Method, device, equipment, medium and product for determining transportation mode of posted objects

By determining the individual and global characteristics of the transportation task, obtaining the claims prediction value, distinguishing vulnerable entrusted items, and adopting appropriate transportation methods, the problem of taking into account both transportation costs and safety is solved, and cost reduction and safety improvement are achieved.

CN119047951APending Publication Date: 2024-11-29BEIJING JINGDONG YUANSHENG TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411178616.8
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-26
Publication Date
2024-11-29

AI Technical Summary

Technical Problem

The prior art cannot take into account the transportation cost of entrusted goods and transportation safety, resulting in excessive transportation costs.

Method used

By determining the individual characteristics and global characteristics of the transportation task, input the pre-trained claims prediction model, obtain the claims probability prediction value, and then determine the transportation method, distinguish between vulnerable and non-vulnerable entrusted items, and adopt the corresponding safety level transportation method.

Benefits of technology

The transportation method is reasonably allocated according to the vulnerability of the entrusted goods, reducing transportation costs, and improving transportation safety and preventing user loss.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119047951A_ABST
    Figure CN119047951A_ABST
Patent Text Reader

Abstract

The embodiment of the invention discloses a method, a device, equipment, a medium and a product for determining a transportation mode of a posted object, and relates to the technical field of logistics, the method comprises the following steps: determining individual characteristics corresponding to a current transportation task under at least two themes; global features corresponding to the topics in the at least two topics are obtained, the global features are determined on the basis of the transportation tasks where target events occur under the corresponding topics in the corresponding statistical periods, and the target events comprise claim settlement events and / or complaint events; inputting the individual features and the global features corresponding to the topics in the at least two topics into a pre-trained claim settlement prediction model to obtain a claim settlement probability prediction value; and determining a transportation mode of the current transportation task based on the claim settlement probability prediction value. By adopting the technical scheme of the embodiment of the invention, the technical effect of considering both the transportation cost and the transportation safety of the posted objects can be achieved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] Embodiments of the present invention relate to the field of logistics technology, and in particular, to a method, device, equipment, medium and product for determining a transportation mode of consigned goods. Background Art

[0002] At present, during the transportation of consignments, couriers must ensure the safety of the consignments. If the consignments are lost or damaged, they usually need to pay a certain amount of compensation to the sender. Compared with consignments with low attribute values, consignments with higher attribute values ​​require the courier to pay higher compensation in the event of loss or damage. For this reason, the existing technology usually regards consignments with guaranteed attribute values ​​(insurance value) exceeding the set threshold as key express delivery objects, and uses transportation methods with higher security levels to complete the delivery process of key consignments.

[0003] However, in the process of implementing the present invention, the inventors found that there are at least the following problems in the prior art:

[0004] Since the transportation cost of transportation methods with higher security levels is much higher than that of ordinary transportation methods, if all consignments with higher security attribute values ​​are taken as key express delivery objects, the overall transportation cost will be higher. Therefore, the existing technology has the problem of not being able to balance the transportation cost and transportation security of consignments. Summary of the invention

[0005] The embodiments of the present invention provide a method, device, equipment, medium and product for determining the transportation mode of consignment, so as to solve the problem that the prior art cannot take into account both the transportation cost and transportation safety of consignment.

[0006] In a first aspect, an embodiment of the present invention provides a method for determining a consignment transportation mode, the method comprising:

[0007] Determine the individual characteristics of the current transport task under at least two themes;

[0008] Acquire global features corresponding to each of the at least two topics, wherein the global features are determined based on transportation tasks in which target events have occurred under the corresponding topics within a corresponding statistical period, wherein the target events include claim settlement events and / or complaint events;

[0009] Inputting the individual features and the global features respectively corresponding to each of the at least two topics into a pre-trained claim prediction model to obtain a claim probability prediction value;

[0010] The transportation mode of the current transportation task is determined based on the claim settlement probability prediction value.

[0011] In a second aspect, an embodiment of the present invention further provides a device for determining a consignment transportation mode, the device comprising:

[0012] An individual feature module, used to determine the individual features corresponding to the current transportation task under at least two topics;

[0013] A global feature module, used to obtain global features corresponding to each of the at least two topics, wherein the global features are determined based on the transportation tasks in which target events have occurred under the corresponding topics within the corresponding statistical period, and the target events include claim settlement events and / or complaint events;

[0014] A prediction module, used for inputting the individual features and the global features respectively corresponding to each of the at least two topics into a pre-trained claim prediction model to obtain a claim probability prediction value;

[0015] The transportation mode determination module is used to determine the transportation mode of the current transportation task based on the claim probability prediction value.

[0016] In a third aspect, an embodiment of the present invention provides an electronic device, the electronic device comprising:

[0017] one or more processors;

[0018] A memory for storing one or more programs;

[0019] When the one or more programs are executed by the one or more processors, the one or more processors implement the method for determining the consignment transportation mode as provided in any embodiment of the present invention.

[0020] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements a method for determining a consignment transportation mode as provided in any embodiment of the present invention.

[0021] In a fifth aspect, an embodiment of the present invention further provides a computer program product on which a computer program is stored, and when the program is executed by a processor, a method for determining a consignment transportation mode as provided in any embodiment of the present invention is implemented.

