Logistics information identification method, device, equipment and medium

Abstract

The present disclosure provides a logistics information recognition method, device, equipment and medium, which can be applied to the fields of artificial intelligence technology and smart logistics. The logistics information recognition method comprises: performing dimension reduction processing on logistics information to obtain reduced logistics feature information; inputting the logistics feature information into a logistics attribute recognition model to obtain a plurality of calculation tasks for representing matrix multiplication operations in the logistics attribute recognition model; calling a target thread from a thread pool to process the plurality of calculation tasks in parallel to obtain a logistics attribute recognition result output by the logistics attribute recognition model, wherein the logistics attribute recognition result is used to represent a logistics attribute type of a target product in the logistics information.

Description

Technical Field

[0001] This disclosure relates to the fields of artificial intelligence technology and smart logistics, and more specifically, to a logistics information identification method, apparatus, equipment, medium, and program product. Background Technology

[0002] Logistics information can be used to characterize the attributes of goods, such as their name, volume, and weight. It can also characterize the logistics attributes generated during warehousing and transportation, such as the mode of transport and warehousing. Logistics information can be stored in the logistics management system using waybill flags. The logistics and goods attributes represented by the logistics information can be identified by recognizing these waybill flags recorded in the logistics management system.

[0003] In realizing the concept disclosed herein, the inventors discovered at least the following problems in the related technologies: because logistics information is usually recorded based on different rule formats, the accuracy of identifying logistics information is low, and the calculation time to obtain the identification results is long, which makes it difficult to meet actual needs. Summary of the Invention

[0004] In view of this, the present disclosure provides a method, apparatus, equipment, medium and program product for identifying logistics information.

[0005] One aspect of this disclosure provides a method for identifying logistics information, including:

[0006] The logistics information is reduced in dimensionality to obtain the reduced logistics feature information.

[0007] The above logistics feature information is input into the logistics attribute recognition model to obtain multiple computational tasks used to characterize matrix multiplication operations in the above logistics attribute recognition model;

[0008] Multiple computational tasks described above are processed in parallel by calling the target thread from the thread pool to obtain the logistics attribute recognition result output by the logistics attribute recognition model. The logistics attribute recognition result is used to characterize the logistics attribute type of the target product in the logistics information.

[0009] According to embodiments of this disclosure, the logistics information is subjected to dimensionality reduction processing to obtain dimensionality-reduced logistics feature information, including:

[0010] The logistics information is reduced in dimensionality using a preset dimensionality reduction algorithm to obtain the logistics feature information.

[0011] The aforementioned preset dimensionality reduction algorithms include at least one of the following: principal component analysis algorithm, linear discriminant analysis algorithm, and factor analysis algorithm.

[0012] According to embodiments of this disclosure, the logistics information is subjected to dimensionality reduction processing to obtain dimensionality-reduced logistics feature information, including:

[0013] The above logistics information is encoded to obtain logistics code information;

[0014] Based on the mean and variance information of the above logistics coding information, determine the standard logistics coding information associated with the above logistics coding information;

[0015] The covariance matrix is ​​used to process the above standard logistics coding information to obtain the coding feature values ​​and coding feature vectors;

[0016] Based on the aforementioned coded feature values ​​and coded feature vectors, the aforementioned logistics feature information is determined.

[0017] According to embodiments of this disclosure, the above-mentioned computational tasks include N;

[0018] The target thread is called from the thread pool to process multiple of the above computational tasks in parallel, and the logistics attribute recognition results output by the above logistics attribute recognition model include:

[0019] M target threads are called from the above thread pool to process M target computing tasks in the computing task queue, and the computing task results of each of the above target computing tasks are obtained. The above computing task queue is composed of multiple above computing tasks, and the above target threads are threads in the above thread pool that are in an idle state, N>M≥1.

[0020] After the aforementioned target computation task obtains its result, the target thread that processed the target computation task returns to the thread pool so that new target computation tasks in the computation task queue can be processed repeatedly until each of the N aforementioned computation tasks has obtained its respective computation result; and

[0021] Based on the results of each of the N computational tasks described above, the results of the logistics attribute identification are determined.

[0022] According to embodiments of this disclosure, before performing dimensionality reduction processing on the logistics information, the above-mentioned logistics information identification method further includes:

[0023] The logistics information is completed according to preset rules to obtain logistics information with a preset character length.

[0024] According to embodiments of this disclosure, the aforementioned logistics information includes waybill flag information; and the aforementioned logistics attribute identification results include product line identification results.

[0025] According to embodiments of this disclosure, the above-mentioned logistics attribute identification model includes at least one of the following:

[0026] Radial basis function neural network model, multilayer perceptron neural network model.

[0027] Another aspect of this disclosure provides a logistics information identification device, comprising:

[0028] The dimensionality reduction module is used to reduce the dimensionality of logistics information to obtain the dimensionality-reduced logistics feature information.

