Waybill data processing method, device and equipment and computer readable medium
By screening risk waybills in logistics business and using decision trees to identify risk parameters, the problem of long processing cycle of waybills data is solved, and timely processing of waybills data and monitoring of payment risks is realized.
Patent Information
- Application Number
- CN202310639584.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2023-06-01
- Publication Date
- 2024-12-03
AI Technical Summary
In logistics business, it is difficult to monitor the delivery payment of the delivery party during the waybill data processing, resulting in a long processing cycle of waybill data, affecting the timely processing of waybill data.
By screening out the risk waybills based on the waybill delivery status in the waybill data, extracting logistics risk data, operational risk data and delivery party risk data, establishing a waybill data decision tree, identifying risk parameters, and sending waybill data processing instructions according to the risk parameters.
The processing cycle of waybill data is shortened, the timely processing of waybill data is ensured, and the risk of misappropriation or embezzlement of payment by the delivery party is reduced.
Smart Images

Figure CN119067430A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of computer technology, and in particular to a method, device, equipment and computer-readable medium for processing waybill data. Background Art
[0002] In the logistics business, it is necessary to process the waybill data. For example, the waybill involves the value-added service of collecting payment on delivery, that is, the cash on delivery service. After the merchant ships the goods, when the goods are delivered to the recipient, the recipient pays the payment to the delivery party, and then the delivery party transfers the payment to the company.
[0003] In the process of realizing the present invention, the inventors found that there are at least the following problems in the prior art: during the processing of waybill data, it is difficult to monitor the delivery party's transfer of payment, resulting in a long processing cycle of waybill data, which in turn affects the timely processing of waybill data. Summary of the invention
[0004] In view of this, embodiments of the present invention provide a method, apparatus, device and computer-readable medium for processing waybill data, which can shorten the processing cycle of waybill data and ensure timely processing of waybill data.
[0005] To achieve the above objective, according to one aspect of an embodiment of the present invention, a method for processing waybill data is provided, comprising:
[0006] According to the delivery status of the waybill in the waybill data, filter out the risky waybill in the waybill of the logistics business;
[0007] Extracting the waybill risk data of the risk waybill, wherein the waybill risk data includes logistics risk data, operational risk data and delivery party risk data;
[0008] The logistics risk data, the operational risk data and the delivery party risk data are used to identify the risk parameters of the risk waybill, and a waybill data processing instruction is sent according to the risk parameters.
[0009] The extracting of the waybill risk data of the risk waybill, wherein the waybill risk data includes logistics risk data, operational risk data and delivery party risk data, includes:
[0010] Selecting the logistics risk data in the data warehouse based on the identification of the risk waybill, and identifying the operational risk data;
[0011] The couriers of the risky waybills are aggregated to determine the couriers' risk data.
[0012] The step of using the logistics risk data, the operational risk data and the delivery party risk data to identify the risk parameters of the risk waybill includes:
[0013] A waybill data decision tree is established based on the information gain of logistics historical risk data, operation historical risk data, and delivery party historical risk data;
[0014] The logistics risk data, the operational risk data and the delivery party risk data are input into the waybill data decision tree to identify the risk parameters of the risk waybill.
[0015] The method of establishing a waybill data decision tree based on the information gain of the logistics historical risk data, the information gain of the operation historical risk data and the information gain of the delivery party historical risk data includes:
[0016] Establishing the root node of the waybill data decision tree based on the information gain of the operation history risk data;
[0017] On the basis of the root node, the internal nodes of the waybill data decision tree are established with the information gain of the logistics historical risk data and the information gain of the delivery party historical risk data.
[0018] The step of inputting the logistics risk data, the operational risk data and the delivery party risk data into the waybill data decision tree to identify the risk parameters of the risk waybill includes:
[0019] Inputting the logistics risk data, the operational risk data and the delivery party risk data into the waybill data decision tree to obtain leaf nodes of the waybill data decision tree;
[0020] According to the leaf nodes of the waybill data decision tree, the risk parameters of the risk waybill are identified.
[0021] The method of screening out risky waybills from the waybills of the logistics business according to the waybill delivery status in the waybill data includes:
[0022] Hive SQL modeling is used to identify the delivery status of the waybill based on the waybill delivery operation and / or the number of unsuccessful waybill deliveries in the waybill data;
[0023] According to the delivery status of the waybill, risky waybills are screened out from the waybills of the logistics business.
