Product risk value determination method and device, storage medium and program product

Abstract

The invention relates to a method and equipment for determining a risk value of a product, a storage medium and a program product. The method comprises the following steps: obtaining logistics behavior data of a product and supply chain data of the product; determining a logistics behavior factor of the product based on the logistics behavior data, and determining a supply chain factor of the product based on the supply chain data; determining the weight of the logistics behavior factor and the weight of the supply chain factor; and determining a target risk value of the product based on the logistics behavior factor, the weight of the logistics behavior factor, the supply chain factor and the weight of the supply chain factor. By adopting the method, the target risk value of the product can be accurately determined through the logistics behavior data of the product and the supply chain data of the product.

Description

Technical Field

[0001] This application relates to the field of data processing technology, and in particular to a method, apparatus, storage medium, and program product for determining the risk value of a product. Background Technology

[0002] With the rapid development of data processing technology, it has also been applied to assess the risk value of products. However, product conditions change in real time and rapidly, which in turn causes the product's risk value to change in real time and rapidly.

[0003] Traditional product risk assessment methods typically rely heavily on expert experience to define risk values, resulting in a lack of flexibility and timeliness in the assessment process. Clearly, if product risk assessment methods cannot overcome the limitations of empiricism and technical constraints, product risk values ​​cannot be accurately and timely determined. Summary of the Invention

[0004] Therefore, it is necessary to provide a method, apparatus, computer equipment, computer-readable storage medium, and computer program product for determining the risk value of a product that can accurately determine the target risk value of the product, in response to the above-mentioned technical problems.

[0005] Firstly, this application provides a method for determining the risk value of a product, including:

[0006] Acquire product logistics behavior data and product supply chain data;

[0007] Based on logistics behavior data, determine the logistics behavior factors of the product; based on supply chain data, determine the supply chain factors of the product.

[0008] Determine the weights of logistics behavior factors and supply chain factors;

[0009] The target risk value of the product is determined based on logistics behavior factors, their weights, supply chain factors, and their weights.

[0010] Secondly, this application also provides a risk value determination device for a product, comprising:

[0011] The acquisition module is used to acquire product logistics behavior data and product supply chain data.

[0012] The first determination module is used to determine the logistics behavior factors of the product based on logistics behavior data and the supply chain factors of the product based on supply chain data.

[0013] The second determining module is used to determine the weights of logistics behavior factors and supply chain factors.

[0014] The third determination module is used to determine the target risk value of a product based on logistics behavior factors, the weights of logistics behavior factors, supply chain factors, and the weights of supply chain factors.

[0015] Thirdly, this application also provides a computer device. The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement some or all of the steps described in any method of the first aspect of the embodiments of this application.

[0016] Fourthly, this application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program thereon, which, when executed by a processor, implements some or all of the steps described in any method of the first aspect of the embodiments of this application.

[0017] Fifthly, this application also provides a computer program product. The computer program product includes a computer program that, when executed by a processor, implements some or all of the steps described in any method of the first aspect of the embodiments of this application.

[0018] The aforementioned method, apparatus, computer equipment, computer-readable storage medium, and computer program product for determining the risk value of a product acquire product logistics behavior data and product supply chain data; determine product logistics behavior factors based on logistics behavior data, and determine product supply chain factors based on supply chain data; determine the weights of logistics behavior factors and supply chain factors; and determine the product's target risk value based on logistics behavior factors, their weights, supply chain factors, and their weights. The product risk value determination method provided in this application can accurately determine the product's target risk value using product logistics behavior data and product supply chain data. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 This is a diagram illustrating the application environment of a risk value determination method for a product in one embodiment.

[0021] Figure 2 This is a flowchart illustrating a method for determining the risk value of a product in one embodiment;

[0022] Figure 3 A structural block diagram of a risk value determination device for a product in one embodiment;

[0023] Figure 4 This is an internal structural diagram of a computer device in one embodiment;

[0024] Figure 5 This is a diagram of the internal structure of a computer device in another embodiment. Detailed Implementation

[0025] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0026] The risk value determination method for products provided in this application embodiment can be applied to, for example... Figure 1 In the application environment shown, terminal 102 communicates with server 104 via a network. A data storage system can store the data that server 104 needs to process. The data storage system can be integrated onto server 104 or located on the cloud or other network servers. Terminal 102 can be, but is not limited to, various personal computers, laptops, smartphones, tablets, IoT devices, and portable wearable devices. IoT devices can include smart speakers, smart TVs, smart air conditioners, smart in-vehicle devices, projection devices, etc. Portable wearable devices can include smartwatches, smart bracelets, head-mounted devices, etc. Head-mounted devices can be virtual reality (VR) devices, augmented reality (AR) devices, smart glasses, etc. Server 104 can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services.

[0027] In one exemplary embodiment, such as Figure 2 As shown, a method for determining the risk value of a product is provided, which can be applied to... Figure 1 Taking the terminal in the example, the explanation includes the following steps 202 to 208. Wherein:

[0028] Step 202: Obtain product logistics behavior data and product supply chain data.

[0029] Among them, products are tangible goods that can be put into logistics activities; products can be tangible goods with interactive functions, and optionally, interactive functions can include functions such as transactions and exchanges; tangible goods can include natural resources, different types of labor products, etc.

[0030] For example, the product can be a commodity for trade; more exemplarily, the product can be a daily necessity or an electronic product.

[0031] Product logistics behavior data refers to data related to the logistics activities of a product within the supply chain. For example, logistics behavior can be logistics transportation behavior. Product logistics behavior data can reflect the entire logistics transportation process of a product from the upstream party to the downstream party in the supply chain, and it can be used to quantify information such as the efficiency and stability of logistics behavior.

[0032] For example, product logistics behavior data may include consignment relationships that have direct or indirect logistics transportation activities with the product.

[0033] Product supply chain data refers to data related to the product's production status, inventory status, and interaction values ​​in supply chain activities. For example, data related to production status may include the product's total shelf life, production time nodes, and other production-related data; data related to inventory status may include the product's outbound quantity, inbound quantity, and inventory quantity, and other inventory-related data; and data related to interaction values ​​may include the product's historical interaction values, the interaction values ​​at the current time point, and other interaction value-related data.

[0034] For example, when the interactive function of a product is a transaction, the interactive value of the product can be the transaction value of the product, that is, the selling price of the product.

[0035] It should be noted that product logistics behavior data and product supply chain data are both parts of product supply chain operation data. However, product logistics behavior data focuses on the logistics activities that cause the physical movement of the product; it is data directly related to the product's logistics and transportation process within the supply chain operation data. In contrast, product supply chain data focuses on data related to the product at each node in the supply chain. For easy understanding, supply chain nodes can include production nodes, storage nodes, etc. For example, the relevant data at each node can refer to data related to the product's production status, inventory status, and interaction status.