[0029] The computational task determination module is used to input the above-mentioned logistics feature information into the logistics attribute recognition model to obtain multiple computational tasks in the above-mentioned logistics attribute recognition model used to represent matrix multiplication operations.

[0030] The identification module is used to call the target thread from the thread pool to process multiple of the above-mentioned computational tasks in parallel, and obtain the logistics attribute identification result output by the above-mentioned logistics attribute identification model. The above-mentioned logistics attribute identification result is used to characterize the logistics attribute type of the target product in the above-mentioned logistics information.

[0031] Another aspect of this disclosure provides an electronic device comprising:

[0032] One or more processors;

[0033] Memory, used to store one or more programs.

[0034] When the one or more programs are executed by the one or more processors, the one or more processors implement the method described above.

[0035] Another aspect of this disclosure provides a computer-readable storage medium storing computer-executable instructions that, when executed, are used to implement the method described above.

[0036] Another aspect of this disclosure provides a computer program product including computer-executable instructions that, when executed, are used to implement the method described above.

[0037] According to embodiments of this disclosure, by employing a technique for dimensionality reduction of logistics information, the resulting dimensionality-reduced logistics feature information can at least partially reduce the amount of logistics information data, saving computational overhead for subsequent logistics attribute recognition model processing. Inputting the logistics feature information into the logistics attribute recognition model yields multiple computational tasks used to characterize matrix multiplication operations. Utilizing a target thread in a thread pool to process these multiple computational tasks in parallel can at least partially avoid the computational resource consumption caused by thread creation. Furthermore, parallel processing of multiple computational tasks, compared to creating a single thread to complete multiple computational tasks in the logistics attribute recognition model, can improve the computational speed of the model. Moreover, by fully learning the feature information of the logistics information, the recognition accuracy for the logistics attribute type of the target product can be improved, thereby achieving the technical effect of reducing the logistics turnaround time of the target product and improving logistics efficiency. Attached Figure Description

[0038] The above and other objects, features and advantages of this disclosure will become clearer from the following description of embodiments with reference to the accompanying drawings, in which:

[0039] Figure 1 An exemplary system architecture for applying the logistics information identification method and apparatus of this disclosure is illustrated schematically;

[0040] Figure 2 A flowchart illustrating a logistics information identification method according to an embodiment of the present disclosure is shown schematically.

[0041] Figure 3 This schematically illustrates a flowchart of a process for reducing the dimensionality of logistics information to obtain reduced logistics feature information according to an embodiment of the present disclosure.

[0042] Figure 4 This schematically illustrates a flowchart of a process for obtaining logistics attribute recognition results output by a logistics attribute recognition model by calling a target thread from a thread pool to process multiple computational tasks in parallel, according to an embodiment of the present disclosure.

[0043] Figure 5 This diagram illustrates an application scenario of the logistics information identification method according to an embodiment of the present disclosure.

[0044] Figure 6 A block diagram of a logistics information identification device according to an embodiment of the present disclosure is schematically shown; and

[0045] Figure 7 A block diagram of an electronic device suitable for implementing a logistics information identification method according to an embodiment of the present disclosure is shown schematically. Detailed Implementation

[0046] The embodiments of the present disclosure will now be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the disclosure. In the following detailed description, numerous specific details are set forth to provide a thorough understanding of the embodiments of the present disclosure for ease of explanation. However, it will be apparent that one or more embodiments may be practiced without these specific details. Furthermore, descriptions of well-known structures and techniques are omitted in the following description to avoid unnecessarily obscuring the concepts of the present disclosure.

[0047] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit this disclosure. The terms “comprising,” “including,” etc., as used herein indicate the presence of the stated features, steps, operations, and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, or components.

[0048] All terms used herein (including technical and scientific terms) have the meanings commonly understood by those skilled in the art, unless otherwise defined. It should be noted that the terms used herein are to be interpreted in a manner consistent with the context of this specification, and not in an idealized or overly rigid way.

[0049] When using expressions such as "at least one of A, B, and C", they should generally be interpreted in accordance with the meaning that is commonly understood by a person skilled in the art (e.g., "a system having at least one of A, B, and C" should include, but is not limited to, a system having A alone, a system having B alone, a system having C alone, a system having A and B, a system having A and C, a system having B and C, and / or a system having A, B, and C, etc.).

[0050] Embodiments of this disclosure provide a method, apparatus, device, medium, and program product for identifying logistics information. The logistics information identification method includes: performing dimensionality reduction processing on logistics information to obtain dimensionality-reduced logistics feature information; inputting the logistics feature information into a logistics attribute identification model to obtain multiple computational tasks in the logistics attribute identification model used to characterize matrix multiplication operations; calling a target thread from a thread pool to process the multiple computational tasks in parallel, and obtaining a logistics attribute identification result output by the logistics attribute identification model, wherein the logistics attribute identification result is used to characterize the logistics attribute type of the target product in the logistics information.

