CN117735244A - Box-type cargo intelligent inspection integrated system and method - Google Patents

Abstract

The invention discloses a box-type cargo intelligent inspection integrated system and a method. The intelligent checking integrated system for the box-type cargos solves the problems that in the prior art, a robot or an automatic device for logistics loading and unloading of customs cannot realize the processes of identifying cargos, counting the quantity, screening abnormal conditions and the like, so that the clearance time of the cargos is long.

Description

Box-type cargo intelligent inspection integrated system and method

Technical Field

The invention relates to the field of intelligent equipment, in particular to an intelligent checking integrated system and method for box-type cargoes.

Background

At present, the problems of bad working environment, low manual operation efficiency, more management staff and the like exist in links such as imported cold chain cargo inspection and the like. While for the logistics loading and unloading of customs, the prior art provides some robots or automatic equipment, and the loading and unloading robots and the automatic equipment only stay on the loading and unloading layer, do not have the whole process of checking the cargoes at the import and export of customs, and cannot realize the processes of recognizing the cargoes, counting the quantity, screening abnormal conditions and the like, so that the staff cannot be assisted in checking, the cargoes are in a long clearance time, and the cargoes cannot be checked and cleared rapidly.

Accordingly, there is a need for improvement and development in the art.

Disclosure of Invention

The invention mainly aims to provide a box-type cargo intelligent checking integrated system and method, and aims to solve the problems that in the prior art, a robot or an automatic device for logistics loading and unloading of customs cannot realize processes of cargo identification, quantity statistics, abnormal condition screening and the like, so that cargo clearance time is long.

In order to achieve the above object, a first aspect of the present invention provides a box cargo intelligent inspection integrated system, wherein the box cargo intelligent inspection integrated system includes a central control platform, a loading and unloading robot, a conveying device, an inspection device, a mark recognition device and a separation device;

the central control platform is connected with the loading and unloading robot, the conveying device, the checking device, the mark recognition device and the separating device through a network and is used for acquiring a checking instruction, analyzing the checking instruction to generate an execution action instruction, sending the execution action to the loading and unloading robot, generating risk attribute quantization parameters of target goods according to the customs clearance information acquired in advance, and displaying the risk attribute quantization parameters on the central control platform;

The loading and unloading robot is used for receiving an execution action instruction, grabbing target goods according to the execution action instruction and placing the target goods on the conveying device;

the conveying device is used for conveying the target goods to the checking device;

the checking device is connected with the tail end of the conveying device and is used for carrying out size measurement, quantity statistics and weight measurement on the target goods to obtain measurement results, comparing preset parameter information with the measurement results to obtain checking results, judging whether the target goods are abnormal according to the checking results to obtain first judgment results, uploading the first judgment results to the central control platform and conveying the target goods to the mark recognition device;

the mark recognition device is connected with the tail end of the checking device and is used for extracting mark information of the target goods, comparing the prestored customs information with the mark information, judging whether the target goods are abnormal or not, obtaining a second judging result, uploading the second judging result and the mark information to the central control platform, and conveying the target goods to the separating device;

The separating device is connected with the tail end of the mark recognition device and is used for receiving the judgment result generated by the central control platform according to the first judgment result and the second judgment result, transmitting the target goods to the target position according to the judgment result and pushing the target position information to the central control platform.

Optionally, the loading and unloading robot comprises a chassis, a vehicle body control box, a series-parallel mechanical arm, a grabbing tail end, a visual perception module and a control module;

the chassis is positioned at the bottom of the loading and unloading robot and is used for driving the loading and unloading robot to move;

the vehicle body control box is fixedly arranged on the chassis and used for loading the control module and the visual perception module;

the series-parallel mechanical arm is arranged on the chassis and used for driving the grabbing tail end to move in space;

the grabbing tail end is arranged at the tail end of the series-parallel mechanical arm and used for adsorbing and conveying the target goods;

the visual perception module is arranged on the series-parallel mechanical arm and is used for acquiring the grabbing pose of the target goods;

the control module is arranged on the vehicle body control box and is used for controlling the chassis, the series-parallel mechanical arm and the grabbing tail end to adsorb the target goods and then transmitting the target goods to the conveying device;

The control module is respectively and electrically connected with the chassis, the visual perception module, the series-parallel mechanical arm and the grabbing tail end.

Optionally, the conveying device comprises a frame, a back-rolling conveying belt, a lifting module and a roller conveying belt;

the frame is used for fixing the back-rolling conveyor belt, the lifting module and the roller conveyor belt;

the back-rolling conveying belt and the lifting module are arranged on the frame in a sliding manner, the roller conveying belt is detachably arranged on the frame, and the roller conveying belt and the lifting module are arranged on the same side of the frame, wherein the back-rolling conveying belt is arranged on the opposite sides of the roller conveying belt and the lifting module;

the back-rolling conveyor belt is used for placing the target goods;

the lifting module is used for adjusting the height of the back-rolling conveyor belt to be the height of the roller conveyor belt;

the roller conveyor belt is used for conveying the target goods to the checking device.

Optionally, the checking device comprises a conveying module, a weighing module, a 3D camera, a control cabinet and an audible and visual alarm module;

the conveying module is used for conveying the target goods to the weighing module;

The weighing module is arranged below the conveying module and is used for carrying out weight measurement on the target goods to obtain weighing information and transmitting the weighing information to the control cabinet;

the 3D camera is fixedly arranged on the control cabinet and is used for carrying out size measurement and quantity statistics on the target goods to obtain size information and quantity information, and the size information and the quantity information are transmitted to the control cabinet;

the control cabinet is arranged beside the conveying module and is used for obtaining the measurement result according to the weighing information, the quantity information and the size information, comparing the parameter information with the measurement result to obtain the checking result, judging whether the target goods are abnormal according to the checking result to obtain a first judging result, and uploading the first judging result to the central control platform;

the audible and visual alarm module is arranged on the control cabinet and used for judging whether to alarm according to the checking result;

the control cabinet is electrically connected with the conveying module, the weighing module, the 3D camera and the audible and visual alarm module respectively.

Optionally, the mark recognition device comprises a mark recognition frame, an industrial camera, a motion mechanism, a rotary platform and a mark recognition conveying module;

The mark identification rack is used for fixing the rotary platform and the movement mechanism;

the moving mechanism is arranged on the mark recognition rack and is used for rotating the target goods;

the industrial camera is used for primarily photographing the target goods to obtain an initial position photo, controlling the movement mechanism to move to a mark position according to the initial position photo, photographing the mark of the target goods to obtain a mark position photo, extracting mark information of the target goods according to the mark position photo, comparing the customs information acquired in advance with the mark information, judging whether the target goods are abnormal or not, obtaining a second judging result, and uploading the second judging result and the mark information to the central control platform;

the moving mechanism is arranged on the mark recognition frame and is used for moving according to the initial position picture;

the mark recognition and conveying module is arranged on the mark recognition rack and is used for conveying the target goods to the separating device.

Optionally, the separating device comprises a roller conveyor belt, a rotating mechanism and an information transmission device;

The roller conveyor belt is connected with the rotating mechanism and is used for conveying the target goods to a target position;

the rotating mechanism is used for rotating according to the judging result;

the information transmission device is arranged in the rotating mechanism and is used for receiving the judging result generated by the central control platform according to the first judging result and the second judging result, acquiring the target position information and pushing the target position information to the central control platform.

Optionally, the central control platform comprises an instruction analysis module and a big data risk assessment module;

the instruction analysis module is used for acquiring a checking instruction, analyzing the checking instruction to generate an execution action instruction, and sending the execution action to the loading and unloading robot;

the big data risk assessment module is used for generating risk attribute quantization parameters of the target goods according to the customs clearance information and displaying the risk attribute quantization parameters on the central control platform.

