Data processing method and device, electronic equipment and storage medium

Abstract

The invention discloses a data processing method and device, electronic equipment and a storage medium, and relates to the technical field of data processing. A specific embodiment of the method comprises the steps of receiving a congestion identification instruction, obtaining corresponding conveyor belt information and a time interval, and querying a package transmission video of a conveyor belt in the time interval; identifying parcel transportation features of each parcel in the parcel transmission video, obtaining conveyor belt features and conveyor belt speed of a conveyor belt, and generating a target transmission feature vector corresponding to the conveyor belt; querying each connection conveyor belt connected with the conveyor belt, and determining a connection transmission feature vector of each connection conveyor belt; and inputting the target transmission feature vector and each connection transmission feature vector into a preset identification model to obtain a congestion degree corresponding to the conveyor belt. According to the embodiment, the problems that the package sorting efficiency is reduced and the timeliness of package sorting cannot be guaranteed due to the fact that only the package condition at the outlet of the conveying belt is considered in a congestion detection mode of a sensor and processing is carried out after congestion occurs can be solved.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a method, apparatus, electronic device, and storage medium for data processing. Background Technology

[0002] In the logistics process, parcel sorting is a crucial step. Sorting centers use conveyor belts to transport parcels requiring sorting to designated areas, where they are then sorted by equipment and transported to distribution stations for delivery. Logistics services typically have strict time-sensitive requirements, and parcel sorting efficiency is a key indicator affecting timeliness. However, when the volume of goods in a sorting center is large, parcel congestion can occur in some areas, thus impacting sorting efficiency. Related technologies can install sensors at the conveyor belt exit to detect congestion and manually clear it when detected. However, this detection method only considers the parcel situation at the conveyor belt exit and only addresses congestion after it has already occurred, which also reduces sorting efficiency and cannot guarantee timely parcel delivery. Summary of the Invention

[0003] In view of this, embodiments of the present invention provide a data processing method, apparatus, electronic device, and storage medium that can solve the problem that the congestion detection method of setting sensors at the conveyor belt exit only considers the package situation at the conveyor belt exit and only processes the situation after congestion has occurred, which reduces the efficiency of package sorting and cannot guarantee the timeliness of package sorting.

[0004] To achieve the above objectives, according to one aspect of the present invention, a data processing method is provided.

[0005] An embodiment of the present invention provides a data processing method comprising: receiving a congestion identification instruction; obtaining corresponding conveyor belt information and a time interval; querying a video of package delivery by the conveyor belt within the time interval; identifying the package transport characteristics of each package in the video of package delivery; obtaining the conveyor belt characteristics and conveyor belt speed of the conveyor belt; generating a target delivery feature vector corresponding to the conveyor belt; querying each connecting conveyor belt connected to the conveyor belt; determining the connection delivery feature vector of each connecting conveyor belt; and inputting the target delivery feature vector and each connection delivery feature vector into a preset identification model to obtain the congestion level corresponding to the conveyor belt.

[0006] In one embodiment, identifying the package transport characteristics of each package in the package transport video includes: identifying each package in the package transport video, determining the detection box corresponding to each package, obtaining the position features of the detection box corresponding to each package, calculating the movement features of each package; and concatenating the position features and the movement features to obtain the package transport characteristics of each package.

[0007] In another embodiment, querying each connecting conveyor belt connected to the conveyor belt and determining the connection transmission feature vector of each connecting conveyor belt includes: querying the connection matrix corresponding to the conveyor belt, identifying the first connecting conveyor belt into which the package enters and the second connecting conveyor belt into which the package enters, obtaining the transmission feature vectors of the first connecting conveyor belt and the second connecting conveyor belt, and determining them as connection transmission feature vectors.

[0008] In another embodiment, inputting the target transmission feature vector and each of the connection transmission feature vectors into a preset recognition model includes: inputting the target transmission feature vector and each of the connection transmission feature vectors into a preset neural network model to obtain a combined feature vector of the conveyor belt; and inputting the combined feature vector into the preset recognition model.

[0009] In another embodiment, before querying each connected conveyor belt connected to the conveyor belt, the method further includes: obtaining the conveyor belt position corresponding to each preset area within the package transmission area, determining the structural relationship between each preset area, and generating a connection matrix of the conveyor belts based on the structural relationship.

[0010] In another embodiment, identifying the package transport characteristics of each package in the package transport video includes: obtaining a preset area included by the conveyor belt, and identifying the package transport characteristics of packages in the preset area in the package transport video.