[0022] The embodiments of the above invention have the following advantages or beneficial effects:

[0023] The technical solution of the method for determining the mode of transport of consigned goods provided in the embodiment of the present invention is that, since the individual features corresponding to at least two topics respectively include all-round information on the correlation between the current transport task and the claim settlement; the global features corresponding to at least two topics respectively include all-round information on the correlation between the market and the claim settlement; therefore, the individual features and global features under each of the at least two topics are input into the pre-trained claim settlement prediction model, an accurate claim settlement probability prediction value can be obtained; the claim settlement probability prediction value can reflect the probability that the consigned goods corresponding to the current transport task need to be compensated, that is, the probability that the consigned goods corresponding to the current transport task will be compensated during the transportation process. For example, when the predicted value of claim probability is high, the probability of damage to the corresponding consignment during transportation is high. Conversely, the probability of damage to the corresponding consignment during transportation is low. Therefore, fragile consignment can be accurately identified according to the predicted value of claim probability, so that reasonable allocation of transportation methods can be completed according to whether the consignment is fragile. In this way, the damage of fragile consignment can be reduced by using target transportation methods with higher safety levels, and non-fragile consignment can be safely transported by non-target transportation methods with lower safety levels, thereby achieving the technical effect of taking into account both transportation cost and transportation safety, and preventing user loss. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 is a flow chart of a method for determining a consignment transportation mode provided by an embodiment of the present invention;

[0025] Figure 2 is another flow chart of the method for determining the mode of transport of consigned goods provided in an embodiment of the present invention;

[0026] Figure 3 is another flow chart of the method for determining the mode of transport of consigned goods provided in an embodiment of the present invention;

[0027] Figure 4 is a schematic diagram of the structure of a device for determining a consignment transportation mode provided by an embodiment of the present invention;

[0028] Figure 5 It is a structural schematic diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0029] The present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the present invention, rather than to limit the present invention. It should also be noted that, for ease of description, only parts related to the present invention, rather than all structures, are shown in the accompanying drawings.

[0030] 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.

[0031] Figure 1 This is a flow chart of a method for determining the transport mode of consigned goods provided in an embodiment of the present invention. This embodiment can be applied to the case where the probability of claim for a target consigned goods is reduced by changing the transport mode of the target consigned goods. The method can be executed by a device for determining the transport mode of consigned goods, which can be implemented by software and / or hardware. Figure 1 As shown, the method specifically comprises the following steps:

[0032] S110: Determine individual characteristics corresponding to the current transportation task under at least two themes.

[0033] Among them, the transportation task can be understood as a waybill.

[0034] When the sender entrusts the carrier (courier) to deliver the consignment, the receiver enters the information of the consignment into the system (server) through the terminal. The system will then generate a transportation task (waybill) corresponding to the consignment. The transportation task includes the consignment information, the sender information, the consignee information, and the route, sorting station, distribution station, delivery personnel, etc. determined based on the sender information and the consignee information.

[0035] The subject can be understood as a "level". For example, the individual characteristics related to the sender are taken as a group of individual characteristics, which is the individual characteristics under the subject of the sender; the individual characteristics related to the consignment are taken as a group of individual characteristics, which is the individual characteristics under the subject of the consignment.

[0036] In one embodiment, at least two topics include at least two of the item owner topic, item acquisition task topic, routing topic, sorting site topic, distribution station topic, transportation tool topic, sender topic, recipient topic, consignment topic, service contractor topic, category topic and guarantee attribute value topic.

[0037] In one embodiment, at least two topics include at least one of the item owner topic, item acquisition task topic, routing topic, sorting site topic, distribution station topic, transportation tool topic, sender topic, recipient topic, consignment topic, service contractor topic, category topic and guarantee attribute value topic.

[0038] Among them, the party to whom the item belongs can be understood as the merchant who sells the item on the shopping platform. The item acquisition task can be understood as the order of the item. The individual characteristics under this theme include but are not limited to the generation time of the item transportation task and the delivery time of the corresponding consignment. It can be understood that for the same consignment, the transportation risks corresponding to different transportation times are different. For example, the consignment that needs to be transported at low temperature has different damage risks when transported in winter and in summer. Route refers to the consignment transportation route; the service contractor can be understood as a salesperson or consultant who signs an item transportation service with the party to whom the item belongs on behalf of the courier. Category refers to the category of the item, such as clothing, medicine, cosmetics, etc.; the guarantee attribute value can be understood as the insurance data. The distribution station can be understood as the last station for the transportation of the consignment, where the deliveryman picks up the consignment from the station and delivers the consignment to the recipient; the means of transportation is the means of transportation used to transport the consignment, such as trucks, trains, airplanes, etc.

[0039] Individual features are features that are closely related to transportation tasks. For example, Li bought a set of porcelain from the target shopping platform and filled in the unit address. The target shopping platform sent a task creation request corresponding to the information to the courier's server. The server generated the corresponding first transportation task based on the request. The first transportation task corresponds to the first feature set, and the first feature set includes individual features corresponding to at least two topics. Li learned that the time when the express arrived at the unit address was a holiday, so he changed the recipient address of the transportation task to his home address. At this time, the first transportation task was changed to the second transportation task, and the second transportation task corresponded to the second feature set, which was different from the first feature set. Because the individual features under the recipient theme in the second feature set are different from the individual features under the recipient theme in the first feature set.

[0040] In one embodiment, based on the first thread, individual characteristics corresponding to the current transport task under at least two topics are pulled from the message queue; wherein the message queue includes at least one transport task identifier, and the individual characteristics corresponding to each of the at least one transport task identifier under the at least two topics; the individual characteristics corresponding to each of the transport task identifiers under the at least two topics are determined by the second thread based on the log information corresponding to the corresponding transport task.

[0041] Specifically, the first thread and the second thread are executed in parallel. When the processor generates a transport task, it will automatically generate corresponding log information; when the processor modifies the transport task, it will automatically modify the corresponding log information. The second thread is used to sequentially determine the individual characteristics corresponding to each transport task under at least two topics based on the log information corresponding to each transport task, and add the transport task identifier of each transport task and the individual characteristics corresponding to each transport task under at least two topics to the message queue; the first thread is used to pull each transport task identifier and all individual characteristics corresponding to each transport task identifier from the message queue based on a set order, and all individual characteristics are the individual characteristics corresponding to the transport task corresponding to the corresponding transport task identifier under at least two topics.

[0042] S120, obtaining global features corresponding to each of the at least two topics, where the global features are determined based on the transportation tasks in which target events have occurred under the corresponding topics within the corresponding statistical period, and the target events include claim events and / or complaint events.

[0043] A claim event can be understood as an event in which the courier pays the claim amount to the sender; a complaint event can be understood as an event in which the sender sends a complaint message to the courier through the complaint channel of the shopping platform.

[0044] The global features are not determined based on the current transport task, but are determined based on the transport tasks in which target events have occurred under the corresponding topic within the corresponding statistical period. The target events include claims events and / or complaint events.

