Waybill management method and device
By extracting real-time and offline feature data of the waybill, combining pre-trained models and weight adjustments, the risk identification problems in waybill management are improved, and the problem of lack of targeted sampling in the existing technology is solved.
Patent Information
- Application Number
- CN202411179630.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-26
- Publication Date
- 2024-12-06
AI Technical Summary
The existing technology lacks targetedness in the random inspection and re-inspection of waybill packages, resulting in low inspection efficiency and poor accuracy, and the inability to effectively identify risk waybills.
By extracting real-time feature data and dimension information from waybill information, obtaining offline feature data in combination with historical data, using pre-trained risk identification models for risk identification, adjusting the weights of different preset cycles to pay attention to real-time and long-term trends, according to the service provider and Loading vehicle dimensions are grouped for improved identification accuracy and efficiency.
It improves the efficiency and accuracy of the identification of risky waybills in waybill management, and can identify high-risk waybills in a targeted manner, reduce unnecessary random inspections, and improves the efficiency and accuracy of waybill management.
Smart Images

Figure CN119090269A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of logistics management, and in particular to a waybill management method and device. Background Art
[0002] In the logistics business, the billing elements of the waybill mainly include volume, weight, item type and other aspects. If there is a deviation in this information, it will affect the transportation cost of the waybill and whether it can be delivered smoothly. The existing technology usually adopts the method of random inspection and re-inspection through the sorting center or the transfer center to avoid the above problems. However, the current random inspection and re-inspection of waybill packages is often random and blind, and the packages cannot be inspected in a targeted manner, resulting in low inspection efficiency and poor accuracy. Summary of the invention
[0003] In view of this, the embodiments of the present disclosure provide a waybill management method, device, electronic device and storage medium, which can improve the efficiency and accuracy of identifying risky waybills in waybill management.
[0004] In a first aspect, an embodiment of the present disclosure provides a waybill management method, including:
[0005] Extracting real-time feature data and dimension information of each dimension from the waybill information of the waybill;
[0006] Determine the dimensional feature data corresponding to each dimensional information based on the historical data, and obtain the offline feature data of the waybill;
[0007] The risk of the waybill is identified based on the real-time feature data and the offline feature data.
[0008] Optionally, using a pre-trained risk identification model to identify risks on the waybill;
[0009] The risk identification model is obtained based on the following steps:
[0010] Based on the historical waybill information, a training sample set is obtained; the training sample set includes offline feature data, real-time feature data and risk features corresponding to the historical waybill in multiple preset periods; the weight of each training sample in the preset period is different;
[0011] The risk identification model is obtained by training using the training sample set.
[0012] Optionally, the method further comprises:
[0013] The risk identification result is sent to the sorting center, and in response to receiving feedback information from the sorting center, the risk identification model is updated.
[0014] Optionally, performing risk identification on the waybill according to the real-time feature data and the offline feature data includes:
[0015] In response to determining that the waybill comes from a preset service provider, determining an initial risk value of the waybill;
[0016] The waybill is subjected to risk identification according to the initial risk value, the real-time feature data and the offline feature data.
[0017] Optionally, after risk identification is performed on the waybill, the method further includes:
[0018] The risk identification result of the waybill set is determined according to the risk identification result of each waybill in the waybill set to which the waybill belongs.
[0019] Optionally, after risk identification is performed on the waybill, the method further includes:
[0020] Group the waybill set to which the waybill belongs according to the service provider dimension to obtain the waybill set corresponding to each service provider;
[0021] The service provider is subjected to risk identification based on the risk identification result of each waybill in the waybill set corresponding to the service provider.
[0022] Optionally, after risk identification is performed on the waybill, the method further includes:
[0023] Group the waybill set to which the waybill belongs according to the loading vehicle dimension to obtain a waybill set corresponding to each loading vehicle;
[0024] The loading vehicle is subjected to risk identification according to the risk identification result of each waybill in the waybill set corresponding to the loading vehicle.
[0025] In a second aspect, an embodiment of the present disclosure provides a waybill management device, including:
[0026] An extraction module, used to extract real-time feature data and dimension information of each dimension from the waybill information of the waybill;
[0027] A feature module, used to determine the dimensional feature data corresponding to each dimensional information based on historical data, and obtain the offline feature data of the waybill;
[0028] An identification module is used to identify the risks of the waybill based on the real-time feature data and the offline feature data.
[0029] In a third aspect, an embodiment of the present disclosure further provides an electronic device, comprising: a processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the computer device is running, the processor and the memory communicate through the bus, and when the machine-readable instructions are executed by the processor, the steps in the above-mentioned first aspect, or any optional implementation of the first aspect are performed.