[0011] In another embodiment, the method further includes: inputting the target transmission feature vector and the connection transmission feature vector into a preset prediction model to obtain the congestion level of the conveyor belt at the predicted time.

[0012] To achieve the above objectives, according to another aspect of the present invention, a data processing apparatus is provided.

[0013] An embodiment of the present invention provides a data processing apparatus comprising: an acquisition unit, configured to receive a congestion identification instruction, acquire corresponding conveyor belt information and a time interval, and query a video of package delivery by the conveyor belt within the time interval; a generation unit, configured to identify the package transport characteristics of each package in the video of package delivery, acquire the conveyor belt characteristics and the conveyor belt speed, and generate a target delivery feature vector corresponding to the conveyor belt; a determination unit, configured to query each connecting conveyor belt connected to the conveyor belt and determine the connection delivery feature vector of each connecting conveyor belt; and an identification unit, configured to input the target delivery feature vector and each connection delivery feature vector into a preset identification model to determine the congestion level corresponding to the conveyor belt.

[0014] In one embodiment, the generating unit is specifically configured to: identify each package in the package delivery video, determine the detection box corresponding to each package, obtain the position features of the detection box corresponding to each package, calculate the movement features of each package, and concatenate the position features and the movement features to obtain the package transportation features of each package.

[0015] In another embodiment, the determining unit is specifically used to: query the connection matrix corresponding to the conveyor belt, identify the first connecting conveyor belt into which the package enters and the second connecting conveyor belt into which the package enters, obtain the transmission feature vectors of the first connecting conveyor belt and the second connecting conveyor belt, and determine them as connection transmission feature vectors.

[0016] In another embodiment, the identification unit is specifically used to: input the target transmission feature vector and each of the connection transmission feature vectors into a preset neural network model to obtain a combined feature vector of the conveyor belt; and input the combined feature vector into a preset identification model.

[0017] In another embodiment, the generating unit is further configured to: obtain the conveyor belt positions corresponding to each preset area within the package transmission area, determine the structural relationship between each preset area, and generate a connection matrix of the conveyor belt based on the structural relationship.

[0018] In another embodiment, the generating unit is specifically used to: acquire the target preset area included by the conveyor belt, and identify the package transportation characteristics of the packages in the target preset area in the package transportation video.

[0019] In another embodiment, the device further includes: the prediction unit, configured to input the target transmission feature vector and the connection transmission feature vector into a preset prediction model to obtain the congestion level of the conveyor belt at the predicted time.

[0020] To achieve the above objectives, according to another aspect of the present invention, an electronic device is provided.

[0021] An electronic device according to an embodiment of the present invention includes: one or more processors; and a storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the data processing method provided in the embodiment of the present invention.

[0022] To achieve the above objectives, according to another aspect of the present invention, a computer-readable medium is provided.

[0023] An embodiment of the present invention provides a computer-readable medium having a computer program stored thereon, which, when executed by a processor, implements the data processing method provided in the embodiment of the present invention.

[0024] To achieve the above objectives, according to another aspect of the present invention, a computer program product is provided.

[0025] A computer program product according to an embodiment of the present invention includes a computer program that, when executed by a processor, implements the data processing method provided in the embodiment of the present invention.

[0026] One embodiment of the above invention has the following advantages or beneficial effects:

[0027] In this embodiment of the invention, after receiving a congestion identification command, the system retrieves video footage of package transport on the conveyor belt within the corresponding time interval to identify the congestion. It then identifies the transport characteristics of each package on the conveyor belt, indicating the current status of the packages being transported. Simultaneously, it acquires the conveyor belt's characteristics and speed, representing its operational status. Based on the package transport characteristics, conveyor belt characteristics, and conveyor belt speed, a target transport feature vector is generated corresponding to the conveyor belt. Next, the system queries each connecting conveyor belt to determine the connection transport feature vector, representing the transport status of the connected conveyor belt. Finally, the target transport feature vector and the connection transport feature vector are input into a preset identification model to determine the degree of congestion corresponding to the conveyor belt. In this embodiment of the invention, the congestion identification model is constructed by inputting multiple dimensions of features, including the characteristics of the conveyor belt being transported, the characteristics of the conveyor belt itself, and the characteristics of the connecting conveyor belts, into the congestion identification model. This allows for accurate identification of the congestion status of the transported packages from multiple perspectives, enabling timely and accurate implementation of corresponding solutions to minimize the reduction in package sorting efficiency caused by conveyor belt congestion and ensure the timeliness of package sorting.