[0036] Step 204: Determine the product's logistics behavior factors based on logistics behavior data, and determine the product's supply chain factors based on supply chain data.

[0037] Among them, the product's logistics behavior factor is a data factor determined from logistics behavior data and that is related to the product's risk value. In other words, the product's logistics behavior factor is a part of the key logistics behavior data that reflects the product's risk value.

[0038] Optionally, the product's logistics behavior factors can be determined based on the consignment relationship with the product that has a direct or indirect logistics transportation behavior.

[0039] The product's supply chain factor is a data factor determined from supply chain data and that is related to the product's risk value. In other words, the product's supply chain factor is a portion of key supply chain data that reflects the product's risk value.

[0040] Optionally, the product's supply chain factors can be production-related data such as the product's total shelf life and production time nodes; inventory-related data can be inventory-related data such as the product's outbound quantity, inbound quantity, and inventory quantity; and interaction value-related data can be interaction value-related data such as the product's historical interaction value and the interaction value at the current time node.

[0041] Step 206: Determine the weights of the logistics behavior factors and the weights of the supply chain factors.

[0042] The weights of logistics behavior factors and supply chain factors can be set manually or determined by training based on the product's historical risk value, the historical weights of logistics behavior factors, and the historical weights of supply chain factors.

[0043] Optionally, the sum of the weights of the logistics behavior factor and the supply chain factor can be 1, thereby determining whether the target risk value of the product depends more on the logistics behavior factor or the supply chain factor by setting the magnitude of the weights.

[0044] Optionally, the weight of the logistics behavior factor can be related to the ease with which the product is damaged during logistics. For example, the more easily a product is damaged during logistics, the more easily its target risk value will be affected by logistics; therefore, the greater the weight of the product's logistics behavior factor should be.

[0045] In an exemplary embodiment, determining the weights of the logistics behavior factor and the supply chain factor includes: determining the product category; and when the product category is a preset category, determining that the weight of the logistics behavior factor is greater than the weight of the supply chain factor.

[0046] Among these, the loss rate of pre-defined product categories in logistics is greater than the pre-defined loss rate. In other words, pre-defined product categories are those whose quality is strongly correlated with logistics performance. The reasons for loss rates in logistics can include: the product's total shelf life, the product's material, and the product's physical properties.

[0047] Step 208: Determine the target risk value of the product based on logistics behavior factors, the weights of logistics behavior factors, supply chain factors, and the weights of supply chain factors.

[0048] The target risk value of a product reflects its trustworthiness. Since the target risk value reflects the level of trustworthiness of a product, it can be further used to determine the product's collateral ratio.

[0049] Optionally, the target risk value of the product = logistics behavior factor × weight of logistics behavior factor + supply chain factor × weight of supply chain factor. Optionally, the target risk value of the product can be in the range of [0, 1].

[0050] The aforementioned method for determining the risk value of a product involves acquiring the product's logistics behavior data and supply chain data; determining the product's logistics behavior factors based on the logistics behavior data and the product's supply chain factors based on the supply chain data; determining the weights of the logistics behavior factors and the supply chain factors; and determining the product's target risk value based on the logistics behavior factors, their weights, the supply chain factors, and their weights. The risk value determination method provided in this application can accurately determine the product's target risk value using the product's logistics behavior data and supply chain data.

[0051] In an exemplary embodiment, the acquisition of product logistics behavior data and product supply chain data includes:

[0052] Obtain product supply chain operation data;

[0053] The supply chain operation data is anonymized to obtain anonymized supply chain operation data;

[0054] Data aggregation of anonymized supply chain operation data is performed according to time-series slicing and classification dimensions to obtain logistics behavior data and supply chain data.

[0055] Among them, the product's supply chain operation data is all the data related to the product's activities in the supply chain.

[0056] Specifically, anonymizing supply chain operation data refers to specially processing sensitive information that may involve personal privacy, trade secrets, or other sensitive information requiring protection within the supply chain operation data. This is to prevent the leakage or misuse of such sensitive information during the determination of target risk values ​​for products. Optionally, this special processing can include data generalization, data masking, data perturbation, data replacement, data encryption, and other data processing techniques. In simple terms, the anonymized supply chain operation data does not contain sensitive information.

[0057] Specifically, time-series slicing refers to dividing continuous supply chain operation data over a time series into multiple smaller time periods or "slices" so that the characteristics and trends of supply chain operation data within each time period can be analyzed separately. For example, supply chain operation data for a specific historical period can be obtained by using time-series slicing.

[0058] Specifically, the classification dimension refers to categorizing supply chain operation data according to a specific subject dimension, so that supply chain operation data for different subjects can be obtained separately. For example, the subject dimension can refer to the interaction party dimension, thereby obtaining the supply chain operation data between a specific interaction party and the product according to the classification dimension.

[0059] In this embodiment, by desensitizing the product's supply chain operation data, and then aggregating the desensitized supply chain operation data according to time-series slices and classification dimensions, it is possible to obtain logistics behavior data and supply chain data that do not contain sensitive information and are arranged in time-series format under each classification dimension.

[0060] In an exemplary embodiment, the above-mentioned determination of product logistics behavior factors based on logistics behavior data includes:

[0061] Determine the product circulation activity and consignment stability based on logistics behavior data;

[0062] The aforementioned supply chain factors for determining products based on supply chain data include:

[0063] Determine the stability of product supply and demand based on supply chain data;

[0064] Determine the time-related depreciation rate of products based on supply chain data;

[0065] Based on supply chain data, determine the product's interaction value maintenance index;

[0066] The weights of the aforementioned logistics behavior factors and supply chain factors are determined as follows:

[0067] The weights for determining circulation activity, deposit stability, supply and demand stability, time-related depreciation rate, and interaction value maintenance index are determined.

[0068] Product circulation activity refers to a quantitative indicator used to measure the activity of a product on an interactive platform. For example, product activity on an interactive platform can be reflected in interaction frequency, circulation speed, and the platform's acceptance level. Product circulation activity can serve as a reference for optimizing product inventory management, adjusting production plans, and formulating risk control strategies.

[0069] Alternatively, when the interactive function of the product is to be used is a transaction, then the interactive platform can be a transaction platform for trading the product.

[0070] Product consignment stability refers to a quantitative indicator used to measure the stability of the cooperative relationship between the product holder and the first interacting party in the supply chain. For example, the stability of the cooperative relationship between the product holder and the first interacting party in the supply chain can be reflected in its continuity, consistency, and predictability. Product consignment stability can be used to assess the partner credit risk of the first interacting party and the overall stability of the supply chain.

[0071] The stability of product supply and demand refers to a quantitative indicator used to measure the stability of the amount of product interaction by the first party within a certain period of time. For example, the stability of product interaction volume can be reflected in the numerical stability and predictability of the interaction volume. The stability of product supply and demand reflects the ease of product interaction; therefore, it can be used to assess the product's credit risk and financing capabilities.