[0030] In a fourth aspect, an embodiment of the present disclosure further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above-mentioned first aspect, or any optional implementation of the first aspect are executed.
[0031] In any one of the above aspects or any implementation method of any one of the aspects, real-time feature data and dimensional information of each dimension are extracted from the waybill information of the waybill; the dimensional feature data corresponding to each dimensional information is determined based on historical data to obtain the offline feature data of the waybill; and the risk of the waybill is identified based on the real-time feature data and the offline feature data. In this way, the risk of the waybill can be identified based on the real-time feature data and the offline feature data of the waybill, thereby improving the efficiency and accuracy of identifying risky waybills in waybill management.
[0032] In a further embodiment of the present disclosure, a pre-trained risk identification model is used to identify the risk of the waybill; the risk identification model is obtained based on the following steps: based on the historical waybill information, a training sample set is obtained; the training sample set includes offline feature data, real-time feature data and risk features corresponding to the historical waybill under multiple preset periods; the weights of the training samples under each preset period are different; the risk identification model is obtained by training with the training sample set. The efficiency of risk waybill identification is thereby further improved, and because the weights of the training samples under each Yunshe period are different, the weights of different preset periods can be adjusted to make the risk identification model focus on different aspects when performing risk identification. For example, setting a higher weight for training samples with a preset period of 60 days can make the model pay more attention to the long-term change trend of offline feature data; and setting a higher weight for training samples with a preset period of 3 days can make the model pay more attention to the immediate situation.
[0033] In a further embodiment of the present disclosure, when risk identification is performed on the waybill, an initial risk value of the waybill can be determined in response to determining that the waybill comes from a preset service provider; risk identification is performed on the waybill based on the initial risk value, the real-time feature data and the offline feature data, thereby improving the pertinence and accuracy of risky waybill identification.
[0034] In a further embodiment of the present disclosure, the waybill set in which the waybill is located is grouped according to the service provider dimension to obtain the waybill set corresponding to each service provider; based on the risk identification result of each waybill in the waybill set corresponding to the service provider, the risk of the service provider is identified, thereby improving the pertinence of risk waybill identification, helping to locate risks in time before checking the waybill, and thus improving the efficiency of waybill risk identification. In addition, grouping can be performed according to the loading vehicle, and risk identification can be performed on each loading vehicle, further improving the pertinence and efficiency of waybill management.
[0035] The effects of the above-mentioned waybill management device, electronic device and storage medium can be found in the description of the above-mentioned waybill management method, which will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS
[0036] In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the following is a brief introduction to the drawings required for use in the embodiments. The drawings herein are incorporated into the specification and constitute a part of the specification. These drawings illustrate embodiments consistent with the present disclosure and are used together with the specification to illustrate the technical solutions of the present disclosure. It should be understood that the following drawings only illustrate certain embodiments of the present disclosure and should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can also be obtained based on these drawings without creative work.
[0037] Figure 1 A flowchart of a waybill management method provided by an embodiment of the present disclosure is shown;
[0038] Figure 2 A schematic diagram of a real-time feature processing process in the waybill management method provided by an embodiment of the present disclosure is shown;
[0039] Figure 3 A schematic diagram of a waybill management process in a waybill management method provided by an embodiment of the present disclosure is shown;
[0040] Figure 4 A schematic diagram showing grouping of waybill sets according to different waybill dimensions in the waybill management method provided by an embodiment of the present disclosure is shown;
[0041] Figure 5 A schematic diagram of a waybill management device provided by an embodiment of the present disclosure is shown;
[0042] Figure 6 An exemplary system architecture is shown in which embodiments of the present disclosure may be applied;
[0043] Figure 7 A schematic diagram of the structure of a computer system of a terminal device or a server used to implement an embodiment of the present disclosure is shown. DETAILED DESCRIPTION
[0044] In order to make the purpose, technical scheme and advantages of the embodiments of the present disclosure clearer, the technical scheme in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only part of the embodiments of the present disclosure, rather than all of the embodiments. The components of the embodiments of the present disclosure generally described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present disclosure provided in the drawings is not intended to limit the scope of the present disclosure for protection, but merely represents the selected embodiments of the present disclosure. Based on the embodiments of the present disclosure, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present disclosure.
[0045] It should be noted that in the technical solution of the present invention, the collection, use, storage, sharing and transfer of user personal information involved are in compliance with the provisions of relevant laws and regulations, and it is necessary to inform the user and obtain the user's consent or authorization. When applicable, the user's personal information is de-identified and / or anonymized and / or encrypted.
