Method and device for determining logistics transfer user, electronic equipment and storage medium

Abstract

The invention provides a method and device for determining a logistics transfer user, electronic equipment and a storage medium, and relates to the technical field of logistics. The method comprises the following steps: acquiring transfer related characteristics of a target user in a logistics process, wherein the transfer related characteristics comprise a receiving characteristic and a sending characteristic; a transfer user judgment model is called to process the transfer related information, transfer judgment information of the target user is obtained, and the transfer judgment information is used for indicating whether the target user is a transfer user or not. According to the method and the device, the logistics transfer user is judged through the transfer user judgment model, so that the accuracy and the stability of judgment are improved. Moreover, whether the user is a transfer user or not can be comprehensively judged by referring to the characteristics of the sending behavior and the receiving behavior of the user in the logistics process.

Description

Technical Field

[0001] This disclosure relates to the field of logistics technology, and in particular to a method, apparatus, electronic device, and storage medium for identifying transit users in logistics. Background Technology

[0002] Express delivery companies typically use big data analytics, machine learning, and other technologies to uncover patterns and preferences in customers' shipping behavior, and then design precise message pushes based on this information.

[0003] This push notification method can only target users with specific types of products that match their preferences. It cannot comprehensively judge and analyze users' logistics behavior. Summary of the Invention

[0004] In view of this, the purpose of this disclosure is to provide a method, apparatus, electronic device and storage medium for identifying transit users in logistics, which can specifically solve existing problems.

[0005] Based on the above objectives, in a first aspect, this disclosure proposes a method for determining transit users in logistics, comprising: acquiring transit-related characteristics of a target user in the logistics process, the transit-related characteristics including receiving characteristics and sending characteristics; calling a transit user judgment model to process transit-related information to obtain transit judgment information of the target user, the transit judgment information being used to indicate whether the target user is a transit user.

[0006] Secondly, an apparatus for determining transit users in logistics is also provided, comprising: an acquisition unit configured to acquire transit-related characteristics of a target user in the logistics process, the transit-related characteristics including receiving characteristics and sending characteristics; and an invocation unit configured to invoke a transit user judgment model to process transit-related information to obtain transit judgment information of the target user, the transit judgment information being used to indicate whether the target user is a transit user.

[0007] Thirdly, an electronic device is also provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, the processor executing the computer program to implement the method of the first aspect.

[0008] Fourthly, a computer-readable storage medium is also provided, on which a computer program is stored, the computer program being executed by a processor to implement the method of any one of the first aspects.

[0009] Fifthly, a computer program product is also provided, including a computer program, wherein the computer program is executed by a processor to implement any one of the first aspects.

[0010] In summary, this disclosure offers at least the following advantages: By using a transit user identification model, the accuracy and stability of the identification process are improved. Furthermore, by referencing the user's sending and receiving behaviors during the logistics process, a comprehensive and integrated assessment of whether a user is a transit user can be made. Attached Figure Description

[0011] In the accompanying drawings, unless otherwise specified, the same reference numerals throughout the various drawings denote the same or similar parts or elements. These drawings are not necessarily drawn to scale. It should be understood that these drawings depict only some embodiments disclosed in this disclosure and should not be construed as limiting the scope of this disclosure.

[0012] Figure 1 A flowchart illustrating a method for determining transit users of logistics according to an embodiment of the present disclosure is shown;

[0013] Figure 2 A flowchart illustrating the training steps of a transit user determination model according to an embodiment of the present disclosure is shown;

[0014] Figure 3 Another flowchart illustrating the training steps of the transit user judgment model according to an embodiment of the present disclosure is shown;

[0015] Figure 4 A schematic diagram of an apparatus for determining transit users of logistics according to an embodiment of the present disclosure is shown;

[0016] Figure 5 A schematic diagram of the structure of an electronic device provided in an embodiment of the present disclosure is shown;

[0017] Figure 6 A schematic diagram of a storage medium provided according to an embodiment of the present disclosure is shown. Detailed Implementation

[0018] The present disclosure will now be described in further detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are for illustrative purposes only and are not intended to limit the invention. Furthermore, it should be noted that, for ease of description, only the parts relevant to the invention are shown in the accompanying drawings.