[0051] According to embodiments of this disclosure, by performing dimensionality reduction processing on logistics information, the resulting dimensionality-reduced logistics feature information can reduce the amount of logistics information data, saving computational overhead for subsequent logistics attribute recognition model processing. Inputting the logistics feature information into the logistics attribute recognition model yields multiple computational tasks used to represent matrix multiplication operations. Utilizing a target thread in a thread pool to process these multiple computational tasks in parallel avoids the computational resource consumption caused by thread creation. Furthermore, parallel processing of multiple computational tasks, compared to creating a single thread to complete multiple computational tasks in the logistics attribute recognition model, improves the computational speed of the model. Simultaneously, by fully learning the feature information of the logistics information, the accuracy of identifying the logistics attribute type of the target product within the logistics information can be improved, thereby achieving the technical effect of reducing the logistics turnaround time of the target product and improving logistics efficiency.

[0052] In the technical solution disclosed herein, the user's authorization or consent is obtained before acquiring or collecting the user's personal information.

[0053] In the technical solution disclosed herein, the collection, storage, use, processing, transmission, provision, disclosure, and application of user personal information comply with the provisions of relevant laws and regulations, necessary confidentiality measures have been taken, and there is no violation of public order and good morals.

[0054] Figure 1 An exemplary system architecture 100 for applying logistics information identification methods and apparatus according to embodiments of this disclosure is illustrated schematically. It should be noted that... Figure 1 The examples shown are merely examples of system architectures that can be applied to the embodiments of this disclosure, in order to help those skilled in the art understand the technical content of this disclosure, but do not mean that the embodiments of this disclosure cannot be used in other devices, systems, environments or scenarios.

[0055] like Figure 1 As shown, the system architecture 100 according to this embodiment may include terminal devices 101, 102, and 103, a network 104, and a server 105. The network 104 serves as a medium for providing a communication link between the terminal devices 101, 102, and 103 and the server 105. The network 104 may include various connection types, such as wired and / or wireless communication links, etc.

[0056] Users can use terminal devices 101, 102, and 103 to interact with server 105 via network 104 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 101, 102, and 103, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, and / or social platform software, etc. (for example only).

[0057] Terminal devices 101, 102, and 103 can be various electronic devices with displays and web browsing capabilities, including but not limited to smartphones, tablets, laptops, and desktop computers.

[0058] Server 105 can be a server that provides various services, such as a backend management server that supports websites browsed by users using terminal devices 101, 102, and 103 (for example only). The backend management server can analyze and process data such as received user requests, and feed back the processing results (such as web pages, information, or data obtained or generated according to user requests) to the terminal devices.

[0059] It should be noted that the logistics information identification method provided in this embodiment can generally be executed by server 105. Correspondingly, the logistics information identification device provided in this embodiment can generally be installed in server 105. The logistics information identification method provided in this embodiment can also be executed by a server or server cluster that is different from server 105 and capable of communicating with terminal devices 101, 102, 103 and / or server 105. Correspondingly, the logistics information identification device provided in this embodiment can also be installed in a server or server cluster that is different from server 105 and capable of communicating with terminal devices 101, 102, 103 and / or server 105. Alternatively, the logistics information identification method provided in this embodiment can also be executed by terminal devices 101, 102, or 103, or by other terminal devices different from terminal devices 101, 102, or 103. Accordingly, the logistics information identification device provided in this embodiment may also be installed in terminal devices 101, 102, or 103, or in other terminal devices different from terminal devices 101, 102, or 103.

[0060] For example, logistics information may originally be stored in any one of terminal devices 101, 102, or 103 (e.g., terminal device 101, but not limited thereto), or it may be stored on an external storage device and imported into terminal device 101. Then, terminal device 101 may execute the logistics information identification method provided in the embodiments of this disclosure locally, or send the logistics information to other terminal devices, servers, or server clusters, and have the other terminal devices, servers, or server clusters that receive the logistics information execute the logistics information identification method provided in the embodiments of this disclosure.

[0061] It should be understood that Figure 1 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.

[0062] Figure 2 A flowchart illustrating a logistics information identification method according to an embodiment of the present disclosure is shown schematically.

[0063] like Figure 2 As shown, the logistics information identification method may include operations S210 to S230.

[0064] In operation S210, the logistics information is reduced in dimensionality to obtain the reduced logistics feature information.

[0065] According to embodiments of this disclosure, logistics information may include attribute information characterizing the target product, and information characterizing the logistics attributes of the target product. The logistics attribute information may be stored in a relevant storage medium in the form of strings, codes, or other formats.

[0066] According to embodiments of this disclosure, the dimensionality-reduced logistics feature information can be information that can characterize the features related to logistics information and logistics attribute types. The dimensionality-reduced logistics feature information can reduce the amount of logistics information data and save computational overhead for subsequent logistics attribute recognition model processing.

[0067] In operation S220, logistics feature information is input into the logistics attribute recognition model, resulting in multiple computational tasks in the logistics attribute recognition model used to characterize matrix multiplication operations.