[0046] The raising of the above problems and the solutions are the results obtained by the inventor after practice and careful research. The discovery process of the above problems and the solutions proposed for the above problems should be the contributions made by the inventor to the present disclosure during the disclosure process.
[0047] The technical solutions in the present disclosure will be clearly and completely described below in conjunction with the drawings in the present disclosure. Obviously, the described embodiments are only part of the embodiments of the present disclosure, rather than all of the embodiments. The components of the present disclosure generally described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present disclosure provided in the drawings is not intended to limit the scope of the present disclosure claimed for protection, but merely represents the selected embodiments of the present disclosure. Based on the embodiments of the present disclosure, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present disclosure.
[0048] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, further definition and explanation thereof is not required in subsequent drawings.
[0049] To facilitate understanding of this embodiment, a waybill management method disclosed in the embodiment of the present disclosure is first introduced in detail. The execution subject of the waybill management method provided in the embodiment of the present disclosure is generally a computer device with certain computing capabilities, and the computer device includes, for example: a terminal device or a server or other processing device, and the terminal device can be a user equipment (User Equipment, UE), a mobile device, a user terminal, a terminal, a cellular phone, a cordless phone, a personal digital assistant (Personal Digital Assistant, PDA), a handheld device, a computing device, a vehicle-mounted device, a wearable device, etc. In some possible implementations, the waybill management method can be implemented by a processor calling a computer-readable instruction stored in a memory.
[0050] See also Figure 1 As shown, it is a flow chart of the waybill management method provided by the embodiment of the present disclosure, and the method includes S101~S103, wherein:
[0051] S101: extracting real-time feature data and dimension information of each dimension from the waybill information of the waybill.
[0052] In the disclosed embodiment, the waybill information can be obtained through a stream processing framework or method, and the real-time feature data of the waybill can be extracted from the waybill information. Specifically, the waybill information can be obtained by using a Flink stream processing framework, an Apache Kafka Streams stream database, an Apache Storm stream processing system, etc., which is not specifically limited in the disclosed embodiment.
[0053] Take the Flink stream processing framework as an example. Figure 2 As shown in FIG. 1 , a schematic diagram of a real-time feature data processing flow of a waybill provided by an embodiment of the present disclosure is provided. Figure 2 As shown, by accessing the waybill information of the waybill, the order information, routing information, full tracking information, etc. corresponding to the waybill can be obtained, and then the real-time feature data corresponding to the waybill can be extracted according to the waybill information. For example, the real-time feature data of the waybill may include feature data under indicators such as the waybill weight, waybill volume, and product type of the waybill; these feature data can reflect the properties of the waybill itself.
[0054] In the embodiments of the present disclosure, dimensional information under various dimensions can also be extracted from the waybill information of the waybill, where the dimensions may include merchant dimension, collection person dimension, collection site dimension, merchant + collection person dimension, etc. Specifically, assuming that it is extracted from the waybill information of the waybill that the waybill comes from merchant A, then the dimensional information of the waybill under the merchant dimension is merchant A, and the feature data about merchant A can be obtained based on the historical data of merchant A. This step is described in S102 and will not be repeated here. It should be noted that the above examples for dimensions are only a possible implementation method of the embodiments of the present disclosure and do not constitute an improper limitation on the present invention.
[0055] S102: Determine the dimensional feature data corresponding to each dimensional information based on historical data to obtain offline feature data of the waybill.
[0056] In this step, the dimensional feature data of the waybill under each dimensional information can be determined and used as the offline feature data of the waybill.
[0057] In the disclosed embodiment, offline feature data may be dimensional feature data under dimensional information of each dimension obtained by extracting and processing features of dimensions such as merchants, collectors, consignees, collection sites, and product types based on historical data. When the waybill information is obtained, the dimensional information under each dimension indicated in the waybill information may be used. For example, if the waybill comes from merchant A, the consignee is B, and the collector is C, the dimensional feature data corresponding to merchant A, the dimensional feature data corresponding to consignee B, and the dimensional feature data corresponding to consignee C may be used as the offline feature data of the waybill under the merchant dimension, consignee dimension, and consignee dimension. Merchant A, consignee B, and consignee C here are the dimensional information of the waybill under different dimensions.