[0072] The time-related depreciation rate of a product is a quantitative indicator used to measure its ability to maintain its interactive value over a certain period of time by retaining its usability. The time-related depreciation rate can serve as a reference for optimizing product inventory management, adjusting production plans, and formulating risk control strategies. It is easy to understand that a product's usability is strongly correlated with its quality; therefore, the time-related depreciation rate corresponds to the product's quality.

[0073] The product interaction value maintenance index is a quantitative indicator used to measure a product's ability to maintain its original interaction value or the interaction value of its platform over a certain period. The product interaction value maintenance index reflects a product's ability to withstand fluctuations in the interaction platform and the decline in its interaction value over time. It can be used to assess the product's financing risk and, more importantly, to help the product's primary interacting party optimize inventory management to reduce the risk of product obsolescence and depreciation. It's easy to understand that a product's ability to withstand fluctuations in the interaction platform and the decline in its interaction value over time is strongly correlated with the interaction platform; therefore, the product interaction value maintenance index has a corresponding relationship with the interaction platform.

[0074] Optionally, the weights of circulation activity, deposit stability, supply and demand stability, time-related depreciation rate, and interaction value maintenance index can be set manually or determined by training based on the product's historical risk value, historical weights of circulation activity, deposit stability, supply and demand stability, time-related depreciation rate, and interaction value maintenance index.

[0075] Optionally, the target risk value of the product is a weighted sum of the following weights: circulation activity, deposit stability, supply and demand stability, time-related depreciation rate, interaction value maintenance index, and interaction value maintenance index. For example, the target risk value of the product = (circulation activity weight × circulation activity) + (deposit stability weight × deposit stability) + (supply and demand stability weight × supply and demand stability) + (time-related depreciation rate weight × time-related depreciation rate) + (interaction value maintenance index weight × interaction value maintenance index).

[0076] In this embodiment, the product's logistics behavior factors include the product's circulation activity and consignment stability, and the product's supply chain factors include the product's supply and demand stability, time-related depreciation rate, and interaction value maintenance index. Therefore, the product's target risk value is determined based on the product's circulation activity, consignment stability, supply and demand stability, time-related depreciation rate, and interaction value maintenance index, so that the product's target risk value depends on both sufficient logistics behavior factors and sufficient supply chain factors, thereby ensuring that the determined product's target risk value has high accuracy and credibility.

[0077] In an exemplary embodiment, the aforementioned logistics behavior data includes a first consignment relationship between the product holder and at least one first interaction party, and a second consignment relationship between each first interaction party and at least one second interaction party.

[0078] Among them, the first consignment relationship refers to the logistics behavior of transferring the product from the product holder to the first interaction party; optionally, the product holder can be the product manufacturer or custodian; optionally, the first interaction party can be the product interaction value provider.

[0079] The second consignment relationship refers to the logistics behavior of transferring products from the first interacting party to the second interacting party; optionally, the second interacting party may be the bearer of the product's interaction value.

[0080] For example, the provider of the interaction value can be the seller, and the bearer of the interaction value can be the consumer. Thus, the first consignment relationship can be a logistics activity of transferring the product from the product's manufacturer to the product's seller, and the second consignment relationship can be a logistics activity of transferring the product from the product's seller to the product's consumer.

[0081] In this embodiment, the logistics behavior data includes a first consignment relationship and a second consignment relationship. Since the first consignment relationship and the second consignment relationship can characterize the transfer relationship of the product between the product holder, the first interaction party, and the second interaction party, the circulation activity and consignment stability of the product can be accurately determined based on the logistics behavior data including the first consignment relationship and the second consignment relationship.

[0082] In an exemplary embodiment, the above-mentioned determination of product circulation activity and consignment stability based on logistics behavior data includes:

[0083] Based on page ranking algorithms and logistics networks, determine the page ranking values ​​of each first interaction party and multiple consigned items, including products.

[0084] Based on the second entrustment relationship, determine the product output degree of each first interaction party;

[0085] The page ranking value of the product is determined based on the page ranking value of each first interaction party, the product output number of each first interaction party, the page ranking value of other consignments besides the product, and the damping coefficient.

[0086] Determine the product's circulation activity level based on its page ranking value;

[0087] The stability of the consignment is determined based on the first consignment relationship and the second consignment relationship.

[0088] In an exemplary embodiment, the method further includes: using multiple consigned items, including products, multiple first interactors, and multiple second interactors as nodes; establishing first relationship edges between each consigned item and each first interactor, and second relationship edges between each first interactor and each second interactor, based on the third consignment relationship between each consigned item and each first interactor and the second consignment relationship between each first interactor and each second interactor; and constructing a logistics relationship network based on the multiple nodes, the multiple first relationship edges, and the multiple second relationship edges.

[0089] Since the product is included in multiple consignments, the third consignment relationship includes the first consignment relationship between the product holder and at least one first interaction party.

[0090] The page ranking algorithm is used to determine the page ranking value of each first interaction party and each consigned item.

[0091] Page ranking score is a quantitative indicator used to measure the ease with which each primary interactor and each item can be found through web page links. Therefore, a product's page ranking score can reflect its circulation activity. Optionally, there is a positive correlation between a product's page ranking score and its circulation activity.

[0092] The product out-degree count of the first interacting party refers to the number of second interacting parties that have interacted with the product and the first interacting party.

[0093] The damping coefficient is used to regulate the randomness of webpage redirection in a product's page ranking value, thereby controlling the product's page ranking value.

[0094] In an exemplary embodiment, determining the product's page ranking value based on the page ranking value of each first interacting party, the product output degree of each first interacting party, the page ranking value of other consignments besides the product, and the damping coefficient includes: determining a first difference between a first preset value and the damping coefficient; determining the sum of the page ranking values ​​of other nodes in the logistics network besides the product divided by a first sum of the product output degrees of each first interacting party for the product; determining a first product between the damping coefficient and the first sum; and determining the product's page ranking value based on the first difference and the first product.

[0095] The first preset value can be 1 or other values.

[0096] In another exemplary embodiment, determining the product's page ranking value based on the page ranking value of each first interacting party, the product output degree of each first interacting party, the page ranking value of other consignments besides the product, and the damping coefficient includes: continuously iteratively optimizing the page ranking value of each first interacting party and the page ranking value of other consignments besides the product based on a page ranking algorithm until the number of iterations reaches a preset number, or until the iterative change rate of the page ranking value of each first interacting party and the page ranking value of other consignments besides the product is less than a preset change rate, and then determining the product's page ranking value based on the page ranking value of each first interacting party, the product output degree of each first interacting party, the page ranking value of other consignments besides the product, and the damping coefficient.

