Logistics risk determination method and device, computer device, and storage medium

Abstract

The present application relates to the technical field of logistics data processing, and discloses a logistics risk determination method and device, computer equipment and a storage medium, wherein the logistics risk determination method comprises: obtaining logistics data, and constructing an association relationship between a sending object, a consigned object and a sending route based on the logistics data to obtain association information; determining a risk transmission factor based on the association information; determining a prediction network model based on the risk transmission factor to determine a logistics risk level and a corresponding logistics risk strategy of a target object according to the prediction network model. The present application can predict the logistics risk level of the target object through the prediction network model, and determine the corresponding logistics risk strategy according to the logistics risk level, thereby improving the convenience of the target object in obtaining services, and making the services pushed to the target object more in line with the logistics risk level of the target object, with higher accuracy and improved user experience of the target object.

Description

Technical Field

[0001] This invention relates to the field of logistics data processing technology, specifically to methods, apparatus, computer equipment, and storage media for determining logistics risks. Background Technology

[0002] Within the express delivery and logistics industry, insurance services can be provided to users when they send packages. In the event that a package is damaged, lost, or fails to reach its destination safely for other reasons during transportation, the insurance company will compensate the user based on the insured amount, thereby reducing the user's financial burden and improving the user experience.

[0003] However, the insurance services offered typically require senders to analyze the risk level themselves and find and select the corresponding insurance services when sending a package. This process is cumbersome and makes it difficult to promote insurance services to senders. It also fails to meet senders' needs for convenience and accuracy in accessing insurance services. Summary of the Invention

[0004] In view of this, the present invention provides a method, apparatus, computer equipment, and storage medium for determining logistics risks, in order to solve the problems of poor convenience and accuracy when users select insurance services when sending packages.

[0005] In a first aspect, the present invention provides a method for determining logistics risks, the method comprising:

[0006] Obtain logistics data and construct the association between the sender, the consigned item, and the sender route based on the logistics data to obtain the association information;

[0007] Based on the associated information, risk transmission factors are identified;

[0008] Based on risk transmission factors, a prediction network model is determined, and the logistics risk level and corresponding logistics risk strategy of the target object are determined according to the prediction network model.

[0009] In this embodiment of the invention, logistics data is first acquired, and a relationship between the sender, the item being sent, and the sending route is constructed based on the logistics data to obtain association information. Based on this association information, a risk transmission factor is determined. Then, a predictive network model is determined based on the risk transmission factor. This predictive network model is used to determine the logistics risk level and corresponding logistics risk strategy of the target object. By predicting the logistics risk level of the target object through the predictive network model and determining the corresponding logistics risk strategy based on this level, the target object can select appropriate insurance services according to the logistics risk strategy. This improves the convenience for the target object to obtain insurance services and makes the insurance services pushed to the target object more consistent with its logistics risk level, resulting in higher accuracy and improved user experience.

[0010] In one alternative implementation, risk transmission factors are determined based on correlation information, including:

[0011] Obtain execution data for logistics risk strategies;

[0012] Based on the execution data, the risk level of the logistics risk strategy corresponding to the shipment object is determined, where the risk level is used to indicate the degree of risk when the logistics risk strategy is executed;

[0013] Based on risk level and related information, the first sub-risk transmission factor corresponding to the sending object, the second sub-risk transmission factor corresponding to the consignment item, and the third sub-risk transmission factor corresponding to the sending route are determined.

[0014] The risk transmission factor is determined based on the first sub-risk transmission factor, the second sub-risk transmission factor, and the third sub-risk transmission factor.

[0015] In this embodiment of the invention, a corresponding sub-risk transmission factor can be determined for each type of entity node in the association relationship, so as to effectively transmit the risk between each node through the structure diagram, thereby realizing the effective transmission of risk between shipping orders, and further quantifying and evaluating the shipping risk of the shipping object from multiple dimensions, thereby improving the confidence of the evaluation results.

[0016] In one optional implementation, the risk level includes: a first sub-risk level corresponding to the sender object in the association relationship, and a second sub-risk level corresponding to the recipient object's receipt;

[0017] Based on the execution data, determine the risk level of the logistics risk strategy corresponding to the shipment object, including:

[0018] Based on the association information, find the recipient object corresponding to the sender object;

[0019] Based on the execution data corresponding to the sending object, the first sub-risk level corresponding to the sending object and the second sub-risk level corresponding to the receiving object are determined.

[0020] In this embodiment of the invention, the first sub-risk level of the sender and the second sub-risk level of the recipient corresponding to the sender in the structure diagram can be determined respectively, so that the elements in the risk level are more comprehensive and the accuracy of the risk transmission factor calculated based on the risk level is improved.

[0021] In one optional implementation, based on the risk level, a first sub-risk transmission factor corresponding to the sending object, a second sub-risk transmission factor corresponding to the consignment item, and a third sub-risk transmission factor corresponding to the sending route are determined, including:

[0022] Get the historical number of items sent corresponding to the recipient and the sender;

[0023] The first sub-risk transmission factor is determined based on the first sub-risk level, the second sub-risk level, and the historical number of pieces.

[0024] Based on the first sub-risk level and historical number of cases, the second sub-risk transmission factor and the third sub-risk transmission factor are determined.

[0025] In this embodiment of the invention, a corresponding sub-risk transmission factor can be determined for each type of entity node in the relational information to calculate the risk transmission factor corresponding to each entity node, thereby effectively transmitting the risk between each entity node, realizing the effective transmission of risk between shipping orders, and further quantifying and evaluating the shipping risk of the shipping object from multiple dimensions, thereby improving the confidence of the evaluation results.