[0058] Exemplarily, take the merchant dimension as an example, and the dimensional information of the waybill under the merchant dimension is merchant A. The basic information of merchant A can be obtained as the unique identifier of the merchant, or a unique identifier of merchant A can be generated to determine the dimensional feature data corresponding to merchant A. Indicators such as merchant A's shipment volume, sampling volume, over-standard volume, difference order volume, difference weight, sampling rate, accountability volume, and accountability rate can also be determined, and then the corresponding feature data can be obtained based on the specific data of merchant A under the above indicators in the past 1 day, 3 days, 7 days, 15 days, 30 days, and 60 days in the historical data. These feature data can then be used as offline feature data of the waybill, and used together with the real-time feature data of the waybill to identify risks for the waybill.
[0059] In a specific implementation, the calculation of the above-mentioned dimensional feature data can be completed in advance, and the calculated dimensional feature data can be stored in the corresponding position. When the waybill information indicates a certain dimensional information, the corresponding dimensional feature data can be obtained as the offline feature data of the waybill. Similarly, the dimensional feature data of multiple merchants such as merchant B and merchant C can also be determined based on historical data. Therefore, after the waybill information is obtained, the dimensional feature data under the merchant dimension corresponding to the waybill can be determined according to the dimensional information under the merchant dimension indicated in the waybill information. It should be noted that in addition to the merchant dimension, the dimensional information under each dimension such as the collection person, collection site, recipient, product type, etc. can also be extracted to obtain the corresponding dimensional feature data, and the present disclosed embodiment does not make specific restrictions on this. In addition, the present disclosed embodiment does not make specific restrictions on the specific method of extracting and processing the above-mentioned features. In actual applications, it can be based on actual needs and be based on the ability to realize its functions.
[0060] In the embodiments of the present disclosure, by extracting dimensional feature data under multiple time windows, the dimensional feature data of different time periods under the same dimensional information can be determined, that is, time tags are added to the dimensional feature data. For example, by performing feature extraction and processing on historical data under multiple time windows, the different dimensional feature data corresponding to the promotional off-season and peak season of merchant A under the same indicator can be determined. In this way, more accurate feature data can be determined based on the time information of the waybill to be shipped, thereby improving the accuracy of subsequent risk identification of the waybill.
[0061] S103: Perform risk identification on the waybill according to the real-time feature data and the offline feature data.
[0062] In this step, the offline feature data obtained based on historical data and the real-time feature data obtained based on the waybill information can be used together to identify the risks of the waybill; among them, the offline feature data obtained based on historical data can reflect the statistical information or long-term trends over a period of time, while the real-time feature data obtained based on the waybill information reflects the immediate status and attributes of the current waybill. Therefore, when the risk of the waybill is identified later, the two can be used in combination, thereby ensuring that the determined waybill risk is more accurate.
[0063] In the embodiments of the present disclosure, real-time feature data refers to instant feature data related to the waybill currently undergoing risk identification. Real-time feature data is used to describe the specific attributes of the current waybill, such as the product type corresponding to the waybill, the waybill weight, etc. These feature data are only related to the current waybill and can only be obtained through the current waybill. They are unrelated to any other waybill and are unique. Offline feature data may refer to feature data that can be processed and stored in advance, has no direct association with the current waybill, and can be obtained based on historical waybills. This means that there is a set of offline feature data for each dimension of information. When a waybill corresponds to one of the dimension information, the offline feature data corresponding to the dimension information can be queried as supplementary feature data to the real-time feature data of the waybill, so as to more comprehensively identify the risks of the waybill.
[0064] In an embodiment of the present disclosure, a pre-trained risk identification model can be used to identify risks of the waybill; the risk identification model is obtained based on the following steps: a training sample set is obtained based on historical waybill information; the training sample set includes offline feature data, real-time feature data and risk feature data corresponding to the historical waybill under multiple preset periods; the weights of the training samples under each preset period are different; and the risk identification model is obtained by training with the training sample set.
