Conveying line congestion prediction method and device, medium and program product

By obtaining the structural information of the conveyor line and the wrapping motion information and using pre-trained models for prediction, the problem of inability to avoid congestion in the prior art is solved, and more accurate congestion prediction and damage reduction are achieved.

CN119026742APending Publication Date: 2024-11-26BEIJING JINGDONG YUANSHENG TECH CO LTD
View PDF 0 Cites 5 Cited by

Patent Information

Application Number
CN202411110753.8
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-13
Publication Date
2024-11-26

AI Technical Summary

Technical Problem

The prior art only conducts alarm processing after congestion occurs, and the damage caused by congestion cannot be avoided in advance.

Method used

By obtaining the structural information of the conveyor line and the package motion information, the pre-trained congestion prediction model is used to predict in advance whether congestion will occur, thereby performing alarm processing and avoiding.

Benefits of technology

It improves the accuracy of congestion prediction of conveyor lines, avoids congestion in advance, and reduces the damage caused by congestion.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119026742A_ABST
    Figure CN119026742A_ABST
Patent Text Reader

Abstract

The embodiment of the invention discloses a transmission line congestion prediction method and device, a medium and a program product. The method comprises the following steps: acquiring target structure information of a target conveying line and a first image sequence shot for the target conveying line; and based on the target congestion prediction model, the target structure information and the first image sequence, predicting whether the target transmission line is congested, and obtaining a congestion prediction result corresponding to the target transmission line. Through the technical scheme of the embodiment of the invention, whether the transmission line is congested or not can be accurately predicted, so that the congestion can be avoided in advance, and the damage caused by the congestion can be reduced.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of logistics technology, and in particular to a method, device, medium and program product for predicting congestion of a conveyor line. Background Art

[0002] Conveyor lines are important equipment in the logistics production process and are widely used in warehousing and sorting. Therefore, ensuring the safe and efficient operation of conveyor lines is an important issue in logistics production. In actual logistics operations, conveyor line congestion is a common problem, which will greatly affect the production capacity of operations such as outbound delivery and sorting.

[0003] At present, sensors installed on the conveyor line are usually used to detect whether the conveyor line is congested so as to promptly issue an alarm. However, in the process of implementing the present invention, the inventors found that there are at least the following problems in the prior art:

[0004] The existing method is to issue an alarm after congestion has occurred, but the damage caused by congestion has already existed and it is impossible to avoid congestion in advance. Summary of the invention

[0005] The embodiments of the present invention provide a method, device, medium and program product for predicting congestion of a transmission line, so as to accurately predict whether congestion occurs in the transmission line, so as to avoid congestion in advance and reduce the damage caused by congestion.

[0006] In a first aspect, an embodiment of the present invention provides a method for predicting congestion of a transmission line, comprising:

[0007] Acquire target structural information of a target conveyor line and a first image sequence captured of the target conveyor line;

[0008] Based on the target congestion prediction model, the target structure information and the first image sequence, it is predicted whether the target conveying line is congested, and a congestion prediction result corresponding to the target conveying line is obtained.

[0009] In a second aspect, an embodiment of the present invention further provides an electronic device, the electronic device comprising:

[0010] one or more processors;

[0011] A memory for storing one or more programs;

[0012] When the one or more programs are executed by the one or more processors, the one or more processors implement the transmission line congestion prediction method provided by any embodiment of the present invention.

[0013] In a third aspect, an embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements a method for predicting congestion of a conveyor line as provided in any embodiment of the present invention.

[0014] In a fourth aspect, an embodiment of the present invention further provides a computer program product, including a computer program, which, when executed by a processor, implements the method for predicting transmission line congestion as provided in any embodiment of the present invention.