[0026] In one alternative implementation, a prediction network model is constructed based on risk transmission factors, including:

[0027] Obtain the coefficients to be determined for the first sub-risk transmission factor, the second sub-risk transmission factor, and the third sub-risk transmission factor;

[0028] The model parameters are determined based on the coefficients to be determined and the first sub-risk transmission factor, the second sub-risk transmission factor, and the third sub-risk transmission factor, and the model to be trained is constructed based on the model parameters.

[0029] The model to be trained is trained based on the training samples to obtain the prediction network model.

[0030] After determining the aforementioned risk transmission factors, model parameters can be determined based on these risk transmission factors. The model to be trained can then be constructed based on these model parameters, and the model to be trained can be trained to obtain a prediction network model, which can then output the risk level of the target object.

[0031] In one optional implementation, the model to be trained is trained based on training samples to obtain a prediction network model, including:

[0032] Based on the training samples, the coefficients to be determined for each sub-risk transmission factor in the model to be trained are adjusted until a prediction network model whose output satisfies the confidence condition is obtained.

[0033] In this embodiment of the invention, model parameters can be determined based on the first sub-risk transmission factor, the second sub-risk transmission factor, and the third sub-risk transmission factor. A model to be trained can be constructed based on these model parameters, and the model to be trained can be trained to obtain a prediction network model. Based on this prediction network model, the logistics risk level of the target object can be predicted, thereby achieving a multi-dimensional quantitative assessment of the logistics risk level of the target object and improving the confidence of the prediction results.

[0034] In one optional implementation, the association between the sender, the item being sent, and the sending route is constructed based on logistics data to obtain association information, including:

[0035] Based on logistics data, determine the recipient corresponding to the sender, the consignment item and the corresponding sender route;

[0036] Establish the first sub-association between the sender object and the recipient object, establish the second sub-association between the consignee and the sender object, and establish the third sub-association between the sender object and the sender route;

[0037] Based on the first sub-association, the second sub-association, and the third sub-association, the sending object, the consigned item, and the sending route are associated to obtain the association information.

[0038] In this embodiment of the invention, the interrelationships and causal relationships between entity nodes can be clearly displayed based on the structure diagram. This allows for the analysis of the complex relationships between risk transmission factors through a systematic and structured approach, thereby improving the accuracy of the final prediction network model.

[0039] In one optional implementation, determining the logistics risk level and corresponding logistics risk strategy of the target object based on a predictive network model includes:

[0040] The logistics risk level is corresponding to the probability of shipment risk of the target object based on the predictive network model.

[0041] Obtain the logistics risk strategy pre-set for the logistics risk level.

[0042] In this embodiment of the invention, multiple logistics risk levels can be pre-defined, and logistics risk strategies can be set for each logistics risk level. This ensures a better user experience while protecting the basic interests of logistics, thereby increasing the order rate of users for insurance services.

[0043] In one alternative implementation, the method further includes:

[0044] Recommended content is generated based on logistics risk strategies;

[0045] When a shipment order request for the target object is detected, recommended content is displayed.

[0046] In this embodiment of the invention, when an order request from a target object is detected, recommended content can be displayed on the order interface so that the target object can select the corresponding insurance in the logistics risk strategy. This simplifies the ordering process for users when ordering insurance services and improves the user experience.

[0047] In a second aspect, the present invention provides a logistics risk determination device, the device comprising:

[0048] The module is used to acquire logistics data and build the association between the sender, the consigned item and the sender route based on the logistics data to obtain the association information;

[0049] The first determination module is used to determine risk transmission factors based on related information;

[0050] The second determination module is used to determine the prediction network model based on the risk transmission factor, so as to determine the logistics risk level of the target object and the corresponding logistics risk strategy according to the prediction network model.

[0051] Thirdly, the present invention provides a computer device, including: a memory and a processor, which are communicatively connected to each other. The memory stores computer instructions, and the processor executes the computer instructions to perform the logistics risk determination method of the first aspect or any corresponding embodiment described above.

[0052] Fourthly, the present invention provides a computer-readable storage medium storing computer instructions for causing a computer to perform the logistics risk determination method of the first aspect or any corresponding embodiment described above.

[0053] Fifthly, the present invention provides a computer program product, including computer instructions for causing a computer to execute the logistics risk determination method described in the first aspect or any corresponding embodiment thereof. Attached Figure Description

[0054] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0055] Figure 1 This is a flowchart illustrating the logistics risk determination method according to an embodiment of the present invention;

[0056] Figure 2 This is a flowchart illustrating another method for determining logistics risks according to an embodiment of the present invention;

[0057] Figure 3 This is a schematic diagram of the associated information graph structure according to an embodiment of the present invention;

[0058] Figure 4 This is a flowchart illustrating another method for determining logistics risks according to an embodiment of the present invention;

[0059] Figure 5 This is a schematic diagram of the process of constructing a model to be trained according to an embodiment of the present invention;

[0060] Figure 6 This is a structural block diagram of a logistics risk determination device according to an embodiment of the present invention;

[0061] Figure 7 This is a schematic diagram of the structure of a computer device according to an optional embodiment of the present invention. Detailed Implementation

[0062] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0063] The application scenarios on which the logistics risk determination method depends are described here.

[0064] Within the express delivery and logistics industry, insurance services can be provided to users when they send packages. In the event that a package is damaged, lost, or fails to reach its destination safely for other reasons during transportation, the insurance company will compensate the user based on the insured amount, thereby reducing the user's financial burden and improving the user experience.

[0065] However, most insurance services require senders to analyze the risk level and choose the appropriate insurance themselves when sending a shipment. For example, if a sender has strict requirements for timely delivery and is concerned about financial losses due to delays, they might choose loss-of-life insurance. Or, if the value of the shipment is low and they want to reduce insurance costs, they might choose basic coverage. Therefore, this method of choosing insurance is cumbersome and not conducive to promoting insurance services to senders. Furthermore, it fails to meet senders' needs for convenience and accuracy in accessing insurance services. For instance, users may have limited knowledge of insurance categories, leading to choices that don't match their actual needs and resulting in low accuracy.