[0028] The further effects of the aforementioned unconventional alternative methods will be explained below in conjunction with specific implementation methods. Attached Figure Description

[0029] The accompanying drawings are provided to better understand the invention and are not intended to unduly limit the scope of the invention. Wherein: Figure 1 This is a main schematic diagram of a conveyor belt structure according to an embodiment of the present invention; Figure 2 This is a schematic diagram of a main flow of a data processing method according to an embodiment of the present invention; Figure 3 This is a schematic diagram of another main flow of a data processing method according to an embodiment of the present invention; Figure 4 This is a schematic diagram of the main units of a data processing apparatus according to an embodiment of the present invention; Figure 5This is an exemplary system architecture diagram in which embodiments of the present invention can be applied; Figure 6 This is a schematic diagram of the structure of a computer system suitable for implementing embodiments of the present invention. Detailed Implementation

[0030] The following description, in conjunction with the accompanying drawings, illustrates exemplary embodiments of the present invention, including various details to aid understanding. These details should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the invention. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0031] It should be noted that, unless otherwise specified, the embodiments and features described in this invention can be combined with each other. The acquisition, transmission, storage, use, and processing of data in this application comply with relevant national laws and regulations. In the embodiments of this application, certain existing industry solutions such as software, components, and models may be mentioned. These should be considered exemplary, intended only to illustrate the feasibility of implementing the technical solution of this application, and do not imply that the applicant has already used or necessarily used such solutions.

[0032] This invention provides a data processing system that can be used for data processing on conveyor belts in sorting centers, specifically for identifying the degree of crowding of packages on the conveyor belt.

[0033] In this embodiment of the invention, the identification of package congestion levels on a conveyor belt in a sorting center is used as an example. Sorting centers typically use conveyor belts to transport packaged parcels to a sorting area for sorting and delivery. When the number of parcels is large, the sorting area may become congested due to the inability to sort them in a timely manner, which can easily affect the delivery timeliness of the parcels. Therefore, in this embodiment of the invention, the congestion status of the conveyor belt can be identified from multiple dimensions to determine the degree of congestion in the conveyor belt in a timely manner. Corresponding solutions can then be adopted for different levels of congestion, thereby avoiding package congestion in the sorting area, improving parcel sorting efficiency, and ensuring the timeliness of parcel sorting.

[0034] In this embodiment of the invention, in order to collect information about each package on the conveyor belt, video or image information of the conveyor belt can be collected using computer vision methods. For example, a camera can be set up to capture real-time images of the conveyor belt. Specifically, this can be done as follows: Figure 1 As shown, a camera is installed next to the conveyor belt to capture video or images of the conveyor belt.

[0035] This invention provides a data processing method, which can be executed by a data processing system, such as... Figure 2 As shown, the method includes the following steps.

[0036] S201: Receive congestion identification command, obtain the corresponding conveyor belt information and time interval, and query the video of package delivery on the conveyor belt within the time interval.

[0037] The congestion identification command can be automatically triggered or sent by an external system, indicating the identification of congestion status of packages on the conveyor belt. The congestion identification command can include conveyor belt information, such as its identifier, to indicate which conveyor belt's congestion status is being identified. Conveyor belt congestion identification typically uses conveyor belt transport information within a time period closest to the identification time point, thus defining a time interval within which conveyor belt information is used for congestion identification. The length of this time interval can be set according to requirements, such as ten minutes or half an hour, etc.

[0038] In embodiments of the present invention, such as Figure 1 As shown, the shooting device can capture and store videos or images of the conveyor belt transporting packages in real time. In this embodiment of the invention, after determining the conveyor belt and the time interval, the video of the package transported by the conveyor belt within this time interval can be retrieved.

[0039] S202: Identify the package transportation characteristics of each package in the package delivery video, obtain the conveyor belt characteristics and conveyor belt speed, and generate the target delivery feature vector corresponding to the conveyor belt.

[0040] The video recordings document the transport of packages on the conveyor belt, including their position, size, quantity, and speed. These package characteristics allow for conveyor belt congestion analysis. Therefore, this step involves identifying the transport characteristics of each package through the video recordings. Simultaneously, the characteristics of the conveyor belt itself also affect package transport, contributing to congestion. Therefore, this step obtains the conveyor belt's features and speed, combining these with the package transport characteristics to generate a target transport feature vector for the corresponding conveyor belt.