[0068] According to embodiments of this disclosure, the logistics attribute identification model may include a model constructed based on a neural network, such as a radial basis function neural network model, a multilayer perceptron neural network model, a recurrent neural network model, etc. Embodiments of this disclosure do not limit the specific network structure of the five- or six-attribute identification model; those skilled in the art can choose according to the actual situation.

[0069] In operation S230, the target thread is called from the thread pool to process multiple computing tasks in parallel, and the logistics attribute recognition result output by the logistics attribute recognition model is obtained. The logistics attribute recognition result is used to characterize the logistics attribute type of the target product in the logistics information.

[0070] According to embodiments of this disclosure, a thread pool may include threads that have already been created. There may be multiple target threads in the thread pool. By having multiple target threads process multiple computing tasks in parallel, the computational resource consumption caused by thread creation and destruction can be avoided. At the same time, parallel processing of computing tasks can improve the computational speed of the logistics attribute recognition model.

[0071] According to embodiments of this disclosure, by performing dimensionality reduction processing on logistics information, the resulting dimensionality-reduced logistics feature information can reduce the amount of logistics information data, saving computational overhead for subsequent logistics attribute recognition model processing. Inputting the logistics feature information into the logistics attribute recognition model yields multiple computational tasks used to represent matrix multiplication operations. Utilizing a target thread in a thread pool to process these multiple computational tasks in parallel avoids the computational resource consumption caused by thread creation. Furthermore, parallel processing of multiple computational tasks, compared to creating a single thread to complete multiple computational tasks in the logistics attribute recognition model, improves the computational speed of the model. Simultaneously, by fully learning the feature information of the logistics information, the accuracy of identifying the logistics attribute type of the target product within the logistics information can be improved, thereby achieving the technical effect of reducing the logistics turnaround time of the target product and improving logistics efficiency.

[0072] According to embodiments of this disclosure, logistics information may include waybill flag information; logistics attribute identification results may include product line identification results.

[0073] According to embodiments of this disclosure, the Waybill Sign information can be a string recording the logistics information for a target product. After a waybill is generated for the target product, to facilitate waybill management, waybill sign information can be generated based on the logistics information in the waybill according to a preset coding rule.

[0074] According to embodiments of this disclosure, the product line may include classification results that characterize the logistics attribute type of the target product. These classification results may include, for example, cold chain logistics, large items, fragile items, etc. By accurately identifying the product line of the target product, the logistics method for the target product can be quickly determined, ensuring that the product is delivered intact to the target address while improving the logistics efficiency of the target product.

[0075] According to embodiments of this disclosure, before performing dimensionality reduction processing on the logistics information, the logistics information identification method may further include the following operations.

[0076] The logistics information is completed according to preset rules to obtain logistics information with a preset character length.

[0077] According to embodiments of this disclosure, the length of logistics information for different target products may vary. For example, when the logistics information is waybill flag information, the waybill flag information corresponding to different target products may be strings with different character lengths. By completing the waybill flag information, waybill flag information with a preset character length can be obtained, that is, logistics information with a preset character length can be obtained, so that the subsequent logistics attribute recognition model can uniformly process different logistics information, thereby improving processing efficiency.

[0078] In one embodiment of this disclosure, the character "-1" can be used for padding, and the preset character length can be the same as the character length of the waybill flag information with the longest character length stored in the logistics system.

[0079] According to an embodiment of this disclosure, operation S210, which involves dimensionality reduction processing of logistics information to obtain dimensionality-reduced logistics feature information, may include the following operations.

[0080] Logistics information is reduced in dimensionality based on a preset dimensionality reduction algorithm to obtain logistics feature information; wherein the preset dimensionality reduction algorithm includes at least one of the following: principal component analysis algorithm, linear discriminant analysis algorithm, and factor analysis algorithm.

[0081] According to embodiments of this disclosure, in order to reduce the computational overhead of the subsequent logistics attribute identification model, any one of the principal component analysis algorithm, linear discriminant analysis algorithm, and factor analysis algorithm can be used to perform dimensionality reduction processing on the logistics information, thereby reducing the data dimension of the logistics information.

[0082] Figure 3 The flowchart illustrates a process of reducing the dimensionality of logistics information to obtain reduced logistics feature information according to an embodiment of the present disclosure.

[0083] like Figure 3 As shown, operation S210 performs dimensionality reduction processing on the logistics information to obtain dimensionality-reduced logistics feature information, which may include operations S310 to S340.

[0084] In operation S310, the logistics information is encoded to obtain logistics code information.

[0085] In operation S320, the standard logistics code information associated with the logistics code information is determined based on the code mean information and code variance information of the logistics code information.

[0086] In operation S330, the covariance matrix is ​​used to process standard logistics coding information to obtain coding feature values ​​and coding feature vectors.

[0087] In operation S340, logistics feature information is determined based on the encoded feature value and the encoded feature vector.