The second aspect of the present invention provides a method for performing inspection, where the method specifically includes:

acquiring a checking instruction, generating an execution action instruction according to the checking instruction, grabbing the target goods by the loading and unloading robot according to the execution action instruction, placing the target goods on the conveying device, generating risk attribute quantization parameters of the target goods by the central control platform according to the customs clearance information acquired in advance, and displaying the risk attribute quantization parameters on the central control platform;

The conveying device transmits the target goods to the checking device, the checking device performs size measurement, quantity statistics and weight measurement on the target goods to obtain measurement results, preset parameter information is compared with the measurement results to obtain checking results, whether the target goods are abnormal or not is judged according to the checking results to obtain first judgment results, the first judgment results are uploaded to the central control platform, and the target goods are conveyed to the mark recognition device;

the mark recognition device is connected with the tail end of the checking device and is used for extracting mark information of the target goods, comparing the prestored customs information with the mark information, judging whether the target goods are abnormal or not, obtaining a second judging result, uploading the second judging result and the mark information to the central control platform, and conveying the target goods to the separating device;

the separation device receives a judging result generated by the central control platform according to the first judging result and the second judging result, transmits the target goods to a target position according to the judging result, and pushes target position information to the central control platform;

And the central control platform generates risk attribute quantization parameters of the target goods according to the customs clearance information, and displays the risk attribute quantization parameters on the central control platform.

Optionally, the checking device performs size measurement, quantity statistics and weight measurement on the target cargo to obtain the measurement result, compares preset parameter information with the measurement result to obtain the checking result, judges whether the target cargo is abnormal according to the checking result to obtain a first judgment result, uploads the first judgment result to the central control platform, and transmits the target cargo to the mark recognition device, and specifically includes:

the conveying module conveys the target goods to the weighing module;

the weighing module performs weight measurement on the target goods to obtain weighing information, and transmits the weighing information to a control cabinet;

the 3D camera performs size measurement and quantity statistics on the target goods to obtain size information and quantity information, and transmits the size information and the quantity information to the control cabinet;

the control cabinet obtains the measurement result according to the weighing information, the quantity information and the size information, compares the parameter information with the measurement result to obtain the checking result, judges whether the target goods are abnormal according to the checking result to obtain a first judging result, judges whether to alarm according to the first judging result, uploads the first judging result to the central control platform, and conveys the target goods to the mark recognition device.

Optionally, the central control platform generates risk attribute quantization parameters of the target cargo according to the pre-acquired customs clearance information, and displays the risk attribute quantization parameters on the central control platform, which specifically includes:

inputting the customs clearance information into a classification model after training;

generating risk attribute quantization parameters of the target goods through the classification model, and displaying the risk attribute quantization parameters on the central control platform;

wherein the classification model is trained based on historical ping data.

From the above, in the system of the invention, the box-type cargo intelligent inspection integrated system comprises a central control platform, a loading and unloading robot, a conveying device, an inspection device, a mark recognition device and a separation device; the central control platform is connected with the loading and unloading robot, the conveying device, the checking device, the mark recognition device and the separating device through a network and is used for acquiring a checking instruction, analyzing the checking instruction to generate an execution action instruction, sending the execution action to the loading and unloading robot, generating risk attribute quantization parameters of target goods according to customs clearance information, and displaying the risk attribute quantization parameters on the central control platform; the loading and unloading robot is used for receiving an execution action instruction, grabbing target goods according to the execution action instruction and placing the target goods on the conveying device; the conveying device is used for conveying the target goods to the checking device; the checking device is connected with the tail end of the conveying device and is used for carrying out size measurement, quantity statistics and weight measurement on the target goods to obtain measurement results, comparing preset parameter information with the measurement results to obtain checking results, judging whether the target goods are abnormal according to the checking results to obtain first judgment results, uploading the first judgment results to the central control platform and conveying the target goods to the mark recognition device; the mark recognition device is connected with the tail end of the checking device and is used for extracting mark information of the target goods, comparing the prestored customs information with the mark information, judging whether the target goods are abnormal or not, obtaining a second judging result, uploading the second judging result and the mark information to the central control platform, and conveying the target goods to the separating device; the separating device is connected with the tail end of the mark recognition device and is used for receiving the judgment result generated by the central control platform according to the first judgment result and the second judgment result, transmitting the target goods to the target position according to the judgment result and pushing the target position information to the central control platform.

Compared with the prior art, the intelligent checking integrated system for the box type cargos, disclosed by the invention, has the advantages that the problems of long cargo clearance time caused by the processes of recognition, quantity statistics, abnormal condition screening and the like of cargos cannot be realized for the robots or automatic equipment for logistics loading and unloading of the current customs, the obtained checking instructions are converted into execution action instructions through the central control platform, the loading and unloading robots automatically move to corresponding positions according to the obtained instructions to grab target cargos and place the target cargos to corresponding conveying devices, the conveying devices convey the cargos to the checking devices to judge whether the size and the weight of the cargos exceed preset requirements, the mark recognition devices again judge whether the cargos have problems or not, and finally the abnormal and non-abnormal cargos are conveyed respectively through the separating devices, so that the cargos are conveyed to the target position, and the type of the target cargos is judged according to the mark information, and the type of the target cargos is also conveyed to the central control platform, and the cold chain grabbing, transmission, checking, size measurement, weighing, separation and information display and checking can be realized through the intelligent box type automatic integrated cargo checking processes, so that the loading and unloading can be realized through the intelligent box type cargo checking integrated system, the corresponding to the information can be realized, the risk of the user can be greatly reduced, the corresponding risk is reduced, the risk is greatly reduced, the risk is reduced, the corresponding to the user performance is greatly risk is reduced, and the risk is required to be evaluated by the user to be compared with the corresponding to the performance information.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the embodiments or the description of the prior art will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

FIG. 1 is a schematic diagram of an integrated system for intelligent inspection of cargo in a box according to an embodiment of the present invention;

fig. 2 is a schematic structural diagram of a loading and unloading robot in the box-type cargo intelligent inspection integrated system according to the embodiment of the invention;

FIG. 3 is a schematic view of the degrees of freedom of the grasping end provided by an embodiment of the invention;

FIG. 4 is a schematic view of the mechanical principle of the gripping tip provided by an embodiment of the present invention;

FIG. 5 is a schematic diagram of a target detection model in a visual perception module in a box cargo intelligent inspection integrated system according to an embodiment of the present invention;

FIG. 6 is a schematic diagram of a conveying device in the integrated system for intelligent inspection of cargo in a box according to an embodiment of the present invention;

FIG. 7 is a schematic diagram of a roller conveyor belt in a conveyor device in a box cargo intelligent inspection integrated system according to an embodiment of the present invention;

FIG. 8 is a schematic diagram of a checking device in the integrated system for intelligently checking box-type cargo according to the embodiment of the present invention;

fig. 9 is a schematic diagram of a mark recognition device in the box cargo intelligent inspection integrated system according to the embodiment of the invention;

fig. 10 is a schematic diagram of a mark recognition device and a separation device in a box-type cargo intelligent inspection integrated system according to an embodiment of the present invention;

fig. 11 is a flowchart illustrating a method of inspection processing according to an embodiment of the present invention.

Reference numerals: 1. a central control platform; 2. a loading and unloading robot; 3. a conveying device; 4. a checking device; 5. mark recognition device; 6. a separation device; 21. a chassis; 22. a series-parallel mechanical arm; 23. grabbing the tail end; 24. a visual perception module; 25. a vehicle body control box; 26. a robot conveyor belt; 261. a primary conveyor belt; 262. a secondary telescopic conveyor belt; 231. a bottom support; 232. a vacuum chuck; 233. a conveyor belt; 31. a frame; 32. a back-rolling conveyor belt; 33. a lifting module; 34. a roller conveyor belt; 41. a transport module; 42. a weighing module; 43. a 3D camera; 44. a control cabinet; 45. an audible and visual alarm module; 51. the mark identifies the frame; 52. an industrial camera; 53. a movement mechanism; 54. rotating the platform; 55. the mark identification and conveying module; 56. a second baffle; 57. a first baffle, 58, a pressure plate; 61. a roller conveyor belt; 62. a rotating mechanism.

