-the-way factor to carry out adaptive sorting to obtain a preferred driver list; and the freight supply and demand matching accuracy is greatly improved.

Claims

1. A cargo multimedia information intelligent extraction method, characterized in that, Comprise: Step S1: Collect the goods pictures, video clips and text annotations uploaded by the consignor, combine the device positioning signal to generate the position coordinate binding, and obtain the multimedia position set; Step S2: Perform content hierarchical scanning on the pictures and video clips in the media position set, separate visual elements and dynamic sequences to form a hierarchical structure, and obtain a hierarchical content group; Step S3: Cross semantic bridging of the hierarchical content group and the text annotation, constructing the inter-element association path, and obtaining the integrated semantic chain; Step S4: Apply attribute extraction cycle to the integrated semantic chain, extract the goods specification details and transportation constraint segments to form an attribute set, and obtain a structured attribute set; Step S5: Generate a driver query sequence based on the structured attribute set and the position coordinate binding, integrate the path order factor for adaptive sorting, and obtain an optimized driver list.

2. The intelligent extraction method of cargo multimedia information according to claim 1, characterized in that, Step S1 includes: Step S11: Receive the goods pictures and video clips from the consignor device, synchronize the text annotation input, add the upload time label to organize the media elements, and obtain the original multimedia package; Step S12: Fuse the device positioning signal with the original multimedia package, bind the position coordinates through coordinate accuracy calibration, and construct auxiliary anchor points with device sensor data, to obtain a coordinate enhanced package; Step S13: Divide the time axis mark corresponding to the video clips in the coordinate enhanced package, associate the position coordinate binding and embed the variation tracking points, to obtain a time sequence position group; Step S14: Fuse the time sequence position group with the goods pictures and text annotations, expand the binding range to cover the position variation between elements, and obtain a multimedia position set.

3. The intelligent extraction of cargo multimedia information method according to claim 2, wherein, Step S12 includes: Step S121: Isolate the goods pictures, video clips and text annotations from the original multimedia package, fuse the device positioning signal and record the fusion time point, to obtain a signal fusion group; Step S122: Perform coordinate accuracy calibration on the signal fusion group, compare the device sensor data and adjust the binding strength, correct the coordinate value through multi-signal source cross verification, to obtain an anchor point strengthening group; Step S123: Bind the elements in the anchor point strengthening group to adjacent media elements, construct a coordinate chain connection, and obtain a chain binding group; Step S124: Apply position variation scanning to the chain binding group, add variation compensation markers and convert them into a coordinate enhanced package.

4. The intelligent extraction of cargo multimedia information method according to claim 3, wherein, Step S2 includes: Step S21: Select the goods pictures from the multimedia position set, perform content hierarchical scanning to separate static visual elements, split the contour texture and background components, and obtain a picture hierarchical layer; Step S22: Apply dynamic sequence segmentation to the video clips in the multimedia position set, capture the motion trajectory and hierarchical dynamic elements, connect the sequence through inter-frame transition markers, and obtain a video hierarchical layer; Step S23: Align the elements of the picture hierarchical layer and the video hierarchical layer, construct cross-layer connections and set alignment anchor points, and obtain an aligned hierarchical layer; Step S24: Associate the aligned hierarchical layer with the position coordinate binding, expand the connection to the time sequence position group elements, and obtain an expanded hierarchical layer; Step S25: Perform element clustering cycle on the expanded hierarchical layer, merge the visual elements and add clustering labels, and obtain a hierarchical content group.

5. The intelligent extraction of cargo multimedia information method according to claim 4, characterized in that, Step S3 includes: Step S31: Extract visual elements from the hierarchical content group, bridge semantics with text annotations to generate preliminary associated paths, add bridge nodes, and obtain a bridge path set; Step S32: Apply a cross-validation cycle to the bridge path set, check semantic consistency between elements and set bridge strength values, expand the validation range, and obtain a validated path set; Step S33: Based on the validated path set, build an integrated semantic chain, expand the path to cover multi-layer element association and embed branch points in the chain.