[0015] One embodiment of the above invention has the following advantages or beneficial effects:

[0016] By acquiring the target structural information of the target conveyor line and the first image sequence taken of the target conveyor line, and based on the target congestion prediction model, the target structural information and the first image sequence, it is predicted whether the target conveyor line is congested, so that the target congestion prediction model can simultaneously take into account the target conveyor line's own structural information and the package movement information on the target conveyor line, and more accurately determine the congestion prediction result corresponding to the target conveyor line, thereby improving the accuracy of the conveyor line congestion prediction, and can avoid congestion in advance and reduce the damage caused by congestion. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0018] Figure 1 It is a flow chart of a method for predicting congestion of a transmission line provided by an embodiment of the present invention;

[0019] Figure 2 is a flow chart of another method for predicting congestion of a transmission line provided by an embodiment of the present invention;

[0020] Figure 3 is an example of an affine transformation process involved in an embodiment of the present invention;

[0021] Figure 4 is a structural example diagram of a target congestion prediction model involved in an embodiment of the present invention;

[0022] Figure 5 It is a structural schematic diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0023] The present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the present invention, rather than to limit the present invention. It should also be noted that, for ease of description, only parts related to the present invention, rather than all structures, are shown in the accompanying drawings.

[0024] Figure 1 This is a flow chart of a method for predicting congestion of a conveyor line provided by an embodiment of the present invention. This embodiment can be applied to predicting whether congestion occurs on a package on a conveyor line. The method can be executed by a conveyor line congestion prediction device, which can be implemented by software and / or hardware and integrated into an electronic device. Figure 1 As shown, the method specifically comprises the following steps:

[0025] S110, acquiring target structural information of a target conveyor line and a first image sequence captured of the target conveyor line.

[0026] The target conveyor line refers to the entire conveyor line for which congestion currently needs to be predicted. The conveyor line is a device for conveying packages. The line body in the conveyor line can be composed of rollers and belts. For example, the conveyor line can refer to a conveyor belt, etc. The target structural information refers to the structural characteristics of the target conveyor line itself. The target structural information refers to the structural information that can cause congestion in the target conveyor line. Exemplarily, the target structural information includes but is not limited to at least one of the following: there is a conveyor line confluence in the target conveyor line, there is a bend in the target conveyor line, a photoelectric sensor is installed in the target conveyor line, and there is an uphill slope in the target conveyor line.

[0027] Among them, when there is a conveyor line confluence on the target conveyor line, that is, when multiple conveyor lines merge into one conveyor line (i.e., the target conveyor line), the packages on the multiple conveyor lines merge, and when the package flow exceeds the current package flow that can be accommodated, the target conveyor line will be congested. When there is a bend in the target conveyor line, if the package on the target conveyor line is stuck on the edge of the bend when passing through the bend, it will block the subsequent packages, which will cause congestion in the target conveyor line. When a photoelectric sensor is installed on the target conveyor line, the photoelectric sensor will determine that congestion has occurred after the light source is blocked for a long enough time, causing the conveyor line to stop, so as to limit the flow and reduce the downstream pressure. However, the light source may be blocked by a relatively long package on the rear conveyor line. After the rear conveyor line stops, it will no longer move forward and continue to block the light source, thus causing a logical deadlock that cannot be solved. When there is an uphill slope on the target conveyor line, some packages may be stuck in the middle section during the uphill process due to their own weight and other factors, blocking subsequent packages, thereby causing congestion in the target conveyor line.

[0028] The first image sequence may include a plurality of first images arranged in sequence according to the shooting time sequence. Each first image refers to a panoramic image of the target conveyor line, that is, an image of the conveyor line captured within the shooting angle of view. The first image sequence may also refer to a video captured of the target conveyor line. The first image sequence may be used to characterize the package movement information on the target conveyor line. Package movement information refers to package distribution information that changes over time. Package distribution information may include package size information, package shape information, package quantity information, etc.

[0029] Specifically, it is detected whether the target conveyor line has structural information that can cause congestion, and the existing structural information is determined as the target structural information. When congestion needs to be predicted, the target conveyor line is photographed using a camera above the target conveyor line to obtain a first image sequence required for the current prediction.

[0030] S120 , predicting whether congestion occurs in the target conveying line based on the target congestion prediction model, the target structure information and the first image sequence, and obtaining a congestion prediction result corresponding to the target conveying line.

[0031] The target congestion prediction model may be a neural network model for predicting whether a transmission line is congested. For example, the target congestion prediction model may be a binary classification model. The target congestion prediction model is obtained by training based on sample data in advance to ensure the accuracy of congestion prediction.