[0066] Based on this, the present invention provides a method for determining logistics risk. The method includes: firstly, acquiring logistics data and constructing a correlation between the sender, the consigned item, and the sender's route based on the logistics data to obtain correlation information; and then determining risk transmission factors based on the correlation information. Next, a predictive network model is determined based on the risk transmission factors. This predictive network model is used to determine the logistics risk level and corresponding logistics risk strategy of the target object. The predictive network model predicts the logistics risk level of the target object, and the corresponding logistics risk strategy is determined based on this level. This allows the target object to select appropriate insurance services based on the logistics risk strategy, improving the convenience of obtaining insurance services for the target object. Simultaneously, the insurance services pushed to the target object are more aligned with its logistics risk level, resulting in higher accuracy and improved user experience.

[0067] According to an embodiment of the present invention, a method for determining logistics risks is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0068] This embodiment provides a method for determining logistics risks, which can be used at service terminals. Figure 1 This is a flowchart of a logistics risk determination method according to an embodiment of the present invention, such as... Figure 1 As shown, the process includes the following steps:

[0069] Step S101: Obtain logistics data and construct the association between the sender, the consigned item and the sender route based on the logistics data to obtain the association information.

[0070] In this embodiment of the invention, logistics data may include express delivery behavior data, consignment data, insurance policy records, insurance claim payment records, etc., from the logistics network within a preset historical period. Related information may include a graph of relationships between different entities constructed using graph theory algorithms. Here, entities may include sender objects, consigned items, and sender routes, where the sender object can be the user sending the item. The consigned item can be a specific mailed item. The sender route includes an integrated process connecting pickup, station operations, sorting, transportation, collection, delivery, and signature confirmation. For example, the sender route may represent a city-receiver city format.

[0071] It should be understood that before constructing the association, the logistics data can be anonymized to obtain anonymized data. Specifically, user privacy information such as personal information, order information, geographical location, and time information in the logistics data can be cleaned.

[0072] After identifying the anonymized data, the association relationships between sender objects, consigned items, and sender routes are constructed based on the aforementioned graph theory algorithm to obtain association information. Specifically, firstly, sender objects within a preset historical time period and the corresponding sender routes for each sender object can be parsed from the delivery behavior data in the logistics data, and the consigned items corresponding to each sender object can be determined based on the consigned item data. Then, the association relationships between sender objects and consigned items, and between sender objects and sender routes, can be constructed based on the sender objects to obtain association information.

[0073] Step S102: Based on the associated information, determine the risk transmission factors.

[0074] In this embodiment of the invention, the risk transmission factor can be used to indicate various factors in which logistics risk is transmitted from one sender to another in the associated information. For example, a corresponding risk transmission factor can be determined for each entity in the sender, the consigned item, and the sender route, or a risk transmission factor can be determined for any entity in the sender, the consigned item, and the sender route. This application does not make specific limitations in this regard, but only to the extent that it can be implemented.

[0075] Step S103: Determine the prediction network model based on the risk transmission factor, and determine the logistics risk level and corresponding logistics risk strategy of the target object according to the prediction network model.

[0076] In this embodiment of the invention, the target object can be the shipment object for which a logistics risk strategy is currently being recommended. The logistics risk strategy may include analysis results of existing shipment risks and insurance type recommendations. Furthermore, when recommending insurance types, the logistics risk strategy can also recommend corresponding preferential strategies, such as discounts for the current type of insurance.

[0077] Specifically, the correlation between various logistics risk levels and corresponding logistics risk strategies can be pre-set based on the loss ratio. Here, the higher the loss ratio, the higher the corresponding logistics risk level. For example, the loss ratio range can be [0%-50%], where the logistics risk level increases by one level for every 10% increase in the loss ratio.

[0078] It should be understood that when the risk level is high, the corresponding insurance type for logistics risk strategies is also higher, thus better meeting user needs and the value of the entrusted goods. Simultaneously, by comprehensively considering the loss ratio, the current insurance type, and the value of the entrusted goods, possible compensation scenarios can be calculated, and corresponding discounts can be predicted based on these scenarios. This ensures a better user experience while safeguarding the basic interests of the logistics company.

[0079] As described above, in this embodiment of the invention, logistics data is first acquired, and a relationship between the sender, the item being sent, and the sending route is constructed based on the logistics data to obtain association information. Based on this association information, a risk transmission factor is determined. Then, a predictive network model is determined based on the risk transmission factor. This predictive network model is used to determine the logistics risk level and corresponding logistics risk strategy of the target object. By predicting the logistics risk level of the target object through the predictive network model and determining the corresponding logistics risk strategy based on this level, the target object can select appropriate insurance services according to the logistics risk strategy. This improves the convenience for the target object to obtain insurance services and makes the insurance services pushed to the target object more consistent with its logistics risk level, resulting in higher accuracy and improved user experience.

[0080] This embodiment provides another method for determining logistics risks, which can be used in the aforementioned service terminals. Figure 2 This is a flowchart of another logistics risk determination method according to an embodiment of the present invention, such as... Figure 2 As shown, the process includes the following steps:

[0081] Step S201: Obtain logistics data and construct the association between the sender, the consigned item and the sender route based on the logistics data to obtain the association information.

[0082] Specifically, step S201 includes:

[0083] Step S2021: Based on logistics data, determine the recipient corresponding to the sender, the consignment item, and the sender route corresponding to the consignment item.

[0084] Step S2022: Construct the first sub-association between the sender object and the recipient object, construct the second sub-association between the consignee and the sender object, and construct the third sub-association between the sender object and the sender route.

