Dynamic scale risk ranking method, device and terminal equipment

Abstract

The application provides a dynamic scale risk ranking method and device, terminal equipment and a computer readable storage medium. The method comprises the following steps: associating effective dynamic scales in a plurality of dynamic scales in a logistics network to obtain an associated dynamic scale network; and ranking the associated dynamic scales in the associated dynamic scale network to obtain a dynamic scale risk ranking result. The dynamic scale risk ranking method provided by the application can rank the dynamic scales in the associated network. The more forward the dynamic scale in the ranking, the greater the risk. Therefore, the ranking can visualize the risk, and the automatically generated ranking can save manual ranking on the basis of the prior art, thereby reducing the labor cost.

Description

Technical Field

[0001] This application relates to the field of logistics, specifically to a dynamic scale risk ranking method, apparatus, terminal equipment, and computer-readable storage medium. Background Technology

[0002] To manage the risk of under-calculation of package weight due to irregularities or malicious actions, the company has implemented end-to-end automated freight charge collection through AI visual analysis and big data risk identification. The re-weighing result of the dynamic scale is a crucial indicator. However, any equipment can malfunction. When the dynamic scale displays an incorrect weight, it can lead to incorrect freight charge collection, resulting in customer complaints and negatively impacting the company's image. Therefore, it is necessary to monitor dynamic scale anomalies and promptly prevent erroneous charge collection. However, due to production priorities and limited manpower, it is impossible to manually monitor the dynamic scale's operation at all times; an automated solution is required. Summary of the Invention

[0003] This application provides a method for ranking the risk of dynamic scales. By associating dynamic scales in operation, the risk of the associated dynamic scales can be ranked.

[0004] Firstly, this application provides a method for ranking the risk of dynamic scales, the method being used to rank multiple dynamic scales, the method comprising:

[0005] The effective dynamic scales among multiple dynamic scales in the associated logistics network are used to obtain the associated dynamic scale network.

[0006] The associated dynamic scales in the network of associated dynamic scales are ranked to obtain the dynamic scale risk ranking results.

[0007] In some embodiments of this application, before obtaining the associated dynamic scale network from the multiple dynamic scales in the associated logistics network, the method further includes:

[0008] Using one of the multiple dynamic scales as the dynamic scale to be tested, obtain the reweight data of the dynamic scale to be tested;

[0009] Determine whether the repeated data is valid, and obtain the determination result;

[0010] Based on the judgment result, determine whether the dynamic scale to be tested is valid;

[0011] Once each of the multiple dynamic scales has completed the determination of its validity, the valid dynamic scale among the multiple dynamic scales is determined.

[0012] In some embodiments of this application, determining whether the duplicate data is valid includes:

[0013] Determine whether the re-weighing data is within the preset re-weighing range;

[0014] If the re-weighing data is within the re-weighing range, then the re-weighing data of the dynamic scale to be tested is determined to be valid;

[0015] If the re-weighing data is not within the re-weighing range, then the re-weighing data of the dynamic scale to be tested is determined to be invalid.

[0016] In some embodiments of this application, determining whether the dynamic scale to be tested is valid based on the judgment result includes:

[0017] If the reweight data of the dynamic scale to be tested is valid, then the dynamic scale to be tested is determined to be a valid dynamic scale.

[0018] If the reweight data of the dynamic scale to be tested is invalid, then the dynamic scale to be tested is determined to be an invalid dynamic scale.

[0019] In some embodiments of this application, the effective dynamic scales among multiple dynamic scales in the associated logistics network constitute an associated dynamic scale network, including:

[0020] Each of the effective dynamic scales is taken as the target dynamic scale, and the target dynamic scale is combined with any other dynamic scale to form a target dynamic scale group. The re-weighing consistency rate of multiple target dynamic scale groups is calculated, and one target dynamic scale group corresponds to one re-weighing consistency rate.

[0021] The process continues until the reweight consistency rate of any dynamic scale in the dynamic scale group is calculated, and then each reweight consistency rate is obtained. Based on the reweight consistency rates, the associated dynamic scale network is obtained.

[0022] In some embodiments of this application, obtaining the associated dynamic scale network based on the respective re-weighing consistency rates includes:

[0023] The average reweight consistency rate of the second reweight consistency rate is calculated, with the reweight consistency rate of 0 being the first reweight consistency rate and the reweight consistency rate of non-zero being the second reweight consistency rate.

[0024] If the re-weighing consistency rate of any one of the multiple target dynamic scale groups is the first re-weighing consistency rate, the dynamic scales in the target dynamic scale group are associated according to the average re-weighing consistency rate.

[0025] If the reweight consistency rate of any one of the multiple target dynamic scale groups is the second reweight consistency rate, then the dynamic scales in the target dynamic scale group are associated according to the second reweight consistency rate.

[0026] The associated dynamic scale network is obtained after any one of the valid dynamic scales completes the association.

[0027] In some embodiments of this application, the step of associating the target dynamic scale group based on the average reweight consistency rate, if the reweight consistency rate of any one of the plurality of target dynamic scale groups is a first reweight consistency rate, includes:

[0028] If the average repetition consistency rate is greater than the preset repetition consistency rate threshold, then the associated target dynamic weighing group is maintained.

[0029] If the average repetition consistency rate is less than or equal to the preset repetition consistency rate threshold, then the target dynamic weighing group is unassociated.

[0030] In some embodiments of this application, the step of associating the target dynamic scale group based on the second re-weighing consistency rate, if the re-weighing consistency rate of any one of the plurality of target dynamic scale groups is a second re-weighing consistency rate, includes:

[0031] If the second repetition consistency rate is greater than the preset repetition consistency rate threshold, then the associated target dynamic group is maintained;

[0032] If the second repetition consistency rate is less than or equal to the preset repetition consistency rate threshold, then the association with the target dynamic weighing group is cancelled.