[0024] The sending of the waybill data processing instruction according to the risk parameter includes:
[0025] The risk parameter includes sending an indication at the waybill data to verify the risk waybill when the risk parameter value of the waybill data is greater than a preset threshold;
[0026] The waybill data decision tree is updated using the verified logistics risk data, operational risk data and delivery party risk data in the risk waybill.
[0027] According to a second aspect of an embodiment of the present invention, a device for processing waybill data is provided, including:
[0028] The screening module is used to screen out risky waybills from the waybills of the logistics business according to the waybill delivery status in the waybill data;
[0029] An extraction module, used to extract the waybill risk data of the risk waybill, wherein the waybill risk data includes logistics risk data, operational risk data and delivery party risk data;
[0030] An identification module is used to use the logistics risk data, the operational risk data and the delivery party risk data to identify the risk parameters of the risk waybill and send a waybill data processing instruction according to the risk parameters.
[0031] According to a third aspect of an embodiment of the present invention, there is provided an electronic device for processing waybill data, comprising:
[0032] one or more processors;
[0033] a storage device for storing one or more programs,
[0034] When the one or more programs are executed by the one or more processors, the one or more processors implement the above method.
[0035] According to a fourth aspect of an embodiment of the present invention, there is provided a computer-readable medium on which a computer program is stored, and when the program is executed by a processor, the method as described above is implemented.
[0036] One embodiment of the above invention has the following advantages or beneficial effects: according to the delivery status of the waybill in the waybill data, the risky waybill is screened out from the waybill of the logistics business; the waybill risk data of the risky waybill is extracted, and the waybill risk data includes logistics risk data, operation risk data and distributor risk data; the risk parameters of the risky waybill are identified by using the logistics risk data, the operation risk data and the distributor risk data, and the waybill data processing instructions are sent according to the risk parameters. Since the waybill data processing instructions can be sent in time according to the risk parameters, the processing cycle of the waybill data can be shortened, and the timely processing of the waybill data can be guaranteed.
[0037] The further effects of the above-mentioned non-conventional optional manner will be described below in conjunction with specific implementation examples. BRIEF DESCRIPTION OF THE DRAWINGS
[0038] The accompanying drawings are used to better understand the present invention and do not constitute an improper limitation of the present invention.
[0039] Figure 1 1 is a schematic diagram of the main flow of a method for processing waybill data according to an embodiment of the present invention;
[0040] Figure 2 It is a schematic diagram of a process of screening out risky waybills from waybills of logistics business according to an embodiment of the present invention;
[0041] Figure 3 is a schematic diagram of a process for extracting risk data of a risky waybill according to an embodiment of the present invention;
[0042] Figure 4 is a schematic diagram of a process for identifying risk parameters of a risky waybill according to an embodiment of the present invention;
[0043] Figure 5 is a schematic diagram of a process for establishing a waybill data decision tree according to an embodiment of the present invention;
[0044] Figure 6 is a schematic diagram of a waybill data decision tree according to an embodiment of the present invention;
[0045] Figure 7 is a schematic diagram of a process for identifying risk parameters of a risky waybill according to an embodiment of the present invention;
[0046] Figure 8 2 is a schematic diagram of the main structure of a device for processing waybill data according to an embodiment of the present invention;
[0047] Fig. 9 is an exemplary system architecture diagram to which embodiments of the present invention may be applied;
[0048] Fig.10 It is a schematic diagram of the structure of a computer system of a terminal device or a server suitable for implementing an embodiment of the present invention. DETAILED DESCRIPTION
[0049] The following is a description of exemplary embodiments of the present invention in conjunction with the accompanying drawings, including various details of the embodiments of the present invention to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present invention. Similarly, for clarity and conciseness, the description of well-known functions and structures is omitted in the following description.
[0050] In the process of the delivery party transferring the payment, there is a risk of misappropriation or embezzlement of the payment, which in turn leads to losses. The risks of collecting payment on behalf of others can be discovered through reporting or random inspections.