[0088] According to embodiments of this disclosure, logistics information can be encoded using any method in the related technologies. For example, ASCII (American Standard Code for Information Interchange) can be used to encode the logistics information. Those skilled in the art can select the specific encoding method according to the actual situation.

[0089] According to embodiments of this disclosure, logistics coding information can be represented as (x1, x2, ... x...). i ).

[0090] Standard logistics code information can be obtained using formula (1).

[0091]

[0092] In formula (1), This represents the average value of the logistics coding information. Representing the variance information of the coding, standard logistics coding information can be represented as follows:

[0093] Using the covariance matrix to process standard logistics coding information, it can be represented as follows: This yields the encoded feature values ​​and encoded feature vectors. Based on these values ​​and vectors, the principal component scores of the encoded feature values ​​can be calculated. Feature extraction is then performed on the encoded feature values ​​whose principal component scores exceed the total contribution threshold to obtain logistics feature information, thus enabling dimensionality reduction processing of logistics information.

[0094] According to embodiments of this disclosure, the logistics attribute identification model may include at least one of the following: a radial basis function neural network model and a multilayer perceptron neural network model.

[0095] According to embodiments of this disclosure, a logistics attribute recognition model can be constructed using a neural network model with classification capabilities to improve the recognition accuracy of logistics attribute types.

[0096] According to embodiments of this disclosure, logistics information in related technologies may include waybill flag information, which can be a string of length n. While decision tree algorithms are commonly used to process this flag information, implementation increases the amount of backend code and redundancy, leading to higher server resource consumption. Furthermore, the increased code size makes later maintenance more difficult. Constructing a logistics attribute recognition model based on either a Radial Basis Function (RBF) neural network model or a Multilayer Perceptron Neural Network (MLPN) model can at least partially reduce the technical problems of large code size and low recognition accuracy in related technologies, providing strong support for improving the efficiency of logistics processing for target products.

[0097] It should be noted that the logistics attribute recognition model in the embodiments of this disclosure can be obtained after training. For example, sample logistics information and corresponding sample labels can be used as training samples to train the initial logistics attribute recognition model. The sample logistics information is input into the initial logistics attribute recognition model to obtain the predicted logistics attribute recognition result. The predicted logistics attribute recognition result and the corresponding sample labels are processed using a loss function to obtain the loss value. The parameters in the initial logistics attribute recognition model are iteratively adjusted according to the loss value until the loss function converges. The logistics attribute recognition model with converged loss function is used as the logistics attribute recognition model obtained after training. Correspondingly, the training samples can also be divided into a training set and a test set, and the logistics attribute recognition model can be trained based on the training set and the test set.

[0098] According to embodiments of this disclosure, the computational tasks may include N.

[0099] Figure 4 The flowchart illustrates a process of calling a target thread from a thread pool to process multiple computational tasks in parallel, according to an embodiment of the present disclosure, to obtain the logistics attribute recognition result output by the logistics attribute recognition model.

[0100] like Figure 4 As shown, operation S230 calls the target thread from the thread pool to process multiple computing tasks in parallel, and the logistics attribute recognition result output by the logistics attribute recognition model can include operations S410 to S430.

[0101] In operation S410, M target threads are called from the thread pool to process M target computing tasks in the computing task queue, and the computing task results of each target computing task are obtained. The computing task queue is composed of multiple computing tasks, and the target threads are threads in the thread pool that are in an idle state, where N > M ≥ 1.

[0102] In operation S420, after the target computation task obtains the computation result, the target thread that processed the target computation task returns to the thread pool so that new target computation tasks in the computation task queue can be processed repeatedly until each of the N computation tasks obtains its own computation result.

[0103] During operation of S430, the logistics attribute identification result is determined based on the calculation results of each of the N calculation tasks.

[0104] According to embodiments of this disclosure, the number of target threads in a thread pool can be determined based on the number of CPU cores. M target threads in the thread pool are used to process M computational tasks in parallel. After a target thread obtains the result of a computational task, it can select a task from the remaining unprocessed tasks for further processing until the number of remaining unprocessed tasks is zero, at which point the target thread can exit. Compared to related technologies that utilize a single thread to process data in a neural network model, this method can improve the computational speed of the logistics attribute recognition model.

[0105] Figure 5 The diagram illustrates an application scenario of the logistics information identification method according to an embodiment of the present disclosure.

[0106] like Figure 5 As shown, the application scenarios of this embodiment may include logistics feature information 510, logistics attribute recognition model 520, thread pool 530, and logistics attribute recognition result 540.

[0107] After the logistics feature information 510 is input into the logistics attribute recognition model 520, computational tasks 521, 522, 523, 524, 525, 526, 527, and 528, which are used to represent matrix multiplication operations, will be generated in the logistics attribute recognition model 520. Among them, computational tasks 521, 522, 523, and 524 can be used as target computational tasks in the computational task queue.