[0032] Specifically, the target structure information and the first image sequence can be directly input into the target congestion prediction model obtained by pre-training to perform congestion prediction, or the target structure information can be first encoded to obtain target structure encoding information, so as to simplify the target structure information and improve the prediction efficiency, such as performing binary encoding processing on the target structure information, i.e., 01 encoding, so as to convert the target structure information into target structure encoding information that is easier to identify by the target congestion prediction model, and then input the target structure encoding information and the first image sequence into the target congestion prediction model obtained by pre-training to perform congestion prediction. Based on the congestion probability value output by the target congestion prediction model, the congestion prediction result corresponding to the target conveying line is determined. For example, if the congestion probability value is greater than or equal to the preset probability value, the congestion prediction result is determined to be that the target conveying line is about to be congested, such as congestion will occur after a preset time length (such as 1 minute) at the end of the shooting of the first image sequence. If the congestion probability value is less than the preset probability value, the congestion prediction result is determined to be that the target conveying line will not be congested. After predicting that the target conveyor line will be congested, an alarm can be issued to remind relevant personnel to handle it in time, thereby avoiding the congestion in advance and reducing the production capacity loss caused by the congestion.

[0033] It should be noted that the target conveyor line's own structural information and the package movement information on the target conveyor line may affect the congestion of the conveyor line. For example, if there is a bend in the conveyor line, if the volume of the goods is too large or the length is too long, it is easy to get stuck in the bend, causing congestion in the rear. Therefore, by simultaneously inputting the target structure encoding information and the first image sequence into the target congestion prediction model, the target congestion prediction model can simultaneously take into account the target conveyor line's own structural information and the package movement information on the target conveyor line, so that it can more accurately predict whether the conveyor line is congested, thereby improving the accuracy of the conveyor line congestion prediction.

[0034] The technical solution of this embodiment obtains the target structural information of the target conveyor line and the first image sequence taken of the target conveyor line, and predicts whether congestion occurs in the target conveyor line based on the target congestion prediction model, the target structural information and the first image sequence, so that the target congestion prediction model can simultaneously take into account the structural information of the target conveyor line itself and the package movement information on the target conveyor line, and more accurately determine the congestion prediction result corresponding to the target conveyor line, thereby improving the accuracy of conveyor line congestion prediction, and can avoid congestion in advance and reduce the damage caused by congestion.

[0035] On the basis of the above-mentioned technical solutions, step S120 may include: based on the target structure information, determining the remaining structure information that does not exist in the target conveying line; encoding the target structure information into a first preset character and encoding the remaining structure information into a second preset character according to the encoding order of the structure information to obtain the target structure encoding information; based on the target congestion prediction model, the target structure encoding information and the first image sequence, predicting whether congestion occurs in the target conveying line, and obtaining the congestion prediction result corresponding to the target conveying line.

[0036] The target structural information refers to structural information existing in the target conveyor line that can cause congestion in the conveyor line. The remaining structural information refers to structural information not existing in the target conveyor line that can cause congestion in the conveyor line. The first preset character is a pre-set character used to represent any character that has structural information in the conveyor line, such as the number "1". The second preset character is a pre-set character used to represent any character that does not have structural information in the conveyor line, such as the number "0". The first preset character is different from the second preset character.

[0037] Specifically, all structural information that can cause congestion in the conveyor line can be obtained in advance, and the remaining structural information except the target structural information in all structural information can be determined. According to the coding order of all structural information, the target structural information is encoded as the first preset character in turn, and the remaining structural information is encoded as the second preset character, so as to obtain the encoded target structural coding information. For example, if all structural information that can cause congestion in the conveyor line is 4 kinds of structural information, namely: merging, curve, photoelectric sensor and uphill, then a four-bit 01 code can be used to represent it, and the four positions from front to back represent merging, curve, photoelectric sensor and uphill respectively, the first preset character is 1, indicating that the structural information exists, and the second preset character is 0, indicating that the structural information does not exist. If the target structural information is: there is only a curve in the target conveyor line, the encoded target structural coding information is: 0100. By inputting the target structural coding information and the first image sequence into the pre-trained target congestion prediction model for congestion prediction, the congestion prediction result corresponding to the target conveyor line can be obtained more quickly.