Detailed Description

In the following description, for purposes of explanation and not limitation, specific details are set forth such as the particular system architecture, techniques, etc., in order to provide a thorough understanding of the embodiments of the present invention. It will be apparent, however, to one skilled in the art that the present invention may be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present invention with unnecessary detail.

It should be understood that the terms "comprises" and/or "comprising," when used in this specification and the appended claims, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.

It is also to be understood that the terminology used in the description of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in this specification and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.

It should be further understood that the term "and/or" as used in the present specification and the appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes such combinations.

As used in this specification and the appended claims, the term "if" may be interpreted in the context of "when …" or "once" or "in response to a determination" or "in response to a classification. Similarly, the phrase "if determined" or "if classified to [ described condition or event ]" may be interpreted in the context of meaning "upon determination" or "in response to determination" or "upon classification to [ described condition or event ]" or "in response to classification to [ described condition or event ]".

The following description of the embodiments of the present invention will be made more fully hereinafter with reference to the accompanying drawings, in which embodiments of the invention are shown, it being evident that the embodiments described are only some, but not all embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.

In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, but the present invention may be practiced in other ways other than those described herein, and persons skilled in the art will readily appreciate that the present invention is not limited to the specific embodiments disclosed below.

According to the box-type cargo intelligent inspection integrated system disclosed by the preferred embodiment of the invention, as shown in fig. 1, the box-type cargo intelligent inspection integrated system comprises a central control platform 1, a loading and unloading robot 2, a conveying device 3, an inspection device 4, a marker identification device 5 and a separation device 6;

the central control platform 1 is connected with the loading and unloading robot 2, the conveying device 3, the checking device 4, the mark recognition device 5 and the separating device 6 through a network, and is used for acquiring a checking instruction, analyzing the checking instruction to generate an execution action instruction, sending the execution action to the loading and unloading robot 2, generating risk attribute quantization parameters of target goods according to pre-acquired customs clearance information, and displaying the risk attribute quantization parameters on the central control platform 1;

the loading and unloading robot 2 is used for receiving an execution action instruction, grabbing target goods according to the execution action instruction and placing the target goods on the conveying device 3;

The conveying device 3 is used for conveying the target goods into the checking device 4;

the checking device 4 is connected to the end of the conveying device 3, and is configured to perform size measurement, quantity statistics and weight measurement on the target cargo, obtain a measurement result, compare preset parameter information with the measurement result, obtain a checking result, determine whether the target cargo is abnormal according to the checking result, obtain a first determination result, upload the first determination result to the central control platform 1, and convey the target cargo to the mark recognition device 5;

the mark recognition device 5 is connected with the tail end of the checking device 4, and is used for extracting mark information of the target goods, comparing the prestored customs information with the mark information, judging whether the target goods are abnormal or not, obtaining a second judging result, uploading the second judging result and the mark information to the central control platform 1, and conveying the target goods to the separation device 6;

the separating device 6 is connected to the end of the mark identifying device 5, and is configured to receive a determination result generated by the central control platform 1 according to the first determination result and the second determination result, transmit the target cargo to a target position according to the determination result, and push target position information to the central control platform 1.

Converting the acquired checking instruction into an execution action instruction through the central control platform 1, controlling the loading and unloading robot 2 to place target cargoes on the conveying device 3 through the execution control instruction, after the conveying device 3 conveys the cargoes on the checking device 4, the checking device 4 performs size measurement, quantity statistics and weight measurement on the target cargoes to obtain a measurement result, comparing preset parameter information with the measurement result to obtain a checking result, judging whether the target cargoes are abnormal according to the checking result to obtain a first judgment result, uploading the first judgment result to the central control platform 1, and conveying the target cargoes to the mark recognition device 5; after comparing the information of the goods again, the mark recognition device 5 obtains a second judgment result, uploads the second judgment result and the mark information to the central control platform 1, and conveys the target goods to the separation device 6; and when the central control platform 1 acquires the checking instruction, generating risk attribute quantization parameters of the target goods according to the customs clearance information acquired in advance, and displaying the risk attribute quantization parameters on the central control platform 1.

In the central control platform 1, a worker may fill in an inspection instruction (such as which platform performs inspection) and customs information (such as a production place, a name, and a specification) according to a format on an upper computer interface of the central control platform 1, and the central control platform 1 is connected to each device, that is, the loading and unloading robot 2, the conveying device 3, the inspection device 4, the mark recognition device 5, and the separation device 6 through a network, and in one embodiment of the present application, is connected through EtherCat communication. After the central control platform 1 receives a specific checking action, a control instruction is sent to the loading and unloading robot 2, so that the loading and unloading robot 2 moves to a checking platform, and the processes of connecting and starting each device, photographing and calculating a grabbing point, moving a mechanical arm, unloading, circulating, checking, identifying a mark, separating and checking on site of customs staff are started. The central control platform 1 comprises an industrial personal computer and a developed software system, and the central control platform 1 can control and regulate the loading and unloading robot 2, the conveying device 3, the checking device 4, the mark recognition device and the separating device 6, monitor the states of all the devices in real time and alarm and process abnormal conditions in all the devices. Meanwhile, the central control system also provides operation and man-machine interaction interfaces, and a user can conveniently check the system state, operation equipment, setting parameters and the like. This allows the operator to more intuitively understand the system operation and make the necessary operations and adjustments.

Specifically, as shown in fig. 2, the loading and unloading robot 2 includes a chassis 21, a vehicle body control box 25, a serial-parallel mechanical arm 22, a grabbing end 23, a visual perception module 24 and a control module;

the chassis 21 is positioned at the bottom of the loading and unloading robot 2 and is used for driving the loading and unloading robot 2 to move;

the vehicle body control box 25 is fixedly arranged on the chassis 21 and is used for loading the control module and supporting the visual perception module 24;

the series-parallel mechanical arm 22 is arranged on the chassis 21 and is used for driving the grabbing tail end 23 to move in space;

the grabbing end 23 is arranged at the end of the serial-parallel mechanical arm 22 and is used for adsorbing and conveying the target goods;

the visual perception module 24 is arranged on the serial-parallel mechanical arm 22 and is used for acquiring the grabbing pose of the target goods;

the control module is arranged on the vehicle body control box 25 and is used for controlling the chassis 21, the series-parallel mechanical arm 22 and the grabbing tail end 23 to adsorb the target goods and then transmit the target goods to the conveying device 3;

the control module is electrically connected with the chassis 21, the visual perception module 24, the series-parallel mechanical arm 22 and the grabbing end 23 respectively.

In one embodiment of the present invention, the loading and unloading robot 2 may be a fully automatic loading and unloading robot. Wherein the full-automatic loading and unloading robot can realize all functions of the loading and unloading robot 2. Further, as shown in fig. 2, the loading and unloading robot 2 further includes a robot conveyor 26, where the robot conveyor is composed of a primary conveyor 261 and a secondary telescopic conveyor 262, the primary conveyor 261 is disposed on the serial mechanical arm 22, and the secondary telescopic conveyor 262 is disposed between the serial mechanical arm 22 and the vehicle body control box 25, for connecting and conveying the target cargo; further, the electric connection between the operation arm module and the visual perception module and between the operation arm module and the central control platform is realized in the vehicle body control box.