[0041] In this embodiment of the invention, each package in the package transport video can be detected first, and then the corresponding package transport features can be obtained. Specifically, in this step, a target detection method can be used to detect all packages on the conveyor belt, obtaining a detection box corresponding to each package. The detection box can be a rectangle used to mark the pixel area of ​​the corresponding package in the image, i.e., the position information. Based on this, a target tracking method can also be used in this step to calculate the trajectory, average speed, and instantaneous speed of each package in each frame by analyzing continuous frames in the package transport video. Therefore, the identification of package transport features in this step can be specifically performed as follows: identifying each package in the package transport video, determining the detection box corresponding to each package, obtaining the position features of the detection box corresponding to each package, calculating the movement features of each package; and concatenating the position features and movement features to obtain the package transport features of each package. The position features can specifically include the vertex coordinates and side length of the detection box, and the movement features can include the movement speed of the package.

[0042] For example, by pre-establishing a two-dimensional XY coordinate system, after obtaining the detection box for each package, the vertex coordinates and side length of the detection box can be determined. After calculating the package's moving speed, its speed in the X and Y directions can be determined. Concatenating these features yields the package transportation features, which can then be converted into a vector representation, such as inputting it into a transformer-encoder model to obtain the corresponding embedding vector for each package. (The image shows packages being transported in a video.) For example, the corresponding vector representation can be ,in Indicates the x-coordinate of the top left corner of the detection box, Indicates the ordinate of the top left corner of the detection box, Indicates the width of the detection frame, Indicates the length of the detection frame, Indicates package In X-axis velocity and Indicates package Velocity on the Y-axis.

[0043] It should be noted that, in the embodiments of the present invention, the target detection method and the target tracking method are not limited. For example, the target detection method can be a YOLO series method, and the target tracking method can be a DeepTrack method.

[0044] Conveyor belt features can include a variety of characteristics. Since the structure of the conveyor belt affects the transportation of packages, these features can include structural characteristics such as length, width, whether it's a merging structure, and whether it's uphill or downhill. Specifically, the structural features of the conveyor belt can be represented by constants such as 0 or 1, resulting in a vector of conveyor belt features. For example, let [a, b, c, d, e, f, g] represent the vector of conveyor belt features, where a represents the conveyor belt length, b represents the conveyor belt width, c indicates whether it's uphill (1 for yes, 0 for no), d indicates whether it's downhill (1 for yes, 0 for no), e indicates whether it's a curve (1 for yes, 0 for no), f indicates whether it's upstream of a merging structure (1 for yes, 0 for no), and g indicates whether it's downstream of a merging structure (1 for yes, 0 for no).

[0045] In this embodiment of the invention, the speed of the conveyor belt can be represented by a constant. Therefore, after obtaining the package transportation characteristics, conveyor belt characteristics, and conveyor belt speed, these characteristics can be concatenated to generate the target transportation feature vector corresponding to the conveyor belt.

[0046] It should be noted that, assuming the conveyor belt contains m packages, generating m corresponding feature vectors of package transport characteristics, these can be filled into a model containing M vectors, where M is greater than or equal to m. If M is greater than m, the remaining elements are padded with 0. There is no sequential relationship between the packages. This vector model can be processed by a transformer, and the output can be pooled to obtain the package feature vectors corresponding to each package (e.g., a vector of length 6n, where n represents the number of pooling methods). This vector vector is then concatenated with the conveyor belt features and the conveyor belt speed to obtain the target transport feature vector.

[0047] S203: Query each connecting conveyor belt connected to the conveyor belt and determine the connection transmission feature vector of each connecting conveyor belt.

[0048] Since the conveyor belts are connected to each other to gather packages, the congestion of one conveyor belt may be affected by other conveyor belts. Therefore, this step can also query each connected conveyor belt to determine the connection transmission feature vector of each connected conveyor belt, which can be used as the feature parameter for conveyor belt congestion identification.

[0049] Specifically, such as Figure 1As shown, the connection relationships of each conveyor belt are different. Some structures allow packages from other downstream conveyor belts to be transferred to that conveyor belt, while others allow packages from that conveyor belt to be transferred to other upstream conveyor belts. Therefore, both upstream and downstream conveyor belts contribute to congestion on that conveyor belt. Specifically, this step can be defined as follows: query the connection matrix corresponding to the conveyor belt, identify the first connecting conveyor belt where packages are transferred and the second connecting conveyor belt where packages are transferred, obtain the transmission feature vectors of the first and second connecting conveyor belts, and determine them as connection transmission feature vectors.

[0050] The connection matrix represents the connection relationship between each conveyor belt. The first and second connecting conveyor belts connected to the conveyor belts can be determined through the connection matrix.