[0038] On the basis of the above-mentioned technical solutions, the target congestion prediction model is obtained by pre-training based on positive sample data and negative sample data; wherein the positive sample data refers to data in which congestion occurs on the conveyor line after a preset time length from the end of the shooting of the image sequence; and the negative sample data refers to data in which congestion does not occur on the conveyor line after a preset time length from the end of the shooting of the image sequence.

[0039] Among them, positive sample data refers to sample data where congestion occurs on the conveyor line. For example, the probability value of congestion corresponding to the conveyor line in the positive sample data is 1. Negative sample data refers to sample data where congestion does not occur on the conveyor line. For example, the probability value of congestion corresponding to the conveyor line in the negative sample data is 0. Both positive sample data and negative sample data include two types of information: structural information of the conveyor line and the captured image sequence, but the sample labels are different.

[0040] Specifically, by detecting whether the conveyor line in each collected sample data is congested within a preset time (such as 1 minute) after the image sequence is shot, it is determined whether each sample data is positive sample data or negative sample data. By obtaining all the positive sample data and negative sample data, the congestion prediction model to be trained is fully trained in a supervised manner to obtain the target congestion prediction model after the training, thereby ensuring the prediction accuracy of the target congestion prediction model.

[0041] Figure 2A flowchart of another method for predicting congestion of a conveyor line provided by an embodiment of the present invention. Based on the above embodiments, this embodiment optimizes the step of "predicting whether congestion occurs in the target conveyor line based on the target congestion prediction model, target structure information and the first image sequence, and obtaining the congestion prediction result corresponding to the target conveyor line". The explanations of the terms that are the same or corresponding to the above embodiments are not repeated here.

[0042] See also Figure 2 Another method for predicting congestion of a transmission line provided in this embodiment specifically includes the following steps:

[0043] S210, acquiring target structural information of a target conveying line and a first image sequence captured of the target conveying line.

[0044] S220: Process the target transmission area in each first image in the first image sequence to obtain a processed second image sequence.

[0045] The target transmission area may refer to a transmission area on the target transmission line where congestion needs to be predicted. The target transmission area may be a partial transmission area of ​​the target transmission line or the entire transmission area of ​​the target transmission line, which may be specifically configured based on business needs. The second image sequence may include multiple second images. The first image corresponds to the second image one by one. The second image may refer to a partial image of the first image where the target transmission area is located.

[0046] Specifically, based on the location information of the target transmission area, each first image in the first image sequence can be cropped, and the cropped local image where the target transmission area is located is determined as the second image, thereby obtaining a second image sequence. It should be noted that each second image only contains the package information in the target transmission area and does not contain other irrelevant information, thereby avoiding the influence of other irrelevant information, realizing the congestion prediction of the conveyor line in a specific area, and improving the prediction accuracy.

[0047] Exemplarily, step S220 may include: performing affine transformation processing on the target transmission area in each first image in the first image sequence to obtain a second image sequence with a preset image size.

[0048] The affine transformation is to perform linear transformation and translation processing on the target transmission area in the first image to convert the local image where the target transmission area is located in the first image into a second image with a preset image size. The preset image size can be the length and width of the second image that are preset.

[0049] Specifically, for each first image in the first image sequence, an affine transformation is performed on the target transmission area in the first image based on an affine transformation function to obtain a second image having a preset image size and only including the target transmission area. The affine transformation function is determined based on the shape information of the target transmission area and the preset image size. The shape information of the target transmission area may include position information of four vertices of the target transmission area, which may be marked in the first image. Figure 3 The strip border area in the first image is the target transmission area. By performing affine transformation on the target transmission area in the first image, the target transmission area in the first image is converted into a second image with the same size, so as to further improve the model prediction efficiency and accuracy.

[0050] S230 , based on the target congestion prediction model, the target structure information and the second image sequence, predict whether congestion occurs in the target conveying line within the target transmission area, and obtain a congestion prediction result corresponding to the target conveying line.