[0019] It should be noted that, unless otherwise specified, the embodiments and features described in this disclosure can be combined with each other. This disclosure will now be described in detail with reference to the accompanying drawings and embodiments.

[0020] Figure 1 This disclosure illustrates a method for identifying transit users in logistics. In embodiments of this disclosure, the method includes:

[0021] Step S101: Obtain transit-related characteristics of the target user in the logistics process. Transit-related characteristics include receiving characteristics and sending characteristics.

[0022] In this embodiment, the entity executing the method for determining transit users in logistics can obtain transit-related characteristics of the target user during the logistics process.

[0023] Transit-related characteristics refer to features that can be used to determine whether a user is a transit user. These could include, for example, the number of items sent and received that reflect the transit user's business scale. The quantity here can be the quantity per unit of time or the total quantity.

[0024] Transit users refer to users who are involved in the transshipment of express deliveries during the logistics process, i.e., intermediaries.

[0025] Step S102: Call the transit user judgment model to process transit-related information and obtain the transit judgment information of the target user. The transit judgment information is used to indicate whether the target user is a transit user.

[0026] In this embodiment, the aforementioned execution entity can call the transit user judgment model to process transit-related information and obtain the transit judgment information of the target user output by the transit user judgment model.

[0027] The information used to determine whether a user is a transit user or not can be either 1 or 0, or it can indicate the probability of being a transit user.

[0028] The intermediary user judgment model has strong accuracy and generalization ability, and can be a deep neural network. Specifically, it can be a lookalike model. For example, this lookalike model could be a random forest or a gradient boosting model.

[0029] These implementation methods can identify transit users in logistics through a transit user identification model, improving the accuracy and stability of the identification. Furthermore, by referencing the user's sending and receiving behaviors during the logistics process, a comprehensive and integrated assessment can be made to determine whether a user is a transit user.

[0030] Figure 2 The training steps of a transit user determination model according to an embodiment of this disclosure are shown. For example... Figure 2 As shown, this step includes:

[0031] Step S201: In the user information set, select users whose transit-related features reach the preset reference value as positive samples. The time correlation between the receiving and sending features of the positive samples is greater than the preset correlation threshold.

[0032] In this embodiment, the aforementioned executing entity can use the transit-related features of typical intermediary customers as positive samples for training the transit user judgment model. The receiving and sending features of the positive samples have a high temporal correlation. For example, a high temporal correlation could mean that the time difference between receiving and sending is small, or that they occur within the same time period.

[0033] The user information set includes transit-related features for multiple users.

[0034] Step S202: Train the transit user judgment model to be trained using positive samples to obtain the trained transit user judgment model.

[0035] In this embodiment, the aforementioned execution entity can employ various methods to train the transit user judgment model using positive samples. For example, the execution entity can train the transit user judgment model using only positive samples. Alternatively, the execution entity can randomly select a certain proportion of non-intermediary customers as negative samples, and use both positive and negative samples to train the transit user judgment model.

[0036] This embodiment can improve the accuracy of identifying positive samples of transit users by finding recipients and senders with high time correlation. Training with these positive samples helps to obtain an accurate transit user identification model.

[0037] Optionally, in the user information set, the transit-related characteristics of users whose transit-related characteristics reach a preset reference value are selected as positive samples, including: in the user set, the transit-related characteristics of users who receive packages at a first frequency and send packages within a first time period from the receipt time are selected as positive samples, wherein the first frequency is greater than a preset frequency, the time period is less than a preset time period, and the number of packages sent is greater than a preset number.

[0038] Among these optional implementations, the aforementioned implementing entity can select users who frequently receive packages and then send a large number of packages within a short period as positive samples. This allows for the accurate identification of users with stronger time correlations and their transit-related characteristics as positive samples, improving the accuracy of positive sample determination.

[0039] Optionally, the above-mentioned training of the transit user judgment model using positive samples includes: inputting the transit-related features of the positive samples and the transit-related features of the candidate users into the transit user judgment model to be trained, so that the transit user judgment model to be trained can identify candidate users who have feature similarity with the positive samples.