6. The intelligent extraction of cargo multimedia information method according to claim 5, wherein, Step S32 includes: Step S321: Select a path from the bridge path set, introduce text annotations as reference anchors, perform semantic consistency checks and record check nodes, and obtain a check path group; Step S322: Set the bridge strength value for the check path group, dynamically adjust the strength based on the distance and semantic overlap between elements, apply the strength propagation mechanism, and obtain a strength-enhanced path set; Step S323: Branch scan the paths in the strength-enhanced path set, add variation compensation and convert to a validated path set; Step S324: Perform a path compression cycle on the validated path set, merge adjacent nodes and add compression labels.

7. The intelligent extraction of cargo multimedia information method according to claim 6, wherein, Step S4 includes: Step S41: Start an attribute extraction cycle from the integrated semantic chain, scan the cargo specification details to split size, material and quantity components, and obtain a specification fragment group; Step S42: Expand the specification fragment group to extract transportation constraint fragments, fuse time-sensitive loading and unloading and path markers to build constraint sub-chains, and obtain a constraint expansion group; Step S43: Merge the specification fragment group with the constraint expansion group, establish links between attributes and set fusion nodes, and obtain a fused attribute group; Step S44: Perform attribute priority sorting for the fused attribute group, adjust fragment weights and add sorting anchors, and obtain a sorted attribute group; Step S45: Bind the sorted attribute group to the end of the integrated semantic chain, expand to location coordinate binding, and obtain an expanded attribute group; Step S46: Apply an attribute verification cycle to the expanded attribute group, check link consistency and add verification labels, and obtain a structured attribute set.

8. The intelligent extraction of cargo multimedia information method according to claim 7, wherein, Step S5 includes: Step S51: Extract cargo specification details and transportation constraint fragments from the structured attribute set, generate an initial driver query sequence with location coordinate binding, add attribute labels, and obtain a sequence draft; Step S52: Integrate path order factors into the sequence draft, simulate driver trajectories and embed order matching points, expand trajectory branches, and obtain a factor-enhanced sequence; Step S53: Perform adaptive sorting based on the factor-enhanced sequence, calculate path overlap and adjust ranking, add sorting markers, and obtain a sorted sequence group.

9. The intelligent extraction of cargo multimedia information method according to claim 8, wherein, Step S52 includes: Step S521: Select a query sequence from the sequence draft, introduce path order factors as trajectory simulation inputs, build simulation sub-paths, and obtain a simulation trajectory group; Step S522: Embed order matching points in the simulation trajectory group, dynamically expand the factor range based on location coordinate binding, apply matching point diffusion, and obtain an expanded trajectory group; Step S523: Integrate trajectories in the expanded trajectory group, set integration nodes and record branch variations, and obtain an integrated trajectory group; Step S524: Perform factor reinforcement cycle on the corresponding integrated trajectory group, adjust the on-road factor weight and attach the reinforcement label, and obtain the reinforced trajectory group; Step S525: Convert the reinforced trajectory group into a factor-enhanced sequence and bind it to the structured attribute set element.

10. A cargo multimedia information intelligent extraction system for implementing the cargo multimedia information intelligent extraction method according to any one of claims 1 to 9, characterized in that, Comprise: Positioning module: Collect the goods pictures, video clips and text annotations uploaded by the consignor, combine with the device positioning signal to generate position coordinate binding, and obtain the multimedia position set; Content analysis module: Perform content hierarchical scanning on the pictures and video clips in the media position set, separate visual elements and dynamic sequences to form a hierarchical structure, and obtain the hierarchical content group; Semantic bridging module: Cross semantic bridging of the hierarchical content group and the text annotations is performed to construct the inter-element association path, and the integrated semantic chain is obtained; Attribute extraction module: Apply attribute extraction cycle to the integrated semantic chain to extract goods specification details and transportation constraint fragments to form attribute set, and obtain the structured attribute set; Adaptation recommendation module: Generate driver query sequence based on the structured attribute set and position coordinate binding, and perform adaptation sorting by integrating path on-road factors to obtain the preferred driver list.

Images