[0045] In one embodiment, for each of the at least two topics, some or all of the transportation tasks in which the target event occurred under the current topic within the corresponding statistical period are determined; some or all of the transportation tasks in which the target event occurred under the current topic are used as a reference sample combination; features for the current topic are extracted from the reference sample combination, and all the extracted features are used as global features corresponding to the current topic.

[0046] Specifically, the corresponding statistical period can be selected as the previous statistical period, and the statistical period lengths corresponding to the global features corresponding to different themes may be the same or different. For example, the global features corresponding to the sender theme are determined based on the transportation tasks for the target event that occurred under the theme in the previous natural month; the global features corresponding to the site theme are based on part or all of the transportation tasks for the target event that occurred under the theme in the previous natural year. That is to say, for the target site, the global features associated with the target site are determined based on part or all of the transportation tasks for the target event that occurred in the previous natural year. Since the statistical period usually has a certain time length, the global features can be understood as long-term features, which are relative to the speed of change of the features under the corresponding theme. For example, the statistical period corresponding to the global features under the merchant theme can be set to be greater than the statistical period corresponding to the global features under the deliveryman theme. Therefore, the speed of change of the merchant's attitude towards the consignment or the packaging method is usually slower than the speed of change of the deliveryman under a certain delivery route.

[0047] When determining the reference sample combination, the number of all transportation tasks for which the target event occurred in the previous period for the corresponding theme should be considered. If the number is less than or equal to the set task number threshold, all transportation tasks are used as the reference sample combination; if the number is greater than the set task number threshold, transportation tasks with the set number threshold are selected from all transportation tasks, and all selected tasks are used as the reference sample combination. Since the reference sample combination includes multiple transportation tasks for which the target event occurred in the previous week for the corresponding theme, the global features under the corresponding theme determined based on the reference sample combination can be regarded as market features.

[0048] In one embodiment, before determining the global features under each theme, at least two themes that are associated with the target event are first determined based on the massive transportation tasks, and then the global features under each of the at least two themes are determined. If the at least two themes that are associated with the target event determined based on the massive transportation tasks are used as the first theme combination, and all the themes corresponding to all the individual features determined based on the current transportation task are used as the second theme combination, then the first theme combination is the same as the second theme combination. In this way, the individual features under each theme are all associated with the target event, and the individual features under each theme can be spliced ​​together with the global features to obtain the target features.

[0049] S130, inputting the individual features and global features corresponding to each of the at least two topics into a pre-trained claim prediction model to obtain a claim probability prediction value.

[0050] Among them, the larger the predicted value of the claim probability, the higher the corresponding claim risk.

[0051] For each of the at least two topics, determine the individual features and global features of the current topic, and splice the individual features and the global features into target features. Input the target features corresponding to each of the at least two topics into the pre-trained claim prediction model to obtain a claim probability prediction value. The use of individual features in conjunction with global features helps the pre-trained claim prediction model to accurately determine the claim probability prediction value corresponding to the current transportation task.

[0052] In one embodiment, a machine learning tree model is used as a claim prediction model. The individual features and global features in this embodiment include unstructured data. Using a machine learning tree model as a claim prediction model can improve the speed and accuracy of feature data analysis, thereby improving the accuracy of the claim probability prediction value.

[0053] The training samples used in the claims prediction model training process in this embodiment only include global features. The labels of the training samples are determined based on whether the target event actually occurs. If the target event actually occurs in the training sample, the training sample is a negative sample; if the target event actually does not occur in the training sample, the training sample is a positive sample.

[0054] S140: Determine the mode of transportation for the current transportation task based on the predicted value of the claim probability.

[0055] The target transportation mode refers to a transportation mode that improves the safety of consignment transportation by strengthening the consignment packaging, full-process tracking, and separate consignment transportation.

[0056] If the predicted value of the claim probability is greater than or equal to the marking probability threshold, the target transportation mode is used as the transportation mode of the consignment corresponding to the current transportation task; if the predicted value of the claim probability is less than the marking probability threshold, the non-target transportation mode is used as the transportation mode of the consignment corresponding to the current transportation task. Among them, the non-target transportation mode is a common transportation mode in the express delivery industry, and this embodiment does not make specific limitations here.

[0057] In one embodiment, if the predicted value of the claim probability meets the set claim conditions, a target identifier corresponding to the target transportation mode is added to the current transportation task. In this way, when the relevant personnel see the target identifier during the transportation of the consignment, they will know that the consignment corresponding to the current transportation task needs to be transported according to the target transportation mode.

[0058] Table 1 is a comparison table of the model-based claim task hit results and the rule-based claim task hit results provided by the embodiment of the present invention. The transport tasks are randomly divided into the first group and the second group. When the security attribute value is 3000-4999 and the claim probability prediction value is greater than 0.2, the target identifier is added to about 12,000 transport tasks in the first group based on the model prediction results, and the target identifier is added to about 12,000 transport tasks in the second group based on the rules; the consignments corresponding to the transport tasks with the added target identifier are transported by the target transportation method. After the transportation is completed, the consignments corresponding to 861 transport tasks in the first group with the added target identifier have target events, and the consignments corresponding to 33 transport tasks in the second group with the added target identifier have target events. Obviously, the accuracy of the target event hit by the embodiment of the present invention is higher. The embodiment of the present invention provides a higher risk identification accuracy by determining whether to add a target identifier to the transport task based on whether the model prediction results meet the set conditions.

[0059] Table 1 Comparison of model-based claims task hit results and rule-based claims task hit results

[0060]

[0061] Among them, the product of the marking probability threshold and the number of transportation tasks is equal to the number of marked tasks.