[0051] Specifically, the target structure information and the second image sequence with the same size are input into the target congestion prediction model obtained by pre-training to predict the congestion of the target transmission area, and the congestion prediction result corresponding to the target transmission line is determined based on the congestion probability value output by the target congestion prediction model. For example, if the congestion probability value is greater than or equal to the preset probability value, the congestion prediction result is determined to be that the target transmission line is about to be congested in the target transmission area, such as congestion will occur after a preset time (such as 1 minute) at the end of the shooting of the first image sequence. If the congestion probability value is less than the preset probability value, the congestion prediction result is determined to be that the target transmission line will not be congested in the target transmission area. After predicting that the target transmission line will be congested in the target transmission area, an alarm process can be performed to remind relevant personnel to promptly handle the parcel situation in the target transmission area, so that congestion can be avoided in advance and the production capacity loss caused by congestion can be reduced.

[0052] Exemplarily, the target congestion prediction model may include: an image processing sub-model and a fully connected sub-model. The image processing sub-model may be a network model for processing image sequences. For example, see Figure 4, the image processing sub-model may include multiple feature extraction layers and a pooling layer. The feature extraction layer corresponds to the input image one by one. All feature extraction layers share parameters. Each feature extraction layer may include a convolutional neural network and a transformer encoder. Among them, the convolutional neural network is used to extract the feature information of a single image, and the transformer encoder is used to learn the associated feature information between image sequences based on the image feature information extracted by the convolutional neural network. The pooling layer is used to pool the image feature information output by all feature extraction layers to obtain the target image feature information with the same dimension, so that image sequences of different lengths can be converted into feature vectors of uniform length. The fully connected sub-model can be a neural network model for nonlinear transformation.

[0053] Exemplarily, step S230 may include: inputting the second image sequence into the image processing sub-model to perform feature extraction and pooling processing on each second image in the second image sequence, and obtaining feature information of the processed target image; inputting the target structure information and the target image feature information into the fully connected sub-model to predict whether congestion occurs, and obtaining a congestion prediction result corresponding to the target conveyor line.

[0054] Specifically, see Figure 4 , each feature extraction layer in the image processing sub-model extracts features from the input second image. For example, the convolutional neural network in each feature extraction layer performs preliminary feature extraction on the input second image, and inputs the extracted image feature information into the transformer encoder for feature extraction again, so as to obtain the candidate image feature information that can characterize the package movement information on the target conveyor line. The candidate image feature information output by each feature extraction layer is input into the pooling layer for minimum pooling or maximum pooling and other processing to obtain the target image feature information with the same dimension. The target image feature information is used to reflect the package movement information on the target conveyor line. The target structure information and the target image feature information can be spliced ​​and input into the fully connected sub-model to predict whether congestion occurs, and the probability value of congestion is output. The final congestion prediction result can be determined based on the probability value of congestion output by the fully connected sub-model.

[0055] It should be noted that, when the target structure information is encoded in advance to obtain the target structure encoding information, the target structure encoding information and the target image feature information are spliced ​​and input into Figure 4 Whether congestion will occur is predicted in the fully connected sub-model in , and the probability value of congestion is output.

[0056] Exemplarily, when training the target congestion prediction model, it is also necessary to process the target transmission area in the image sequence in the positive sample data and the negative sample data in the manner of step S220 to obtain an image sequence with the same size. Supervised model training is performed based on the structural information of the conveyor line in the positive sample data and the image sequence with the same size, and the structural information of the conveyor line in the negative sample data and the image sequence with the same size, so as to obtain a universal target congestion prediction model, which can be applied to the congestion prediction of different conveyor lines.

[0057] The technical solution of this embodiment processes the target transmission area in each first image in the first image sequence to obtain a processed second image sequence, and based on the target congestion prediction model, the target structure information and the second image sequence, it can more accurately predict whether congestion occurs in the target conveyor line within the target transmission area, thereby realizing congestion prediction of the conveyor line in a specific area and further improving the accuracy of congestion prediction.