[0051] Relying on reports, due to the huge number of waybills collected on behalf of the customers every day, a large number of risky waybills will be missed, and even more risky waybills will not be reported, resulting in huge losses. In addition, the number of waybills covered by random inspections is limited, and the timeliness is very low. A large number of risky waybills cannot be discovered in time. By the time they are discovered later, the payment for the goods has been misappropriated and is difficult to recover.
[0052] In summary, during the waybill data processing process, it is difficult to monitor the delivery party's transfer of payment, which leads to a long waybill data processing cycle, thus affecting the timely processing of waybill data.
[0053] In order to solve the technical problem of long processing cycle of waybill data, the following technical solution in the embodiment of the present invention can be adopted.
[0054] See also Figure 1 , Figure 1 1 is a schematic diagram of the main flow of the method for processing waybill data according to an embodiment of the present invention, analyzing waybill data, identifying risk parameters of risky waybills, and triggering waybill data processing instructions. Figure 1 As shown, the specific steps include:
[0055] S101. Screen out risky waybills from the waybills of the logistics business according to the waybill delivery status in the waybill data.
[0056] In an embodiment of the present invention, waybill data is data related to waybills in logistics business. As an example, waybill data includes waybill start time, waybill operation, and distributor identification. It is understandable that each waybill has corresponding waybill data. Due to the large number of waybills, waybill data can be stored in a data warehouse. Then, the technical solution in the embodiment of the present invention is applied to the data warehouse.
[0057] See also Figure 2 , Figure 2 The flowchart of screening out risky waybills from waybills of logistics business according to an embodiment of the present invention includes the following steps:
[0058] S201. Hive SQL modeling is adopted to identify the waybill delivery status based on the waybill delivery operation and / or the number of unsuccessful waybill delivery in the waybill data.
[0059] In an embodiment of the present invention, the technical solution is applied to a data warehouse, and Hive SQL modeling can be used to identify the delivery status of the waybill. The delivery status of the waybill is a parameter that characterizes whether the waybill is delivered normally. Based on the delivery status of the waybill, risky waybills can be screened out. Risky waybills are waybills that may have the risk of collecting payment on delivery.
[0060] The waybill delivery status may be identified based on the waybill delivery operation and / or the number of unsuccessful waybill deliveries in the waybill data.
[0061] Waybill delivery operations include undelivered or detained waybill after delivery. Undelivered waybill after delivery includes waybill assigned to the delivery party but not delivered to the consignee. For example: there is no follow-up operation for 3 days or more after the last operation of the waybill. Detention includes waybill detained at the delivery party or delivery station.
[0062] Among them, the waybill is delivered successfully after completing the normal delivery process and being handed over to the recipient. After the waybill is delivered successfully, the whole process means that it has ended normally. The waybill cannot be delivered in time due to customer reasons, natural disasters, etc., and is temporarily stored at the station is called detention.
[0063] The number of unsuccessful delivery of waybills includes the number of times the waybills were not successfully delivered to the consignee. For example, if the waybill is resubmitted multiple times after delivery, and the number of resubmission operations exceeds 5 times, the repeated resubmissions per day are only counted once.
[0064] Hive SQL modeling is used to identify the waybill delivery status based on the waybill delivery operations and / or the number of unsuccessful waybill deliveries in the waybill data.
[0065] As an example, if the waybill delivery operation includes waybill retention, or the waybill is not successfully delivered more than 6 times, the waybill delivery status is marked as: not successfully delivered on schedule.
[0066] As another example, the waybill delivery operation includes that the waybill has been successfully delivered, and the waybill delivery status is identified as: successfully delivered on schedule.
[0067] S202. Filter out risky waybills from the waybills of the logistics business according to the waybill delivery status.
[0068] You can filter out risky waybills from the waybills of the logistics business according to the waybill delivery status. Waybills with a delivery status of "not delivered on time" are considered risky waybills.
[0069] exist Figure 2 In the embodiment of the invention, the risky waybills can be directly screened out by using the waybill delivery status, thereby narrowing the processing scope of the waybill data.
[0070] S102. Extract the waybill risk data of the risk waybill, where the waybill risk data includes logistics risk data, operational risk data and delivery party risk data.