[0051] In one implementation, the connection matrix can be pre-generated. Specifically, this can be done by: obtaining the conveyor belt positions corresponding to each preset area within the package transport area, determining the structural relationships between the preset areas, and generating the connection matrix of the conveyor belt based on the structural relationships.

[0052] The preset area refers to the pre-set conveyor belt area. Based on the location information of these preset areas, the connection structure can be determined, and then the connection matrix of the conveyor belt can be generated.

[0053] like Figure 1 As shown, the preset area includes conveyor belts 1, 2, 3, and 4, which include the main line, branch lines, and U-branch lines of the conveyor belts. Based on the location information of each preset area, the upstream and downstream connections between them can be determined. This connection relationship can be represented by a directed acyclic graph, specifically by a connection matrix. Figure 1 Taking the structure shown as an example, the generated connection matrix is ​​[[1,0,0,1],[0,1,0,1],[0,0,1,1],[0,0,0,1]]. In the connection matrix, an element with a value of 1 indicates merging, and an element with a value of 0 indicates no relationship. The diagonal elements of the connection matrix are forced to be 1. For example, in the above connection matrix, the second element of the first row is 0, which means that conveyor belt 1 and conveyor belt 2 have no connection relationship. The fourth element of the first row is 1, which means that conveyor belt 1 is included in conveyor belt 4, and the two are connected conveyor belts. Conveyor belt 1 belongs to the first connected conveyor belt of conveyor belt 4.

[0054] It should be noted that, in this embodiment of the invention, to facilitate the identification of conveyor belt congestion, the conveyor belt can be divided into areas. Since some conveyor belts do not involve special structures such as intersections, their congestion will not significantly affect subsequent package sorting. Therefore, in this embodiment of the invention, the hot zones of the conveyor belt, i.e., areas prone to congestion, can be identified first, such as conveyor belt intersection areas, U-shaped areas of the conveyor belt, etc. Figure 1 The conveyor belt area shown can be a pre-set hot zone, i.e. a preset area. Then, the congestion in the preset area is identified to reduce the amount of data processed for congestion identification, while also obtaining accurate identification results.

[0055] In this embodiment of the invention, the method for generating the connection transmission feature vector of each connecting conveyor belt can be the same as the method for generating the target transmission feature vector in step S202, and will not be repeated here.

[0056] S204: Input the target transmission feature vector and each connection transmission feature vector into the preset recognition model to obtain the congestion level of the conveyor belt.

[0057] The recognition model is pre-trained and used to identify the congestion level of the conveyor belt. After obtaining the target transmission feature vector and the connection transmission feature vector, these can be input into the preset recognition model to obtain the corresponding congestion level of the conveyor belt. The output of the recognition model can be a value between 0 and 1 to represent the congestion level of the conveyor belt. Typically, an output of 0 indicates that no reading is needed, and an output of 1 indicates congestion.

[0058] Specifically, in this embodiment of the invention, the target transmission feature vector and the connection transmission feature vector are combined using a graph convolutional neural network, as shown in Formula 1.

[0059] (1)

[0060] In Formula 1, This represents the feature vector representation of the combination of the target transmission feature vector and the connection transmission feature vector corresponding to conveyor belt q. This indicates that conveyor belt q corresponds to the first set of connected conveyor belts. This indicates that conveyor belt q corresponds to the second set of connected conveyor belts. , and The parameters in a graph convolutional neural network are obtained through pre-training. This represents the target transport feature vector corresponding to conveyor belt q. This represents the connection transmission feature vector of each conveyor belt in the first set of connected conveyor belts. This represents the connection transmission feature vector of each conveyor belt in the second set of connecting conveyor belts.

[0061] In this embodiment of the invention, the recognition model can specifically be a classification model constructed using a bidirectional LSTM network. The model consists of a bidirectional LSTM layer, a fully connected layer, and a sigmoid output layer. During model training, training data can be obtained by labeling historical data. In this step, the model's output is converted into a value between 0 and 1 using the sigmoid function, representing the degree of congestion.

[0062] In this embodiment of the invention, corresponding processing strategies can be set according to different levels of congestion. After identifying the level of congestion on the conveyor belt in this step, the corresponding target processing strategy can be queried, allowing for timely processing of packages and preventing delays in sorting due to congestion. Therefore, this embodiment of the invention can also execute the following: query the corresponding target processing strategy based on the level of congestion on the conveyor belt, and trigger the processing task corresponding to the target processing strategy. The processing strategy can include various methods, such as notifying manual intervention, in which case the corresponding processing task could include sending a task prompt message to the relevant personnel; or adding sorting equipment, in which case the corresponding processing task could include sending an instruction to the equipment control module to add equipment.