[0065] In the specific implementation, offline big data processing technology can be used to extract and process the features of merchants, collectors, recipients, collection sites, waybill information, sampling information, sampling results, and accountability results. Since the calculation results are used for algorithm model training and supervised learning can be used, only the historical waybills that have been tested can be calculated. The feature data used to train the model can be obtained based on the merchant information, collector information, collection site information, waybill information, merchant + collector information, sampling information, and other information of the historical waybills. Specifically, the merchant information to which the waybill belongs may include the basic information of the merchant and the ordering account; the shipment volume, sampled inspection volume, over-limit volume, and responsible volume in the past 1 day, 3 days, 7 days, 15 days, 30 days, and 60 days; the collection person information may include the basic information of the waybill collection person; merchant type; contract information; calculation of the collection volume, sampled inspection volume, over-limit volume, and responsible volume in the past 1 day, 3 days, 7 days, 15 days, 30 days, and 60 days; the collection station information may include the basic information of the waybill collection station; calculation of the collection volume, sampled inspection volume, over-limit volume, and responsible volume in the past 1 day, 3 days, 7 days, 15 days, 30 days, and 60 days 0-day, 60-day collection volume, sampled volume, over-standard volume, and accountable volume data; waybill information may include waybill shipping address information, delivery address information, sender, recipient, collection weight, collection volume, main product type, number of packages, timeliness type, freight type, etc.; merchant + collector information may include the collection volume, sampled volume, over-standard volume, and accountable volume data in the past 1 day, 3 days, 7 days, 15 days, 30 days, and 60 days; sampling information may include review site, review weight, review volume, whether it exceeds the standard, type of over-standard, whether it is accountable, etc. It should be noted that the above description of the extraction of feature data in the training sample set is only used as an example of a possible implementation method of the disclosed embodiment, and does not constitute an improper limitation of the present invention.
[0066] In a specific implementation, after obtaining the above-mentioned feature data for training the risk identification model, the Catboost algorithm, LightGBM algorithm, etc. can be used for model training. In a preferred implementation, in order to ensure the accuracy and generalization ability of the risk identification model, the Catboost algorithm can be used to train the model. It should be noted that the above-mentioned model training method is only a preferred implementation method of the embodiment of the present disclosure. In actual implementation, it can be based on actual conditions and needs, and its functions can be realized. The present invention does not make specific limitations on this.
[0067] In a specific implementation, when training a risk identification model based on the above-mentioned training sample set, different weights can be assigned to the training data under different preset periods. For example, the weight of the training data under the preset period of nearly 60 days can be set higher, so that the risk identification model can pay more attention to the long-term change trend of the characteristics; and the weight of the training data under the preset period of nearly 3 days can be set higher, so that the risk identification model can pay more attention to the characteristics of the current time period.
[0068] In the disclosed embodiment, Figure 3 The following is a flowchart of waybill management. Figure 3 As shown, for the waybills that have been collected, risk identification can be performed using the risk identification model based on the real-time feature data and offline feature data obtained above to determine the probability of exceeding the standard for each waybill package.
[0069] In an embodiment of the present disclosure, risk identification is performed on the waybill based on the real-time feature data and the offline feature data, including: in response to determining that the waybill comes from a preset service provider, determining an initial risk value of the waybill; and risk identification is performed on the waybill based on the initial risk value, the real-time feature data, and the offline feature data.
[0070] In specific implementations, when identifying the risks of waybills, it is possible to first determine whether the waybill comes from a preset service provider. The preset service provider here can be a high-risk service provider, that is, a service provider with a higher risk rate; it can also be a service provider set based on actual conditions, such as setting a preset service provider according to dimensions such as maps, economic conditions, and infectious disease scope, thereby indicating that the service provider may have additional risks. If the waybill comes from a preset service provider, an initial risk value can be added to it first, and then based on the initial risk value, risk identification can be performed based on real-time feature data and offline feature data.
[0071] For example, assuming that risk identification is to determine the probability of a waybill exceeding the standard, before calculating the probability of a waybill exceeding the standard based on the real-time feature data and offline feature data, the initial probability of a waybill exceeding the standard should be 0; and when it is determined that the waybill comes from a preset service provider, the initial probability of a waybill exceeding the standard can be set to 5%, and the actual probability of a waybill exceeding the standard is calculated by adding the probability of exceeding the standard determined based on the real-time feature data and offline feature data to the 5%. The preset service provider here can be a service provider that frequently exceeds the standard based on historical data; that is, assuming that for the same waybill, when the probability of exceeding the standard is 50% when it does not come from the preset service provider, the probability of exceeding the standard when it comes from the preset service provider may be 55% or even higher.
[0072] It should be noted that the above-mentioned specific application for risk identification and the setting for the preset service provider are merely exemplified as a possible implementation of the embodiment of the present disclosure and do not constitute an improper limitation on the present invention.
[0073] In another possible implementation, assume that service provider A is located in Township B, and service provider B is also located in Township B. Since Township B has recently experienced a high incidence of influenza, service providers A and B can be set as preset service providers, and initial risk values can be added to them before determining the probability of exceeding the standard to ensure the accuracy of waybill management. Or, assume that service provider C has a higher historical liability rate than its peers, service provider C can also be set as the preset service provider, and initial risk values can be added to waybills issued by service provider C.