[0085] Step S2023: Based on the first sub-association, the second sub-association, and the third sub-association, associate the sending object, the consigned item, and the sending route to obtain the association information.

[0086] In this embodiment of the invention, after obtaining the entrusted data of logistics data, the sending behavior can be aggregated according to different dimensions. Specifically, basic logistics factor features can be formed on basic features such as exclusive use of receiving and sending, type of receiving and sending items, city of receiving and sending, and number of sending items. Based on these basic logistics factors, entities such as the receiving object, the entrusted item and the sending route corresponding to the entrusted item can be determined.

[0087] Next, entities can be aggregated according to aggregated indicators such as fees, claim amounts, insurance period, and claim processing time.

[0088] Specifically, we can construct the first sub-association between the sending objects, i.e., the sending relationship, denoted as A1, and count the relevant attributes of the sending object node and the first sub-association. We can also construct the second sub-association between the sending object and the consigned item, i.e., the sending object and the consigned item relationship, denoted as A2, and count the relevant attributes of the sending object node, the consigned item node, and the second sub-association.

[0089] Then, a third sub-association can be constructed between the sending object and the sending route. This sending route can cover geographical locations such as cities, districts, and outlets. Here, it is necessary to count the relevant attributes of nodes and relationships. For example, the sending route: City A - City B refers to the logistics and express delivery information sent from City A to City B. The relationship between the sending object and it is how many express delivery orders were sent from City A to City B in the past. This third sub-association is denoted as A3.

[0090] Specifically, when determining the relationships between entity nodes, the logistics data can be used to match each sender object with a corresponding recipient object, consignment item, and corresponding sender route. For example, the recipient object corresponding to sender object 1 is sender object 2 (sender object 2 has records of mailing to other objects, therefore it is a sender object), the type of the corresponding consignment item can be a file, and the sender route corresponding to the file can be city A-city B.

[0091] Here, the sender objects can be associated with each other through the sender-receiver relationship between them, in order to obtain, for example... Figure 3The graph structure is shown. Nodes are connected by unidirectional edges, forming a first-to-third sub-association. For example, sender object 1 and sender object 2 have a sender-receiver relationship, meaning they have a first-to-third sub-association A1. Item 3C is the item corresponding to sender object 1, and there is a second-to-third sub-association A2 between them. The sender route city A-city B is the sender route corresponding to sender object 1, and there is a third-to-third sub-association A3 between them.

[0092] Step S202: Based on the correlation information, determine the risk transmission factors. For details, please refer to [link to relevant documentation]. Figure 1 Step S102 of the illustrated embodiment will not be described again here.

[0093] Step S203: Determine the prediction network model based on the risk transmission factors, and then determine the logistics risk level and corresponding logistics risk strategy for the target object based on the prediction network model. For details, please refer to [link to details]. Figure 1 Step S103 of the illustrated embodiment will not be described again here.

[0094] In this embodiment of the invention, the interrelationships and causal relationships between entity nodes can be clearly displayed based on the structure diagram. This allows for the analysis of the complex relationships between risk transmission factors through a systematic and structured approach, thereby improving the accuracy of the final prediction network model.

[0095] This embodiment provides another method for determining logistics risks, which can be used in the aforementioned service terminals. Figure 4 This is a flowchart of another logistics risk determination method according to an embodiment of the present invention, such as... Figure 4 As shown, the process includes the following steps:

[0096] Step S401: Obtain logistics data and construct the association between the sender, the consigned item, and the sender route based on the logistics data to obtain the association information. For details, please refer to [link to relevant documentation]. Figure 1 Step S101 of the illustrated embodiment will not be described again here.

[0097] Step S402: Based on the associated information, determine the risk transmission factors.

[0098] Specifically, step S402 includes:

[0099] Step S4021: Obtain the execution data of the logistics risk strategy.

[0100] Step S4022: Based on the execution data, determine the risk level of the logistics risk strategy corresponding to the shipment object, wherein the risk level is used to indicate the degree of risk of the logistics risk strategy during execution.

[0101] Step S4023: Based on the risk level and associated information, determine the first sub-risk transmission factor corresponding to the sending object, the second sub-risk transmission factor corresponding to the consignment item, and the third sub-risk transmission factor corresponding to the sending route.

[0102] Step S4024: Determine the risk transmission factor based on the first sub-risk transmission factor, the second sub-risk transmission factor, and the third sub-risk transmission factor.

[0103] In this embodiment of the invention, the execution data corresponding to the logistics risk strategy may include insurance application records, insurance claim payment records, etc., corresponding to the logistics risk strategy. The risk level can be determined based on the actual insurance payout situation corresponding to the logistics risk strategy; for example, the risk level can be expressed as the insurance payout amount / premium.

[0104] After determining the risk level, the risk transmission factor of the N-degree neighbor corresponding to the sending object (i.e., the first sub-risk transmission factor mentioned above, hereinafter referred to as F1), the risk transmission factor of the entrusted item (i.e., the second sub-risk transmission factor mentioned above, hereinafter referred to as F2), and the risk transmission factor (i.e., the third sub-risk transmission factor mentioned above, hereinafter referred to as F3) can be determined based on the structure diagram in the wind direction level and the associated information.

[0105] Step S403: Determine the prediction network model based on the risk transmission factors, and then determine the logistics risk level and corresponding logistics risk strategy for the target object based on the prediction network model. For details, please refer to [link to details]. Figure 1 Step S103 of the illustrated embodiment will not be described again here.

[0106] In this embodiment of the invention, a corresponding sub-risk transmission factor can be determined for each type of entity node in the association relationship, so as to effectively transmit the risk between each node through the structure diagram, thereby realizing the effective transmission of risk between shipping orders, and further quantifying and evaluating the shipping risk of the shipping object from multiple dimensions, thereby improving the confidence of the evaluation results.