Further, as shown in fig. 4, the gripping end 23 includes a shoe 231, a vacuum chuck 232, and a conveyor 233;

the shoe 231 is used for supporting the vacuum chuck 232 and the conveyor belt 233;

the vacuum chuck 232 is slidably disposed on the base 231 through a slider, and is used for adsorbing the target cargo onto the conveyor belt 233;

the conveyor belt 233 is covered on the shoe 231 for transferring the target cargo to the conveyor 3.

Specifically, the method of combining side surface adsorption with bottom surface support is that the vacuum chuck 232 can move back and forth to drag the goods onto the bottom bracket 231, and the gravity of the goods is provided by the supporting force of the bottom bracket 231, wherein the bottom bracket 231 is the base of the conveying belt 233, and the supporting function can be achieved. However, when the lowest layer of goods is grabbed, the bottom support 231 with a certain height interferes with the side surface of the container, so that the degree of freedom of movement in the vertical direction is increased for the vacuum chuck 232, and the goods can be lifted for a certain distance. Further, the conveyor belt 233 with the shoe 231 has a main force due to friction between the cargo and the conveyor belt, so that the target cargo box can be grasped more efficiently and reliably. Thus, from the above, the end gripping mechanism has at least three degrees of freedom, namely, a degree of freedom of movement in the vertical and horizontal directions of the vacuum cups 232 and a rotational movement of the conveyor belt, as shown in fig. 3. Furthermore, in the grabbing end 23, the vertical movement freedom of the vacuum chuck 232 is a parallel four-bar mechanism combined with a cam guide mechanism for setting a lifting track, the horizontal movement freedom of the vacuum chuck 232 is a linear guide mechanism, and the two movements are completed by driving a linear guide slider by the same motor, namely, the parallel four-bar mechanism can also passively deform along with the cam guide mechanism in the horizontal movement process of the grabbing end 23, so that the vertical lifting movement of the vacuum chuck 232 is realized; the rotary motion of the conveyor belt is driven by motorized rollers.

Further, the visual perception module 24 includes a laser radar depth camera and a neural network, and the laser radar acquires depth information of the object to be measured and acquires the grabbing pose of the target cargo. The method comprises the steps of firstly shooting a photo of a cargo box placed in a container through a laser radar depth camera, identifying the cargo box and dividing the cargo box at a pixel level by adopting a neural network of a Mask R-CNN architecture, namely a target detection model, obtaining a Mask result, extracting a picture pixel region from the Mask result, and converting the corresponding Mask region into a three-dimensional point cloud. Extracting a grabbing plane of the packaging box by adopting a random sampling consistency algorithm, taking local points belonging to the plane as a final effective point set, and adopting an algorithm of calculating a rectangle surrounded by the minimum area of the point set to obtain a rectangular boundary of the goods grabbing top surface; and acquiring depth information returned by the laser radar depth camera in a scanning way, and calculating the space position of the grabbing surface of the goods, namely the grabbing pose of the target goods, through a RANSAC algorithm. The control module controls the chassis 21, the serial-parallel mechanical arm 22 and the grabbing tail end 23 to adsorb the target cargo and then transmit the target cargo to the conveying device 3 through the space position of the target cargo and the rectangular boundary of the cargo grabbing top surface.

Specifically, to the box goods detection and location problem of intensive stack, snatch the position appearance and draw through the target detection model, specifically: firstly, interweaving detection branches and segmentation branches together to perform joint multi-stage processing, wherein a network framework for providing space context information by adopting semantic segmentation branches is more suitable for mask prediction of dense targets; therefore, as shown in fig. 5, the object detection model shown in fig. 5 is improved based on an example segmentation network of a mixed task cascade (HTC), specifically, RGB images and corresponding depth information are taken as input, noise and depth deletion problems of the RGBD depth images are solved, the original depth images are subjected to noise removal by adopting median filtering, an empty region is filled by adopting a weighted combined bilateral filtering method, an analog interaction layer is added to produce an interaction image, then Resnet101 is taken as a feature image extracted by a feature extraction module of a backbone network to be input into a feature pyramid FPN, a feature pyramid structure is added after the feature pyramid, a dual feature pyramid structure is formed, so that space information of each level of feature images is enhanced, after the corresponding feature region is extracted by each layer, a feature fusion layer is added, and after the feature images of all levels are fused, the feature images are input to a subsequent object mask prediction network; and in addition, a mask head module is added at the end of the network model, the example features and the prediction mask are taken as input, the maximum pooling layer is used for enabling the prediction mask to have the same space size as the ROI features, and then IOU between the 3 convolution layers and the 3 complete connection layer regression prediction mask and the ground true mask is used for obtaining more reliable dynamic mask scores, so that the network prediction precision is improved.

For the grabbing surface, extracting the area based on the target detection model result; obtaining a mask result of the corresponding packaging box according to the prediction of the target detection model, and taking out a corresponding picture pixel region; and converting the corresponding mask area into a three-dimensional point cloud, and adopting a depth map to three-dimensional point cloud algorithm for processing. Specifically, the corresponding relation between a space point [ x, y, z ] and pixel coordinates [ u, v, d ] in an image in the depth map-to-three-dimensional point cloud algorithm is shown as the following formula:

；

；

；

wherein,，/>refers to the focal length of the camera in both x, y axes, < >>，/>Refer to the center of the aperture of the camera, and s refers to the scaling factor of the depth map. And deriving (x, y, z) from (x, y, z) to (u, v, d), which can be written as known (u, v, d), the process of deriving (x, y, z) from the depth map can be expressed as the following formula:

。

then, a random sampling consensus algorithm (RANSAC algorithm) is adopted to extract the grabbing plane of the packing box, local points belonging to the plane are used as a final effective point set, and a rectangular boundary of the grabbing top surface of the packing box is estimated by adopting an algorithm that the minimum area of the calculated point set surrounds a rectangle. The RANSAC algorithm comprises the following specific steps:

step 1, randomly selecting three points from a point cloud;

Step 2: a plane is formed by the three points;

step 3, calculating the distance from all other points to the plane, and if the distance is smaller than a threshold value T, considering the points to be in the same plane;

step 4, if the number of points in the same plane exceeds n, saving the plane, marking the points in the plane as matched, and recycling the steps 1 to 4;

and 5, iteratively cycling the steps 1 to 4 until the plane is smaller than n points, or three unlabeled points cannot be found.

In addition, the loading and unloading robot 2 further comprises a control system and a sensor module, wherein the control system is responsible for overall coordination of the chassis 21, the serial-parallel mechanical arm 22, the grabbing tail end 23, the vision and other modules and executing control instructions of the operation flow. The sensor modules are arranged on the mechanical arm and are divided into three types, namely photoelectric sensors for detecting containers passing through the conveyor belt; the distance measuring sensor comprises laser distance measuring and ultrasonic distance measuring, and provides the distance in the advancing direction, the left-right direction and the up-down direction for the mechanical arm; the safety sensor and the laser scanner prevent the mechanical arm from colliding with a person and a wall, and the limit sensor ensures that the mechanical arm works in a safe working space and prevents accidents.

As shown in fig. 6 and 7, the conveying device 3 includes a frame 31, a back-rolling conveyor belt 32, a lifting module 33, and a roller conveyor belt 34;

the frame is used for fixing the back-rolling conveyor belt 32, the lifting module 33 and the roller conveyor belt 34;

the back-rolling conveyor belt 32 and the lifting module 33 are slidably arranged on the frame 31, the roller conveyor belt 34 is detachably arranged on the frame 31, and the roller conveyor belt 34 and the lifting module 33 are arranged on the same side of the frame 31, wherein the back-rolling conveyor belt 32 is arranged on the opposite sides of the roller conveyor belt 34 and the lifting module 33;

the back-rolling conveyor 32 is used for placing the target goods;

the lifting module 33 is used for adjusting the height of the back-rolling conveyor belt 32 to the height of the roller conveyor belt 34;

the roller conveyor 34 is used to convey the target cargo to the inspection device 4.