[0108] Target threads 531, 532, 533, and 534 are called from thread pool 530 to process target computation tasks 521, 522, 523, and 524 in parallel. After obtaining the computation result of target computation task 521, a new target computation task 525 can be added to the computation task queue, and target thread 531 can return to thread pool 530 to process the new target computation task 525. Target threads 531, 532, 533, and 534 in the thread pool can process the N computation tasks in the logistics attribute recognition model 520 in parallel according to the above method, until all N computation tasks in the logistics attribute recognition model 520 have obtained their respective computation results, and the logistics attribute recognition result 540 is obtained based on the fact that all N computation tasks have obtained their respective computation results.

[0109] Figure 6 A block diagram of a logistics information identification device according to an embodiment of the present disclosure is shown schematically.

[0110] like Figure 6 As shown, the logistics information identification device 600 includes a dimensionality reduction processing module 610, a calculation task determination module 620, and an identification module 630.

[0111] The dimensionality reduction module 610 is used to reduce the dimensionality of logistics information to obtain the dimensionality-reduced logistics feature information.

[0112] The computation task determination module 620 is used to input logistics feature information into the logistics attribute recognition model to obtain multiple computation tasks in the logistics attribute recognition model used to characterize matrix multiplication operations.

[0113] The identification module 630 is used to call the target thread from the thread pool to process multiple computing tasks in parallel and obtain the logistics attribute identification result output by the logistics attribute identification model. The logistics attribute identification result is used to characterize the logistics attribute type of the target product in the logistics information.

[0114] According to embodiments of this disclosure, the dimensionality reduction module includes a dimensionality reduction processing unit.

[0115] The dimensionality reduction unit is used to perform dimensionality reduction processing on logistics information based on a preset dimensionality reduction algorithm to obtain logistics feature information. The preset dimensionality reduction algorithm includes at least one of the following: principal component analysis algorithm, linear discriminant analysis algorithm, and factor analysis algorithm.

[0116] According to embodiments of this disclosure, the dimensionality reduction processing module includes: an encoding unit, a first determining unit, a first processing unit, and a second determining unit.

[0117] The coding unit is used to encode logistics information to obtain logistics coding information.

[0118] The first determining unit is used to determine the standard logistics code information associated with the logistics code information based on the code mean information and code variance information of the logistics code information.

[0119] The first processing unit is used to process standard logistics coding information using the covariance matrix to obtain coding feature values ​​and coding feature vectors.

[0120] The second determining unit is used to determine logistics feature information based on the coded feature value and the coded feature vector.

[0121] According to embodiments of this disclosure, the computational tasks may include N.

[0122] The identification module may include: a calling unit, a second processing unit, and a third determining unit.

[0123] The calling unit is used to call M target threads from the thread pool to process M target computing tasks in the computing task queue, and obtain the computing task results of each target computing task. The computing task queue is composed of multiple computing tasks, and the target thread is a thread in the thread pool that is in an idle state, where N > M ≥ 1.

[0124] The second processing unit is used to return the target thread that processed the target computation task to the thread pool after the target computation task obtains the computation task result, so as to repeatedly process new target computation tasks in the computation task queue until each of the N computation tasks obtains its own computation task result.

[0125] The third determining unit is used to determine the logistics attribute identification result based on the calculation results of each of the N calculation tasks.

[0126] According to embodiments of this disclosure, the logistics information identification device may further include a completion module before performing dimensionality reduction processing on the logistics information.

[0127] The completion module is used to complete logistics information according to preset rules, so as to obtain logistics information with a preset character length.

[0128] According to embodiments of this disclosure, logistics information includes waybill flag information; and logistics attribute identification results include product line identification results.

[0129] According to embodiments of this disclosure, the logistics attribute identification model includes at least one of the following:

[0130] Radial basis function neural network model, multilayer perceptron neural network model.

[0131] Any one or more of the modules or units according to embodiments of this disclosure, or at least a portion thereof, may be implemented in a single module. Any one or more of the modules or units according to embodiments of this disclosure may be implemented by dividing them into multiple modules. Any one or more of the modules or units according to embodiments of this disclosure may be at least partially implemented as hardware circuitry, such as a Field-Programmable Gate Array (FPGA), a Programmable Logic Array (PLA), a System-on-Chip, a System-on-Substrate, a System-on-Package, an Application-Specific Integrated Circuit (ASIC), or implemented in hardware or firmware by any other reasonable means of integrating or packaging the circuitry, or implemented in software, hardware, or firmware, or in any suitable combination of any of these three methods. Alternatively, one or more of the modules or units according to embodiments of this disclosure may be at least partially implemented as computer program modules, which, when run, can perform corresponding functions.