[0040] The candidate users for the input transit user judgment model can be a single user or multiple users. If there are multiple users, they can be ranked according to their feature similarity to positive samples. A predetermined number of candidate users are then selected in descending order of feature similarity.

[0041] Specifically, electronic devices used to train the transit user judgment model can use supervised algorithms to identify candidate users with similar features to positive samples, and then train the transit user judgment model.

[0042] In some optional application scenarios, the transit-related features of positive samples and transit-related features of candidate users are input into the transit user judgment model to be trained for training, including: calculating the distance between the transit-related features of candidate users and positive samples through the transit user judgment model to perform nearest distance matching; and training the transit user judgment model to be trained based on the results of the nearest distance matching.

[0043] In these application scenarios, the electronic device used for training can identify candidate users with similar features to the positive sample through nearest-distance matching. Specifically, the electronic device can calculate the distance between the transit-related features between the candidate user and the positive sample using a transit user judgment model to perform nearest-distance matching.

[0044] like Figure 3 As shown in the figure, the process of nearest-distance matching is illustrated using the transit-related features of users corresponding to positive samples and candidate users. Through customer group diffusion, high-potential transit users, i.e., high-potential intermediaries, with high similarity to candidate user features are found during model prediction.

[0045] Furthermore, the identified high-potential intermediaries can be promoted through both online visits and offline outreach.

[0046] These application scenarios can use nearest-neighbor matching to quantify the feature similarity between candidate users and positive samples, thereby improving the accuracy of identifying candidate users who have feature similarity to positive samples.

[0047] In some optional implementations of any embodiment of this disclosure, the receiving characteristics and sending characteristics include at least one of the following: receiving volume and sending volume, receiving frequency and sending frequency, receiving stability and sending stability, concentration of receiving categories and concentration of sending frequency, and the weight range in which the receiving weight and the weight range in which the sending weight are located.

[0048] Among these optional implementations, the number of items received and sent can reflect the scale of a user's business. The frequency of receiving and sending items can reflect the user's business activity. The concentration of received item categories and the concentration of sending item frequency can reflect the concentration of items shipped by the user. The weight range of received items and the weight range of sent items can indicate whether the user has purchasing and shipping activities.

[0049] Specifically, the above features can be classified through methods such as clustering to obtain recipient features and sender features.

[0050] The receiving and sending characteristics in these implementation methods can reflect the user's role and upstream / downstream relationships in the logistics supply chain, enabling more comprehensive feature analysis. This approach overcomes the limitations of traditional single-dimensional analysis and improves the accuracy of transit user identification. These implementation methods comprehensively consider multi-dimensional characteristics such as the user's receiving volume, frequency, category, and weight range during data collection and feature extraction. This multi-dimensional data analysis ensures that the transit user identification model can comprehensively capture customer behavioral characteristics and potential needs, thereby more accurately identifying transit users.

[0051] In some optional implementations of any embodiment of this disclosure, the relay judgment information is a probability; the method further includes: if the probability of the target user is greater than or equal to a probability threshold, determining the preset feature level at which the probability is located; and generating promotional information to be pushed to the target user based on the preset feature level.

[0052] In these implementations, the aforementioned execution entity can determine the preset feature level of the probability when the probability of the target user is greater than or equal to the probability threshold, in order to perform user segmentation.

[0053] Different preset feature levels can be used to push promotional information with different frequencies and content, thereby increasing the targeting of promotions.

[0054] This disclosure provides an apparatus for determining transit users in logistics, which is used to perform the method for determining transit users in logistics described in the above embodiments, such as... Figure 4 As shown, the device includes: an acquisition unit 401, configured to acquire transit-related features of a target user in the logistics process, the transit-related features including receiving features and sending features; and a calling unit 402, configured to call a transit user judgment model to process transit-related information and obtain transit judgment information of the target user, the transit judgment information being used to indicate whether the target user is a transit user.

[0055] Optionally, the training steps of the transit user judgment model include: in the user information set, selecting transit-related features of users whose transit-related features reach a preset reference value as positive samples, wherein the time correlation between the receiving and sending features of the positive samples is greater than a preset correlation threshold; and training the transit user judgment model to be trained using the positive samples to obtain the trained transit user judgment model.