Specifically, after the target cargo is picked up by the loading and unloading robot 2 and placed on the conveying device 3, the conveying device 3 conveys the cargo from the back-rolling conveying belt 32 to the roller conveying belt 34 through the lifting module 33, and the cargo is transferred to the inspection device 4 through the roller conveying belt 34.

Further, as shown in fig. 6 and 7, the frame 31 further includes a connector 35 for detachably disposing the roller conveyer 34 on the frame 31.

Specifically, as shown in fig. 8, the inspection device 4 includes a conveying module 41, a weighing module 42, a 3D camera 43, a control cabinet 44, and an audible and visual alarm module 45;

the transport module is used for conveying the target goods to the weighing module 42;

the weighing module 42 is disposed below the conveying module 41, and is configured to perform the weight measurement on the target cargo, obtain weighing information, and transmit the weighing information to the control cabinet 44;

the 3D camera is fixedly arranged on the control cabinet 44, and is used for performing size measurement and quantity statistics on the target goods to obtain size information and quantity information, and transmitting the size information and the quantity information to the control cabinet 44;

the control cabinet 44 is disposed beside the conveying module 41, and is configured to obtain the measurement result according to the weighing information, the quantity information and the size information, compare the parameter information with the measurement result to obtain the inspection result, determine whether the target cargo is abnormal according to the inspection result, obtain a first determination result, and upload the first determination result to the central control platform 1;

The audible and visual alarm module 45 is arranged on the control cabinet and is used for judging whether to alarm according to the checking result;

the control cabinet 44 is electrically connected with the conveying module 41, the weighing module 42, the 3D camera 43 and the audible and visual alarm module 45, respectively.

Specifically, the conveying module 41 drives the conveying belt to run through the power roller, so that the target goods can pass through the conveying belt. The weighing module 42 weighs the target cargo passing through the transport module 41 by means of the underlying load cells. After the weighing sensor acquires the analog quantity signal, A/D conversion is carried out, and the measuring result outputs corresponding weighing information in a bus serial mode; meanwhile, the 3D camera 43 acquires depth information and RGB images of the object to be measured, thereby acquiring the three-dimensional size of the cargo box and obtaining size information. An industrial personal computer is built in the control cabinet 44 for counting and recording the parameter information such as the size, the weight, the number and the like of all inspected equipment for tracing and inspection comparison, uploading the parameter information to the central control platform 1, and meanwhile, presetting the parameter information, wherein the parameter information is preset weight, number and size information of the batch of customs clearance cargoes, namely the standard range of the cargoes. By comparing the parameter information with the measurement result, the inspection result is obtained, and once the inspected goods exceed the standard range, the audible and visual alarm module 45 can rapidly alarm, so that abnormal interception can be effectively performed. And judging whether the target goods are abnormal or not according to the checking result, obtaining a first judging result, uploading the first judging result to the central control platform 1, and conveying the target goods to the mark recognition device 5.

Further, the audible and visual alarm module 45 receives the inspection result; when the inspection result is the first inspection result, the audible and visual alarm module 45 alarms; when the inspection result is the second inspection result, the audible and visual alarm module 45 does not alarm. Wherein, when the measurement result is displayed in the checking result and the parameter information requirement is not met, the checking result is a first checking result; and when the measurement result is displayed in the checking results to meet the parameter information requirement, the checking result is a second checking result. When the checking result is a first checking result, the first judging result is abnormal; and when the checking result is a second checking result, the first judging result is normal.

Specifically, as shown in fig. 9, the mark recognition device 5 includes a mark recognition frame 51, an industrial camera 52, a movement mechanism 53, a rotary platform 54, and a mark recognition transport module 55;

the mark recognition frame 51 is used for fixing the rotary platform 54 and the movement mechanism 53;

the motion mechanism 53 is arranged on the mark recognition frame 51 and is used for rotating the target goods;

the industrial camera 52 is configured to primarily photograph the target cargo to obtain an initial position photograph, control the movement mechanism 53 to move to a mark position according to the initial position photograph, photograph a mark of the target cargo to obtain a mark position photograph, extract mark information of the target cargo according to the mark position photograph, compare the pre-acquired customs information with the mark information, determine whether the target cargo is abnormal, obtain a second determination result, and upload the second determination result and the mark information to the central control platform 1;

The moving mechanism 53 is arranged on the mark recognition frame 51 and is used for moving according to the initial position photo;

the mark recognition and conveying module 55 is disposed on the mark recognition frame 51, and is used for conveying the target goods to the separating device 6.

Specifically, the marker identification device 5 includes an industrial camera 52, a 3DOF movement mechanism 53, a rotary platform 54, a marker identification transport module 55, a first shutter 57, a second shutter 56, and a platen 58. The target cargo is moved onto the rotary platform 54 via the transport module 41 in the inspection device 4 until the first barrier 57 is in close proximity to one side of the target cargo, the platen 58 presses the other side of the cargo box flush with the second barrier 56, and the rotary platform 54 is rotated 90 counter-clockwise with the marker label side of the target cargo facing the industrial camera 52. The industrial camera 52 is mounted on a movement mechanism 53 for automatic alignment by photographing, and the alignment step specifically includes: the width D of the goods can be known through the goods information obtained by the central control platform 1, a short focal length and large depth of field camera is used, the target goods (the whole container) are all exposed under the field of view of the camera through the setting of experience values, the first photographing is carried out, the container is subjected to image acquisition through a character recognition module camera, and meanwhile, the definition and quality of the image are ensured; the pixel coordinate values of the target goods can be obtained by combining the target detection and image processing technology, namely, the width pixel coordinate value and the height pixel coordinate value of a container (namely, the container_width and the container_height) and the pixel coordinate value of a marker label, wherein the pixel coordinate value of the marker label comprises the leftmost pixel point of the label, the pixel coordinate value of the label width and the pixel coordinate value of the label height (namely, the label_left and the label_top and the label_height); acquiring the physical size corresponding to each pixel according to the unit=d/box_width; obtaining the length, the heel and the width of the tag according to the unit_label_width, wherein the unit_label_height is 2D (the length of the tag is width, and the width is height); obtaining the center point coordinate of the label, and obtaining the center point coordinate (x, y) according to the center_x=label_left+0.5×label_width and the center_y=label_top+0.5×label_high; finally, solving the difference between the coordinates of the center point of the tag and the coordinates of the center point of the photo, namely, the coordinates of the center point of the photo are (pic_width/2, pic_height/2), delta_x= (center_x-pic_width/2), delta_y= (center_x-pic_height/2), wherein pic represents the acquired picture, and the difference between the coordinates of the center point of the tag and the coordinates of the center point of the photo is obtained; after the coordinates delta_y of the coordinates delta_x of the label center point and the coordinates delta_x of the photo center point x are obtained, the controller controls the conveying screw rods in the directions x, y and z in the moving mechanism 53, and the camera moves to the position of the label so as to align the camera with the label.

The camera then takes a second photograph of the mark and then OCR recognizes the mark information. Specifically, the photographed photo is uploaded to a third party cloud, and key information (production place, name and specification) is extracted in a classified mode through OCR recognition of the cloud, and structured information is output. The customs information, such as the place of production, name of goods, number, specification (length, width, height, weight, etc.), is compared with the structured information (i.e. the information identified by the mark information) one by one, and for abnormal goods, the place of production on the mark label is inconsistent with the customs information, etc., in one embodiment of the present application, an alarm is set in the mark identifying device 5. The alarm is given by the alarm, and the alarm is separated by the following separating device 6, and is uploaded to the central control platform 1 for recording and statistics for analysis and tracing.

Further, comparing the customs clearance information obtained in advance with the mark information, namely comparing the structured information with the customs clearance information, judging whether the target goods are abnormal, if the structured information is different from the customs clearance information, the second judging result is abnormal, if the structured information is same with the customs clearance information, the second judging result is normal, and uploading the second judging result and the mark information to the central control platform 1.