[0033] In some embodiments of this application, ranking the associated dynamic scales to obtain a dynamic scale risk ranking result includes:

[0034] Obtain the probability transition matrix of the associated dynamic scale network;

[0035] Calculate the ranking score of the associated dynamic scale based on the probability transition matrix;

[0036] Based on the ranking score, the associated dynamic scales are ranked to obtain the risk ranking result.

[0037] In some embodiments of this application, ranking the associated dynamic scales according to the ranking score to obtain the risk ranking result includes:

[0038] Calculate the convergent ranking score of the ranking score;

[0039] The associated dynamic scales are ranked according to their convergence ranking scores in ascending order to obtain the risk ranking result.

[0040] In some embodiments of this application, after ranking the associated dynamic scales according to the convergence ranking scores in ascending order to obtain the risk ranking result, the method further includes:

[0041] If there is an unassociated dynamic scale, the unassociated dynamic scale is ranked first in the risk ranking results. The unassociated dynamic scale is the dynamic scale that is not associated with any other valid dynamic scale among the valid dynamic scales.

[0042] If there are multiple unassociated dynamic scales, all of them will be ranked first in the ranking results.

[0043] Secondly, this application also provides a dynamic scale risk ranking device, the device comprising:

[0044] The association module is used to associate valid dynamic scales among multiple dynamic scales in the logistics network to obtain an associated dynamic scale network.

[0045] The ranking module is used to rank the associated dynamic scales in the network of associated dynamic scales and obtain the dynamic scale risk ranking results.

[0046] In some embodiments of this application, the association module is specifically used for:

[0047] Each of the effective dynamic scales is taken as the target dynamic scale, and the target dynamic scale is combined with any other dynamic scale to form a target dynamic scale group. The re-weighing consistency rate of multiple target dynamic scale groups is calculated, and one target dynamic scale group corresponds to one re-weighing consistency rate.

[0048] The process continues until the reweight consistency rate of any dynamic scale in the dynamic scale group is calculated, and then each reweight consistency rate is obtained. Based on the reweight consistency rates, the associated dynamic scale network is obtained.

[0049] In some embodiments of this application, the association module is further used for:

[0050] The average reweight consistency rate of the second reweight consistency rate is calculated, with the reweight consistency rate of 0 being the first reweight consistency rate and the reweight consistency rate of non-zero being the second reweight consistency rate.

[0051] If the reweight consistency rate of any one of the multiple target dynamic scale groups is the first reweight consistency rate, the dynamic scales in the target dynamic scale group are associated according to the average reweight consistency rate.

[0052] If the reweight consistency rate of any one of the multiple target dynamic scale groups is the second reweight consistency rate, then the dynamic scales in the target dynamic scale group are associated according to the second reweight consistency rate.

[0053] The associated dynamic scale network is obtained after any one of the valid dynamic scales completes the association.

[0054] In some embodiments of this application, the association module is further used for:

[0055] If the average repetition consistency rate is greater than the preset repetition consistency rate threshold, then the associated target dynamic weighing group is maintained.

[0056] If the average repetition consistency rate is less than or equal to the preset repetition consistency rate threshold, then the target dynamic weighing group is unassociated.

[0057] In some embodiments of this application, the association module is further used for:

[0058] If the second repetition consistency rate is greater than the preset repetition consistency rate threshold, then the associated target dynamic group is maintained;

[0059] If the second repetition consistency rate is less than or equal to the preset repetition consistency rate threshold, then the association with the target dynamic weighing group is cancelled.

[0060] In some embodiments of this application, the ranking module is specifically used for:

[0061] Obtain the probability transition matrix of the associated dynamic scale network;

[0062] Calculate the ranking score of the associated dynamic scale based on the probability transition matrix;

[0063] Based on the ranking score, the associated dynamic scales are ranked to obtain the risk ranking result.

[0064] In some embodiments of this application, the ranking module is further used for:

[0065] Calculate the convergent ranking score of the ranking score;

[0066] The associated dynamic scales are ranked according to their convergence ranking scores in ascending order to obtain the risk ranking result.

[0067] In some embodiments of this application, the ranking module is further used for:

[0068] If there is an unassociated dynamic scale, the unassociated dynamic scale is ranked first in the risk ranking results. The unassociated dynamic scale is the dynamic scale that is not associated with any other valid dynamic scale among the valid dynamic scales.

[0069] If there are multiple unassociated dynamic scales, all of them will be ranked first in the ranking results.

[0070] Thirdly, this application also provides a terminal device, the terminal device including a processor, a memory, and a computer program stored in the memory and executable on the processor, the processor executing the computer program to implement the steps in any of the dynamic scale risk ranking methods described above.

[0071] Fourthly, this application also provides a computer-readable storage medium storing a computer program that is executed by a processor to implement the steps in any of the dynamic scale risk ranking methods described above.

[0072] The dynamic scale risk ranking method provided in this application can rank the dynamic scales in the associated network by risk. The higher the dynamic scale ranks, the greater the risk. Therefore, the ranking can visualize the risk. At the same time, the automatically generated ranking can save manual ranking in the existing technology, thereby reducing labor costs. Attached Figure Description

[0073] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0074] Figure 1 This is a schematic diagram of a scenario for the dynamic scale risk ranking system provided in this application embodiment;

[0075] Figure 2 This is a schematic flowchart of one embodiment of the dynamic scale risk ranking method in this application;

[0076] Figure 3 This is a schematic diagram of a functional module of the dynamic scale risk ranking device in the embodiments of this application;

[0077] Figure 4 This is a schematic diagram of the structure of the terminal device in the embodiments of this application. Detailed Implementation

[0078] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0079] In the description of this application, it should be understood that the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this application, "multiple" means two or more, unless otherwise explicitly specified.