[0056] Optionally, in the user information set, the transit-related characteristics of users whose transit-related characteristics reach a preset reference value are selected as positive samples, including: in the user set, the transit-related characteristics of users who receive packages at a first frequency and send packages within a first time period from the receipt time are selected as positive samples, wherein the first frequency is greater than a preset frequency, the time period is less than a preset time period, and the number of packages sent is greater than a preset number.

[0057] Optionally, the transit user judgment model to be trained is trained using positive samples, including: inputting the transit-related features of the positive samples and the transit-related features of the candidate users into the transit user judgment model to be trained, so that the transit user judgment model to be trained can identify candidate users who have feature similarity with the positive samples.

[0058] Optionally, the transit-related features of the positive sample and the transit-related features of the candidate user are input into the transit user judgment model to be trained for training, including: calculating the distance between the transit-related features of the candidate user and the positive sample through the transit user judgment model to perform nearest distance matching; and training the transit user judgment model to be trained based on the result of the nearest distance matching.

[0059] Optionally, the characteristics of receiving and sending items include at least one of the following: the number of items received and the number of items sent, the frequency of receiving and the frequency of sending, the stability of receiving and the stability of sending, the concentration of receiving categories and the concentration of sending frequency, and the weight range of receiving weight and the weight range of sending weight.

[0060] Optionally, the relay judgment information is a probability; the device is also configured to: if the probability of the target user is greater than or equal to a probability threshold, determine the preset feature level at which the probability is located; and generate promotional information to be pushed to the target user based on the preset feature level.

[0061] The apparatus for determining transit users of logistics provided in the above embodiments of this disclosure and the method for determining transit users of logistics provided in the embodiments of this disclosure are based on the same inventive concept and have the same beneficial effects as the methods adopted, run or implemented by their stored applications.

[0062] This disclosure also provides an electronic device corresponding to the method for determining transit users of logistics provided in the foregoing embodiments, for executing the method for determining transit users of logistics described above. This disclosure is not limiting.

[0063] Please refer to Figure 5 This illustrates a schematic diagram of an electronic device provided by some embodiments of the present disclosure. For example... Figure 5 As shown, the electronic device 50 includes: a processor 500, a memory 501, a bus 502 and a communication interface 503. The processor 500, the communication interface 503 and the memory 501 are connected through the bus 502. The memory 501 stores a computer program that can run on the processor 500. When the processor 500 runs the computer program, it executes the method provided in any of the foregoing embodiments of this disclosure.

[0064] The memory 501 may include high-speed random access memory (RAM) or non-volatile memory, such as at least one disk storage device. Communication between this system network element and at least one other network element is achieved through at least one communication interface 503 (which can be wired or wireless), such as the Internet, wide area network, local area network, or metropolitan area network.

[0065] Bus 502 can be an ISA bus, PCI bus, or EISA bus, etc. Buses can be divided into address buses, data buses, control buses, etc. Memory 501 is used to store programs. After receiving execution instructions, processor 500 executes the program. The method for determining transit users of logistics disclosed in any of the foregoing embodiments of this disclosure can be applied to processor 500, or implemented by processor 500.

[0066] The processor 500 may be an integrated circuit chip with signal processing capabilities. In implementation, each step of the above method can be completed by the integrated logic circuitry in the hardware of the processor 500 or by instructions in software form. The processor 500 may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), an off-the-shelf programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this disclosure. The general-purpose processor may be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this disclosure can be directly embodied in the execution of a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor. The software modules may reside in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. The storage medium is located in memory 501. The processor 500 reads the information in memory 501 and, in conjunction with its hardware, completes the steps of the above method.

[0067] The electronic device provided in this disclosure and the method for determining transit users of logistics provided in this disclosure are based on the same inventive concept and have the same beneficial effects as the methods they employ, operate, or implement.

[0068] This disclosure also provides a computer-readable storage medium corresponding to the method for determining transit users of logistics provided in the foregoing embodiments. Please refer to... Figure 6 The computer-readable storage medium shown is an optical disc 60, on which a computer program (i.e., a program product) is stored. When the computer program is run by a processor, it executes the method for determining transit users of logistics provided in any of the aforementioned embodiments.