[0058] Figure 5 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. Figure 5 A block diagram of an exemplary electronic device 12 suitable for use in implementing embodiments of the present invention is shown. Figure 5 The electronic device 12 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0059] like Figure 5 As shown, the electronic device 12 is in the form of a general purpose computing device. The components of the electronic device 12 may include, but are not limited to: one or more processors or processing units 16, a system memory 28, and a bus 18 that connects various system components (including the system memory 28 and the processing unit 16).

[0060] Bus 18 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor or a local bus using any of a variety of bus architectures. By way of example, these architectures include, but are not limited to, an Industry Standard Architecture (ISA) bus, a Micro Channel Architecture (MAC) bus, an Enhanced ISA bus, a Video Electronics Standards Association (VESA) local bus, and a Peripheral Component Interconnect (PCI) bus.

[0061] The electronic device 12 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by the electronic device 12, including volatile and non-volatile media, removable and non-removable media.

[0062] The system memory 28 may include computer system readable media in the form of volatile memory, such as random access memory 30 (RAM) and / or cache memory 32. The electronic device 12 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, the storage system 34 may be used to read and write non-removable, non-volatile magnetic media ( Figure 5 not shown, usually called a "hard drive"). Although Figure 5 Not shown in the figure, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk"), and an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, a DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to the bus 18 via one or more data medium interfaces. The system memory 28 may include at least one program product having a set (e.g., at least one) of program modules that are configured to perform the functions of the various embodiments of the present invention.

[0063] A program / utility 40 having a set (at least one) of program modules 42 may be stored, for example, in system memory 28, such program modules 42 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment. Program modules 42 generally perform the functions and / or methods of the embodiments described herein.

[0064] The electronic device 12 may also communicate with one or more external devices 14 (e.g., keyboards, pointing devices, displays 24, etc.), may communicate with one or more devices that enable a user to interact with the electronic device 12, and / or may communicate with any device that enables the electronic device 12 to communicate with one or more other computing devices (e.g., network cards, modems, etc.). Such communication may be performed via an input / output (I / O) interface 22. Furthermore, the electronic device 12 may also communicate with one or more networks (e.g., local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) via a network adapter 20. As shown, the network adapter 20 communicates with other modules of the electronic device 12 via a bus 18. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the electronic device 12, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0065] The processing unit 16 executes various functional applications and data processing by running the program stored in the system memory 28, for example, implementing a method for predicting congestion of a conveyor line provided in any embodiment of the present invention, the method comprising:

[0066] Acquire target structural information of a target conveyor line and a first image sequence captured of the target conveyor line;

[0067] Based on the target congestion prediction model, the target structure information and the first image sequence, it is predicted whether the target conveying line is congested, and a congestion prediction result corresponding to the target conveying line is obtained.

[0068] Of course, those skilled in the art can understand that the processor can also implement the technical solution of the transmission line congestion prediction method provided by any embodiment of the present invention.

[0069] This embodiment provides a computer-readable storage medium having a computer program stored thereon. When the program is executed by a processor, the method steps for predicting congestion of a conveyor line provided in any embodiment of the present invention are implemented. The method includes:

[0070] Acquire target structural information of a target conveyor line and a first image sequence captured of the target conveyor line;

[0071] Based on the target congestion prediction model, the target structure information and the first image sequence, it is predicted whether the target conveying line is congested, and a congestion prediction result corresponding to the target conveying line is obtained.

[0072] The computer storage medium of the embodiment of the present invention can adopt any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, but not limited to: an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, a computer-readable storage medium can be any tangible medium containing or storing a program, which can be used by an instruction execution system, device or device or used in combination with it.

[0073] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0074] The program code embodied on the computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0075] Computer program code for performing the operations of the present invention may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0076] An embodiment of the present invention further provides a computer program product, including a computer program, which, when executed by a processor, implements the method for predicting congestion of a transmission line provided by any embodiment of the present invention.

[0077] In the process of implementation, the computer program product can be written in one or more programming languages ​​or a combination thereof to perform the computer program code of the present invention, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (for example, using an Internet service provider to connect through the Internet).