[0080] In this application, the term "exemplary" is used to mean "used as an example, illustration, or description." Any embodiment described as "exemplary" in this application is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is provided to enable any person skilled in the art to make and use this application. Details are set forth in the following description for purposes of explanation. It should be understood that those skilled in the art will recognize that this application can be made without using these specific details. In other instances, well-known structures and processes are not described in detail to avoid obscuring the description of this application with unnecessary detail. Therefore, this application is not intended to be limited to the embodiments shown, but is consistent with the broadest scope of the principles and features disclosed in this application.

[0081] This application provides a method, apparatus, terminal device, and computer-readable storage medium for dynamic scale risk ranking, which are described in detail below.

[0082] Please see Figure 1 , Figure 1 This is a schematic diagram illustrating a scenario of the dynamic scale risk ranking method provided in an embodiment of this application. The dynamic scale risk ranking system may include a terminal device 100 and a storage device 200, and the storage device 200 may transmit data to the terminal device 100. Figure 1 The terminal device 100 can obtain the recorded data of the dynamic scale stored in the storage device 200 to obtain the re-weighing consistency rate of the dynamic scale group, so as to execute the dynamic scale risk ranking method in this application.

[0083] In this embodiment of the application, the terminal device 100 may include, but is not limited to, desktop computers, portable computers, network servers, PDAs (personal digital assistants), tablet computers, wireless terminal devices, embedded devices, etc.

[0084] In the embodiments of this application, the terminal device 100 and the storage device 200 can communicate through any communication method, including but not limited to mobile communication based on the 3rd Generation Partnership Project (3GPP), Long Term Evolution (LTE), and Worldwide Interoperability for Microwave Access (WiMAX), or computer network communication based on the TCP / IP Protocol Suite (TCP / IP) and User Datagram Protocol (UDP).

[0085] It should be noted that, Figure 1 The schematic diagram of the dynamic scale risk ranking system shown is merely an example. The dynamic scale risk ranking system and scenario described in this application embodiment are for the purpose of more clearly illustrating the technical solutions of this application embodiment and do not constitute a limitation on the technical solutions provided in this application embodiment. As those skilled in the art will know, with the evolution of the dynamic scale risk ranking system and the emergence of new business scenarios, the technical solutions provided in this application embodiment are also applicable to similar technical problems.

[0086] like Figure 2 As shown, Figure 2 This is a flowchart illustrating an embodiment of a dynamic scale risk ranking method according to this application. The dynamic scale risk ranking method may include the following steps 201-202:

[0087] 201. Among the effective dynamic scales in the associated logistics network, the associated dynamic scale network is obtained.

[0088] Among them, a dynamic scale is a type of scale capable of dynamic weighing. The difference between dynamic and static weighing is that the object being weighed does not remain stationary in the weighing area. Typically, the object moves through the weighing area at a specific speed, such as a package passing through a conveyor belt weighing area or a tollbooth weighing area. Traditional static scales cannot weigh moving objects, thus requiring another type of scale. This type of scale, capable of weighing moving objects, is the dynamic scale. In this application's embodiments, the dynamic scale mentioned can refer to a dynamic scale in a logistics network that records weighing data. These dynamic scales can be connected via network communication or not. Specifically, these dynamic scales can be dynamic scales in sorting centers, distribution centers, etc.

[0089] Secondly, among multiple dynamic scales, there may be some that are damaged or not working. When these dynamic scales are damaged or not working for some reason, they can be regarded as abnormal or risky conditions. Therefore, there is no need to rank these damaged or not working dynamic scales by risk. Thus, these damaged or not working dynamic scales can be regarded as invalid dynamic scales. After excluding the invalid dynamic scales from multiple dynamic scales, the remaining dynamic scales can be regarded as valid dynamic scales.

[0090] Since it is necessary to rank the dynamic scales by risk, if the dynamic scales are not compared or analogized, no differences can be generated, and therefore no ranking can be made. Therefore, the purpose of associating the valid dynamic scales is to compare them to a certain extent or to bind them together, so that these dynamic scales can be ranked.

[0091] To better implement the embodiments of this application, in one embodiment of this application, before obtaining the associated dynamic scale network from the effective dynamic scales among multiple dynamic scales in the associated logistics network, the method further includes:

[0092] Using one of the multiple dynamic scales as the dynamic scale to be tested, obtain the reweight data of the dynamic scale to be tested;

[0093] Determine whether the repeated data is valid and obtain the determination result;

[0094] Based on the judgment results, determine whether the dynamic scale to be tested is valid;

[0095] Once each of the multiple dynamic scales has completed its validity assessment, the valid dynamic scale among the multiple dynamic scales is determined.

[0096] Since the concept of a valid dynamic scale has already been mentioned in step 201, this application embodiment relates to a screening scheme for valid dynamic scales in order to improve the reliability of the final risk ranking. Specifically, since the dynamic scales in this scheme are mainly used for weighing express parcels, in order to improve the accuracy of express parcel weighing, it is necessary to screen dynamic scales based on the weight of the express parcels. Therefore, dynamic scales that do not meet the requirements for repeated weighing data are filtered out, which means that in this application, the repeated weighing data of the dynamic scales is screened to determine whether they are valid. Dynamic scales that do not meet the repeated weighing data requirements are filtered out, thus allowing for the selection of dynamic scales with valid repeated weighing data.

[0097] The specific method for determining the validity of reweighing data can be based on the average weight of the shipment. For example, the weight of a typical shipment generally does not exceed 60KG. Furthermore, to avoid the influence of random errors on small shipments, shipments with a reweighing result below 1KG are excluded. That is, only when the reweighing data falls within the range of [1KG, 60KG] is the dynamic scale considered valid. This involves determining whether the reweighing data is within a preset reweighing range, which is [1KG, 60KG]. Of course, this preset reweighing range can be adjusted according to actual conditions. When judging the reweighing data, the following two results will occur:

[0098] (1) If the re-weighing data is within the re-weighing range, then the re-weighing data of the dynamic scale to be tested is valid.

[0099] (2) If the re-weighing data is not within the re-weighing range, then the re-weighing data of the dynamic scale to be tested is invalid.