[0107] In some optional implementations, the aforementioned risk level includes: a first sub-risk level corresponding to the sender in the association relationship, and a second sub-risk level corresponding to the recipient. Step S4022, based on execution data, determines the risk level of the logistics risk strategy corresponding to the sender, including:

[0108] Step a1: Based on the association information, find the recipient corresponding to the sender.

[0109] Step a2: Based on the execution data corresponding to the sending object, determine the first sub-risk level corresponding to the sending object and the second sub-risk level corresponding to the receiving object.

[0110] In this embodiment of the invention, the receiving object that has an A1 relationship with the sending object can be found based on the structure diagram in the association relationship, and the second sub-risk level corresponding to the receiving object and the first sub-risk level corresponding to the sending object can be determined respectively.

[0111] For example, if the sender corresponds to R in the above result diagram... i The node, the recipient object, corresponds to R in the structure diagram. j If we consider a node, then the first sub-risk level can be represented as R. i The payout / premium corresponding to the node, and the second sub-risk level can be represented as R. j The compensation amount / premium corresponding to the node.

[0112] In this embodiment of the invention, the first sub-risk level of the sender and the second sub-risk level of the recipient corresponding to the sender in the structure diagram can be determined respectively, so that the elements in the risk level are more comprehensive and the accuracy of the risk transmission factor calculated based on the risk level is improved.

[0113] In some optional implementations, step S4023 above, based on risk level and association information, determines a first sub-risk transmission factor corresponding to the sending object, a second sub-risk transmission factor corresponding to the consignment item, and a third sub-risk transmission factor corresponding to the sending route, including:

[0114] Step b1: Obtain the historical number of shipments corresponding to the recipient and the sender.

[0115] Step b2: Determine the first sub-risk transmission factor based on the first sub-risk level, the second sub-risk level, and the historical number of cases.

[0116] Step b3: Based on the first sub-risk level and historical number of cases, determine the second sub-risk transmission factor and the third sub-risk transmission factor.

[0117] In this embodiment of the invention, the number of historical mailed items includes C. ji And C i Among them, C ji This refers to the number of shipments made from the sender to the recipient within the aforementioned preset historical period, for example, the number of shipments made within the last 3 months. i The total number of inbound shipments to the sender is the total number of waybills sent to the sender within a preset historical period.

[0118] After obtaining the historical shipment count, the first sub-risk transmission factor F1 can be determined based on the first sub-risk level, the second sub-risk level, and the historical shipment count. It should be understood that the risk level of a shipment object can be propagated first, second, or even Nth degree based on the shipping behavior between shipment objects, until the first sub-risk transmission factor F1 for each shipment object in the structure diagram is determined. Here,

[0119] Additionally, a second risk transmission factor F2 can be calculated for each consignment node in the structure diagram. Specifically, the association relationship A2 between the consignment node and the sender node can be used to quantify the risk propagation of consignments. Global routing risk can be shared based on the share of consignment relationship data in the sender's information within a preset historical period, ultimately determining the second sub-risk transmission factor F2 for each consignment. Here,

[0120] Additionally, a second risk transmission factor F3 can be calculated for each sending route node in the structure diagram. Specifically, the association relationship A3 between the sending route node and the sending object node can be used to determine the share of the sending route among all sending route nodes corresponding to the sending object within a preset historical period, thereby sharing the global routing risk and ultimately determining the third sub-risk transmission factor F3 for each sending route. Here,

[0121] In this embodiment of the invention, a corresponding sub-risk transmission factor can be determined for each type of entity node in the relational information to calculate the risk transmission factor corresponding to each entity node, thereby effectively transmitting the risk between each entity node, realizing the effective transmission of risk between shipping orders, and further quantifying and evaluating the shipping risk of the shipping object from multiple dimensions, thereby improving the confidence of the evaluation results.

[0122] In some optional implementations, step S103 above, which involves constructing a prediction network model based on risk transmission factors, includes:

[0123] Step S1031: Obtain the coefficients to be determined for the first sub-risk transmission factor, the second sub-risk transmission factor, and the third sub-risk transmission factor.

[0124] Step S1032: Determine the model parameters based on the coefficients to be determined and the first sub-risk transmission factor, the second sub-risk transmission factor and the third sub-risk transmission factor, and construct the model to be trained based on the model parameters.

[0125] Step S1033: Train the model to be trained based on the training samples to obtain the prediction network model.

[0126] In this embodiment of the invention, corresponding coefficients to be determined can be set for the first sub-risk transmission factor, the second sub-risk transmission factor and the third sub-risk transmission factor, respectively, and the intercepts corresponding to the model parameters can be set.

[0127] For example, the model parameters can be expressed as: B + w1F1 + w2F2 + w3F3. Here, B is the intercept, w1 is the coefficient to be determined corresponding to the first sub-risk transmission factor F1, w2 is the coefficient to be determined corresponding to the second sub-risk transmission factor F2, and w3 is the coefficient to be determined corresponding to the third sub-risk transmission factor F3.

[0128] Next, the model to be trained can be constructed based on the model parameters, such as... Figure 5 The diagram shows the process of building a model to be trained. The model building process can be divided into data processing and model parameter building.

[0129] Here, the first step is to clean the acquired logistics data to remove data anonymization, resulting in anonymized data. As mentioned above, logistics data can include express delivery behavior data, consignment data, insurance policy records, and insurance claim payment records from the logistics network within a preset historical time period. The specific data cleaning process is as described above. Figure 1 The corresponding implementation examples will not be described in detail here.