[0132] For example, any plurality of the dimensionality reduction processing module 610, the computation task determination module 620, and the identification module 630 can be combined into one module / unit / subunit, or any one of these modules / units / subunits can be split into multiple modules / units / subunits. Alternatively, at least part of the functionality of one or more of these modules / units / subunits can be combined with at least part of the functionality of other modules / units / subunits and implemented in one module / unit / subunit. According to embodiments of the present disclosure, at least one of the dimensionality reduction processing module 610, the computation task determination module 620, and the identification module 630 can be at least partially implemented as hardware circuitry, such as a field-programmable gate array (FPGA), a programmable logic array (PLA), a system-on-a-chip, a system-on-a-substrate, a system-on-package, an application-specific integrated circuit (ASIC), or any other reasonable means of integrating or packaging circuitry, or implemented in software, hardware, or firmware, or in any suitable combination of any of these three implementation methods. Alternatively, at least one of the dimensionality reduction processing module 610, the computation task determination module 620, and the identification module 630 can be at least partially implemented as a computer program module, which can perform corresponding functions when the computer program module is run.

[0133] It should be noted that the logistics information identification device part in the embodiments of this disclosure corresponds to the logistics information identification method part in the embodiments of this disclosure. The description of the logistics information identification system part is specifically referred to in the logistics information identification method part, and will not be repeated here.

[0134] Figure 7 A block diagram of an electronic device suitable for implementing a logistics information identification method according to an embodiment of the present disclosure is shown schematically. Figure 7 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments disclosed herein.

[0135] like Figure 7 As shown, an electronic device 700 according to an embodiment of the present disclosure includes a processor 701, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 702 or a program loaded from a storage portion 708 into a random access memory (RAM) 703. The processor 701 may include, for example, a general-purpose microprocessor (e.g., a CPU), an instruction set processor and / or an associated chipset and / or a special-purpose microprocessor (e.g., an application-specific integrated circuit (ASIC)), etc. The processor 701 may also include onboard memory for caching purposes. The processor 701 may include a single processing unit or multiple processing units for performing different actions of the method flow according to an embodiment of the present disclosure.

[0136] RAM 703 stores various programs and data required for the operation of electronic device 700. Processor 701, ROM 702, and RAM 703 are interconnected via bus 704. Processor 701 performs various operations of the method flow according to embodiments of the present disclosure by executing programs in ROM 702 and / or RAM 703. It should be noted that the programs may also be stored in one or more memories other than ROM 702 and RAM 703. Processor 701 may also perform various operations of the method flow according to embodiments of the present disclosure by executing programs stored in said one or more memories.

[0137] According to embodiments of this disclosure, the electronic device 700 may further include an input / output (I / O) interface 705, which is also connected to a bus 704. The system 700 may also include one or more of the following components connected to the I / O interface 705: an input section 706 including a keyboard, mouse, etc.; an output section 707 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 708 including a hard disk, etc.; and a communication section 709 including a network interface card such as a LAN card, modem, etc. The communication section 709 performs communication processing via a network such as the Internet. A drive 710 is also connected to the I / O interface 705 as needed. A removable medium 711, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on the drive 710 as needed so that computer programs read from it can be installed into the storage section 708 as needed.

[0138] According to embodiments of this disclosure, the method flow according to embodiments of this disclosure can be implemented as a computer software program. For example, embodiments of this disclosure include a computer program product comprising a computer program carried on a computer-readable storage medium, the computer program containing program code for performing the methods shown in the flowchart. In such embodiments, the computer program can be downloaded and installed from a network via communication section 709, and / or installed from removable medium 711. When the computer program is executed by processor 701, it performs the functions defined in the system of embodiments of this disclosure. According to embodiments of this disclosure, the systems, devices, apparatuses, modules, units, etc., described above can be implemented by computer program modules.

[0139] This disclosure also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiments; or it may exist independently and not assembled into the device / apparatus / system. The computer-readable storage medium carries one or more programs that, when executed, implement the method according to the embodiments of this disclosure.

[0140] According to embodiments of this disclosure, the computer-readable storage medium can be a non-volatile computer-readable storage medium. Examples include, but are not limited to: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this disclosure, the computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0141] For example, according to embodiments of this disclosure, a computer-readable storage medium may include the ROM 702 and / or RAM 703 described above and / or one or more memories other than ROM 702 and RAM 703.

[0142] Embodiments of this disclosure also include a computer program product comprising a computer program containing program code for performing the methods provided in the embodiments of this disclosure. When the computer program product is run on an electronic device, the program code enables the electronic device to implement the logistics information identification method provided in the embodiments of this disclosure.

[0143] When the computer program is executed by the processor 701, it performs the functions defined in the system / apparatus of this disclosure embodiments. According to embodiments of this disclosure, the systems, apparatuses, modules, units, etc., described above can be implemented by computer program modules.

[0144] In one embodiment, the computer program may rely on a tangible storage medium such as an optical storage device or a magnetic storage device. In another embodiment, the computer program may also be transmitted and distributed in the form of signals over a network medium, and may be downloaded and installed via the communication section 709, and / or installed from a removable medium 711. The program code contained in the computer program can be transmitted using any suitable network medium, including but not limited to: wireless, wired, etc., or any suitable combination thereof.