[0062] The larger the predicted probability value, the higher the probability of the target event occurring, but it does not mean that the target event will not occur when the predicted probability value is small. Therefore, in theory, the smaller the predicted probability threshold used for marking, the better, that is, the smaller the marking probability threshold, the better. However, the reduction of the marking probability threshold will cause more transport tasks to be marked, thereby increasing the transportation volume of the target transport mode. In one embodiment, in order to take into account the transport capacity of the target transport mode and increase the hit volume of the target transport task, the marking probability threshold is determined based on the amount of transport tasks that the target transport mode can undertake and the total amount of transport tasks to be completed; if the claim probability prediction value is greater than the marking probability threshold, the target transport mode is used as the transport mode for the consignment corresponding to the current transport task. For example, the total amount of transport tasks to be completed is 100,000, and the amount of transport tasks that the target transport mode can undertake is 10,000. At this time, the marking probability threshold can be adjusted to 0.1 at the lowest, that is, a target identifier is added to a maximum of 10,000 transport tasks. Based on the amount of transport tasks that the target transport mode can undertake and the total amount of transport tasks to be completed, the marking probability threshold is dynamically adjusted to effectively reduce the probability of the target event by maximizing the use of the transport capacity of the target transport mode.

[0063] This embodiment can accurately identify risky waybills and provide special protection, such as separate package collection, full-process dedicated supervision, package reinforcement and other closed-loop protection measures to achieve a closed loop. After special protection, it can avoid the loss, damage, customer complaints and other problems caused by violent sorting, trampling, throwing, vehicle-cargo mismatch and other reasons in most scenes of sorting, transportation and distribution, improve the sender's experience, reduce claims risks, and reduce operating costs and claims funds.

[0064] The technical solution of the method for determining the mode of transport of consigned goods provided in the embodiment of the present invention is that, since the individual features corresponding to at least two topics respectively include all-round information on the correlation between the current transport task and the claim settlement; the global features corresponding to at least two topics respectively include all-round information on the correlation between the market and the claim settlement; therefore, the individual features and global features under each of the at least two topics are input into the pre-trained claim settlement prediction model, an accurate claim settlement probability prediction value can be obtained; the claim settlement probability prediction value can reflect the probability that the consigned goods corresponding to the current transport task need to be compensated, that is, the probability that the consigned goods corresponding to the current transport task will be compensated during the transportation process. For example, when the predicted value of claim probability is high, the probability of damage to the corresponding consignment during transportation is high. Conversely, the probability of damage to the corresponding consignment during transportation is low. Therefore, fragile consignment can be accurately identified according to the predicted value of claim probability, so that reasonable allocation of transportation methods can be completed according to whether the consignment is fragile. In this way, the damage of fragile consignment can be reduced by using target transportation methods with higher safety levels, and non-fragile consignment can be safely transported by non-target transportation methods with lower safety levels, thereby achieving the technical effect of taking into account both transportation cost and transportation safety, and preventing user loss.

[0065] Figure 2 Another flow chart of the method for determining the mode of transport of consigned goods provided in the embodiment of the present invention. The embodiment of the present invention refines the method for determining individual characteristics based on the above embodiment. Figure 2 As shown, the method includes:

[0066] S210: If the current transport task includes a guarantee attribute value, and the guarantee attribute value is greater than or equal to a first set threshold, determine the individual characteristics corresponding to the current transport task under at least two topics.

[0067] For the sender, if the consignment is valuable or fragile, he or she will usually request a property value guarantee (insurance) to ensure that the consignment can be safely delivered to the recipient, or if the consignment is not safely delivered to the recipient, he or she will request compensation from the courier to reduce losses.

[0068] For couriers, if consignments with higher security attribute values ​​are damaged or lost, they will have to pay more compensation than consignments with lower security attribute values. Therefore, if the target transportation method with a higher security level has limited corresponding transportation capacity, if the overall compensation is to be reduced, it is preferred to insure consignments that are fragile and have higher security attribute values.

[0069] In summary, in one embodiment, when the current transport task is detected, it is determined whether the current transport task includes a security attribute value; if the current transport task includes a security attribute value, it is determined whether the security attribute value is greater than or equal to a first set threshold; if so, the individual characteristics corresponding to the current transport task under the at least two topics are determined. This embodiment is suitable for the service end (for example, the task receiving layer of the service end), and determines whether to predict its claim probability prediction value through the relationship between the security attribute value and the first set threshold.

[0070] In one embodiment, if the current transport task includes a guarantee attribute value, and the guarantee attribute value is modified from less than the first set threshold to greater than or equal to the first set threshold, individual features corresponding to the current transport task under at least two themes are determined.

[0071] Specifically, the transport task is configured as a modifiable task, that is, the sender can modify the shipping information according to needs, such as the recipient, recipient contact information, security attribute value, etc. It is understandable that the sender can increase or decrease the security attribute value filled in.

[0072] If the security attribute value corresponding to the current transport task is modified from less than the first set threshold to greater than or equal to the first set threshold, it means that there is currently no individual feature corresponding to the current transport task in the system, and therefore the individual features corresponding to the current transport task under at least two topics are determined.

[0073] It can be understood that if there is an individual feature corresponding to the current transport task, it means that the initial security attribute value corresponding to the current transport task is greater than or equal to the first set threshold value. Therefore, when it is detected that the security attribute value corresponding to the current transport task has changed, and the changed security attribute value is still greater than the first set threshold value, the corresponding individual feature is kept unchanged. If the security attribute value of the current transport task has changed, and the security attribute value is modified from being greater than or equal to the first set threshold value to being less than the first set threshold value, the individual features corresponding to the current transport task under at least two topics are marked as invalid features.

[0074] This embodiment is also applicable to the task processing terminal (courier work platform). This embodiment can be automatically executed by the task processing terminal, or can be manually triggered by the user. For the latter: when it is detected that the guarantee attribute value corresponding to the current transportation task is modified from less than the first set threshold to greater than or equal to the first set threshold, a prompt message is output; the user clicks or touches the corresponding guaranteed transportation option on the task processing terminal; in response to the triggering operation of the guaranteed transportation option, the individual characteristics corresponding to the current transportation task under at least two themes are determined. This embodiment helps users to pay attention to the consigned items corresponding to the transportation tasks with changed requirements in a timely manner.

[0075] Among them, the first set threshold can be determined according to actual conditions, for example, according to the capacity of the target transportation mode, the operating cost of the target transportation mode and the claims data corresponding to different protection attribute values ​​as thresholds, etc., to determine the first set threshold.