[0063] like Figure 1 As shown, the conveyor belt can be set with a preset area. The congestion level of the conveyor belt can be determined by identifying the congestion in the preset area. Therefore, in this embodiment of the invention, in step S202, the target preset area included in the conveyor belt can be obtained first, and then the package transportation characteristics of the packages in the target preset area included in the package transportation video can be identified. That is, the congestion level of the target preset area in the conveyor belt is identified as the congestion level of the conveyor belt. Therefore, the package transportation characteristics in step S202 represent the package transportation characteristics of the packages in the preset area included in the conveyor belt.

[0064] It should be noted that, in this embodiment of the invention, if the conveyor belt includes multiple target preset areas, steps S202-S204 in this embodiment of the invention can be performed on each target preset area to obtain the congestion level of each target preset area, and then the congestion level of each target preset area can be determined by weighted summation to determine the congestion level of the conveyor belt.

[0065] In this embodiment of the invention, a prediction model can be pre-set to predict the congestion level of the conveyor belt. The prediction model can be implemented as described in the identification model implementation method, and then trained using historical data to obtain a prediction model capable of predicting congestion levels. In this embodiment, the target transmission feature vector and the connection transmission feature vector are input into the preset prediction model to obtain the congestion level of the conveyor belt at the predicted time. The prediction time can be set according to the prediction model. For example, if the prediction mode is to predict the congestion level one minute later, then in this embodiment, after inputting the target transmission feature vector and the connection transmission feature vector into the preset prediction model, the congestion level one minute after the time point corresponding to the maximum value in the time interval can be obtained.

[0066] In this embodiment of the invention, for the conveyor belt undergoing congestion identification, multiple dimensions of features, including the characteristics of the conveyed packages, the characteristics of the conveyor belt itself, and the characteristics of the connecting conveyor belts, are input into the identification model to identify the degree of congestion. This allows for accurate identification of the congestion status of the conveyed packages from multiple perspectives, enabling timely and accurate implementation of corresponding solutions to minimize the reduction in package sorting efficiency due to conveyor belt congestion and ensure the timeliness of package sorting.

[0067] The following is combined Figure 2 The illustrated embodiments provide a detailed description of the data processing methods in the embodiments of the present invention, such as... Figure 3 As shown, the method includes the following steps.

[0068] S301: Receives congestion identification instructions, obtains the corresponding conveyor belt information and time interval, and queries the video of package delivery within the time interval.

[0069] S302: Identify each package in the package delivery video, determine the detection box corresponding to each package, obtain the position features of the detection box corresponding to each package, and calculate the movement features of each package.

[0070] S303: Combine location features and movement features to obtain the parcel transportation features of each parcel.

[0071] S304: Query the connection matrix connected to the conveyor belt, and identify the first connecting conveyor belt into which the package enters and the second connecting conveyor belt into which the package enters.

[0072] S305: Obtain the transmission feature vectors of the first connecting conveyor belt and the second connecting conveyor belt, and determine them as the connecting transmission feature vectors.

[0073] S306: Input the target transmission feature vector and each connection transmission feature vector into the preset prediction model to obtain the congestion level of the conveyor belt at the predicted time.

[0074] It should be noted that the data processing principle in the embodiments of the present invention is the same as... Figure 2 The data processing principles in the illustrated embodiments are the same and will not be repeated here.

[0075] To address the problems existing in the prior art, embodiments of the present invention provide a data processing apparatus 400, such as... Figure 4As shown, the device 400 includes: an acquisition unit 401, configured to receive a congestion identification command, acquire corresponding conveyor belt information and time intervals, and query video of package delivery within the time interval; a generation unit 402, configured to identify the package transport characteristics of each package in the video of package delivery, acquire the conveyor belt characteristics and the conveyor belt speed, and generate a target delivery feature vector corresponding to the conveyor belt; a determination unit 403, configured to query each connecting conveyor belt connected to the conveyor belt and determine the connection delivery feature vector of each connecting conveyor belt; and an identification unit 404, configured to input the target delivery feature vector and each connection delivery feature vector into a preset identification model to determine the congestion level corresponding to the conveyor belt.

[0076] It should be understood that the manner in which embodiments of the present invention are implemented is different from the implementation method. Figure 2 The embodiments shown are the same and will not be described again here.

[0077] In one embodiment, the generation unit 402 is specifically used to: identify each package in the package delivery video, determine the detection box corresponding to each package, obtain the position features of the detection box corresponding to each package, calculate the movement features of each package; and concatenate the position features and the movement features to obtain the package transportation features of each package.