[0145] According to embodiments of this disclosure, program code for executing the computer programs provided in embodiments of this disclosure can be written in any combination of one or more programming languages. Specifically, these computational programs can be implemented using high-level procedural and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages ​​include, but are not limited to, languages ​​such as Java, C++, Python, "C", or similar programming languages. The program code can execute entirely on the user's computing device, partially on the user's device, partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0146] 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 disclosure. In this regard, each block in a flowchart or block diagram may represent a module, 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. Those skilled in the art will understand that the features recited in the various embodiments and / or claims of this disclosure can be combined and / or combined in various ways, even if such combinations or combinations are not expressly described in this disclosure. In particular, the features described in the various embodiments and / or claims of this disclosure may be combined and / or combined in various ways without departing from the spirit and teachings of this disclosure. All such combinations and / or combinations fall within the scope of this disclosure.

[0147] The embodiments of this disclosure have been described above. However, these embodiments are for illustrative purposes only and are not intended to limit the scope of this disclosure. Although various embodiments have been described above, this does not mean that the measures in the various embodiments cannot be used advantageously in combination. The scope of this disclosure is defined by the appended claims and their equivalents. Various substitutions and modifications can be made by those skilled in the art without departing from the scope of this disclosure, and all such substitutions and modifications should fall within the scope of this disclosure.

Claims

1. A method for identifying logistics information, comprising: The waybill flag information in the logistics information is encoded to obtain the logistics code information; Based on the mean and variance information of the logistics coding information, determine the standard logistics coding information associated with the logistics coding information; The standard logistics coding information is processed using the covariance matrix to obtain coding feature values ​​and coding feature vectors; Based on the encoded feature value and the encoded feature vector, the logistics feature information is determined; The logistics feature information is input into the logistics attribute recognition model to obtain multiple computational tasks in the logistics attribute recognition model used to characterize matrix multiplication operations; Multiple computational tasks are processed in parallel by calling the target thread from the thread pool to obtain the product line identification result representing the logistics method for the target product in the logistics attribute identification result output by the logistics attribute identification model. The logistics attribute identification result is used to characterize the logistics attribute type of the target product in the logistics information.

2. The method according to claim 1, wherein, The logistics information is reduced in dimensionality to obtain the following logistics feature information: The logistics information is reduced in dimensionality using a preset dimensionality reduction algorithm to obtain the logistics feature information. The preset dimensionality reduction algorithm includes at least one of the following: principal component analysis algorithm, linear discriminant analysis algorithm, and factor analysis algorithm.

3. The method according to claim 1, wherein, The computational tasks include N; The logistics attribute recognition results output by the logistics attribute recognition model are obtained by calling the target thread from the thread pool to process multiple computing tasks in parallel, including: M target threads are called from the thread pool to process M target computing tasks in the computing task queue, and the computing task results of each target computing task are obtained. The computing task queue is composed of multiple computing tasks, and the target thread is a thread in the thread pool that is in an idle state, where N > M ≥ 1. After the target computation task obtains its result, the target thread that processed the target computation task returns to the thread pool to repeatedly process new target computation tasks in the computation task queue, until each of the N computation tasks has obtained its respective computation result; and The logistics attribute identification result is determined based on the calculation results of each of the N calculation tasks.

4. The method according to claim 1, wherein, Before performing dimensionality reduction processing on the logistics information, the logistics information identification method further includes: The logistics information is completed according to preset rules to obtain logistics information with a preset character length.

5. The method according to claim 1, wherein, The logistics attribute identification model includes at least one of the following: Radial basis function neural network model, multilayer perceptron neural network model.

6. A logistics information identification device, comprising: The dimensionality reduction module is used to reduce the dimensionality of logistics information to obtain the dimensionality-reduced logistics feature information. The computational task determination module is used to input the logistics feature information into the logistics attribute recognition model to obtain multiple computational tasks in the logistics attribute recognition model used to characterize matrix multiplication operations. The identification module is used to call the target thread from the thread pool to process multiple computing tasks in parallel, and obtain the product line identification result representing the logistics method for the target product in the logistics attribute identification result output by the logistics attribute identification model, wherein the logistics attribute identification result is used to represent the logistics attribute type of the target product in the logistics information; The dimensionality reduction processing module includes: The coding unit is used to encode the waybill flag information in the logistics information to obtain the logistics coding information; The first determining unit is used to determine the standard logistics code information associated with the logistics code information based on the code mean information and code variance information of the logistics code information; The first processing unit is used to process the standard logistics coding information using the covariance matrix to obtain coding feature values ​​and coding feature vectors. The second determining unit is used to determine logistics feature information based on the encoded feature value and the encoded feature vector.

7. An electronic device, comprising: One or more processors; Memory, used to store 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 method of any one of claims 1 to 5.

8. A computer-readable storage medium having executable instructions stored thereon, which, when executed by a processor, cause the processor to perform the method of any one of claims 1 to 5.

9. A computer program product comprising a computer program that, when executed by a processor, implements the method according to any one of claims 1 to 5.

Images