[0071] For risky waybills, it is necessary to extract waybill risk data, which is used as the basis for identifying risky waybills. Risky waybills involve a variety of data, and waybill risk data can be extracted from the following three aspects: extract logistics risk data from the logistics aspect; extract operational risk data from the operational aspect; and extract distributor risk data from the distributor aspect.
[0072] See also Figure 3 , Figure 3 This is a flow chart of extracting the risk data of a risky waybill according to an embodiment of the present invention. Specifically, it includes the following steps:
[0073] S301. Select logistics risk data in the data warehouse based on the identification of risk waybills, and identify operational risk data.
[0074] Logistics risk data refers to the logistics data of risky waybills. Logistics risk data can be selected in the data warehouse based on the identification of risky waybills. As an example, logistics risk data includes one or more of the following: the number of waybills resubmitted, the number of days without follow-up on waybills, and the number of abnormal delivery process operations of waybills.
[0075] The following is an explanation of the subordinate parameters of logistics risk data.
[0076] Number of waybill resubmissions (ct_ag)
[0077] The number of re-delivery is calculated by tracking the whole process of the waybill, and the total number of re-delivery after the delivery of the waybill is started. The repeated re-delivery is counted only once a day. For example, after the delivery party completes the delivery of the goods and receives the payment, it does not operate the delivery and does not pay the payment to the company, but keeps making false operations to re-deliver in order to embezzle or misappropriate the payment.
[0078] Noop days for waybills (noop_days)
[0079] The number of days without any update on the waybill is the number of days that there is no update on the waybill status after the last operation on the waybill. For example, after the delivery party completes the delivery of the goods and receives the payment, he flees with the money.
[0080] Number of abnormal delivery process operations for waybills (ct_abop)
[0081] The number of abnormal delivery process operations of the waybill is the total number of "detained inventory" or "goods return to the station" operations on the waybill, and repeated operations are counted only once a day. For example, after the delivery party completes the delivery of the goods and receives the payment, it does not pay the payment to the company, but continues to falsely operate "detained inventory" or "goods return to the station" to embezzle or misappropriate the payment.
[0082] Operational risk data is data on the operation of risky waybills in waybills. Operational risk data can be identified based on risky waybills. Operational risk data can be identified by marking. For example, marking 1 means there is a preset operation; marking 0 means there is no preset operation. As an example, operational risk data includes one or more of the following: reverse waybills, claim waybills, and detained waybills.
[0083] Reverse waybill (is_rt)
[0084] Reverse waybill is to determine whether there is a reverse waybill number and go through the reverse process. Reverse means that after the customer returns or refuses to accept the goods, the waybill needs to be returned to the warehouse or merchant by the original route. In the reverse process, the original waybill will generate a new waybill number.
[0085] For example, if the recipient returns or refuses to accept the goods, the original waybill will generate a reverse order number and go through the reverse process. However, for a COD waybill, there is a case where the distributor delivers the goods and receives the payment, but then falsely refuses to accept the goods and generates a reverse order number, but does not go through the reverse process, thereby misappropriating or misappropriating the payment. Therefore, when generating the reverse waybill identifier, the initial value -1 is set if there is no reverse order number; the value is 1 if there is a reverse order number and the reverse process is actually followed; and the value is 0 if there is a reverse order number and the goods are not returned in reverse within three days. A value of -1 means there is no reverse information; a value of 1 means that the reverse process has been followed and the waybill is risk-free; a value of 0 can be understood as a false reverse, and the waybill is high-risk.
[0086] Claim waybill (is_lp)
[0087] Claim bill is to determine whether there is claim information on the bill. Claim is the customer's complaint and compensation request for the bill.
[0088] For example, a waybill with claim information and claim type of loss is high risk, while a waybill with claim reason of package damage, unsatisfied time limit, etc. is low risk. The risk level of some waybill can be determined based on whether there is claim information and claim reason.
[0089] Detained waybill (is_zl)
[0090] The detention of the waybill is to judge whether the waybill is detained due to objective reasons that cause the goods to be not delivered in time.
[0091] A large portion of waybills are detained and not delivered in time. It is necessary to analyze from multiple angles whether the waybill is a detained waybill. The risk of detained waybills is relatively small, while risky waybills are mainly non-detained waybills.