[0076] Exemplarily, it is assumed that the capacity of the target mode of transport is sufficient, and the operating cost of the target mode of transport is known. Determine the corresponding claims data when at least two different security attribute values ​​are used as thresholds. The at least two different thresholds include a first experimental threshold, a second experimental threshold, and a third experimental threshold. Among them, determine the value of the claims data corresponding to the first experimental threshold to be amortized to each transport task, use this value as the claim cost, determine the sum of the claim cost and the operating cost, and determine the remaining attribute value corresponding to the first experimental threshold and whether the remaining attribute value is greater than the set remaining threshold based on the claim cost, operating cost, and service attribute value corresponding to each transport task. If the remaining attribute value is greater than the set threshold, the first experimental threshold is determined to be an acceptable threshold. Similarly, determine whether the second experimental threshold is an acceptable threshold, and whether the third experimental threshold is an acceptable threshold; determine the target acceptable threshold corresponding to the minimum experimental threshold, or the target acceptable threshold corresponding to the maximum remaining attribute value among all acceptable thresholds, and use the experimental threshold corresponding to the target acceptable threshold as the first set threshold.

[0077] In one embodiment, the task processing terminal determines the individual features of the current transport task under at least two themes, including individual features under the collection theme and individual features under the pre-sorting theme. This embodiment improves the accuracy of the claim probability prediction value output by the pre-trained claim prediction model by converting all available information into individual features.

[0078] S220. Obtain global features corresponding to each of the at least two topics, where the global features are determined based on transportation tasks in which target events have occurred under the corresponding topic within a corresponding statistical period, where the target events include claim events and / or complaint events.

[0079] S230. Input the individual features and global features corresponding to each of the at least two topics into a pre-trained claim prediction model to obtain a claim probability prediction value.

[0080] S240: Determine the mode of transportation for the current transportation task based on the predicted value of the claim probability.

[0081] This embodiment is applicable to both the courier's service end and the task processing terminal (courier's workstation). If the execution subject of this embodiment is the service end, when the claim probability prediction value meets the set claim conditions, after adding the target identifier corresponding to the target transportation mode to the current transportation task, the current transportation task in the service end includes the target identifier; if the execution subject of this embodiment is the task processing terminal, when the claim probability prediction value meets the set claim conditions, after adding the target identifier corresponding to the target transportation mode to the current transportation task, the current transportation task of the task processing terminal includes the target identifier, and at the same time, when the service end checks the current transportation task, it can also see that the current transportation task includes the target identifier.

[0082] The technical solution of this embodiment can be used in conjunction with the aforementioned embodiment. The shipping personnel of the party to which the consignment belongs (such as a merchant) creates a transport request task at the transport request end, and the courier service end processes the transport request task to generate a corresponding transport task; determines whether the transport task includes a target transport mode request, and if so, directly adds a target identifier corresponding to the target transport mode to the current transport task; if it does not include the target transport request, determines whether the security attribute value corresponding to the current transport task is greater than or equal to a first set threshold, and if so, executes S110-S130 in the aforementioned embodiment to obtain a claim probability prediction value, and if the claim probability prediction value meets the set claim conditions, adds the target identifier corresponding to the target transport mode to the current transport task, otherwise, does not add the target identifier corresponding to the target transport mode to the current transport task; if the security attribute value corresponding to the current transport task is less than the first set threshold, does not add the target identifier corresponding to the target transport mode to the current transport task.

[0083] Regardless of whether the current transport task includes the target identification, the server-side processor (such as the order receiving layer) will send the current transport task to the task processing terminal (the courier's work platform). When collecting the consignment, the user of the task processing terminal will determine whether it includes the target identification, and if it includes the target identification, the user will use the packaging requirements corresponding to the target transportation method to complete the collection and packaging of the consignment; if the user completes the collection of the consignment and finds that the sender has modified the security attribute value of the corresponding consignment at the corresponding terminal, the user will determine the specific modification method of the security attribute value.

[0084] If the guarantee attribute value is modified from being lower than the first set threshold value to being greater than or equal to the first set threshold value, S110-S130 in the aforementioned embodiment is executed to obtain a claim probability prediction value, and when the claim probability prediction value meets the claim conditions, a target identifier corresponding to the target transportation mode is added to the current transportation task.

[0085] If the guarantee attribute value is modified from being greater than or equal to the first set threshold value to being less than the first set threshold value, the pre-trained claim prediction model is called to determine the claim prediction probability value, and when the claim prediction probability value is greater than or equal to the marking probability threshold, the target identification of the current transportation task is retained, or a prompt message corresponding to the retained target identification is output, and in response to the user's confirmation operation, the target identification of the current transportation task is retained.

[0086] If the security attribute values ​​before and after the modification are both lower than the first set threshold, the target identifier corresponding to the target transport mode will not be added to the current transport mode, or the pre-trained claim prediction model will be called to determine the claim prediction probability value, and when the claim prediction probability value is greater than or equal to the marking probability threshold, the target identifier of the current transport task will be retained, or a prompt message corresponding to the retained target identifier will be output, and in response to the user's confirmation operation, the target identifier of the current transport task will be retained.

[0087] If the security attribute values ​​before and after the modification are both higher than the first set threshold, the target identification of the current transportation task is retained.

[0088] If the current transport task includes a target identifier, the user of the task processing terminal shall complete the transport task of the consignment transport section assigned by the system according to the transport requirements corresponding to the target transport method; if the current transport task does not include a target identifier, a non-target transport method shall be used to complete the transportation of the corresponding consignment.

[0089] The embodiment of the present invention achieves a balance between accuracy and speed in determining the mode of transport by using a first set threshold in conjunction with a pre-trained claims prediction model, which can not only improve the courier's transportation task processing speed, but also ensure the safety of each consignment, thereby improving the sender's shipping experience.

[0090] Figure 3 Another flow chart of the method for determining the mode of transport of consigned goods provided in the embodiment of the present invention. The embodiment of the present invention refines the method for determining individual characteristics based on the above embodiment. Figure 3 As shown, the method includes:

[0091] S3101. Input the item description information in the current transportation task into the natural language processing model to obtain the category identifier corresponding to the category to which the corresponding consignment belongs.