[0097] For example, if the product node is represented as X, the product's page ranking value is represented as PR(X), the damping coefficient is represented as d, other nodes besides the product are represented as PR(N), and the product out-degree of each first interaction party is represented as C(N), then the product's page ranking value can be represented as: PR(X) = (1-d) + d × Σ[(PR(N) / C(N))].

[0098] In this embodiment, the product's circulation activity is determined by the product's page ranking value, which reflects the ease with which the product can be found by other web page links on the network. Furthermore, the consignment stability between the product and each first interaction party is determined by the first consignment relationship and the second consignment relationship. Thus, the product's target risk value can be accurately determined based on the product's logistics behavior data and supply chain data.

[0099] In an exemplary embodiment, the determination of consignment stability based on the first consignment relationship and the second consignment relationship includes:

[0100] Based on the first consignment relationship and historical time, determine the number of consignment inbound waybills for the product during the historical time, the number of consignment outbound waybills for each first interaction party during the historical time, the number of consignment waybills between the product and each first interaction party during the historical time, and the total weight of consignment waybills between the product and each first interaction party during the historical time.

[0101] Based on the first consignment relationship and the current time, determine the first consignment time span and the second consignment time span between the product and each first interaction party; the first consignment time span is greater than the second consignment time span;

[0102] Based on the first and second postage time spans, the first time adjustment function and the second time adjustment function are determined respectively.

[0103] Based on the number of incoming shipments for the product within a historical period, the number of outgoing shipments for each first interaction party within a historical period, the number of shipments between the product and each first interaction party within a historical period, the first time adjustment coefficient, the first time adjustment function, the second time adjustment coefficient, the second time adjustment function, the total weight of shipments between each first interaction party within a historical period, the first row adjustment coefficient, and the second row adjustment coefficient, the initial shipment stability between the product and each first interaction party is determined.

[0104] Determine the entrustment stability based on the initial entrustment stability between the product and each first interaction party.

[0105] The number of inbound shipments for a product within a historical period refers to the number of first-party transactions that processed the shipment of the product within that historical period. The number of outbound shipments for a product by a first-party transaction within a historical period refers to the number of shipments processed by the first-party transaction within that historical period.

[0106] The number of shipping orders between the product and each of the first interacting parties during the historical period refers to the total number of shipping orders processed by each of the first interacting parties during the historical period. The total weight of shipping orders between the product and each of the first interacting parties during the historical period refers to the total weight of the product shipped by each of the first interacting parties during the historical period.

[0107] Optionally, the historical time can be 6 months, 12 months, or other past times relative to the current time.

[0108] In an exemplary embodiment, the above-mentioned determination of the first and second shipping time spans between the product and each first interaction party based on the first shipping relationship and the current time includes: determining the earliest and latest shipping times of each first interaction party to the product based on the first shipping relationship and the current time; and determining the first and second shipping time spans between the product and each first interaction party based on the earliest and latest shipping times.

[0109] The first consignment time span refers to the time span between the earliest consignment time of each first interaction party and the current time. The second consignment time span refers to the time span between the latest consignment time of each first interaction party and the current time. It is easy to understand that since the earliest consignment time must be before the latest consignment time, the first consignment time span is longer than the second consignment time span.

[0110] In an exemplary embodiment, the determination of the initial shipment stability between the product and each first interaction party based on the number of inbound shipments of the product within a historical period, the number of outbound shipments of each first interaction party within a historical period, the number of shipments between the product and each first interaction party within a historical period, a first time adjustment coefficient, a first time adjustment function, a second time adjustment coefficient, a second time adjustment function, the total weight of shipments between each first interaction party within a historical period, a first row adjustment coefficient, and a second row adjustment coefficient includes: determining the initial shipment stability between the product and each first interaction party based on the number of inbound shipments of the product within a historical period, the number of outbound shipments of each first interaction party within a historical period, the number of shipments between the product and each first interaction party within a historical period, a first row adjustment coefficient, and a second row adjustment coefficient. The product's timeliness indicators are determined based on the number of outbound waybills between the product and each first interacting party within a historical period, the number of waybills between the product and each first interacting party within a historical period, the first time adjustment coefficient, the first time adjustment function, the second time adjustment coefficient, and the second time adjustment function. The product's interactivity indicators are determined based on the number of waybills between the product and each first interacting party within a historical period, the total weight of waybills between each first interacting party within a historical period, the first line adjustment coefficient, and the second line adjustment coefficient. Finally, the initial stability of the product's outbound waybills between the product and each first interacting party is determined based on the product's timeliness indicators and interactivity indicators.

[0111] Optionally, the magnitudes of the first time adjustment factor and the second time adjustment factor can be set manually. Further, optionally, the magnitudes of the first time adjustment factor and the second time adjustment factor should ensure that the value range of the product's time-related indicators is [0, 1].

[0112] In an exemplary embodiment, the determination of the product's timeliness index based on the number of inbound shipments of the product within a historical period, the number of outbound shipments of each first interacting party within a historical period, the number of shipments between the product and each first interacting party within a historical period, a first time adjustment coefficient, a first time adjustment function, a second time adjustment coefficient, and a second time adjustment function includes: determining a first ratio between the number of shipments between the product and each first interacting party within a historical period and the number of outbound shipments of each first interacting party within a historical period; determining a second ratio between the number of shipments between the product and each first interacting party within a historical period and the number of inbound shipments of the product within a historical period; determining a second product between the first time adjustment coefficient and the first time adjustment function; determining a third product between the second time adjustment coefficient and the second time adjustment function; determining a second sum between the first ratio and the second ratio; determining a fourth product between a second preset value and the second sum; and determining the third sum between the second product, the third product, and the fourth product as the timeliness index.

[0113] The second preset value can be 1 / 4 or other values. The first time adjustment coefficient can be 1 / 64 or other values, and the second time adjustment coefficient can be 1 / 32 or other values.

[0114] For example, the first shipping time span is denoted as T1, the second shipping time span is denoted as T2, and the number of inbound shipping orders for the product within the historical time period is denoted as I. j The number of outbound shipping orders for each first interacting party within a historical time period is represented as I. i The number of shipping orders between the product and each of the first interacting parties within a historical period is represented as I. ij Let the first time adjustment coefficient be denoted as m1, the first time adjustment function as γ1(T1), the second time adjustment coefficient as m2, the second time adjustment function as γ2(T2), and the time index as T. Optionally, the time index can be expressed as: T = 1 / 4 × (I ij / I i +I ij / I j )+ m1×γ1 (T1)+ m2×γ2(T2).

[0115] Optionally, the first shipping time span is positively correlated with the first time adjustment function, and the second shipping time span is negatively correlated with the second time adjustment function.

[0116] Optionally, there may be a mapping table between the first shipping time span and the first time adjustment function, and between the second shipping time span and the second time adjustment function. Thus, based on the first shipping time span, the second shipping time span, and the mapping table, the first time adjustment function and the second time adjustment function can be directly determined respectively.