[0100] Therefore, after determining whether the re-weighing data is valid, the corresponding dynamic scale can be judged based on whether the re-weighing data is valid. Similarly, the following two judgment results will also occur:

[0101] A. If the reweight data of the dynamic scale to be tested is valid, then the dynamic scale to be tested is determined to be a valid dynamic scale.

[0102] B. If the reweight data of the dynamic scale to be tested is invalid, then the dynamic scale to be tested is determined to be an invalid dynamic scale.

[0103] This judgment method only considers one dynamic scale among multiple dynamic scales. The other dynamic scales among the multiple dynamic scales can be judged using this exemplary scheme, and all valid dynamic scales can be obtained in the end.

[0104] To better implement the embodiments of this application, in one embodiment of this application, associating multiple valid dynamic scales among the dynamic scales to obtain an associated dynamic scale network may include the following steps S1 to S2:

[0105] S1. Take any one of the valid dynamic scales as the target dynamic scale, and the target dynamic scale and any other dynamic scale as the target dynamic scale group. Calculate the re-weighing consistency rate of multiple target dynamic scale groups. One target dynamic scale group corresponds to one re-weighing consistency rate.

[0106] As shown in the above embodiments, different dynamic scales have their own reweighing records (or weighing records). Specifically, the reweighing records of each dynamic scale can be managed through the waybill number of each express delivery. For example, when an express delivery task is initiated, a waybill number is created, let's say it's 123456. When the express delivery is reweighed, a weighing record is generated, and this record is associated with the express delivery with waybill number 123456. Since the destination can check the weight of the express delivery with waybill number 123456 again after it arrives from the origin, another weighing record is generated. Combining these two weighing records yields a reweighing record. Therefore, this reweighing record can be understood as a record of repeated weighing results. If the two weighing records are the same or within a certain range, the reweighing record is considered consistent. When multiple waybill numbers are used for express delivery, multiple reweighing records will appear. The proportion of consistent records among these multiple reweighing records is the reweighing consistency rate. Specifically, the consistency rate of this repetition can be calculated using the following formula:

[0107]

[0108] Where i represents any one of the valid dynamic scales, j represents any other valid dynamic scale besides i, and m ij Represents consistent duplicate records, n ij This represents all duplicate records. ij With w ji Both can represent the repetition rate of dynamic scale i and dynamic scale j. It should be noted that if m... ij or n ij If both values ​​are not zero, then the two dynamic scales can be associated. In other words, if the re-weighing consistency rate between dynamic scale i and dynamic scale j is not zero, they are associated. If the re-weighing consistency rate between dynamic scale i and dynamic scale j is zero, then dynamic scale i and dynamic scale j still need to be associated, but since the re-weighing consistency rate is zero, dynamic scale i and dynamic scale j cannot be associated. It should be noted that if there is no re-weighing consistency rate between the two dynamic scales, i.e., n... ij When the value is 0, it is treated as if the re-weighing consistency rate between the two dynamic scales is 0. In this case, an alternative association method is needed to associate two dynamic scales with a re-weighing consistency rate of 0. Specifically, the association can be performed as follows:

[0109] Since there can be multiple effective dynamic scales, there will be a re-weighing consistency rate between any two effective dynamic scales. Specifically, any one of the two dynamic scales, let's say scale A, can also be combined with any other effective dynamic scale (excluding scale A) to form two pairs. Therefore, within these combinations of multiple pairs of dynamic scales, scale A will have multiple re-weighing consistency rates. Some of these re-weighing consistency rates may be 0, while others may not be. Therefore:

[0110] For ease of description, the first reweight consistency rate is defined as the reweight consistency rate of 0 among multiple target dynamic scale groups, and the second reweight consistency rate is defined as the reweight consistency rate of non-zero reweight consistency rate. The average reweight consistency rate of the second reweight consistency rate is calculated. After the calculation is completed, the target dynamic scale, i.e., dynamic scale A, can be fully associated.

[0111] The average repetition consistency rate can be calculated using algorithms such as arithmetic mean or variance mean, without specific limitations. However, it should be noted that the average repetition consistency rate calculated using algorithms such as arithmetic mean or variance mean is not the average repetition consistency rate referred to in this application. To obtain the average repetition consistency rate of this application, the average value calculated by the mean algorithm needs to be amplified. The specific amplification formula is as follows:

[0112]

[0113] Where k represents the target dynamic scale, A represents another dynamic scale in the target dynamic scale group to which the re-weighing consistency rate is not 0, and i belongs to A, N A w represents the quantity of this type of dynamic scale. ki This involves summing the non-zero repetition consistency rates, w kj In this context, 'j' represents the dynamic weighing group where the target dynamic weighing scale 'k' belongs, where the re-weighing consistency rate is 0. 'j' also represents another dynamic weighing scale. This assigns the amplified average re-weighing consistency rate to the re-weighing consistency rate of 0. A specific example could be: when a dynamic weighing scale intersects with four other dynamic weighing scales, forming four dynamic weighing groups, assuming the re-weighing consistency rates are 1, 1, 1, and 0 respectively. Without amplification, the average re-weighing consistency rate would be (1+1+1) / 4 = 0.75, while after amplification, the padded value is 0.9375, thus reducing some error.

[0114] Once the amplified average repetition consistency rate is obtained, the specific association methods include the following two:

[0115] (1) If the re-weighing consistency rate of any one of the target dynamic scale groups is the first re-weighing consistency rate, the dynamic scales in the target dynamic scale group are associated based on the average re-weighing consistency rate.

[0116] When this situation (1) occurs, that is, there is no re-weight consistency rate between the target dynamic scale groups (as explained above, the situation of no re-weight consistency rate is treated as the case of 0 re-weight consistency rate), or when the re-weight consistency rate is 0, a value can be assigned to the re-weight consistency rate that is 0. The specific assigned value is the average re-weight consistency rate. When the re-weight consistency rate of the target dynamic scale group is replaced by the average re-weight consistency rate, the target dynamic scale group has a re-weight consistency rate. Then, the two dynamic scales in the target dynamic scale group can be associated. Since this method associates all valid dynamic scales, in order to improve the reliability of subsequent rankings, it is also necessary to judge the association situation to determine whether the two associated dynamic scales can maintain the association relationship.