[0078] It should be understood by those skilled in the art that the modules or steps of the present invention described above can be implemented by a general-purpose computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, optionally, they can be implemented by a program code executable by a computer device, so that they can be stored in a storage device and executed by the computing device, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software.

[0079] Note that the above are only preferred embodiments of the present invention and the technical principles used. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in more detail through the above embodiments, the present invention is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present invention, and the scope of the present invention is determined by the scope of the appended claims.

Claims

1. A method for predicting congestion in a transmission line, characterized in that: include: Acquire target structural information of a target conveyor line and a first image sequence captured of the target conveyor line; Based on the target congestion prediction model, the target structure information and the first image sequence, it is predicted whether the target conveying line is congested, and a congestion prediction result corresponding to the target conveying line is obtained.

2. The method according to claim 1, characterized in that The target structure information includes at least one of the following: The target conveying line has a conveying line confluence, the target conveying line has a curve, the target conveying line is installed with a photoelectric sensor, and the target conveying line has an uphill slope.

3. The method according to claim 1, characterized in that: The predicting whether the target conveying line is congested based on the target congestion prediction model, the target structure information and the first image sequence to obtain a congestion prediction result corresponding to the target conveying line includes: Based on the target structural information, determining other structural information that does not exist in the target conveying line; According to the coding order of the structure information, the target structure information is encoded into a first preset character, and the remaining structure information is encoded into a second preset character to obtain target structure coding information; Based on the target congestion prediction model, the target structure encoding information and the first image sequence, it is predicted whether the target conveying line is congested, and a congestion prediction result corresponding to the target conveying line is obtained.

4. The method according to claim 1, characterized in that: The predicting whether the target conveying line is congested based on the target congestion prediction model, the target structure information and the first image sequence to obtain a congestion prediction result corresponding to the target conveying line includes: Processing the target transmission area in each first image in the first image sequence to obtain a processed second image sequence; Based on the target congestion prediction model, the target structure information and the second image sequence, it is predicted whether the target conveying line is congested in the target transmission area, and a congestion prediction result corresponding to the target conveying line is obtained.

5. The method according to claim 4, characterized in that The step of processing the target transmission area in each first image in the first image sequence to obtain a processed second image sequence includes: Affine transformation processing is performed on the target transmission area in each first image in the first image sequence to obtain a second image sequence with a preset image size.

6. The method according to claim 4, characterized in that The target congestion prediction model includes: an image processing sub-model and a fully connected sub-model; The predicting whether congestion occurs in the target conveying line within the target transmission area based on the target congestion prediction model, the target structure information and the second image sequence, and obtaining the congestion prediction result corresponding to the target conveying line, comprises: Inputting the second image sequence into the image processing sub-model to perform feature extraction and pooling processing on each second image in the second image sequence to obtain feature information of the processed target image; The target structure information and the target image feature information are input into the fully connected sub-model to predict whether congestion occurs, and a congestion prediction result corresponding to the target conveying line is obtained.

7. The method according to any one of claims 1 to 6, characterized in that: The target congestion prediction model is obtained by training in advance based on positive sample data and negative sample data; The positive sample data is data showing that the conveyor line is congested after a preset time period from the end of the shooting of the image sequence; and the negative sample data is data showing that the conveyor line is not congested after a preset time period from the end of the shooting of the image sequence.

8. An electronic device, characterized in that: The electronic device comprises: one or more processors; A memory for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the transmission line congestion prediction method as described in any one of claims 1-7.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method for predicting transmission line congestion as described in any one of claims 1 to 7 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the computer program implements the method for predicting congestion of a conveyor line as described in any one of claims 1 to 7.

Citation Information

Cited By

  • Intelligent matching system for dynamic speed regulation of conveyor belt for flexible production

    CN120191663A

  • A flexible production conveyor belt dynamic speed regulation intelligent matching system

    CN120191663B

  • Logistics conveying line integrated control system based on modularized intelligent driving card

    CN120779831A

  • Conveyor belt control method and device, electronic equipment and computer readable medium

    CN121516508A

  • Data processing method and device, electronic equipment and storage medium

    CN121659016A