[0092] For example, whether a waybill is a detained waybill can be determined based on the specific remarks of the customer changing the delivery time in the full process information of the waybill, whether there is a detained reporting status, etc. For detained waybill, it is considered that there is no risk of collecting payment on behalf of the customer.
[0093] S302. Aggregate the couriers of risky waybills to determine the couriers' risk data.
[0094] The distributor is responsible for delivering the goods on the waybill. The distributor needs to deliver the goods on multiple waybills. From the distributor's perspective, the distributors of risky waybills can be aggregated to determine the distributor risk data.
[0095] In one embodiment of the present invention, the delivery party risk data includes one or more of the following: the number of orders involved by the delivery party, the total amount collected by the delivery party, the number of consignees involved in the waybill, the delivery time limit of the waybill and the delivery party's delivery time limit.
[0096] The number of bills involved in the delivery (ct_bill)
[0097] The number of shipping orders involved by the delivery party is the total number of COD shipping orders currently delivered by each delivery party after the shipping orders suspected of being at risk are aggregated by delivery party. The more COD shipping orders a delivery party handles at the same time, the greater the risk.
[0098] Total amount collected by the delivery party (sum_cod)
[0099] The total amount of money collected by the delivery party is the total amount of money collected by each delivery party after the risky waybills are aggregated by the delivery party dimension. The larger the total amount of money collected by a delivery party at the same time, the greater the risk.
[0100] Number of consignees involved in the waybill (ct_res)
[0101] The number of consignees involved in the waybill is the number of consignees involved in the COD waybill that each delivery party is currently responsible for delivering after the risk waybill is aggregated by the delivery party dimension. As an example, the number of waybills involved in the COD waybills operated by a delivery party at the same time is ct_bill. If ct_bill>1, and the number of consignees ct_res is 1, the risk is small, and most of the time it is caused by the consignee.
[0102] Waybill delivery time (risk_perf)
[0103] The delivery time of waybills is calculated by calculating the average delivery time of the waybills from delivery to delivery in the past three months for each courier corresponding to the waybills. For couriers who have misappropriated the payment on delivery, their average delivery time is longer than that of other couriers delivering to the same area in the same time period.
[0104] Delivery time of the delivery party (non_risk_perf)
[0105] The delivery time is the average time from delivery to successful delivery of each waybill by other non-risk couriers delivering the same route at the same station in the past three months.
[0106] See Table 1, which shows the waybill risk data of the risky waybill.
[0107] Table 1
[0108]
[0109] exist Figure 3 In the embodiment, the waybill risk data is extracted from the data warehouse according to the identification of the risk waybill.
[0110] S103: Using logistics risk data, operational risk data and delivery party risk data, identify risk parameters of risk waybills, and send waybill data processing instructions according to the risk parameters.
[0111] In the embodiment of the present invention, after the logistics risk data, the operation risk data and the delivery party risk data are extracted, the risk parameters of the risk waybill can be identified using the extracted risk data.
[0112] See also Figure 4 , Figure 4 The following is a flow chart of identifying risk parameters of risky waybills according to an embodiment of the present invention. Specifically, the following steps are included:
[0113] S401. Establish a waybill data decision tree based on the information gain of logistics historical risk data, the information gain of operation historical risk data and the information gain of delivery party historical risk data.
[0114] In an embodiment of the present invention, a waybill data decision tree is used to identify risk parameters of risky waybills, wherein the waybill data decision tree is trained using information gain of logistics historical risk data, information gain of operation historical risk data, and information gain of delivery party historical risk data.
[0115] The following is a brief introduction to the training process of the waybill data decision tree.
[0116] Training the waybill data decision tree model is to summarize a set of classification rules from the training data set so that it has the highest degree of fit with the training data set and has good generalization ability. The information gain of each feature of the training data set needs to be calculated. The greater the information gain, the better the classification effect. The training data set includes logistics historical risk data, operation historical risk data, and delivery party historical risk data.
[0117] The specific operation process is: starting from the root node, calculate the information gain of all possible features of the node, select the feature with the largest information gain as the feature of the node, and establish child nodes with different values of the feature; then recursively call the above method on the child nodes until the information gain of all features is very small or no features can be selected. Among them, information gain represents the degree to which the uncertainty of the classification of data set D is reduced due to feature A.