[0078] In another embodiment, the determining unit 403 is specifically used to: query the connection matrix corresponding to the conveyor belt, identify the first connecting conveyor belt into which the package enters and the second connecting conveyor belt into which the package enters, obtain the transmission feature vectors of the first connecting conveyor belt and the second connecting conveyor belt, and determine them as connection transmission feature vectors.

[0079] In another embodiment, the identification unit 404 is specifically used to: input the target transmission feature vector and each of the connection transmission feature vectors into a preset neural network model to obtain a combined feature vector of the conveyor belt; and input the combined feature vector into a preset identification model.

[0080] In another embodiment, the generation unit 402 is further configured to: obtain the conveyor belt positions corresponding to each preset area within the package transmission area, determine the structural relationship between each preset area, and generate a connection matrix of the conveyor belt based on the structural relationship.

[0081] In another embodiment, the generation unit 402 is specifically used to: obtain the target preset area included by the conveyor belt, and identify the package transportation characteristics of the packages in the target preset area in the package transportation video.

[0082] In another embodiment, the device 400 further includes: the prediction unit, configured to input the target transmission feature vector and the connection transmission feature vector into a preset prediction model to obtain the congestion level of the conveyor belt at the predicted time.

[0083] It should be understood that the manner in which embodiments of the present invention are implemented is different from the implementation method. Figure 2 , 3 The embodiments shown are the same and will not be described again here.

[0084] In this embodiment of the invention, for the conveyor belt undergoing congestion identification, multiple dimensions of features, including the characteristics of the conveyed packages, the characteristics of the conveyor belt itself, and the characteristics of the connecting conveyor belts, are input into the identification model to identify the degree of congestion. This allows for accurate identification of the congestion status of the conveyed packages from multiple perspectives, enabling timely and accurate implementation of corresponding solutions to minimize the reduction in package sorting efficiency due to conveyor belt congestion and ensure the timeliness of package sorting.

[0085] According to embodiments of the present invention, an electronic device and a readable storage medium are also provided.

[0086] An electronic device according to an embodiment of the present invention includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to cause the at least one processor to perform the data processing method provided in the embodiment of the present invention.

[0087] Figure 5 An exemplary system architecture 500 is shown, in which a data processing method or data processing apparatus to which embodiments of the present invention can be applied is illustrated.

[0088] like Figure 5 As shown, system architecture 500 may include terminal devices 501, 502, and 503, a network 504, and a server 505. Network 504 serves as the medium for providing communication links between terminal devices 501, 502, and 503 and server 505. Network 504 may include various connection types, such as wired or wireless communication links, or fiber optic cables, etc.

[0089] Users can use terminal devices 501, 502, and 503 to interact with server 505 via network 504 to receive or send messages, etc. Various client applications can be installed on terminal devices 501, 502, and 503.

[0090] Terminal devices 501, 502, and 503 can be various electronic devices with displays that support web browsing, including but not limited to smartphones, tablets, laptops, and desktop computers.

[0091] Server 505 can be a server that provides various services. The server can analyze and process data such as received product information query requests, and feed back the processing results (such as product information - just an example) to the terminal device.

[0092] It should be noted that the data processing method provided in the embodiments of the present invention is generally executed by server 505, and correspondingly, the data processing device is generally located in server 505.

[0093] It should be understood that Figure 5 The number of terminal devices, networks, and servers shown is merely illustrative. Depending on implementation needs, any number of terminal devices, networks, and servers can be included.

[0094] The following is for reference. Figure 6 It shows a schematic diagram of the structure of a computer system 600 suitable for implementing embodiments of the present invention. Figure 6 The computer system shown is merely an example and should not be construed as limiting the functionality and scope of use of the embodiments of the present invention.

[0095] like Figure 6 As shown, the computer system 600 includes a central processing unit (CPU) 601, which can perform various appropriate actions and processes based on programs stored in read-only memory (ROM) 602 or programs loaded from storage section 608 into random access memory (RAM) 603. The RAM 603 also stores various programs and data required for the operation of the system 600. The CPU 601, ROM 602, and RAM 603 are interconnected via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0096] The following components are connected to I / O interface 605: an input section 606 including a keyboard, mouse, etc.; an output section 607 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and speakers, etc.; a storage section 608 including a hard disk, etc.; and a communication section 609 including a network interface card such as a LAN card, modem, etc. The communication section 609 performs communication processing via a network such as the Internet. A drive 610 is also connected to I / O interface 605 as needed. A removable medium 611, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on drive 610 as needed so that computer programs read from it can be installed into storage section 608 as needed.