[0117] For example, the mapping relationship table can be as shown in Table 1. Based on Table 1, assuming that the first postage period is 6 months and the second postage period is 2 months, the value of the first time adjustment function is 2 and the value of the second time adjustment function is 4.

[0118]

[0119] Table 1

[0120] In an exemplary embodiment, the determination of the product's interactivity index based on the number of shipping orders between the product and each first interacting party within a historical period, the total weight of shipping orders between the first interacting parties within a historical period, the first row adjustment coefficient, and the second row adjustment coefficient includes: determining a first logarithm of the number of shipping orders between the product and each first interacting party within a historical period, based on a third preset value, and determining a second logarithm of the total weight of shipping orders between the first interacting parties within a historical period, based on a third preset value; determining a fifth product between the first row adjustment coefficient and the first logarithm, and determining a sixth product between the second row adjustment coefficient and the second logarithm; and determining a fourth sum between the fifth product and the sixth product as the interactivity index.

[0121] The third preset value can be 2 or other values. The first row is the adjustment coefficient, which can be 1.18 or other values, and the second row is the adjustment coefficient, which can be 1 or other values.

[0122] For example, the number of shipping orders between the product and each first interacting party within a historical period is represented as I. ij Let w represent the total weight of the shipping documents among the first interacting parties within a historical period, let k1 represent the first row as the adjustment coefficient, let k2 represent the second row as the adjustment coefficient, and let P represent the interactivity index. Optionally, the interactivity index can be expressed as: P = k1 × log2I ij +k2×log2w.

[0123] In an exemplary embodiment, determining the initial trust stability between the product and each first interacting party based on the product's time-related and interaction-related metrics includes: determining the initial trust stability between the product and each first interacting party based on the product's time-related and interaction-related metrics. Exemplarily, the initial trust stability between the product and each first interacting party is represented as Y, and optionally, Y = T × P.

[0124] In an exemplary embodiment, determining the entrustment stability based on the initial entrustment stability between the product and each first interaction party includes: determining the entrustment stability based on the mathematical operation result between the initial entrustment stability between the product and each first interaction party.

[0125] Optionally, the mathematical result of the initial reliance stability between the product and each first interaction party can be the sum, mean, median, mode, root mean square deviation, standard deviation, or other mathematical result of the initial reliance stability.

[0126] In this embodiment, by using the first entrustment relationship, historical time, and current time, the initial entrustment stability between the product and each first interaction party can be determined, thereby further determining the product's entrustment stability. In turn, the stability of the cooperative relationship between the product holder and the first interaction party in the supply chain can be measured, ensuring that the target risk value of the product determined based on the entrustment stability has high accuracy and credibility.

[0127] In one exemplary embodiment, determining the supply and demand stability of a product based on supply chain data includes:

[0128] Based on supply chain data, determine the actual number of products entering and leaving the warehouse, the average daily number of products entering and leaving the warehouse, the number of products leaving the warehouse, and the average inventory level.

[0129] The coefficient of variation for product inbound and outbound operations is determined based on the actual inbound and outbound quantities and the average daily inbound and outbound quantities.

[0130] The product turnover rate is determined based on the number of items shipped and the average inventory level.

[0131] Determine the first supply and demand coefficient corresponding to the coefficient of variation of inbound and outbound goods, and the second supply and demand coefficient corresponding to the turnover rate;

[0132] The stability of product supply and demand is determined based on the first supply and demand coefficient, the coefficient of variation of inbound and outbound goods, the second supply and demand coefficient, and the turnover rate.

[0133] The actual quantity of products entering and leaving the warehouse refers to the total actual quantity of products entering the warehouse and the total actual quantity of products leaving the warehouse during a historical period.

[0134] The average daily inbound and outbound quantity of products refers to the average daily actual quantity of products entering the warehouse and the average daily actual quantity of products leaving the warehouse over a historical period.

[0135] The number of products shipped out of the warehouse refers to the number of products shipped out of the warehouse within a historical period.

[0136] Average inventory level refers to the average daily inventory of products in a warehouse over a historical period.

[0137] In an exemplary embodiment, determining the product's inbound / outbound variation coefficient based on the actual inbound / outbound quantities and the average daily inbound / outbound quantities includes: determining the daily inbound quantity and daily outbound quantity of the product based on the actual inbound / outbound quantities; determining the standard deviation between the product's inbound / outbound quantities based on the product's daily inbound quantity and daily outbound quantity; and determining the product's inbound / outbound variation coefficient based on the standard deviation between the product's inbound / outbound quantities and the average daily inbound / outbound quantity.

[0138] The coefficient of variation (COP) for product inbound and outbound shipments is a quantitative indicator that measures the volatility or dispersion of product inbound and outbound quantities. It can be used to assess the stability of product inventory management. Simply put, the smaller the COP, the more stable the demand for the product.

[0139] Optionally, the coefficient of variation for product inbound and outbound shipments is the ratio of the standard deviation between the quantity of products inbound and outbound shipments to the average daily quantity of products inbound and outbound shipments. For example, the coefficient of variation for product inbound and outbound shipments = standard deviation between the quantity of products inbound and outbound shipments / average daily quantity of products inbound and outbound shipments.

[0140] Product turnover rate is a quantitative indicator used to measure the logistics activities that occur within a certain period of time in relation to the quantity of product inventory. It can be used to assess the frequency of logistics activities.

[0141] Optionally, product turnover rate is the ratio between the number of items shipped and the average inventory level. For example, product turnover rate = number of items shipped / average inventory level.

[0142] Product supply and demand stability measures the stability of product demand over time. It can also be used to assess the stability of the first party's interaction with the product.

[0143] Optionally, the first supply and demand coefficient can correspond to the coefficient of variation of inbound and outbound goods, thereby adjusting the contribution of the coefficient of variation of inbound and outbound goods to the stability of product supply and demand. The second supply and demand coefficient can correspond to the turnover rate, thereby adjusting the contribution of the turnover rate to the stability of product supply and demand.

[0144] Optionally, the magnitudes of the first and second supply and demand coefficients can be set manually.

[0145] Specifically, the terminal determines the actual number of products entering and leaving the warehouse, the average daily number of products entering and leaving the warehouse, the number of products leaving the warehouse, and the average inventory level based on inventory-related data in the supply chain data.

[0146] In this embodiment, based on inventory-related data in the supply chain data, the actual inbound and outbound quantities of products, the average daily inbound and outbound quantities, the outbound quantity, and the average inventory level are determined. Thus, the inbound and outbound variation coefficient and turnover rate of the products are determined. Furthermore, based on the first supply and demand coefficient, the inbound and outbound variation coefficient, the second supply and demand coefficient, and the turnover rate, the supply and demand stability of the products is determined. This achieves accurate quantification of the stability of product demand over time, ensuring that the target risk value of the products can be accurately determined subsequently.