[0117] Therefore, in order to better implement the embodiments of this application, in one embodiment of this application, if the re-weighing consistency rate of any one of the multiple target dynamic scale groups is a first re-weighing consistency rate, the target dynamic scale groups are associated based on the average re-weighing consistency rate, including:

[0118] If the average duplication rate is greater than the preset duplication rate threshold, then the dynamic grouping of associated targets will be maintained.

[0119] If the average duplication consistency rate is less than or equal to the preset duplication consistency rate threshold, then the dynamic grouping of associated targets will be cancelled.

[0120] If we continue with the example below in formula ② above, the re-weighing consistency rates of the four dynamic scale groups are 1, 1, 1, and 0.9375. If the preset re-weighing consistency rate threshold is 0.9, the association between the four groups will remain. If the preset re-weighing consistency rate threshold is 0.95, the dynamic scale group with a re-weighing consistency rate of 1 will remain associated, while the dynamic scale group with a re-weighing consistency rate of 0.9375 will be de-associated. It should be noted that the re-weighing consistency rate threshold can be set according to specific circumstances, and is not limited here.

[0121] (2) If the re-weighing consistency rate of any one of the target dynamic scale groups is the second re-weighing consistency rate, the dynamic scales in the target dynamic scale group are associated based on the second re-weighing consistency rate.

[0122] If the reweighing consistency rate of any one of the multiple target dynamic scale groups is the second reweighing consistency rate, then based on the second reweighing consistency rate, the target dynamic scale groups are associated, including:

[0123] If the second repetition consistency rate is greater than the preset repetition consistency rate threshold, then the dynamic grouping of associated targets will be maintained.

[0124] If the second repetition consistency rate is less than or equal to the preset repetition consistency rate threshold, then the dynamic grouping of associated targets is cancelled.

[0125] The comparison method here is the same as in case (1) above, and will not be described in detail here.

[0126] The associated dynamic scale network is obtained after any one of the valid dynamic scales completes the association.

[0127] S2. Continue until the reweight consistency rate of any dynamic scale in the effective dynamic scale group is calculated, obtain the reweight consistency rate of each scale, and obtain the associated dynamic scale network based on the reweight consistency rate of each scale.

[0128] As explained above, a dynamic scale A can be paired with any other dynamic scale in the valid dynamic scales. Therefore, the target dynamic scale group here can be any pair of dynamic scale groups.

[0129] Here, following the association method described above, each dynamic scale in the valid dynamic scales is associated. It should be noted that a valid dynamic scale can be associated multiple times. For example, valid dynamic scale A can have a non-zero weight consistency rate with valid dynamic scale B, meaning valid dynamic scale A can be associated with valid dynamic scale B. In practice, valid dynamic scale A can also conduct business transactions with other dynamic scales, such as sending a package from the origin of valid dynamic scale A to the destination of valid dynamic scale C. Therefore, valid dynamic scale A can also have a non-zero weight consistency rate with valid dynamic scale C, meaning valid dynamic scale A can also be associated with valid dynamic scale C. This results in multiple pairs of associated dynamic scales and multiple associated dynamic scale groups. These multiple pairs of associated dynamic scale groups can form an association network, i.e., an associated dynamic scale network. Of course, the weight consistency rate between two dynamic scales can also be 0. When the weight consistency rate is 0, the association can be performed as described in the above embodiment, which will not be elaborated further here.

[0130] 202. Rank the associated dynamic scales in the associated dynamic scale network to obtain the dynamic scale risk ranking results.

[0131] Once the network of associated dynamic scales is obtained, the scales can be ranked. It's important to note that, based on the ranking results, scales ranked higher have higher risk, while those ranked lower have lower risk. Staff can manually assess the risk of the top-ranked scales, eliminating the need for manual assessment of the lower-ranked scales. For example, in a ranking of 100 scales, the top 20 scales can be manually assessed for risk, while the bottom 80 can be left unassessed. This significantly reduces labor costs.

[0132] To better implement the embodiments of this application, in one embodiment, the associated dynamic scales in the associated dynamic scale network are ranked to obtain a dynamic scale risk ranking result, including:

[0133] Obtain the probability transition matrix of the associated dynamic scale network;

[0134] Calculate the ranking score of the associated dynamic scale based on the probability transition matrix;

[0135] Based on the ranking score, the associated dynamic scales are ranked to obtain the risk ranking results of the dynamic scales.

[0136] The probability transition matrix of this associated dynamic scale network can be calculated using the following formula:

[0137] M = [m ij ] n×n ……③

[0138] Where, m ij In this context, 'i' represents the i-th row of the matrix, 'j' represents the j-th column, and 'n' represents the number of dynamic scales remaining after the above embodiments. Since in the above embodiments, if the re-weighing consistency rate between dynamic scale groups is less than the set re-weighing consistency rate threshold, the association will be canceled. Therefore, it is possible that the re-weighing consistency rate of a dynamic scale combined with any other dynamic scale group is less than the re-weighing consistency rate threshold, meaning that the dynamic scale will not be associated with any other dynamic scale, resulting in an isolated dynamic scale. In this case, 'n' represents the number of dynamic scales after removing the isolated ones. Where m... ij Specifically, if dynamic scale j has k re-weight consistency rates, and dynamic scale i is one of its associated dynamic scales, then mij = 1 / k; otherwise, mij = 0.

[0139] Once the probability transition matrix is ​​calculated using formula ③ above, the ranking score can be calculated. Specifically, the ranking score can be calculated as follows:

[0140] Calculate the convergent rank score;

[0141] The associated dynamic scales are ranked according to their convergence ranking scores from smallest to largest to obtain the dynamic scale risk ranking results.