[0097] In particular, according to the embodiments disclosed in this invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this invention include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 609, and / or installed from removable medium 611. When the computer program is executed by central processing unit (CPU) 601, it performs the functions defined above in the system of this invention.

[0098] It should be noted that the computer-readable medium shown in this invention can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this invention, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this invention, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media can also be any computer-readable medium other than computer-readable storage media, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0099] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a unit, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0100] The units described in the embodiments of the present invention can be implemented in software or hardware. The described units can also be housed in a processor; for example, a processor can be described as including an acquisition unit, a generation unit, a determination unit, and an identification unit. The names of these units do not necessarily limit the specific unit; for example, an acquisition unit can also be described as a "unit for acquiring functions."

[0101] In another aspect, the present invention also provides a computer-readable medium, which may be included in the device described in the above embodiments; or it may exist independently and not assembled into the device. The computer-readable medium carries one or more programs that, when executed by the device, cause the device to perform the data processing method provided by the present invention.

[0102] In another aspect, the present invention also provides a computer program product, including a computer program that, when executed by a processor, implements the data processing method provided in the embodiments of the present invention.

[0103] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can occur depending on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A data processing method, characterized in that, include: Receive congestion identification instructions, obtain the corresponding conveyor belt information and time interval, and query the video of package delivery within the time interval; Identify the package transportation characteristics of each package in the package delivery video, obtain the conveyor belt characteristics and conveyor belt speed, and generate the target delivery feature vector corresponding to the conveyor belt; Query each connecting conveyor belt that is connected to the aforementioned conveyor belt, and determine the connection transmission feature vector of each connecting conveyor belt; The target transmission feature vector and each of the connection transmission feature vectors are input into a preset recognition model to obtain the congestion level of the conveyor belt.

2. The method according to claim 1, characterized in that, Identifying the package transportation characteristics of each package in the package delivery video, including: Identify each package in the package delivery video, determine the detection box corresponding to each package, obtain the position features of the detection box corresponding to each package, and calculate the movement features of each package; By concatenating the location features and the movement features, the package transportation features of each package are obtained.

3. The method according to claim 1, characterized in that, Query each connecting conveyor belt connected to the aforementioned conveyor belt, and determine the connection transmission feature vector of each connecting conveyor belt, including: Query the connection matrix corresponding to the conveyor belt, identify the first connecting conveyor belt into which the package enters and the second connecting conveyor belt into which the package enters, obtain the transmission feature vectors of the first connecting conveyor belt and the second connecting conveyor belt, and determine them as connection transmission feature vectors.

4. The method according to claim 1 or 3, characterized in that, Inputting the target transmission feature vector and each of the connection transmission feature vectors into a preset recognition model includes: The target transmission feature vector and each of the connection transmission feature vectors are input into a preset neural network model to obtain the combined feature vector of the conveyor belt; The combined feature vectors are input into a preset recognition model.

5. The method according to claim 1, characterized in that, Before querying each connected conveyor belt connected to the aforementioned conveyor belt, the process further includes: Obtain the conveyor belt positions corresponding to each preset area within the package transmission area, determine the structural relationships between each preset area, and generate a connection matrix for the conveyor belts based on the structural relationships.

6. The method according to claim 1, characterized in that, Identifying the package transportation characteristics of each package in the package delivery video, including: Obtain the target preset area included by the conveyor belt, and identify the package transportation characteristics of the packages in the target preset area in the package transportation video.

7. The method according to claim 1, characterized in that, Also includes: The target transmission feature vector and the connection transmission feature vector are input into a preset prediction model to obtain the congestion level of the conveyor belt at the predicted time.

8. A data processing apparatus, characterized in that, include: The acquisition unit is used to receive congestion identification instructions, acquire the corresponding conveyor belt information and time interval, and query the video of package delivery on the conveyor belt within the time interval. The generation unit is used to identify the package transportation features of each package in the package delivery video, obtain the conveyor belt features and the conveyor belt speed, and generate the target delivery feature vector corresponding to the conveyor belt. The determining unit is used to query each connecting conveyor belt connected to the conveyor belt and determine the connection transmission feature vector of each connecting conveyor belt. The identification unit is used to input the target transmission feature vector and each of the connection transmission feature vectors into a preset identification model to obtain the congestion level of the conveyor belt.

9. An electronic device, characterized in that, include: One or more processors; Storage device 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 method as described in any one of claims 1-7.

10. A computer-readable medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the method as described in any one of claims 1-7.

Images