[0130] Then, a structure diagram of the above-mentioned associated information can be constructed based on the de-identified data. The structure diagram consists of the above-mentioned entity node sending object, consignment item and sending route, and the corresponding association relationships A1, A2, and A3 between entity nodes.

[0131] Next, the risk transmission factors corresponding to the entity nodes can be calculated based on the above structure diagram. As can be seen from the above, the risk transmission factors can include the risk transmission factor F1 corresponding to the sending object, the risk transmission factor F2 corresponding to the consignment item, and the risk transmission factor F3 corresponding to the sending route. The specific method for determining the risk transmission factors is as described in step S4023 above, and will not be repeated here.

[0132] After determining the aforementioned risk transmission factors, model parameters can be determined based on these risk transmission factors. The model to be trained can then be constructed based on these model parameters, and the model to be trained can be trained to obtain a prediction network model, which can then output the risk level of the target object.

[0133] Specifically, after constructing the model to be trained based on the model parameters, the model can be trained using training samples to obtain a prediction network model. This process includes the following steps:

[0134] Based on the training samples, the coefficients to be determined for each sub-risk transmission factor in the model to be trained are adjusted until a prediction network model whose output satisfies the confidence condition is obtained.

[0135] In this embodiment of the invention, training samples can be determined based on historical logistics data, and the model to be trained can be trained according to the training samples, and the model parameters can be adjusted until a prediction network model whose prediction results meet the confidence conditions is obtained.

[0136] Specifically, the coefficients w1-w3 in the model parameters B+w1F1+w2F2+w3F3 can be adjusted to obtain the optimal weight coefficients. The specific model training method is not limited in this invention; the method that can be implemented is the standard.

[0137] In this embodiment of the invention, model parameters can be determined based on the first sub-risk transmission factor, the second sub-risk transmission factor, and the third sub-risk transmission factor. A model to be trained can be constructed based on these model parameters, and the model to be trained can be trained to obtain a prediction network model. Based on this prediction network model, the logistics risk level of the target object can be predicted, thereby achieving a multi-dimensional quantitative assessment of the logistics risk level of the target object and improving the confidence of the prediction results.

[0138] In some optional implementations, step S103 above, which determines the logistics risk level and corresponding logistics risk strategy of the target object based on the prediction network model, includes:

[0139] Step S11: Output the logistics risk level corresponding to the shipment risk probability of the target object based on the prediction network model.

[0140] Step S12: Obtain the logistics risk strategy pre-set for the logistics risk level.

[0141] In this embodiment of the invention, different logistics risk levels can be set in advance according to the risk probability. For example, the risk levels can be divided based on the normal distribution of the risk probability, and corresponding logistics risk strategies can be set for each logistics risk level, thereby ensuring a better user experience while protecting the basic interests of logistics.

[0142] In this embodiment of the invention, when setting corresponding logistics risk strategies for logistics risk levels, the profit margin corresponding to each logistics risk level can be calculated based on the total cost of the insurance project, and the discount amount corresponding to the sales promotion tool can be determined based on the profit margin.

[0143] Specifically, the total cost can first be broken down into each logistics risk level, and the gross profit margin corresponding to each logistics risk level can be calculated separately to update the overall gross profit margin of the insurance project. Then, based on the expected profit concession level of the insurance business, the profit concession margin for each logistics risk level can be calculated. The net profit corresponding to the logistics risk level is calculated as: revenue - cost - claims - profit concession margin. When calculating the profit concession margin, it should be ensured that the net profit is not lower than the minimum preset profit.

[0144] After determining the profit margin corresponding to the logistics risk level, this profit margin can be converted into the insurance premium of the target audience. Then, the corresponding discount can be pushed to the target audience through sales promotion tools to reduce the cost of the target audience choosing a logistics risk strategy.

[0145] In this embodiment of the invention, multiple logistics risk levels can be pre-defined, and logistics risk strategies can be set for each logistics risk level. This ensures a better user experience while protecting the basic interests of logistics, thereby increasing the order rate of users for insurance services.

[0146] In some alternative implementations, the above Figure 1 Corresponding embodiments also include:

[0147] Step S21: Generate recommended content based on logistics risk strategies.

[0148] Step S22: When a shipping order request for the target object is detected, the recommended content is displayed.

[0149] In this embodiment of the invention, the recommended content can be used to display the insurance types and corresponding discount amounts corresponding to the logistics risk strategy. Here, the logistics risk strategy may include at least one form of discount amount for the target audience to choose from.

[0150] For example, if the insurance type is full-price insurance and the discount amount is X, then the discount amount can be displayed directly, or the discount amount can be planned relative to the current full-price insurance and displayed to the target audience.

[0151] In this embodiment of the invention, when an order request from a target object is detected, recommended content can be displayed on the order interface so that the target object can select the corresponding insurance in the logistics risk strategy. This simplifies the ordering process for users when ordering insurance services and improves the user experience.

[0152] In summary, in this embodiment of the invention, logistics data is first acquired, and the association between the sender, the consigned item, and the sender route is constructed based on the logistics data to obtain association information. Based on this association information, risk transmission factors are determined. Then, a predictive network model is determined based on the risk transmission factors. This predictive network model is used to determine the logistics risk level and corresponding logistics risk strategy of the target object. By predicting the logistics risk level of the target object through the predictive network model and determining the corresponding logistics risk strategy based on this level, the target object can select appropriate insurance services according to the logistics risk strategy. This improves the convenience for the target object to obtain insurance services and makes the insurance services pushed to the target object more consistent with its logistics risk level, resulting in higher accuracy and improved user experience.