[0142] Specifically, the formula for calculating the ranking score can be used as follows:

[0143]

[0144]

[0145]

[0146] It should be noted that formula ④ is an iterative calculation formula, such as R. i+1 Approaching R sufficiently i Stop the iterative calculation and let R i =R i+1 A close approximation can be understood as R i+1 The limit and R i The limits are equal. Where d is the damping factor, a constant between [0,1]; n is the number of associated dynamic scales, where the number of terms within the parentheses in formula ⑤ is equal to n; where i represents the number of all dynamic scale groups to which the target dynamic scale belongs, and j represents the number of associated dynamic scale groups within the dynamic scale group to which the target dynamic scale belongs; PR i R represents the convergence ranking score for each dynamic scale to be calculated. i This is the ranking score.

[0147] Once the convergence ranking score of each dynamic scale is calculated using the above formula, the scales can be ranked. For example, if the convergence ranking scores of 10 dynamic scales are calculated, and the scores of scales 1 through 10 also increase sequentially from smallest to largest, then the ranking could be: 1st: Scale 1, 2nd: Scale 2, 3rd: Scale 3, 4th: Scale 4, 5th: Scale 5, 6th: Scale 6, 7th: Scale 7, 8th: Scale 8, 9th: Scale 9, 10th: Scale 10. It should be noted that this ranking method is merely an example for illustrative purposes. In practice, the ranking should be based on the actual number of dynamic scales and their corresponding convergence ranking scores; specific details are not specified here. Furthermore, the higher the ranking of a dynamic scale, the greater the probability of it having an anomaly risk, and the lower the ranking, the lower the probability. In specific situations, staff can check each dynamic scale individually based on its ranking.

[0148] To better implement the embodiments of this application, in one embodiment of this application, before ranking the associated dynamic scales according to the convergence ranking scores in ascending order, the method further includes:

[0149] If there is an unassociated dynamic scale, the unassociated dynamic scale will be ranked first in the risk ranking results. An unassociated dynamic scale is a dynamic scale that is not associated with any other valid dynamic scale among the valid dynamic scales.

[0150] If there are multiple unlinked dynamic scales, all of them will be ranked first in the ranking results.

[0151] As explained in the above embodiments, during the association process, there may be situations where one or more dynamic scales are not associated with any other dynamic scales. In such cases, it should be assumed that the dynamic scale in this situation has the highest probability of risk. Therefore, the dynamic scale in this situation should be placed at the top of the ranking, replacing the first position. For example, if 3 out of 10 dynamic scales are not associated with any other dynamic scales, these 3 scales should be ranked first. Then, the remaining 7 dynamic scales should be arranged starting from fourth place according to their convergent ranking scores. It should be noted that the arrangement methods listed in the embodiments of this application are merely for illustrative purposes and do not constitute a limitation of this application.

[0152] The dynamic scale risk ranking method provided in this application can rank the dynamic scales in the associated network by risk. The higher the dynamic scale ranks, the greater the risk. Therefore, the ranking can visualize the risk. At the same time, the automatically generated ranking can save manual ranking in the existing technology, thereby reducing labor costs.

[0153] To better implement the dynamic scale risk ranking method in this application embodiment, this application embodiment also provides a dynamic scale risk ranking device, such as... Figure 3 As shown, the device 300 includes:

[0154] The association module 301 is used to associate valid dynamic scales among multiple dynamic scales to obtain an associated dynamic scale network;

[0155] The ranking module 302 is used to rank the associated dynamic scales in the associated dynamic scale network and obtain the dynamic scale risk ranking results.

[0156] The dynamic scale risk ranking device provided in this application can associate dynamic scales in operation through the association module 301, and then perform risk assessment and ranking of dynamic scales in the association network through the ranking module 302. The higher the dynamic scale ranks, the greater the risk. Therefore, the ranking can visualize the risk. At the same time, the automatically generated ranking can save manual ranking in the existing technology, thereby reducing labor costs.

[0157] In some embodiments of this application, the association module 301 is specifically used for:

[0158] Each target dynamic scale is selected as any one of the valid dynamic scales. The target dynamic scale and any other dynamic scale are selected as the target dynamic scale group. The re-weighing consistency rate of multiple target dynamic scale groups is calculated. One target dynamic scale group corresponds to one re-weighing consistency rate.

[0159] The process continues until the reweight consistency rate of any dynamic scale in the dynamic scale group is calculated, and then the reweight consistency rate is obtained. Based on the reweight consistency rate, the associated dynamic scale network is obtained.

[0160] In some embodiments of this application, the association module 301 is further configured to:

[0161] The first reweight consistency rate is defined as the reweight consistency rate of 0 among multiple target dynamic scale groups, and the second reweight consistency rate is defined as the reweight consistency rate of non-zero reweight consistency rate. The average reweight consistency rate of the second reweight consistency rate is calculated.

[0162] If the re-weighing consistency rate of any one of the target dynamic scale groups is the first re-weighing consistency rate, then the dynamic scales in the target dynamic scale group are associated based on the average re-weighing consistency rate.

[0163] If the re-weighing consistency rate of any one of the target dynamic scale groups is the second re-weighing consistency rate, then the dynamic scales in the target dynamic scale group are associated based on the second re-weighing consistency rate.

[0164] The associated dynamic scale network is obtained after any one of the valid dynamic scales completes the association.

[0165] In some embodiments of this application, the association module 301 is further configured to:

[0166] If the average duplication consistency rate is greater than the preset duplication consistency rate threshold, then the dynamic grouping of associated targets will be maintained.

[0167] If the average duplication consistency rate is less than or equal to the preset duplication consistency rate threshold, then the dynamic grouping of associated targets will be cancelled.

[0168] In some embodiments of this application, the association module 301 is further configured to:

[0169] If the second repetition consistency rate is greater than the preset repetition consistency rate threshold, then the dynamic grouping of associated targets is maintained.