Specifically, as shown in fig. 10, the separating device 6 includes a roller conveyor 61, a rotating mechanism 62, and an information transmission device;

the roller conveyor 61 is connected to the rotating mechanism 62 for conveying the target cargo to a target position;

the rotating mechanism 62 is configured to rotate according to the determination result;

the information transmission device is built in the rotating mechanism 62, and is configured to receive a determination result generated by the central control platform 1 according to the first determination result and the second determination result, obtain the target position information, and push the target position information to the central control platform 1.

Specifically, as shown in fig. 10, a roller conveyor belt is disposed in the mark recognition device 5 and the separation device 6 to convey the target goods. The separating device 6 is composed of a roller conveyor 61 and a rotating mechanism 62, the rotating mechanism 62 is controlled by a motor, the rotating mechanism 62 does not rotate, the target cargo normally flows to the next link and is transmitted to the first target position, and for abnormal cargo, the rotating mechanism 62 rotates by 90 degrees, and the target cargo is transported to the abnormal cargo handling area, namely the second target position.

It should be noted that, the information transmission device is built in the rotating mechanism 62, and is configured to receive a determination result generated by the central control platform 1 according to the first determination result and the second determination result, and rotate according to the determination result, specifically, when the first determination result and the second determination result are both normal goods, the rotating mechanism 62 does not rotate, and the target goods normally flow to the next link and are transmitted to the first target position; otherwise the rotation mechanism 62 rotates 90 deg., and the target cargo is transported to the area of abnormal cargo handling, i.e., the second target location. In the separating device 6, the abnormal goods screened by the checking device 4 and the mark recognition device are separated from the normal goods by the separating device 6 and are divided into two stacks, and further, when the user obtains the target goods placed at the second target position at the central control platform 1, the user can correspondingly perform manual re-detection so as to ensure the integrity of screening the abnormal conditions. The inspection personnel can further check abnormal conditions of the goods in a targeted manner according to the information of the central control platform 1.

Further, the central control platform comprises an instruction analysis module and a big data risk assessment module;

The instruction analysis module is used for acquiring a checking instruction, analyzing the checking instruction to generate an execution action instruction, and sending the execution action to the loading and unloading robot;

the big data risk assessment module is used for generating risk attribute quantization parameters of the target goods according to the customs clearance information and displaying the risk attribute quantization parameters on the central control platform.

Further, in an embodiment of the present application, the instruction analysis module and the big data risk assessment module are disposed on a central control machine of the central control platform. The customs clearance information and mark information specifically comprise information such as a production place of goods, a type of goods and the like, the risk attribute quantification parameters comprise risk categories and risk degrees, the risk categories comprise abnormal goods names, abnormal goods quantity, abnormal goods specifications, abnormal goods production places and the like, the risk degrees are weights corresponding to the risk categories, and the goods have risks of the type. In one embodiment of the present application, the balsa in the first target area is treated, so that targeted control is performed according to the cargo of each batch. When the abnormal risk index of the number of the balsa fish in the first target area is 6 through the decision tree C5.0 model, the risk attribute quantization parameter of the balsa fish in the first target area is the abnormal risk of the number of cargoes, and corresponding personnel can check and control the balsa fish from the first target area in a targeted manner, so that the number is emphasized.

The method comprises the steps of transmitting customs clearance information into a classification model, and outputting risk attribute quantization parameters of target goods; and displaying the risk attribute quantization parameters on the central control platform. The training process of the classification model specifically comprises the following steps: acquiring a preliminary training data set, performing feature engineering on the preliminary training data set to acquire risk attribute quantization parameters, and then labeling each data sample to generate a risk label, so as to obtain an available training data set and an available test data set, and training a classification model through the available training data set; and stopping training when the classification model reaches a preset training condition, taking the classification model obtained by the last training as a classification model after training, and outputting the classification model. The classification model selects a decision tree C5.0 model, and the preliminary model is established by adopting a scikit-learn package of Python, default parameters are used for parameter selection as a whole, and the depth of the tree is selected 16.

Further, in the training process, acquiring the preliminary training data set includes acquiring all import and export goods data in the database to form the preliminary training data set, including specific information such as goods production place, goods type, goods quantity, goods specification, goods quantity, goods weight, goods size, etc.

Then, a training data set is obtained through feature engineering processing; namely, by carrying out feature engineering on data of a preliminary training data set, adopting a text feature extraction method and using a natural language processing technology to identify information related to risks, wherein firstly, an entity identification technology extracts entities related to risks, such as cargo types, places of production, risk indexes and the like, from the text, which is helpful for determining specific objects in question in the text and helping to analyze risk information related to the entities and extract features related to the risks; meanwhile, unstructured information related to goods of data statistics is processed by using a text mining technology. The step of obtaining unstructured information comprises the following steps: data collection and cleansing, collecting unstructured text data containing cargo information, cleansing the data to remove noise, such as HTML tags, special characters, or other irrelevant information; word segmentation is carried out, and a text is segmented into words or phrases; then, extracting word stems and restoring word shapes, wherein the word stems are extracted to cut the words into the basic form, and the word shapes are restored to the original form; further, entity recognition is performed, and entities in the text, such as product names, places of production, weights and the like, are recognized, which is very important for understanding specific cargo information in the text; keyword extraction is then performed to capture core information of the text by extracting keywords or phrases in the text. The importance of words in text can be measured using TF-IDF (word frequency-inverse document frequency) methods; the use of topic modeling techniques (e.g., latent Dirichlet Allocation, LDA) to discover topic structures in text is employed to help understand the underlying topics and relevance of cargo descriptions. Text is divided into different categories or groups using a supervised learning classification algorithm. This helps organize and understand the large amount of text data. Finally, according to specific requirements, unstructured information related to the goods, such as the place of origin, size, weight and the like of the goods, is extracted from the processed text.

And labeling the training data set with a data label to obtain an available training data set. The method comprises the steps of marking corresponding risk attribute quantization parameters for samples of each training data set according to historical data, namely marking multidimensional risk labels for each sample, wherein label content comprises goods names, goods quantity, goods specifications, goods producing places, risk categories and the like, and the risk labels are used as training targets of a classification model. Wherein, in one embodiment of the present application, the format of the tag may be expressed as: [ product name: durian, number: 1200 boxes, specification (length x width x height) 300x150x400, weight: 15kg, origin: target region, risk attribute quantization parameters: weight abnormality risk). After labeling, an available training data set is obtained, and the decision tree C5.0 model is trained through the available training data set. In the training process, 80% of data are mined and extracted to serve as a training set, and 20% of data are served as a testing set. The training set is used to train the model and the test set is used to evaluate the performance of the model. At the completion of each training, an evaluation is made, and the test set is used to evaluate the performance of the model. Judging whether to continue training according to the evaluation result, stopping training when the decision tree C5.0 model reaches a preset training condition, taking the decision tree C5.0 model obtained by the last training as a decision tree C5.0 model after training is completed, and outputting the decision tree C5.0 model; the preset training condition is that the performance of the decision tree C5.0 model reaches a preset value, and preferably, in one embodiment of the application, training is stopped after the accuracy reaches more than 98%.

Further, in the application, for the trained decision tree C5.0 model, a training data set may be constructed by regularly acquiring historical data according to user settings, so that the decision tree C5.0 model is trained again, and the decision tree C5.0 model may be continuously learned. The model is trained by using historical data, and the improvement of the model performance mainly depends on continuously collected high-quality incremental data and the existing data to carry out training update according to a certain frequency. The big data risk assessment module obtains a risk assessment result after receiving the customs clearance information, and then carries out risk management and control.