[0147] In one exemplary embodiment, determining the time-related depreciation rate of a product based on supply chain data includes:

[0148] Based on supply chain data, determine the total shelf life of the product and the production time nodes;

[0149] Based on the current time point and the production time point, determine the remaining effective time of the product;

[0150] The time-related depreciation rate of the product is determined based on the total shelf life and the remaining effective time.

[0151] The total shelf life of a product refers to the length of time a product has after it has been manufactured; it can also be understood as the product's expiration date. The production time point refers to the point in time when the product was manufactured.

[0152] For example, the total shelf life of the product is 6 months, which means that the product meets the manufacturer's expected quality standards from the production date until 6 months later.

[0153] For example, if the current time point is August 1, X year, the total shelf life of the product is 6 months, and the production time point of the product is May 1, X year, then based on the current time point and the production time point, the remaining effective time of the product is determined to be: 6 - (8 - 5) = 3 months ≈ 90 days.

[0154] Optionally, the time-related depreciation rate of a product = remaining effective time / total shelf life × 100%. This formula can represent that when a product still has remaining effective time, that is, when the product is within its shelf life, the time-related depreciation rate of the product will linearly decrease from 100% to 0%, and when the product has no remaining effective time, that is, when the product expires, the time-related depreciation rate of the product will remain at 0%.

[0155] In this embodiment, the time-related depreciation rate of the product is determined based on the product's total shelf life and remaining effective time. Thus, by accurately determining the product's time-related depreciation rate, it is ensured that the target risk value of the product can be accurately determined subsequently.

[0156] In one exemplary embodiment, determining the product's interaction value maintenance index based on supply chain data includes:

[0157] Based on supply chain data, determine the product's historical interaction values ​​and the interaction values ​​at the current time point;

[0158] Based on historical interaction values, the initial interaction value of the product is determined, and a linear model between the interaction value decay rate and time points is constructed.

[0159] The interaction value of the product at the target time point is predicted based on a linear model;

[0160] Based on the interaction value at the current time node and the interaction value at the target time node, determine the interaction value maintenance index.

[0161] The product's historical interaction values ​​can refer to the interaction values ​​at a specific historical point in time, or to the interaction values ​​within a specific historical period. The product's initial interaction values ​​refer to the interaction values ​​when the product is first used for interactive functions.

[0162] A linear model relating interaction value decay rate to a specific time point is used to predict the interaction value of a product at a given time point. Optionally, the linear model is constructed by linearly fitting the product's initial interaction value, historical interaction values, and the time difference between the time point corresponding to the historical interaction value and the time point corresponding to the initial interaction value, thereby determining the product's interaction value decay rate.

[0163] Optionally, the linear formula for the interaction value of the product at the target time node in the linear model can be: interaction value of the product at the target time node = initial interaction value - interaction value decay rate × (time node corresponding to historical interaction value - time node corresponding to initial interaction value).

[0164] A target time point is a future time point relative to the current time point. For example, a target time point could be one month from the current time point.

[0165] The product's interaction value maintenance index represents its ability to maintain interaction value. A higher interaction value maintenance index indicates a better ability to maintain interaction value and that the product's interaction value is less likely to depreciate. Optionally, the interaction value maintenance index = (interaction value at the current time point - interaction value at the target time point) / interaction value at the current time point.

[0166] In an exemplary embodiment, the above-mentioned determination of the product's historical interaction value and the interaction value at the current time point based on supply chain data includes: determining the product's historical interaction records and the interaction value at the current time point based on supply chain data; and determining the product's historical interaction value based on the product's historical interaction records.

[0167] For example, when the product is a commodity, the product's historical interaction record can be the commodity's historical sales record, and the product's historical interaction value can be the commodity's historical sales price.

[0168] In this embodiment, the initial interaction value of the product is determined through historical interaction values, and a linear model between the interaction value decay rate and time nodes is constructed. Thus, the interaction value of the product at the target time node is predicted based on the linear model. Then, based on the interaction value at the current time node and the interaction value at the target time node, the interaction value maintenance index is determined. Furthermore, by fitting a linear model with an accurate interaction value decay rate to the interaction value of the product at the target time node, the product's interaction value maintenance ability can be quantified, and the determined interaction value maintenance index is also highly accurate, ensuring that the target risk value of the product can be accurately determined subsequently.

[0169] In an exemplary embodiment, the determination of the target risk value of a product based on logistics behavior factors, the weights of logistics behavior factors, supply chain factors, and the weights of supply chain factors includes:

[0170] The initial risk value of the product is determined based on logistics behavior factors, the weights of logistics behavior factors, supply chain factors, and the weights of supply chain factors.

[0171] The target risk value of the product is determined based on the product's initial risk value and bias coefficient.

[0172] The bias coefficient is used to adjust the target risk value of the product. Optionally, the magnitude of the bias coefficient can be set manually.

[0173] Optionally, the initial risk value of the product = logistics behavior factor × weight of logistics behavior factor + supply chain factor × weight of supply chain factor; the target risk value of the product = initial risk value of the product × bias coefficient.

[0174] In this embodiment, the initial risk value of the product is first determined based on the logistics behavior factor, the weight of the logistics behavior factor, the supply chain factor, and the weight of the supply chain factor. Then, the target risk value of the product is determined based on the initial risk value and the bias coefficient. Thus, by setting the bias coefficient to adjust the target risk value of the product, the process of determining the target risk value of the product is made more flexible and accurate.

[0175] In an exemplary embodiment, the above-mentioned determination of the initial risk value of a product based on logistics behavior factors, the weights of logistics behavior factors, supply chain factors, and the weights of supply chain factors includes: determining the initial risk value of a product based on a fourth preset value, logistics behavior factors, the weights of logistics behavior factors, supply chain factors, and the weights of supply chain factors.

[0176] The value of the fourth preset value can be set manually.

[0177] Optionally, the initial risk value of the product = fourth preset value + logistics behavior factor × weight of logistics behavior factor + supply chain factor × weight of supply chain factor.

[0178] In an exemplary embodiment, determining the target risk value of a product based on its initial risk value and bias coefficient includes: weighting and summing the logistics behavior factor, the weight of the logistics behavior factor, the supply chain factor, and the weight of the supply chain factor to obtain a fifth sum; summing the fourth preset value, the fifth preset value, and the fifth sum to obtain a sixth sum; and determining the seventh product between the sixth sum and the bias coefficient as the target risk value.

[0179] The fifth preset value can be 1 or other values.

[0180] Optionally, the target risk value of the product = bias coefficient × (fourth preset value + fifth preset value + weight of circulation activity × circulation activity + weight of deposit stability × deposit stability + weight of supply and demand stability × supply and demand stability + weight of time-related depreciation rate × time-related depreciation rate + weight of interaction value maintenance index × interaction value maintenance index).