[0170] If the second repetition consistency rate is less than or equal to the preset repetition consistency rate threshold, then the dynamic grouping of associated targets is cancelled.

[0171] In some embodiments of this application, the ranking module 302 is further configured to:

[0172] Obtain the probability transition matrix of the associated dynamic scale network;

[0173] Calculate the ranking score of the associated dynamic scale based on the probability transition matrix;

[0174] Based on the ranking score, the associated dynamic scales are ranked to obtain the dynamic scale risk ranking results.

[0175] In some embodiments of this application, the ranking module 302 is further configured to:

[0176] Calculate the convergent rank score;

[0177] The convergence ranking scores are then used to rank the associated dynamic scales in ascending order to obtain the dynamic scale risk ranking results.

[0178] In some embodiments of this application, the ranking module 302 is further configured to:

[0179] If there is an unassociated dynamic scale, the unassociated dynamic scale will be ranked first in the risk ranking results. An unassociated dynamic scale is a dynamic scale that is not associated with any other valid dynamic scale among the valid dynamic scales.

[0180] If there are multiple unlinked dynamic scales, all of them will be ranked first in the ranking results.

[0181] This application also provides a terminal device, which includes a processor, a memory, and a computer program stored in the memory and executable on the processor. The processor executes the computer program to implement the steps of the dynamic scale risk ranking method according to any one of the embodiments of this application. This terminal device integrates any one of the dynamic scale risk ranking methods provided in the embodiments of this application, such as... Figure 4 As shown, it illustrates a structural schematic diagram of the terminal device involved in the embodiments of this application. Specifically:

[0182] The terminal device may include components such as a processor 401 with one or more processing cores, a memory 402 with one or more computer-readable storage media, a power supply 403, and an input unit 404. Those skilled in the art will understand that... Figure 4The terminal device structure shown does not constitute a limitation on the terminal device and may include more or fewer components than shown, or combine certain components, or have different component arrangements. Wherein:

[0183] The processor 401 is the control center of the terminal device. It connects various parts of the terminal device via various interfaces and lines, and performs various functions and processes data by running or executing software programs and / or modules stored in the memory 402, and by calling data stored in the memory 402, thereby providing overall monitoring of the terminal device. Optionally, the processor 401 may include one or more processing cores; the processor 401 may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor. Preferably, the processor 401 may integrate an application processor and a modem processor, wherein the application processor mainly handles the operating system, user interface, and application programs, and the modem processor mainly handles wireless communication. It is understood that the aforementioned modem processor may not be integrated into the processor 401.

[0184] The memory 402 can be used to store software programs and modules. The processor 401 executes various functional applications and data processing by running the software programs and modules stored in the memory 402. The memory 402 may mainly include a program storage area and a data storage area. The program storage area may store the operating system, application programs required for at least one function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created according to the use of the terminal device, etc. In addition, the memory 402 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device. Accordingly, the memory 402 may also include a memory controller to provide the processor 401 with access to the memory 402.

[0185] The terminal device also includes a power supply 403 that supplies power to the various components. Preferably, the power supply 403 can be logically connected to the processor 401 through a power management system, thereby enabling functions such as charging, discharging, and power consumption management through the power management system. The power supply 403 may also include one or more DC or AC power supplies, recharging systems, power fault detection circuits, power converters or inverters, power status indicators, and other arbitrary components.

[0186] The terminal device may also include an input unit 404, which can be used to receive input digital or character information, and generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function control.

[0187] Although not shown, the terminal device may also include a display unit, etc., which will not be described in detail here. Specifically, in this embodiment, the processor 401 in the terminal device loads the executable files corresponding to the processes of one or more applications into the memory 402 according to the following instructions, and the processor 401 runs the applications stored in the memory 402 to realize various functions, such as:

[0188] By associating the valid dynamic scales among multiple dynamic scales, a network of associated dynamic scales is obtained.

[0189] The associated dynamic scales in the associated dynamic scale network are ranked to obtain the dynamic scale risk ranking results.

[0190] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be performed by instructions, or by instructions controlling related hardware. These instructions can be stored in a computer-readable storage medium and loaded and executed by a processor.

[0191] Therefore, embodiments of this application provide a computer-readable storage medium, which may include: read-only memory (ROM), random access memory (RAM), a disk, or an optical disk, etc. A computer program is stored thereon, and the computer program is loaded by a processor to execute the steps in any of the dynamic risk ranking methods provided in embodiments of this application. For example, the computer program loaded by the processor can execute the following steps:

[0192] By associating the valid dynamic scales among multiple dynamic scales, a network of associated dynamic scales is obtained.

[0193] The associated dynamic scales in the associated dynamic scale network are ranked to obtain the dynamic scale risk ranking results.

[0194] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the detailed descriptions of other embodiments above, which will not be repeated here.

[0195] In practice, each of the above units or structures can be implemented as an independent entity or can be arbitrarily combined to be implemented as the same or several entities. For the specific implementation of each of the above units or structures, please refer to the previous method embodiments, which will not be repeated here.

[0196] For details on the implementation of each of the above operations, please refer to the previous examples, which will not be repeated here.

[0197] The above provides a detailed description of a dynamic scale risk ranking method and apparatus provided in the embodiments of this application. Specific examples have been used to illustrate the principles and implementation methods of this application. The description of the above embodiments is only for the purpose of helping to understand the method and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A dynamic scale risk ranking method, characterized in that, The method includes: Each target dynamic scale is selected from among the active dynamic scales in a logistics network. This target dynamic scale is grouped with any other active scale. The weight consistency rate of each target dynamic scale group is calculated, with at most one weight consistency rate corresponding to each target dynamic scale group. This process continues until the weight consistency rate of the dynamic scale group containing any active scale is calculated, resulting in individual weight consistency rates. The amplified average weight consistency rate of the weight consistency rates of the multiple target dynamic scale groups is then calculated. If any target dynamic scale group has no weight consistency rate, the scales within that target dynamic scale group are associated based on the amplified average weight consistency rate. If any target dynamic scale group has a weight consistency rate, the scales within that target dynamic scale group are associated based on that weight consistency rate. This process continues until any active scale in the active dynamic scale group is associated, resulting in an associated dynamic scale network. Obtain the probability transition matrix of the associated dynamic scale network; calculate the ranking score of the associated dynamic scale based on the probability transition matrix; rank the associated dynamic scale based on the ranking score to obtain the risk ranking result.