[0074] In the embodiment of the present disclosure, after the risk identification is performed on the waybill, the method further includes: determining the risk identification result of the waybill set according to the risk identification result of each waybill in the waybill set to which the waybill belongs.
[0075] In specific implementations, waybills are often issued in the form of waybill collections, which may come from the same or nearby collection stations or merchants, etc. Therefore, the risk identification results of the waybill collection can be determined based on the risk identification results of each waybill in the waybill collection, thereby improving the efficiency of waybill management.
[0076] In the embodiments of the present disclosure, Figure 4 As shown, Figure 4 The figure is a schematic diagram of grouping waybill sets according to different dimensions. Specifically, waybill sets can be grouped according to multiple dimensions such as service provider, loading vehicle, product type, etc.
[0077] In a possible implementation manner, after risk identification is performed on the waybill, the following step is further included:
[0078] The waybill set to which the waybill belongs is grouped according to the service provider dimension to obtain a waybill set corresponding to each service provider; and risk identification is performed on the service provider based on the risk identification result of each waybill in the waybill set corresponding to the service provider.
[0079] like Figure 3 and Figure 4As shown, after determining the risk identification results of the waybill set, the waybill can be grouped according to the service provider dimension, and risk analysis can be performed for each service provider group, thereby determining the risk identification results corresponding to each service provider. For example, assuming that the waybills in the waybill set come from three service providers, namely service provider A, service provider B and service provider C, 80% of the waybills whose risk identification results of exceeding the standard risk exceed the preset range are from service provider A. At this time, it can be determined that the risk of exceeding the standard of service provider A does not meet the preset requirements, and service provider A can be listed as a high-risk service provider, and an investigation can be conducted based on the determined high-risk service provider to standardize the behavior of the service provider and improve the efficiency of waybill management. The risk identification results exceeding the preset range here can include that the probability of exceeding the standard of the waybill exceeds the preset threshold, the difference between the actual cost of the waybill package and the reported cost exceeds the preset threshold, etc., and the disclosed embodiment does not make specific limitations on this. In this way, risks can be located in advance, and high-risk service providers can be investigated and managed in a timely manner, thereby avoiding further losses and improving the efficiency of waybill management.
[0080] In another possible implementation, after the risk identification is performed on the waybill, the further step includes: grouping the waybill set to which the waybill belongs according to the loading vehicle dimension to obtain a waybill set corresponding to each loading vehicle; and performing risk identification on the loading vehicle based on the risk identification result of each waybill in the waybill set corresponding to the loading vehicle.
[0081] like Figure 3 and Figure 4 As described above, the waybill set can also be grouped according to the dimension of the loaded vehicle. If grouping according to the service provider can locate the risk in advance, then grouping according to the vehicle dimension can do the maximum investigation for the risk that has occurred. In the specific implementation, the risk identification of each loaded vehicle can be determined based on the loading information of each waybill package in the waybill set, combined with the risk identification result of each waybill package. The risk identification result for each vehicle here can be the excess proportion, that is, the ratio of the risk waybill that may exist in the vehicle to all waybill packages. Of course, it can also be other meanings, and the embodiment of the present disclosure does not limit this. After determining the risk identification result of the vehicle, the vehicle whose excess risk identification result does not meet the preset requirements can be determined as a high-risk vehicle, and then the determined high-risk vehicle can be sent to the corresponding sorting center, and the sorting center can conduct random inspections on each high-risk vehicle. Alternatively, the excess proportion of each vehicle can also be sent to the corresponding sorting center, so that the sorting center can conduct random inspections on the vehicle in combination with its own random inspection capabilities. In this way, the sorting center no longer conducts blind inspections. Instead, it can combine its own inspection capabilities and, under the premise of a certain total inspection volume, give priority to inspecting vehicles with greater risks. Compared with random inspections, this improves the efficiency of waybill management.
[0082] In another possible implementation, grouping can also be performed according to product type dimensions, sender dimensions, etc. The present disclosure embodiment does not make specific limitations on this. In actual applications, it can be based on actual needs and circumstances to achieve its purpose.
[0083] In the disclosed embodiment, the risk identification result can also be sent to the sorting center, and the risk identification model can be updated in response to receiving feedback information from the sorting center. In a specific implementation, the feedback information here can be the information obtained after the sorting center conducts random inspections on the waybills in the waybill set based on the risk identification results, such as random inspection information, risk results, accountability results, etc. The model can be iterated through these data to improve the recognition accuracy of the model.