[0181] In an exemplary embodiment, the acquisition of product logistics behavior data and product supply chain data includes: acquiring real-time product logistics behavior data and real-time product supply chain data; determining product logistics behavior factors based on logistics behavior data and determining product supply chain factors based on supply chain data includes: determining product real-time logistics behavior factors based on real-time logistics behavior data and determining product real-time supply chain factors based on real-time supply chain data; determining product target risk value based on logistics behavior factors, the weights of logistics behavior factors, supply chain factors, and the weights of supply chain factors includes: determining product real-time target risk value based on real-time logistics behavior factors, the weights of logistics behavior factors, real-time supply chain factors, and the weights of supply chain factors.

[0182] In this embodiment, since the product's logistics behavior data and supply chain data are acquired in real time, real-time logistics behavior factors and real-time supply chain factors can be determined based on these data. Consequently, the real-time target risk value of the product can be determined in real time. It can be seen that by timely acquisition of real-time changing logistics behavior data and supply chain data, this embodiment can dynamically adjust the product's target risk value in real time. This ensures both the accuracy and real-time dynamism of the target risk value, overcoming the problems of subjectivity and lag in traditional technologies that rely on empirical methods to determine product risk values.

[0183] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0184] Based on the same inventive concept, this application also provides a risk value determination apparatus for implementing the risk value determination method for the product described above. The solution provided by this apparatus is similar to the implementation described in the above method; therefore, the specific limitations in the embodiments of the risk value determination apparatus for one or more products provided below can be found in the limitations of the product risk value determination method described above, and will not be repeated here.

[0185] In one exemplary embodiment, such as Figure 3 As shown, a risk value determination device for a product is provided, comprising: an acquisition module 302, a first determination module 304, a second determination module 306, and a third determination module 308, wherein:

[0186] The acquisition module 302 is used to acquire product logistics behavior data and product supply chain data.

[0187] The first determining module 304 is used to determine the logistics behavior factors of the product based on logistics behavior data and to determine the supply chain factors of the product based on supply chain data.

[0188] The second determining module 306 is used to determine the weights of logistics behavior factors and supply chain factors.

[0189] The third determination module 308 is used to determine the target risk value of the product based on logistics behavior factors, the weights of logistics behavior factors, supply chain factors, and the weights of supply chain factors.

[0190] In an exemplary embodiment, the acquisition module 302 is further configured to acquire product supply chain operation data; perform desensitization processing on the supply chain operation data to obtain desensitized supply chain operation data; and aggregate the desensitized supply chain operation data according to time-series slices and classification dimensions to obtain logistics behavior data and supply chain data.

[0191] In an exemplary embodiment, the first determining module 304 is further configured to determine the circulation activity and consignment stability of the product based on logistics behavior data; the first determining module 304 is further configured to determine the supply and demand stability of the product based on supply chain data; determine the time-related depreciation rate of the product based on supply chain data; and determine the interaction value maintenance index of the product based on supply chain data; the second determining module 306 is further configured to determine the weights of circulation activity, consignment stability, supply and demand stability, time-related depreciation rate, and interaction value maintenance index.

[0192] In an exemplary embodiment, the aforementioned logistics behavior data includes a first consignment relationship between the product holder and at least one first interaction party, and a second consignment relationship between each first interaction party and at least one second interaction party.

[0193] In an exemplary embodiment, the first determining module 304 is further configured to: determine the page ranking value of each first interacting party and multiple consignments, including products, based on the page ranking algorithm and logistics relationship network; determine the product output number of each first interacting party based on the second consignment relationship; determine the page ranking value of the product based on the page ranking value of each first interacting party, the product output number of each first interacting party, the page ranking value of other consignments besides products, and the damping coefficient; determine the circulation activity of the product based on the page ranking value of the product; and determine the consignment stability based on the first consignment relationship and the second consignment relationship.

[0194] In an exemplary embodiment, the first determining module 304 is further configured to, based on the first consignment relationship and historical time, determine the number of inbound consignment orders for the product within a historical time period, the number of outbound consignment orders for each first interacting party within a historical time period, the number of consignment orders between the product and each first interacting party within a historical time period, and the total weight of consignment orders between the product and each first interacting party within a historical time period; based on the first consignment relationship and the current time, determine the first consignment time span and the second consignment time span between the product and each first interacting party; the first consignment time span is greater than the second consignment time span; based on the first consignment time span and the second consignment time span... First and second time adjustment functions are determined respectively. Based on the number of inbound shipments of the product within a historical period, the number of outbound shipments of each first interaction party within a historical period, the number of shipments between the product and each first interaction party within a historical period, the first time adjustment coefficient, the first time adjustment function, the second time adjustment coefficient, the second time adjustment function, the total weight of shipments between each first interaction party within a historical period, the first row adjustment coefficient, and the second row adjustment coefficient, the initial shipment stability between the product and each first interaction party is determined. Based on the initial shipment stability between the product and each first interaction party, the shipment stability is determined.

[0195] In an exemplary embodiment, the first determining module 304 is further configured to determine, based on supply chain data, the actual number of products entering and leaving the warehouse, the average daily number of products entering and leaving the warehouse, the number of products leaving the warehouse, and the average inventory level; determine the coefficient of variation of the product entering and leaving the warehouse based on the actual number of products entering and leaving the warehouse and the average daily number of products entering and leaving the warehouse; determine the product turnover rate based on the number of products leaving the warehouse and the average inventory level; determine a first supply and demand coefficient corresponding to the coefficient of variation of the product entering and leaving the warehouse and a second supply and demand coefficient corresponding to the turnover rate; and determine the supply and demand stability of the product based on the first supply and demand coefficient, the coefficient of variation of the product entering and leaving the warehouse, the second supply and demand coefficient, and the turnover rate.

[0196] In an exemplary embodiment, the first determining module 304 is further configured to determine the total shelf life and production time node of the product based on supply chain data; determine the remaining effective time of the product based on the current time node and production time node; and determine the time-related depreciation rate of the product based on the total shelf life and the remaining effective time.

[0197] In an exemplary embodiment, the first determining module 304 is further configured to determine the historical interaction value of the product and the interaction value at the current time node based on supply chain data; determine the initial interaction value of the product based on the historical interaction value, and construct a linear model between the interaction value decay rate and the time node; predict the interaction value of the product at the target time node based on the linear model; and determine the interaction value maintenance index based on the interaction value at the current time node and the interaction value at the target time node.

[0198] In an exemplary embodiment, the third determining module 308 is further configured to determine the initial risk value of the product based on the logistics behavior factor, the weight of the logistics behavior factor, the supply chain factor, and the weight of the supply chain factor; and to determine the target risk value of the product based on the initial risk value of the product and the bias coefficient.