Aiming at the problems that the processes of identification, quantity statistics, abnormal condition screening and the like of cargoes cannot be realized in the current logistics loading and unloading robots or automatic equipment of customs, so that the cargo clearance time is long, the box-type cargo intelligent checking integrated system provided by the invention converts the obtained checking instruction into an execution action instruction through the central control platform, and the loading and unloading robots automatically move to corresponding positions to grab target cargoes according to the acquired instruction and place the target cargoes into corresponding conveying devices, the conveying devices convey the cargoes to the checking devices to judge whether the size and the weight of the cargoes exceed preset requirements, and the mark recognition devices again judge whether the cargoes have problems or not, finally the abnormal and non-abnormal cargoes are conveyed respectively through the separating devices, so that the cargoes are conveyed to the target position, and the conveyed target position information is pushed to the central control platform.

Further, based on the box-type cargo intelligent inspection integrated system shown in fig. 1, the preferred embodiment of the present invention provides an inspection processing method of the box-type cargo intelligent inspection integrated system, as shown in fig. 11, the inspection processing method comprises the following steps:

step S10, a central control platform acquires a checking instruction, generates an execution action instruction according to the checking instruction, and the loading and unloading robot grabs the target goods according to the execution action instruction and places the target goods on the conveying device, meanwhile, the central control platform generates risk attribute quantization parameters of the target goods according to the pre-acquired customs clearance information and displays the risk attribute quantization parameters on the central control platform;

step S20, the conveying device transmits the target goods to the checking device, the checking device performs size measurement, quantity statistics and weight measurement on the target goods to obtain measurement results, compares preset parameter information with the measurement results to obtain checking results, judges whether the target goods are abnormal according to the checking results to obtain first judgment results, uploads the first judgment results to the central control platform, and conveys the target goods to the mark recognition device;

Step S30, the mark recognition device is connected with the tail end of the checking device and is used for extracting mark information of the target goods, comparing the prestored customs information with the mark information, judging whether the target goods are abnormal or not, obtaining a second judging result, uploading the second judging result and the mark information to the central control platform, and conveying the target goods to the separating device;

and S40, the separation device receives a judging result generated by the central control platform according to the first judging result and the second judging result, transmits the target goods to a target position according to the judging result, and pushes target position information to the central control platform.

Further, the inspection device performs size measurement, quantity statistics and weight measurement on the target cargo to obtain the measurement result, compares preset parameter information with the measurement result to obtain the inspection result, judges whether the target cargo is abnormal according to the inspection result to obtain a first judgment result, uploads the first judgment result to the central control platform, and transmits the target cargo to the mark recognition device, and the method specifically comprises the following steps:

The conveying module conveys the target goods to the weighing module;

the weighing module performs weight measurement on the target goods to obtain weighing information, and transmits the weighing information to a control cabinet;

the 3D camera performs size measurement and quantity statistics on the target goods to obtain size information and quantity information, and transmits the size information and the quantity information to the control cabinet;

the control cabinet obtains the measurement result according to the weighing information, the quantity information and the size information, compares the parameter information with the measurement result to obtain the checking result, judges whether the target goods are abnormal according to the checking result to obtain a first judging result, judges whether to alarm according to the first judging result, uploads the first judging result to the central control platform, and conveys the target goods to the mark recognition device.

The central control platform generates risk attribute quantization parameters of the target goods according to the customs clearance information acquired in advance, and displays the risk attribute quantization parameters on the central control platform, and the method specifically comprises the following steps:

acquiring customs clearance information, and inputting the customs clearance information into a classification model after training;

Generating risk attribute quantization parameters of the target goods through the classification model, and displaying the risk attribute quantization parameters on the central control platform;

wherein the classification model is trained based on historical ping data.

According to the invention, the obtained checking instruction is converted into the execution action instruction through the central control platform, the loading and unloading robot automatically moves to the corresponding position according to the obtained instruction to pick up target goods and place the target goods into the corresponding conveying device, the conveying device conveys the goods to the checking device to judge whether the size and the weight of the goods exceed the preset requirements, the mark recognition device is used for judging whether the goods have problems again, finally, the abnormal goods and the non-abnormal goods are conveyed respectively through the separating device, so that the goods are conveyed to the target position, the conveyed target position information is pushed onto the central control platform, in addition, when the type of the target goods can be exceeded according to the mark information, the goods can be pushed onto the central control platform as well, so that the processes of cold chain grabbing, loading and unloading, conveying, checking, size measuring, weighing and separating and information displaying can be realized automatically through a box-type goods intelligent integrated system, the workload of corresponding workers is reduced, the corresponding risk quantization parameters are generated through processing of the report information through the big data risk assessment module, the risk display is greatly improved, the risk display efficiency is convenient for users are increased.

Further, the invention may be designed to be modified, for example, a serial mechanical arm is used instead of a serial mechanical arm; or a mode of 2D laser radar and a reflecting plate is adopted, or a mode of RFID and mark points is adopted to realize the navigation and autonomous movement of the loading and unloading robot; or in the checking equipment, a distance measuring sensor is arranged on the top and two sides of the checking equipment, the top sensor can measure the height and the length of the container, and the two side sensors can measure the width of the container, so that the size information of the target goods can be detected.

It is to be understood that the invention is not limited in its application to the examples described above, but is capable of modification and variation in light of the above teachings by those skilled in the art, and that all such modifications and variations are intended to be included within the scope of the appended claims.

It should be understood that the sequence number of each step in the above embodiment does not mean the sequence of execution, and the execution sequence of each process should be determined by its function and internal logic, and should not be construed as limiting the implementation process of the embodiment of the present invention.

It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-described division of the functional units and modules is illustrated, and in practical application, the above-described functional distribution may be performed by different functional units and modules according to needs, i.e. the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-described functions. The functional units and modules in the embodiment may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit, where the integrated units may be implemented in a form of hardware or a form of a software functional unit. In addition, the specific names of the functional units and modules are only for distinguishing from each other, and are not used for limiting the protection scope of the present invention. The specific working process of the units and modules in the above device may refer to the corresponding process in the foregoing method embodiment, which is not described herein again.

In the foregoing embodiments, the descriptions of the embodiments are emphasized, and in part, not described or illustrated in any particular embodiment, reference is made to the related descriptions of other embodiments.

Those of ordinary skill in the art will appreciate that the elements and algorithm steps of the examples described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.

The above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art will understand that; the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions are not intended to depart from the spirit and scope of the various embodiments of the invention, which are also within the spirit and scope of the invention.

Claims (10)

1. The box-type cargo intelligent inspection integrated system is characterized by comprising a central control platform, a loading and unloading robot, a conveying device, an inspection device, a mark recognition device and a separation device;

the central control platform is connected with the loading and unloading robot, the conveying device, the checking device, the mark recognition device and the separating device through a network and is used for acquiring a checking instruction, analyzing the checking instruction to generate an execution action instruction, sending the execution action to the loading and unloading robot, generating risk attribute quantization parameters of target goods according to the customs clearance information acquired in advance, and displaying the risk attribute quantization parameters on the central control platform;

the loading and unloading robot is used for receiving an execution action instruction, grabbing target goods according to the execution action instruction and placing the target goods on the conveying device;

the conveying device is used for conveying the target goods to the checking device;

the checking device is connected with the tail end of the conveying device and is used for carrying out size measurement, quantity statistics and weight measurement on the target goods to obtain measurement results, comparing preset parameter information with the measurement results to obtain checking results, judging whether the target goods are abnormal according to the checking results to obtain first judgment results, uploading the first judgment results to the central control platform and conveying the target goods to the mark recognition device;

The mark recognition device is connected with the tail end of the checking device and is used for extracting mark information of the target goods, comparing the prestored customs information with the mark information, judging whether the target goods are abnormal or not, obtaining a second judging result, uploading the second judging result and the mark information to the central control platform, and conveying the target goods to the separating device;

the separating device is connected with the tail end of the mark recognition device and is used for receiving the judgment result generated by the central control platform according to the first judgment result and the second judgment result, transmitting the target goods to the target position according to the judgment result and pushing the target position information to the central control platform.