[0084] According to a second aspect of the embodiment of the present disclosure, Figure 5 As shown, a waybill management device 500 is provided, comprising:
[0085] An extraction module 501 is used to extract real-time feature data and dimension information of each dimension from the waybill information of the waybill;
[0086] A feature module 502 is used to determine the dimension feature data corresponding to each dimension information based on historical data, and obtain the offline feature data of the waybill;
[0087] The identification module 503 is used to identify the risk of the waybill according to the real-time feature data and the offline feature data.
[0088] Optionally, using a pre-trained risk identification model to identify risks on the waybill;
[0089] The identification module 503 is specifically used for:
[0090] Based on the historical waybill information, a training sample set is obtained; the training sample set includes offline feature data, real-time feature data and risk features corresponding to the historical waybill in multiple preset periods; the weight of each training sample in the preset period is different;
[0091] The risk identification model is obtained by training using the training sample set.
[0092] Optionally, the identification module 503 is further used for:
[0093] The risk identification result is sent to the sorting center, and in response to receiving feedback information from the sorting center, the risk identification model is updated.
[0094] Optionally, the identification module 503 is specifically used for:
[0095] In response to determining that the waybill comes from a preset service provider, determining an initial risk value of the waybill;
[0096] The waybill is subjected to risk identification according to the initial risk value, the real-time feature data and the offline feature data.
[0097] Optionally, the identification module 503 is further used for:
[0098] The risk identification result of the waybill set is determined according to the risk identification result of each waybill in the waybill set to which the waybill belongs.
[0099] Optionally, the identification module 503 is further used for:
[0100] Group the waybill set to which the waybill belongs according to the service provider dimension to obtain the waybill set corresponding to each service provider;
[0101] The service provider is subjected to risk identification based on the risk identification result of each waybill in the waybill set corresponding to the service provider.
[0102] Optionally, the identification module 503 is further used for:
[0103] Group the waybill set to which the waybill belongs according to the loading vehicle dimension to obtain a waybill set corresponding to each loading vehicle;
[0104] The loading vehicle is subjected to risk identification according to the risk identification result of each waybill in the waybill set corresponding to the loading vehicle.
[0105] According to the third aspect of an embodiment of the present disclosure, an electronic device for waybill management is provided, comprising: one or more processors; a storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the method provided by the first aspect of the embodiment of the present disclosure.
[0106] According to a fourth aspect of an embodiment of the present disclosure, a computer-readable medium is provided, on which a computer program is stored, and when the program is executed by a processor, the method provided by the first aspect of the embodiment of the present disclosure is implemented.
[0107] Figure 6 An exemplary system architecture 600 to which the waybill management method or the waybill management apparatus implemented by the present disclosure can be applied is shown.
[0108] like Figure 6 As shown, system architecture 600 may include terminal devices 601, 602, 603, network 604 and server 605. Network 604 is used to provide a medium for communication links between terminal devices 601, 602, 603 and server 605. Network 604 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.
[0109] The user can use the terminal devices 601, 602, 603 to interact with the server 605 through the network 604 to receive or send messages, etc. Various communication client applications can be installed on the terminal devices 601, 602, 603, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social platform software, etc. (only for example).
[0110] The terminal devices 601 , 602 , and 603 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers, and desktop computers, etc.
[0111] The server 605 may be a server that provides various services, such as a backend management server (for example only) that provides support for shopping websites browsed by users using the terminal devices 601, 602, and 603. The backend management server may process the received waybill management request and feed back the processing result (for example only) to the terminal device.
[0112] It should be noted that the waybill management method provided in the embodiment of the present invention is generally executed by the server 605, and accordingly, the waybill management device is generally set in the server 605. The waybill management method provided in the embodiment of the present invention can also be executed by the terminal devices 601, 602, and 603, and accordingly, the waybill management device can be set in the terminal devices 601, 602, and 603.
[0113] It should be understood that Figure 6 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.
[0114] Reference below Figure 7 , which shows a schematic diagram of the structure of a computer system 700 of a terminal device suitable for implementing an embodiment of the present invention. Figure 7 The terminal device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.
[0115] like Figure 7 As shown, the computer system 700 includes a central processing unit (CPU) 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 part 708 into a random access memory (RAM) 703. In the RAM 703, various programs and data required for the operation of the system 700 are also stored. The CPU 701, the ROM 702, and the RAM 703 are connected to each other through a bus 704. An input / output (I / O) interface 705 is also connected to the bus 704.
[0116] The following components are connected to the I / O interface 705: an input section 706 including a keyboard, a mouse, etc.; an output section 707 including a cathode ray tube (CRT), a 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, a 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 magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 710 as needed, so that a computer program read therefrom is installed into the storage section 708 as needed.