[0153] This embodiment also provides a logistics risk determination device, which is used to implement the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" can be a combination of software and / or hardware that performs a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0154] This embodiment provides a logistics risk determination device, such as... Figure 6 As shown, it includes:

[0155] Module 601 is used to acquire logistics data and construct the association between the sender object, the consigned item and the sender route based on the logistics data to obtain the association information;

[0156] The first determining module 602 is used to determine risk transmission factors based on related information;

[0157] The second determining module 603 is used to determine the prediction network model based on the risk transmission factor, so as to determine the logistics risk level of the target object and the corresponding logistics risk strategy according to the prediction network model.

[0158] In some alternative implementations, the first determining module 602 is further configured to:

[0159] Obtain execution data for logistics risk strategies;

[0160] Based on the execution data, the risk level of the logistics risk strategy corresponding to the shipment object is determined, where the risk level is used to indicate the degree of risk when the logistics risk strategy is executed;

[0161] Based on risk level and related information, the first sub-risk transmission factor corresponding to the sending object, the second sub-risk transmission factor corresponding to the consignment item, and the third sub-risk transmission factor corresponding to the sending route are determined.

[0162] The risk transmission factor is determined based on the first sub-risk transmission factor, the second sub-risk transmission factor, and the third sub-risk transmission factor.

[0163] In some optional implementations, the risk level includes: a first sub-risk level corresponding to the sender object in the association relationship, and a second sub-risk level corresponding to the recipient object; the first determining module 602 is further configured to:

[0164] Based on the association information, find the recipient object corresponding to the sender object;

[0165] Based on the execution data corresponding to the sending object, the first sub-risk level corresponding to the sending object and the second sub-risk level corresponding to the receiving object are determined.

[0166] In some alternative implementations, the first determining module 602 is further configured to:

[0167] Get the historical number of items sent corresponding to the recipient and the sender;

[0168] The first sub-risk transmission factor is determined based on the first sub-risk level, the second sub-risk level, and the historical number of pieces.

[0169] Based on the first sub-risk level and historical number of cases, the second sub-risk transmission factor and the third sub-risk transmission factor are determined.

[0170] In some alternative implementations, the first determining module 602 is further configured to:

[0171] Obtain the coefficients to be determined for the first sub-risk transmission factor, the second sub-risk transmission factor, and the third sub-risk transmission factor;

[0172] The model parameters are determined based on the coefficients to be determined and the first sub-risk transmission factor, the second sub-risk transmission factor, and the third sub-risk transmission factor, and the model to be trained is constructed based on the model parameters.

[0173] The model to be trained is trained based on the training samples to obtain the prediction network model.

[0174] In some alternative implementations, the first determining module 602 is further configured to:

[0175] Based on the training samples, the coefficients to be determined for each sub-risk transmission factor in the model to be trained are adjusted until a prediction network model whose output satisfies the confidence condition is obtained.

[0176] In some alternative implementations, the construction module 601 is further configured to:

[0177] Based on logistics data, determine the recipient corresponding to the sender, the consignment item and the corresponding sender route;

[0178] Establish the first sub-association between the sender object and the recipient object, establish the second sub-association between the consignee and the sender object, and establish the third sub-association between the sender object and the sender route;

[0179] Based on the first sub-association, the second sub-association, and the third sub-association, the sending object, the consigned item, and the sending route are associated to obtain the association information.

[0180] In some alternative implementations, the second determining module 603 is further configured to:

[0181] The logistics risk level is corresponding to the probability of shipment risk of the target object based on the predictive network model.

[0182] Obtain the logistics risk strategy pre-set for the logistics risk level.

[0183] In some alternative implementations, the device is also used for:

[0184] Recommended content is generated based on logistics risk strategies;

[0185] When a shipment order request for the target object is detected, recommended content is displayed.

[0186] Further functional descriptions of the above modules and units are the same as those in the corresponding embodiments described above, and will not be repeated here.

[0187] In this embodiment, the logistics risk determination device is presented in the form of a functional unit. Here, a unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that execute one or more software or fixed programs, and / or other devices that can provide the above functions.

[0188] This invention also provides a computer device having the above-described features. Figure 6 The device shown is for determining logistics risks.

[0189] Please see Figure 7 , Figure 7 This is a schematic diagram of the structure of a computer device provided in an optional embodiment of the present invention, such as... Figure 7As shown, the computer device includes one or more processors 10, memory 20, and interfaces for connecting the components, including high-speed interfaces and low-speed interfaces. The components communicate with each other via different buses and can be mounted on a common motherboard or otherwise installed as needed. The processors can process instructions executed within the computer device, including instructions stored in or on memory to display graphical information of a GUI on external input / output devices (such as display devices coupled to the interfaces). In some alternative implementations, multiple processors and / or multiple buses can be used with multiple memories and multiple memory modules, if desired. Similarly, multiple computer devices can be connected, each providing some of the necessary operations (e.g., as a server array, a group of blade servers, or a multiprocessor system). Figure 7 Take a processor 10 as an example.

[0190] Processor 10 may be a central processing unit, a network processor, or a combination thereof. Processor 10 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The programmable logic device may be a complex programmable logic device (CAMP), a field-programmable gate array (FPGA), a general-purpose array logic (GDA), or any combination thereof.

[0191] The memory 20 stores instructions executable by at least one processor 10 to cause at least one processor 10 to perform the method shown in the above embodiments.

[0192] The memory 20 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created based on the use of the computer device. Furthermore, the memory 20 may include high-speed random access memory and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some alternative embodiments, the memory 20 may optionally include memory remotely located relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0193] The memory 20 may include volatile memory, such as random access memory; the memory may also include non-volatile memory, such as flash memory, hard disk or solid-state drive; the memory 20 may also include a combination of the above types of memory.

[0194] The computer device also includes a communication interface 30 for communicating with other devices or communication networks.