2. The dynamic scale risk ranking method according to claim 1, characterized in that, Before obtaining the associated dynamic scale network from multiple dynamic scales in the associated logistics network, the method further includes: Using one of the multiple dynamic scales as the dynamic scale to be tested, obtain the reweight data of the dynamic scale to be tested; Determine whether the repeated data is valid, and obtain the determination result; Based on the judgment result, determine whether the dynamic scale to be tested is valid; Once each of the multiple dynamic scales has completed the determination of its validity, the valid dynamic scale among the multiple dynamic scales is determined.

3. The dynamic scale risk ranking method according to claim 2, characterized in that, The determination of whether the duplicate data is valid includes: Determine whether the re-weighing data is within the preset re-weighing range; If the re-weighing data is within the re-weighing range, then the re-weighing data of the dynamic scale to be tested is determined to be valid; If the re-weighing data is not within the re-weighing range, then the re-weighing data of the dynamic scale to be tested is determined to be invalid.

4. The dynamic scale risk ranking method according to claim 3, characterized in that, The step of determining whether the dynamic scale to be tested is valid based on the judgment result includes: If the reweight data of the dynamic scale to be tested is valid, then the dynamic scale to be tested is determined to be a valid dynamic scale. If the reweight data of the dynamic scale to be tested is invalid, then the dynamic scale to be tested is determined to be an invalid dynamic scale.

5. The dynamic scale risk ranking method according to claim 1, characterized in that, If any one of the multiple target dynamic scale groups does not have a re-weighing consistency rate, before associating the dynamic scales in the target dynamic scale group based on the amplified average re-weighing consistency rate, the method further includes: Based on the aforementioned consistency rates, calculate the consistency rate threshold.

6. The dynamic scale risk ranking method according to claim 5, characterized in that, If any one of the multiple target dynamic scale groups does not have a re-weighing consistency rate, the dynamic scales in the target dynamic scale group are associated based on the amplified average re-weighing consistency rate, including: If the amplified average reweight consistency rate is greater than the reweight consistency rate threshold, then the dynamic scales in the target dynamic scale group are maintained in association. If the amplified average reweight consistency rate is less than or equal to the reweight consistency rate threshold, then the dynamic scales in the target dynamic scale group are unassociated.

7. The dynamic scale risk ranking method according to claim 5, characterized in that, If any one of the plurality of target dynamic scale groups has a re-weighing consistency rate, the dynamic scales in the target dynamic scale group are associated based on the re-weighing consistency rate of the target dynamic scale group, including: If the re-weighing consistency rate of the target dynamic scale group is greater than the re-weighing consistency rate threshold, then the association with the target dynamic scale group is maintained. If the re-weighing consistency rate of the target dynamic weighing group is less than or equal to the re-weighing consistency rate threshold, then the association with the target dynamic weighing group is cancelled.

8. The dynamic scale risk ranking method according to claim 1, characterized in that, The step of ranking the associated dynamic scales according to the ranking score to obtain the risk ranking result includes: Calculate the convergent ranking score of the ranking score; The associated dynamic scales are ranked according to their convergence ranking scores in ascending order to obtain the risk ranking result.

9. The dynamic scale risk ranking method according to claim 8, characterized in that, After ranking the associated dynamic scales according to the convergence ranking scores in ascending order to obtain the risk ranking result, the method further includes: If there is an unassociated dynamic scale, the unassociated dynamic scale is ranked first in the risk ranking results. The unassociated dynamic scale is the dynamic scale that is not associated with any other valid dynamic scale among the valid dynamic scales. If there are multiple unassociated dynamic scales, based on the historical order volume of these multiple unassociated dynamic scales, and in descending order of the historical order volume, these multiple unassociated dynamic scales are placed before the dynamic scale with the smallest convergent ranking score in the ranking results. The unassociated dynamic scale with the largest historical order volume is ranked first, and the dynamic scale with the smallest convergent ranking score is ranked one place lower than the unassociated dynamic scale with the smallest historical order volume.

10. A dynamic scale risk ranking device, characterized in that, The device includes: The association module is used to calculate the weight consistency rate of multiple target dynamic scales, taking any one of the valid dynamic scales in a logistics network as the target dynamic scale, and the target dynamic scale group with any other dynamic scale as the target dynamic scale group. Each target dynamic scale group corresponds to at most one weight consistency rate. This process continues until the weight consistency rate of the dynamic scale group containing any of the valid dynamic scales is calculated, resulting in individual weight consistency rates. The module then calculates the amplified average weight consistency rate of the multiple target dynamic scale groups. If any of the target dynamic scale groups has no weight consistency rate, the module associates the dynamic scales in that target dynamic scale group based on the amplified average weight consistency rate. If any of the target dynamic scale groups has a weight consistency rate, the module associates the dynamic scales in that target dynamic scale group based on that weight consistency rate. This process continues until any of the valid dynamic scales is associated, resulting in an associated dynamic scale network. The ranking module is used to obtain the probability transition matrix of the associated dynamic scale network; calculate the ranking score of the associated dynamic scale based on the probability transition matrix; and rank the associated dynamic scale based on the ranking score to obtain the risk ranking result.

11. A terminal device, characterized in that, The terminal device includes a processor, a memory, and a computer program stored in the memory and executable on the processor. The processor executes the computer program to implement the steps of the dynamic scale risk ranking 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 a computer program that is executed by a processor to implement the steps of the dynamic scale risk ranking method according to any one of claims 1 to 9.

Images