[0117] In particular, according to the embodiments disclosed in the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present invention include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 709, and / or installed from the removable medium 711. When the computer program is executed by the central processing unit (CPU) 701, the above-mentioned functions defined in the system of the present invention are executed.
[0118] It should be noted that the computer-readable medium shown in the present invention may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present invention, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.
[0119] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present invention. In this regard, each box in the flow chart or block diagram can represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flow chart, and the combination of the boxes in the block diagram or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.
[0120] The modules involved in the embodiments of the present invention may be implemented by software or hardware. The modules described may also be set in a processor. For example, a processor includes a feature module, an over-standard module, and a risk module, wherein the names of these modules do not constitute limitations on the modules themselves in certain circumstances. For example, an identification module may also be described as "a risk identification module for the waybill based on the real-time feature data and the offline feature data."
[0121] As another aspect, the present invention further provides a computer-readable medium, which may be included in the device described in the above embodiment; or may exist independently without being assembled into the device. The above computer-readable medium carries one or more programs, and when the above one or more programs are executed by a device, the device implements the following method:
[0122] Extracting real-time feature data and dimension information of each dimension from the waybill information of the waybill;
[0123] Determine the dimensional feature data corresponding to each dimensional information based on the historical data, and obtain the offline feature data of the waybill;
[0124] The risk of the waybill is identified based on the real-time feature data and the offline feature data.
[0125] Finally, it should be noted that the above-described embodiments are only specific implementation methods of the present disclosure, which are used to illustrate the technical solutions of the present disclosure, rather than to limit them. The protection scope of the present disclosure is not limited thereto. Although the present disclosure is described in detail with reference to the above-described embodiments, ordinary technicians in the field should understand that any technician familiar with the technical field can still modify the technical solutions recorded in the above-described embodiments within the technical scope disclosed in the present disclosure, or can easily think of changes, or make equivalent replacements for some of the technical features therein; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present disclosure, and should be included in the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure shall be based on the protection scope of the claims.
Claims
1. A waybill management method, characterized in that: include: Extracting real-time feature data and dimension information of each dimension from the waybill information of the waybill; Determine the dimensional feature data corresponding to each dimensional information based on the historical data to obtain the offline feature data of the waybill; The risk of the waybill is identified based on the real-time feature data and the offline feature data.
2. The method according to claim 1, characterized in that: Using a pre-trained risk identification model to identify risks on the waybill; The risk identification model is obtained based on the following steps: Based on the historical waybill information, a training sample set is obtained; The training sample set includes offline feature data, real-time feature data and risk feature data corresponding to the historical waybills in multiple preset periods; the weight of the training samples in each preset period is different; The risk identification model is obtained by training using the training sample set.
3. The method according to claim 1, characterized in that The method further comprises: The risk identification result is sent to the sorting center, and in response to receiving feedback information from the sorting center, the risk identification model is updated.
4. The method according to claim 1, characterized in that: According to the real-time feature data and the offline feature data, risk identification is performed on the waybill, including: In response to determining that the waybill comes from a preset service provider, determining an initial risk value of the waybill; The waybill is subjected to risk identification according to the initial risk value, the real-time feature data and the offline feature data.
5. The method according to claim 1, characterized in that After risk identification of the waybill, it also includes: The risk identification result of the waybill set is determined according to the risk identification result of each waybill in the waybill set to which the waybill belongs.
6. The method according to claim 1, characterized in that After risk identification of the waybill, it also includes: Group the waybill set to which the waybill belongs according to the service provider dimension to obtain the waybill set corresponding to each service provider; The service provider is subjected to risk identification based on the risk identification result of each waybill in the waybill set corresponding to the service provider.
7. The method according to claim 1, characterized in that After risk identification of the waybill, it also includes: Group the waybill set to which the waybill belongs according to the loading vehicle dimension to obtain a waybill set corresponding to each loading vehicle; The loading vehicle is subjected to risk identification according to the risk identification result of each waybill in the waybill set corresponding to the loading vehicle.
8. A waybill management device, characterized in that: include: An extraction module, used to extract real-time feature data and dimension information of each dimension from the waybill information of the waybill; A feature module, used to determine the dimensional feature data corresponding to each dimensional information based on historical data, and obtain the offline feature data of the waybill; An identification module is used to identify the risks of the waybill based on the real-time feature data and the offline feature data.
9. An electronic device, characterized in that: include: one or more processors; a storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 7.
10. A computer readable medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.
Citation Information
Cited By
Logistics information processing method and device
CN119809479A