[0195] This invention also provides a computer-readable storage medium. The methods described above according to embodiments of the invention can be implemented in hardware or firmware, or implemented as computer code that can be recorded on a storage medium, or implemented as computer code downloaded via a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and then stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code, which, when accessed and executed by the computer, processor, or hardware, implements the methods shown in the above embodiments.

[0196] A portion of this invention can be applied as a computer program product, such as computer program instructions, which, when executed by a computer, can invoke or provide the methods and / or technical solutions according to the invention through the operation of the computer. Those skilled in the art will understand that the forms in which computer program instructions exist in a computer-readable medium include, but are not limited to, source files, executable files, installation package files, etc. Correspondingly, the ways in which computer program instructions are executed by a computer include, but are not limited to: the computer directly executing the instructions, or the computer compiling the instructions and then executing the corresponding compiled program, or the computer reading and executing the instructions, or the computer reading and installing the instructions and then executing the corresponding installed program. Here, the computer-readable medium can be any available computer-readable storage medium or communication medium accessible to a computer.

[0197] Although embodiments of the invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the invention, and such modifications and variations all fall within the scope defined by the appended description.

Claims

1. A method for determining logistics risks, characterized in that, The method includes: Obtain logistics data, and construct the association relationship between the sender, the consigned item, and the sender route based on the logistics data to obtain association information; Based on the aforementioned correlation information, risk transmission factors are determined; Based on the risk transmission factors, a prediction network model is determined, and the logistics risk level and corresponding logistics risk strategy of the target object are determined according to the prediction network model.

2. The method according to claim 1, characterized in that, The determination of risk transmission factors based on the associated information includes: Obtain execution data for logistics risk strategies; Based on the execution data, the risk level of the logistics risk strategy corresponding to the shipment object is determined, wherein the risk level is used to indicate the degree of risk of the logistics risk strategy during execution; Based on the risk level and the associated information, a first sub-risk transmission factor corresponding to the sending object, a second sub-risk transmission factor corresponding to the consignment item, and a third sub-risk transmission factor corresponding to the sending route are determined. The risk transmission factor is determined based on the first sub-risk transmission factor, the second sub-risk transmission factor, and the third sub-risk transmission factor.

3. The method according to claim 2, characterized in that, The risk level includes: the first sub-risk level corresponding to the sender in the association, and the second sub-risk level corresponding to the recipient. The step of determining the risk level of the logistics risk strategy corresponding to the shipment object based on the execution data includes: Based on the association information, locate the recipient object corresponding to the sender object; Based on the execution data corresponding to the sending object, the first sub-risk level corresponding to the sending object and the second sub-risk level corresponding to the receiving object are determined.

4. The method according to claim 3, characterized in that, The step of determining, based on the risk level, a first sub-risk transmission factor corresponding to the sending object, a second sub-risk transmission factor corresponding to the consignment item, and a third sub-risk transmission factor corresponding to the sending route, includes: Get the historical number of mails sent corresponding to the recipient and the sender; The first sub-risk transmission factor is determined based on the first sub-risk level, the second sub-risk level, and the historical number of pieces. Based on the first sub-risk level and the historical number of pieces, the second sub-risk transmission factor and the third sub-risk transmission factor are determined.

5. The method according to claim 2, characterized in that, The construction of the prediction network model based on the risk transmission factor includes: Obtain the coefficients to be determined for the first sub-risk transmission factor, the second sub-risk transmission factor, and the third sub-risk transmission factor; The model parameters are determined based on the coefficients to be determined and the first sub-risk transmission factor, the second sub-risk transmission factor and the third sub-risk transmission factor, and the model to be trained is constructed based on the model parameters. The model to be trained is trained based on the training samples to obtain the prediction network model.

6. The method according to claim 5, characterized in that, The step of training the model to be trained based on training samples to obtain the prediction network model includes: Based on the training samples, the coefficients to be determined corresponding to each sub-risk transmission factor in the model to be trained are adjusted until a prediction network model whose output results satisfy the confidence conditions is obtained.

7. The method according to claim 1, characterized in that, The process of constructing the association between the sender, the item being sent, and the route based on the logistics data to obtain association information includes: Based on the logistics data, determine the recipient, the item to be sent, and the shipping route corresponding to the item to be sent. Construct a first sub-association between the sender object and the recipient object, construct a second sub-association between the consignment item and the sender object, and construct a third sub-association between the sender object and the sending route; The association information is obtained by associating the sender object, the consigned item, and the sender route based on the first sub-association, the second sub-association, and the third sub-association.

8. The method according to claim 1, characterized in that, The step of determining the logistics risk level and corresponding logistics risk strategy of the target object based on the prediction network model includes: Based on the prediction network model, the logistics risk level corresponding to the shipment risk probability of the target object is output; Obtain the logistics risk strategy pre-set for the logistics risk level.

9. The method according to claim 1, characterized in that, The method further includes: Recommended content is generated based on the aforementioned logistics risk strategy; When a shipment order request for the target object is detected, the recommended content is displayed.

10. A logistics risk determination device, characterized in that, The device includes: The module is used to acquire logistics data and construct the association between the sender, the consigned item and the sender route based on the logistics data to obtain the association information; The first determining module is used to determine the risk transmission factor based on the associated information; The second determining module is used to determine a prediction network model based on the risk transmission factor, so as to determine the logistics risk level and corresponding logistics risk strategy of the target object according to the prediction network model.

11. A computer device, characterized in that, include: A memory and a processor are interconnected, the memory storing computer instructions, and the processor executing the computer instructions to perform the logistics risk determination method according to any one of claims 1 to 9.

12. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing the computer to perform the logistics risk determination method according to any one of claims 1 to 9.

13. A computer program product, characterized in that, Includes computer instructions for causing a computer to perform the logistics risk determination method according to any one of claims 1 to 9.

Images