[0092] The natural language processing model is an existing natural language processing model, and this embodiment does not limit the specific name of the natural language processing model. In actual use, the natural language processing model can be determined according to the required category accuracy, or the order of magnitude of the training parameters can be determined according to the required category accuracy, and then the corresponding natural language processing model can be determined according to the order of magnitude.

[0093] The current transportation task includes information under at least two topics, and the at least two topics include a category topic, and the category topic includes the consignment topic, consignment name, consignment description information, consignment volume, consignment weight, etc. Exemplarily, the consignment is liquor, and the item description information of the transportation task of the consignment may include: mark A, mark B, mark C, etc., where each mark is the name of liquor, so there may be tens of thousands of description information of the same category of consignment. Another example, such as clothing, the consignment may be marked as "outfit for small people", "fashionable and atmospheric with small red dots", "black Korean windbreaker jacket", "super temperament", etc., so there will be tens of thousands of description information of consignments of such a category.

[0094] For consignments, similar items usually have the same or similar physical properties, chemical properties, shapes, packaging requirements and other commonalities. Therefore, it is necessary to extract the category of the consignment from the item description information of the transportation task.

[0095] In order to accurately determine the category of the consignment, this embodiment inputs the item description information in the current transportation task into the natural language processing model to obtain the category identifier of the category to which the corresponding consignment belongs.

[0096] S3102. Use the category identification as the individual feature of the current transportation task under the category theme.

[0097] After the category of the consignment is determined, the category identifier corresponding to the category is used as the individual feature of the current transportation task under the category theme. Compared with other information in the item description information, the category of the consignment can reflect the physical and / or chemical properties of the consignment as a whole, thereby improving the accuracy of the claim probability prediction value determined by the subsequent pre-trained claim prediction model based on all individual features.

[0098] S3103. Determine the individual characteristics corresponding to the current transportation task under at least one non-category theme.

[0099] The non-category topic refers to other topics that are not category topics in at least two topics. At the same time / after / before the individual features of the current transport task under the category topic are determined, the individual features corresponding to the current transport task under at least one non-category topic are determined to obtain the individual features corresponding to each topic in the at least two topics.

[0100] S3104. Use the individual characteristics of the current transport task under the category theme and the individual characteristics corresponding to the at least one non-category theme as the individual characteristics corresponding to the current transport task under at least two themes.

[0101] After the individual characteristics of the current transport task under the category theme and the individual characteristics of the current transport task under the category theme are determined, the individual characteristics of the current transport task corresponding to the aforementioned at least two themes are determined.

[0102] S320, obtaining global features corresponding to each of the at least two topics, where the global features are determined based on the transportation tasks in which target events have occurred under the corresponding topics within the corresponding statistical period, and the target events include claim events and / or complaint events.

[0103] S330, inputting the individual features and global features corresponding to each of the at least two topics into a pre-trained claim prediction model to obtain a claim probability prediction value.

[0104] S340: Determine the mode of transportation for the current transportation task based on the predicted value of the claim probability.

[0105] The embodiment of the present invention determines the category identification corresponding to the item description information in the current transport task through a natural language training model, thereby achieving the technical effect of simply and quickly determining the category to which the consignment corresponding to the current transport task belongs, thereby improving the speed and accuracy of determining the individual characteristics of the current transport task under the category theme, as well as the accuracy of the input data of the pre-trained claims prediction model, and ultimately improving the accuracy of the claim probability prediction value output by the pre-trained claims prediction model.

[0106] The following is an embodiment of a device for determining a consignment transport mode provided in an embodiment of the present invention. The device and the method for determining a consignment transport mode of the above-mentioned embodiment belong to the same inventive concept. For details not fully described in the embodiment of the device for determining a consignment transport mode, reference can be made to the contents of the above-mentioned embodiments.

[0107] Figure 4 The present invention is a schematic diagram of the structure of the device for determining the transport mode of consigned goods provided in an embodiment of the present invention. The present invention and the above-mentioned embodiment belong to the same inventive concept. Figure 4 As shown, the device comprises:

[0108] An individual feature module 410 is used to determine the individual features corresponding to the current transportation task under at least two themes;

[0109] A global feature module 420 is used to obtain global features corresponding to each of the at least two topics, wherein the global features are determined based on the transportation tasks in which target events have occurred under the corresponding topics within the corresponding statistical period, and the target events include claim settlement events and / or complaint events;

[0110] A prediction module 430, configured to input the individual features and the global features respectively corresponding to each of the at least two topics into a pre-trained claim prediction model to obtain a claim probability prediction value;

[0111] The transportation mode determination module 440 is used to determine the transportation mode of the current transportation task based on the claim settlement probability prediction value.

[0112] In one embodiment, the individual feature module 410 is specifically used to:

[0113] If the current transport task includes a guarantee attribute value, and the guarantee attribute value is greater than or equal to a first set threshold, individual features corresponding to the current transport task under at least two topics are determined.

[0114] In one embodiment, the individual feature module 410 is specifically used to:

[0115] If the current transport task includes a guarantee attribute value, and the guarantee attribute value is modified from being less than the first set threshold to being greater than or equal to the first set threshold, individual features corresponding to the current transport task under at least two topics are determined.

[0116] In one embodiment, the at least two topics include a category topic and at least one non-category topic, and the individual feature module 410 is specifically used to:

[0117] Inputting the item description information in the current transport task into a natural language processing model to obtain a category identifier corresponding to the category to which the corresponding consignment belongs;

[0118] Using the category identifier as an individual feature of the current transport task under the category theme;

[0119] Determine the individual characteristics corresponding to the current transportation task under the at least one non-category topic;

[0120] The individual features corresponding to the current transport task under the category theme and the individual features corresponding to the at least one non-category theme are used as the individual features corresponding to the current transport task under at least two themes.

[0121] In one embodiment, the individual feature module 410 is specifically used to:

[0122] Based on the first thread, individual features of the current transportation task corresponding to at least two topics are pulled from the message queue;

[0123] The message queue includes at least one transport task identifier and individual features corresponding to each of the at least one transport task identifier under the at least two topics;

[0124] The individual features corresponding to each of the transport task identifiers under the at least two topics are determined by the second thread based on the log information corresponding to the corresponding transport task.