[0199] The various modules in the risk value determination device for the aforementioned products can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the operations corresponding to each module.

[0200] In one exemplary embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 4 As shown, this computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operating system and computer programs stored in the non-volatile storage media. The database stores product logistics data and product supply chain data. The I / O interfaces allow the processor to exchange information with external devices. The communication interface allows communication with external terminals via a network connection. When executed by the processor, the computer program implements a method for determining the risk value of a product.

[0201] In one exemplary embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 5 As shown, the computer device includes a processor, memory, input / output interfaces, a communication interface, a display unit, and an input device. The processor, memory, and input / output interfaces are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The input / output interfaces are used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, Near Field Communication (NFC), or other technologies. When the computer program is executed by the processor, it implements a method for determining the risk value of a product. The display unit is used to form a visually visible image and can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the casing of the computer device, or external keyboards, touchpads, or mice, etc.

[0202] Those skilled in the art will understand that Figure 5 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0203] In one exemplary embodiment, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments.

[0204] In one exemplary embodiment, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the steps in the above-described method embodiments.

[0205] In one exemplary embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0206] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0207] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0208] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0209] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for determining the risk value of a product, characterized in that, The method includes: Acquire product logistics behavior data and product supply chain data; Based on the logistics behavior data, determine the logistics behavior factors of the product; based on the supply chain data, determine the supply chain factors of the product. Determine the weights of the logistics behavior factors and the weights of the supply chain factors; The target risk value of the product is determined based on the logistics behavior factors, the weights of the logistics behavior factors, the supply chain factors, and the weights of the supply chain factors.

2. The method according to claim 1, characterized in that, The acquisition of product logistics behavior data and product supply chain data includes: Obtain the supply chain operation data of the product; The supply chain operation data is anonymized to obtain anonymized supply chain operation data; The anonymized supply chain operation data is aggregated according to time-series slicing and classification dimensions to obtain the logistics behavior data and the supply chain data.

3. The method according to claim 2, characterized in that, The determination of the logistics behavior factors of the product based on the logistics behavior data includes: The circulation activity and consignment stability of the product are determined based on the logistics behavior data. The determination of the supply chain factors for the product based on the supply chain data includes: Based on the supply chain data, the supply and demand stability of the product is determined; Based on the supply chain data, the time-related depreciation rate of the product is determined; Based on the supply chain data, the interaction value maintenance index of the product is determined; Determining the weights of the logistics behavior factors and the supply chain factors includes: The weights of the circulation activity, the deposit stability, the supply and demand stability, the time-related depreciation rate, and the interaction value maintenance index are determined.

4. The method according to claim 3, characterized in that, The logistics behavior data includes a first consignment relationship between the product holder and at least one first interaction party, and a second consignment relationship between each of the first interaction parties and at least one second interaction party.

5. The method according to claim 4, characterized in that, The determination of the product's circulation activity and consignment stability based on the logistics behavior data includes: Based on the page ranking algorithm and logistics relationship network, determine the page ranking value of each first interactive party and multiple consigned items, including the product; Based on the second entrustment relationship, the product output degree of each of the first interaction parties is determined; The page ranking value of the product is determined based on the page ranking value of each of the first interactive parties, the product output number of each of the first interactive parties, the page ranking value of other consignments besides the product, and the damping coefficient. The circulation activity of the product is determined based on its page ranking value. The stability of the consignment is determined based on the first consignment relationship and the second consignment relationship.

6. The method according to claim 4, characterized in that, The determination of consignment stability based on the first consignment relationship and the second consignment relationship includes: Based on the first consignment relationship and historical time, determine the number of consignment inbound waybills for the product during the historical time, the number of consignment outbound waybills for each of the first interaction parties during the historical time, the number of consignment waybills between the product and each of the first interaction parties during the historical time, and the total weight of consignment waybills between the product and each of the first interaction parties during the historical time. Based on the first consignment relationship and the current time, a first consignment time span and a second consignment time span are determined between the product and each of the first interacting parties; the first consignment time span is greater than the second consignment time span. Based on the first and second shipping time spans, a first time adjustment function and a second time adjustment function are determined respectively. Based on the number of inbound shipments of the product within a historical period, the number of outbound shipments of each of the first interacting parties within the historical period, the number of shipments between the product and each of the first interacting parties within the historical period, a first time adjustment coefficient, a first time adjustment function, a second time adjustment coefficient, a second time adjustment function, the total weight of shipments between each of the first interacting parties within the historical period, a first line adjustment coefficient, and a second line adjustment coefficient, the initial shipment stability between the product and each of the first interacting parties is determined. The entrustment stability is determined based on the initial entrustment stability between the product and each of the first interacting parties.

7. The method according to claim 3, characterized in that, Determining the supply and demand stability of the product based on the supply chain data includes: Based on the supply chain data, determine the actual inbound and outbound quantities of the product, the average daily inbound and outbound quantities, the outbound quantity, and the average inventory level. Based on the actual inbound and outbound quantities and the average daily inbound and outbound quantities, the coefficient of variation for the inbound and outbound quantities of the product is determined. The product turnover rate is determined based on the outbound quantity and the average inventory level. Determine the first supply and demand coefficient corresponding to the inbound and outbound variation coefficients and the second supply and demand coefficient corresponding to the turnover rate; The supply and demand stability of the product is determined based on the first supply and demand coefficient, the inbound and outbound variation coefficient, the second supply and demand coefficient, and the turnover rate.

8. The method according to claim 3, characterized in that, Determining the time-related depreciation rate of the product based on the supply chain data includes: Based on the supply chain data, the total shelf life and production time nodes of the product are determined; Based on the current time point and the production time point, determine the remaining effective time of the product; The time-related depreciation rate of the product is determined based on the total shelf life and the remaining effective time.

9. The method according to claim 3, characterized in that, The determination of the interaction value maintenance index of the product based on the supply chain data includes: Based on the supply chain data, determine the historical interaction value of the product and the interaction value at the current time point; Based on the historical interaction values, the initial interaction value of the product is determined, and a linear model between the interaction value decay rate and time nodes is constructed. The interaction value of the product at the target time node is predicted based on the linear model. Based on the interaction value at the current time node and the interaction value at the target time node, the interaction value maintenance index is determined.

10. The method according to any one of claims 1-9, characterized in that, The determination of the target risk value of the product based on the logistics behavior factors, the weights of the logistics behavior factors, the supply chain factors, and the weights of the supply chain factors includes: Based on the logistics behavior factors, the weights of the logistics behavior factors, the supply chain factors, and the weights of the supply chain factors, the initial risk value of the product is determined. Based on the initial risk value and bias coefficient of the product, the target risk value of the product is determined.

11. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 10.

12. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 10.

13. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 10.

Images