2. The integrated box cargo intelligent inspection system according to claim 1, wherein the loading and unloading robot comprises a chassis, a vehicle body control box, a series-parallel mechanical arm, a grabbing end, a visual perception module and a control module;

the chassis is positioned at the bottom of the loading and unloading robot and is used for driving the loading and unloading robot to move;

the vehicle body control box is fixedly arranged on the chassis and used for loading the control module and the visual perception module;

The series-parallel mechanical arm is arranged on the chassis and used for driving the grabbing tail end to move in space;

the grabbing tail end is arranged at the tail end of the series-parallel mechanical arm and used for adsorbing and conveying the target goods;

the visual perception module is arranged on the series-parallel mechanical arm and is used for acquiring the grabbing pose of the target goods;

the control module is arranged on the vehicle body control box and is used for controlling the chassis, the series-parallel mechanical arm and the grabbing tail end to adsorb the target goods and then transmitting the target goods to the conveying device;

the control module is respectively and electrically connected with the chassis, the visual perception module, the series-parallel mechanical arm and the grabbing tail end.

3. The integrated system for intelligently inspecting cargo in a box according to claim 1, wherein the conveying device comprises a frame, a back-rolling conveying belt, a lifting module and a roller conveying belt;

the frame is used for fixing the back-rolling conveyor belt, the lifting module and the roller conveyor belt;

the back-rolling conveying belt and the lifting module are arranged on the frame in a sliding manner, the roller conveying belt is detachably arranged on the frame, and the roller conveying belt and the lifting module are arranged on the same side of the frame, wherein the back-rolling conveying belt is arranged on the opposite sides of the roller conveying belt and the lifting module;

The back-rolling conveyor belt is used for placing the target goods;

the lifting module is used for adjusting the height of the back-rolling conveyor belt to be the height of the roller conveyor belt;

the roller conveyor belt is used for conveying the target goods to the checking device.

4. The integrated system for intelligently inspecting cargo in a box according to claim 1, wherein the inspecting device comprises a conveying module, a weighing module, a 3D camera, a control cabinet and an audible and visual alarm module;

the conveying module is used for conveying the target goods to the weighing module;

the weighing module is arranged below the conveying module and is used for carrying out weight measurement on the target goods to obtain weighing information and transmitting the weighing information to the control cabinet;

the 3D camera is fixedly arranged on the control cabinet and is used for carrying out size measurement and quantity statistics on the target goods to obtain size information and quantity information, and the size information and the quantity information are transmitted to the control cabinet;

the control cabinet is arranged beside the conveying module and is used for obtaining the measurement result according to the weighing information, the quantity information and the size information, comparing the parameter information with the measurement result to obtain the checking result, judging whether the target goods are abnormal according to the checking result to obtain a first judging result, and uploading the first judging result to the central control platform;

The audible and visual alarm module is arranged on the control cabinet and used for judging whether to alarm according to the checking result;

the control cabinet is electrically connected with the conveying module, the weighing module, the 3D camera and the audible and visual alarm module respectively.

5. The integrated system for intelligently inspecting cargo in a box according to claim 1, wherein the marker identification device comprises a marker identification rack, an industrial camera, a movement mechanism, a rotary platform and a marker identification and conveying module;

the mark identification rack is used for fixing the rotary platform and the movement mechanism;

the moving mechanism is arranged on the mark recognition rack and is used for rotating the target goods;

the industrial camera is used for primarily photographing the target goods to obtain an initial position photo, controlling the movement mechanism to move to a mark position according to the initial position photo, photographing the mark of the target goods to obtain a mark position photo, extracting mark information of the target goods according to the mark position photo, comparing the customs information acquired in advance with the mark information, judging whether the target goods are abnormal or not, obtaining a second judging result, and uploading the second judging result and the mark information to the central control platform;

The moving mechanism is arranged on the mark recognition frame and is used for moving according to the initial position picture;

the mark recognition and conveying module is arranged on the mark recognition rack and is used for conveying the target goods to the separating device.

6. The integrated system for intelligent inspection of cargo in a tank according to claim 1, wherein said separating means comprises a roller conveyor, a rotating mechanism and an information transmission means;

the roller conveyor belt is connected with the rotating mechanism and is used for conveying the target goods to a target position;

the rotating mechanism is used for rotating according to the judging result;

the information transmission device is arranged in the rotating mechanism and is used for receiving the judging result generated by the central control platform according to the first judging result and the second judging result, acquiring the target position information and pushing the target position information to the central control platform.

7. The integrated box cargo intelligent inspection system according to claim 1, wherein the central control platform comprises an instruction analysis module and a big data risk assessment module;

the instruction analysis module is used for acquiring a checking instruction, analyzing the checking instruction to generate an execution action instruction, and sending the execution action to the loading and unloading robot;

The big data risk assessment module is used for generating risk attribute quantization parameters of the target goods according to the customs clearance information and displaying the risk attribute quantization parameters on the central control platform.

8. A method of inspection based on the integrated system for intelligent inspection of cargo in a tank as claimed in any one of claims 1 to 7, comprising:

the central control platform acquires a checking instruction, generates an execution action instruction according to the checking instruction, the loading and unloading robot grabs the target goods according to the execution action instruction and places the target goods on the conveying device, and meanwhile, the central control platform generates risk attribute quantization parameters of the target goods according to the acquired customs clearance information in advance and displays the risk attribute quantization parameters on the central control platform;

the conveying device transmits the target goods to the checking device, the checking device performs size measurement, quantity statistics and weight measurement on the target goods to obtain measurement results, preset parameter information is compared with the measurement results to obtain checking results, whether the target goods are abnormal or not is judged according to the checking results to obtain first judgment results, the first judgment results are uploaded to the central control platform, and the target goods are conveyed to the mark recognition device;

The mark recognition device is connected with the tail end of the checking device and is used for extracting mark information of the target goods, comparing the prestored customs information with the mark information, judging whether the target goods are abnormal or not, obtaining a second judging result, uploading the second judging result and the mark information to the central control platform, and conveying the target goods to the separating device;

the separation device receives the judging result generated by the central control platform according to the first judging result and the second judging result, transmits the target goods to the target position according to the judging result, and pushes the target position information to the central control platform.

9. The inspection processing method according to claim 8, wherein the inspection device performs size measurement, quantity statistics and weight measurement on the target cargo to obtain the measurement result, compares preset parameter information with the measurement result to obtain the inspection result, determines whether the target cargo is abnormal according to the inspection result to obtain a first determination result, uploads the first determination result to the central control platform, and transmits the target cargo to the mark recognition device, and specifically comprises:

The conveying module conveys the target goods to the weighing module;

the weighing module performs weight measurement on the target goods to obtain weighing information, and transmits the weighing information to a control cabinet;

the 3D camera performs size measurement and quantity statistics on the target goods to obtain size information and quantity information, and transmits the size information and the quantity information to the control cabinet;

the control cabinet obtains the measurement result according to the weighing information, the quantity information and the size information, compares the parameter information with the measurement result to obtain the checking result, judges whether the target goods are abnormal according to the checking result to obtain a first judging result, judges whether to alarm according to the first judging result, uploads the first judging result to the central control platform, and conveys the target goods to the mark recognition device.

10. The method for inspecting and processing according to claim 8, wherein the central control platform generates risk attribute quantization parameters of the target cargo according to the customs clearance information acquired in advance, and displays the risk attribute quantization parameters on the central control platform, specifically comprising:

Inputting the customs clearance information into a classification model after training;

generating risk attribute quantization parameters of the target goods through the classification model, and displaying the risk attribute quantization parameters on the central control platform;

wherein the classification model is trained based on historical ping data.