[0125] In one embodiment, the transportation mode determination module 440 is specifically used to:

[0126] Determine the marking probability threshold based on the amount of transportation tasks that the target transportation mode can undertake and the total amount of transportation tasks to be completed;

[0127] If the predicted value of the claim probability is greater than the marking probability threshold, the target transportation mode is used as the transportation mode for the consignment corresponding to the current transportation task.

[0128] In one embodiment, the transportation mode determination module 440 is specifically used to:

[0129] If the predicted value of the claim probability meets the set claim conditions, a target identifier corresponding to the target transportation mode is added to the current transportation task.

[0130] In one embodiment, the at least two topics include at least two of the item owner topic, item acquisition task topic, routing topic, sorting site topic, distribution station topic, transportation tool topic, sender topic, recipient topic, consignment topic, service contractor topic, category topic and guarantee attribute value topic.

[0131] In one embodiment, the device further includes a global feature determination module, the global feature determination module being configured to:

[0132] For each of the at least two topics, determining part or all of the transportation tasks for which target events have occurred under the current topic within the corresponding statistical period;

[0133] Taking part or all of the transportation tasks in which the target event occurred under the current subject as a reference sample combination;

[0134] Features for the current theme are extracted from the reference sample combination, and all extracted features are used as global features corresponding to the current theme.

[0135] The technical solution of the device for determining the mode of transport of consigned goods provided by the embodiment of the present invention is that, since the individual features corresponding to at least two topics respectively include all-round information on the correlation between the current transport task and the claim settlement; the global features corresponding to at least two topics respectively include all-round information on the correlation between the market and the claim settlement; therefore, the individual features and global features under each of the at least two topics are input into the pre-trained claim settlement prediction model, an accurate claim settlement probability prediction value can be obtained; the claim settlement probability prediction value can reflect the probability that the consigned goods corresponding to the current transport task need to be compensated, that is, the probability that the consigned goods corresponding to the current transport task will be compensated during the transportation process. For example, when the predicted value of claim probability is high, the probability of damage to the corresponding consignment during transportation is high. Conversely, the probability of damage to the corresponding consignment during transportation is low. Therefore, fragile consignment can be accurately identified according to the predicted value of claim probability, so that reasonable allocation of transportation methods can be completed according to whether the consignment is fragile. In this way, the damage of fragile consignment can be reduced by using target transportation methods with higher safety levels, and non-fragile consignment can be safely transported by non-target transportation methods with lower safety levels, thereby achieving the technical effect of taking into account both transportation cost and transportation safety, and preventing user loss.

[0136] The device for determining the consignment transportation mode provided in the embodiment of the present invention can execute the method for determining the consignment transportation mode provided in the embodiment of the present invention, and has the corresponding functional modules and beneficial effects for executing the method for determining the consignment transportation mode.

[0137] Figure 5 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. Figure 5 A block diagram of an exemplary server 12 suitable for use in implementing embodiments of the present invention is shown. Figure 5 The server 12 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0138] like Figure 5 As shown, the server 12 is in the form of a general purpose computing device. The components of the server 12 may include, but are not limited to: one or more processors or processing units 16, a system memory 28, and a bus 18 that connects various system components (including the system memory 28 and the processing unit 16).

[0139] Bus 18 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor or a local bus using any of a variety of bus architectures. By way of example, these architectures include, but are not limited to, an Industry Standard Architecture (ISA) bus, a Micro Channel Architecture (MAC) bus, an Enhanced ISA bus, a Video Electronics Standards Association (VESA) local bus, and a Peripheral Component Interconnect (PCI) bus.

[0140] The server 12 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by the server 12, including volatile and non-volatile media, removable and non-removable media.

[0141] The system memory 28 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 30 and / or cache memory 32. The server 12 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, the storage system 34 may be used to read and write non-removable, non-volatile magnetic media ( Figure 5 not shown, usually called a "hard drive"). Although Figure 5 Not shown in the figure, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk"), and an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, a DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to the bus 18 via one or more data medium interfaces. The system memory 28 may include at least one program product having a set (e.g., at least one) of program modules that are configured to perform the functions of the various embodiments of the present invention.

[0142] A program / utility 40 having a set (at least one) of program modules 42 may be stored, for example, in system memory 28, such program modules 42 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment. Program modules 42 generally perform the functions and / or methods of the embodiments described herein.

[0143] The server 12 may also communicate with one or more external devices 14 (e.g., keyboards, pointing devices, displays 24, etc.), may communicate with one or more devices that enable a user to interact with the server 12, and / or may communicate with any device that enables the server 12 to communicate with one or more other computing devices (e.g., network cards, modems, etc.). Such communication may be performed via an input / output (I / O) interface 22. In addition, the server 12 may also communicate with one or more networks (e.g., local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) via a network adapter 20. As shown, the network adapter 20 communicates with other modules of the server 12 via a bus 18. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the server 12, including, but not limited to, microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0144] The processing unit 16 executes various functional applications and data processing by running the program stored in the system memory 28, for example, implementing the steps of the method for determining the transport mode of consigned goods provided in the embodiment of the present invention, the method comprising:

[0145] Determine the individual characteristics of the current transport task under at least two themes;

[0146] Acquire global features corresponding to each of the at least two topics, wherein the global features are determined based on transportation tasks in which target events have occurred under the corresponding topics within a corresponding statistical period, wherein the target events include claim settlement events and / or complaint events;

[0147] Inputting the individual features and the global features respectively corresponding to each of the at least two topics into a pre-trained claim prediction model to obtain a claim probability prediction value;

[0148] The transportation mode of the current transportation task is determined based on the claim settlement probability prediction value.

[0149] Of course, those skilled in the art will appreciate that the processor may also implement the technical solution of the method for determining the mode of transport of consigned goods provided in any embodiment of the present invention.

[0150] This embodiment provides a computer-readable storage medium, on which a computer program is stored. When the program is executed by a processor, the steps of the method for determining the transportation mode of consigned goods provided in the above embodiment of the present invention are implemented. The method includes:

[0151] Determine the individual characteristics of the current transport task under at least two themes;

[0152] Acquire global features corresponding to each of the at least two topics, wherein the global features are determined based on transportation tasks in which target events have occurred under the corresponding topics within a corresponding statistical period, wherein the target events include claim settlement events and / or complaint events;

[0153] Inputting the individual features and the global features respectively corresponding to each of the at least two topics into a pre-trained claim prediction model to obtain a claim probability prediction value;

[0154] The transportation mode of the current transportation task is determined based on the claim settlement probability prediction value.