[0069] It should be noted that examples of computer-readable storage media may also include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other optical and magnetic storage media, which will not be elaborated here.

[0070] The computer-readable storage medium provided in the above embodiments of this disclosure and the method for determining transit users of logistics provided in the embodiments of this disclosure are based on the same inventive concept and have the same beneficial effects as the methods adopted, run or implemented by the applications stored therein.

[0071] It should be noted that:

[0072] In the foregoing text, the terms "comprising," "including," or any other variations thereof are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element. Furthermore, it should be noted that the scope of the methods and apparatuses in this disclosure is not limited to performing functions in the order shown or discussed, but may also include performing functions substantially simultaneously or in the reverse order, depending on the functions involved. For example, the described methods may be performed in a different order than described, and various steps may be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.

[0073] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this disclosure, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes several instructions to cause a terminal (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of this disclosure.

[0074] The embodiments of this disclosure have been described above with reference to the accompanying drawings. These are merely specific implementations of this disclosure, but this disclosure is not limited to the specific implementations described above. The specific implementations described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of this disclosure without departing from the spirit and scope of the claims, and all of these forms are within the protection scope of this disclosure.

Claims

1. A method of determining a transit user of a logistics, characterized by, The method comprises: obtaining transfer-related features of a target user in a logistics process, the transfer-related features comprising receiving features and sending features; calling a transfer user judgment model to process the transfer-related information to obtain transfer judgment information of the target user, the transfer judgment information being used to indicate whether the target user is a transfer user.

2. The method of claim 1, wherein, The training steps of the transfer user judgment model comprise: in a user information set, screening transfer-related features of a user whose transfer-related features reach a preset reference value as positive samples, the time correlation of the receiving features and the sending features of the positive samples being greater than a preset correlation threshold; training the transfer user judgment model to be trained through the positive samples to obtain a trained transfer user judgment model.

3. The method of claim 2, wherein, The screening of the transfer-related features of the user whose transfer-related features reach the preset reference value as the positive samples in the user information set comprises: in the user set, screening transfer-related features of a user who receives at a first frequency and sends within a time period that is within a first time length from the receiving time as the positive samples, the first frequency being greater than a preset frequency, the time period being less than a preset time length, and the number of sending being greater than a preset number.

4. The method of claim 2, wherein, The training of the transfer user judgment model to be trained through the positive samples comprises: inputting the transfer-related features of the positive samples and transfer-related features of candidate users into the transfer user judgment model to be trained for training, so that the transfer user judgment model to be trained identifies candidate users that have feature similarity with the positive samples.

5. The method of claim 4, wherein, The inputting of the transfer-related features of the positive samples and the transfer-related features of the candidate users into the transfer user judgment model to be trained for training comprises: calculating the distance of the transfer-related features between the candidate users and the positive samples through the transfer user judgment model to perform nearest distance matching; training the transfer user judgment model to be trained according to the result of the nearest distance matching.

6. The method of claim 1, wherein, The receiving features and the sending features comprise at least one of the following: receiving quantity and sending quantity, receiving frequency and sending frequency, receiving stability and sending stability, receiving category concentration degree and sending frequency concentration degree, weight segment of receiving weight and weight segment of sending weight.

7. The method of claim 1, wherein, The transfer judgment information is a probability; the method further comprises: if the probability of the target user is greater than or equal to a probability threshold, determining a preset feature level to which the probability belongs; generating promotion information to be pushed for the target user according to the preset feature level.

8. An apparatus for determining a transit user of a logistics, characterized by, The method comprises: an obtaining unit configured to obtain transfer-related features of a target user in a logistics process, the transfer-related features comprising receiving features and sending features; a calling unit configured to call a transfer user judgment model to process the transfer-related information to obtain transfer judgment information of the target user, the transfer judgment information being used to indicate whether the target user is a transfer user.

9. An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, The processor runs the computer program to implement the method of any one of claims 1-7.

10. A computer-readable storage medium having stored thereon a computer program, characterized in that, The program is executed by the processor to implement the method of any one of claims 1-7.

Images