[0155] The computer storage medium of the embodiment of the present invention can adopt any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, but not limited to: an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, a computer-readable storage medium can be any tangible medium containing or storing a program, which can be used by an instruction execution system, device or device or used in combination with it.

[0156] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0157] The program code embodied on the computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0158] Computer program code for performing the operations of the present invention may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0159] An embodiment of the present invention further provides a computer program product, including a computer program, which, when executed by a processor, implements the method for determining the transportation mode of consigned goods as provided in any embodiment of the present application.

[0160] In the process of implementation, the computer program product can be written in one or more programming languages ​​or a combination thereof to perform the computer program code of the present invention, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (for example, using an Internet service provider to connect through the Internet).

[0161] It should be understood by those skilled in the art that the modules or steps of the present invention described above can be implemented by a general-purpose computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, optionally, they can be implemented by a program code executable by a computer device, so that they can be stored in a storage device and executed by the computing device, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software.

[0162] Note that the above are only preferred embodiments of the present invention and the technical principles used. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in more detail through the above embodiments, the present invention is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present invention, and the scope of the present invention is determined by the scope of the appended claims.

Claims

1. A method for determining a consignment transportation mode, characterized in that: The method comprises: Determine the individual characteristics of the current transport task under at least two themes; Acquire global features corresponding to each of the at least two topics, wherein the global features are determined based on transportation tasks in which target events have occurred under the corresponding topics within a corresponding statistical period, wherein the target events include claim settlement events and / or complaint events; Inputting the individual features and the global features respectively corresponding to each of the at least two topics into a pre-trained claim prediction model to obtain a claim probability prediction value; The transportation mode of the current transportation task is determined based on the claim settlement probability prediction value.

2. The method according to claim 1, characterized in that The determining of the individual characteristics corresponding to the current transportation task under at least two themes includes: If the current transport task includes a guarantee attribute value, and the guarantee attribute value is greater than or equal to a first set threshold, individual features corresponding to the current transport task under at least two topics are determined.

3. The method according to claim 2, characterized in that If the current transport task includes a guarantee attribute value, and the guarantee attribute value is greater than or equal to a first set threshold, determining individual features corresponding to the current transport task under at least two topics, including: If the current transport task includes a guarantee attribute value, and the guarantee attribute value is modified from being less than the first set threshold to being greater than or equal to the first set threshold, individual features corresponding to the current transport task under at least two topics are determined.

4. The method according to claim 1, characterized in that The at least two topics include a category topic and at least one non-category topic, and determining the individual features corresponding to the current transportation task under the at least two topics respectively includes: Inputting the item description information in the current transport task into a natural language processing model to obtain a category identifier corresponding to the category to which the corresponding consignment belongs; Using the category identifier as an individual feature of the current transport task under the category theme; Determine the individual characteristics corresponding to the current transportation task under the at least one non-category topic; The individual features corresponding to the current transport task under the category theme and the individual features corresponding to the at least one non-category theme are used as the individual features corresponding to the current transport task under at least two themes.

5. The method according to claim 1, characterized in that The determining of the individual characteristics corresponding to the current transportation task under at least two themes includes: Based on the first thread, individual features of the current transportation task corresponding to at least two topics are pulled from the message queue; The message queue includes at least one transport task identifier and individual features corresponding to each of the at least one transport task identifier under the at least two topics; The individual features corresponding to each of the transport task identifiers under the at least two topics are determined by the second thread based on the log information corresponding to the corresponding transport task.

6. The method according to claim 1, characterized in that The determining of the mode of transport for the current transport task based on the predicted value of the claim probability includes: Determine the marking probability threshold based on the amount of transportation tasks that the target transportation mode can undertake and the total amount of transportation tasks to be completed; If the predicted value of the claim probability is greater than the marking probability threshold, the target transportation mode is used as the transportation mode for the consignment corresponding to the current transportation task.

7. The method according to claim 1, characterized in that The determining of the mode of transport for the current transport task based on the predicted value of the claim probability includes: If the predicted value of the claim probability meets the set claim conditions, a target identifier corresponding to the target transportation mode is added to the current transportation task.

8. The method according to claim 1, characterized in that: The at least two topics include at least two of the item owner topic, item acquisition task topic, routing topic, sorting site topic, distribution station topic, transportation tool topic, sender topic, recipient topic, consignment topic, service contractor topic, category topic and guarantee attribute value topic.

9. The method according to claim 1, characterized in that: The global features corresponding to each of the at least two topics are determined by the following steps: For each of the at least two topics, determining part or all of the transportation tasks for which target events have occurred under the current topic within the corresponding statistical period; Taking part or all of the transportation tasks in which the target event occurred under the current subject as a reference sample combination; Features for the current theme are extracted from the reference sample combination, and all extracted features are used as global features corresponding to the current theme.

10. A device for determining a consignment transport mode, characterized in that: include: An individual feature module, used to determine the individual features corresponding to the current transportation task under at least two topics; A global feature module, used to obtain global features corresponding to each of the at least two topics, wherein the global features are determined based on the transportation tasks in which target events have occurred under the corresponding topics within the corresponding statistical period, and the target events include claim settlement events and / or complaint events; A prediction module, used for inputting the individual features and the global features respectively corresponding to each of the at least two topics into a pre-trained claim prediction model to obtain a claim probability prediction value; The transportation mode determination module is used to determine the transportation mode of the current transportation task based on the claim probability prediction value.

11. An electronic device, characterized in that: The electronic device comprises: one or more processors; A memory for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the method for determining the consignment transportation mode as described in any one of claims 1-9.

12. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method for determining the transportation mode of consigned goods as described in any one of claims 1 to 9 is implemented.

13. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the computer program implements the method for determining the transportation mode of consigned goods as described in any one of claims 1 to 9.