[0118] The information gain calculation process is:
[0119] 1) Calculate the empirical entropy
[0120] Entropy is a measure of the uncertainty of a random variable, and is used to measure the expected value of a random variable. If the uncertainty of information is greater, the entropy value will be greater, and there will be more situations.
[0121] Assume that the possible values of random variable X are x1, x2..., xn. For each possible value xi, the probability P(X=xi)=pi, (i=1,2,...,n), then the entropy of random variable X is:
[0122]
[0123] For the sample set D, the random variable X is the category of the sample. Assuming that the sample has k categories, the probability of each category is Where |Ck| represents the number of samples of category k, |D| represents the total number of samples, then for the sample set D, the empirical entropy is:
[0124]
[0125] 2) Calculate information gain
[0126] Define the difference between the empirical entropy H(D) of set D and the empirical conditional entropy H(D|A) of D under given conditions of feature A as the information gain g(D,A) of feature A for training data set D, then:
[0127] g(D,A)=H(D)-H(D|A) Formula 3
[0128] The historical logistics risk data, historical operation risk data and historical delivery risk data are used as training sample data. The information gain of each feature is calculated through formula 1, formula 2 and formula 3, and the size is compared to select the feature with the largest information gain. After the calculation is completed, the waybill data decision tree is generated.
[0129] See also Figure 5 , Figure 5 1 is a flow chart of establishing a waybill data decision tree according to an embodiment of the present invention. Specifically, the following steps are included:
[0130] S501. Establish a root node of the waybill data decision tree by operating the information gain of the historical risk data.
[0131] Compared with the information gain of logistics historical risk data and the information gain of delivery party historical risk data, the information gain of operation historical risk data is larger. Therefore, the root node of the waybill data decision tree is established based on the information gain of operation historical risk data.
[0132] The manipulation risk data includes one or more of the following: reverse waybills, claim waybills, and detained waybills. Specifically, the information gain of each parameter can be calculated using formulas 1 to 3. Then, the parameter is determined as the root node in the manipulation risk data. The remaining parameters can be used as internal nodes.
[0133] S502: On the basis of the root node, internal nodes of a single data decision tree are established based on the information gain of the logistics historical risk data and the information gain of the delivery party historical risk data.
[0134] After the root node is established, the internal nodes of the single data decision tree can be established based on the root node. Specifically, Formula 1 to Formula 3 are used to calculate the information gain of the logistics historical risk data and the information gain of the distribution party historical risk data, respectively, and then the internal nodes of the single data decision tree are established.
[0135] exist Figure 5 In the embodiment, the root node is established with the information gain of the operation history risk data, and the information gain of the logistics history risk data and the information gain of the delivery party history risk data are used as internal nodes to construct a waybill data decision tree.
[0136] See also Figure 6 , Figure 6 Schematic diagram of a waybill data decision tree according to an embodiment of the present invention. Figure 6 In the embodiment of the invention, the operational risk data includes one or more of the following: reverse waybills, claim waybills, and detained waybills. The logistics risk data includes one or more of the following: the number of waybills resubmitted, the number of days without a waybills, and the number of abnormal delivery process operations of waybills. The delivery party risk data includes one or more of the following: the number of orders involved by the delivery party, the total amount collected by the delivery party, the number of consignees involved in the waybills, the delivery time limit of the waybills, and the delivery time limit of the delivery party.
[0137] The root node of the waybill data decision tree is established by operating the information gain of the historical risk data. Specifically, the detained waybill is used as the root node, and the reverse waybill and claim waybill are used as the internal nodes of the waybill data decision tree.
[0138] On the basis of the root node, the internal nodes of the waybill data decision tree are established with the information gain of the logistics historical risk data and the information gain of the delivery party's historical risk data. That is, the number of delivery parties involved, the number of consignees involved in the waybill, the total amount collected by the delivery party, the number of days without a waybill, the number of waybill resubmissions, the number of abnormal delivery process operations of the waybill, the time limit for the successful delivery of the waybill, and the time limit for the successful delivery of the delivery party are all used as the internal nodes of the waybill data decision tree.
[0139] Figure 6 The thresholds in can be set in advance based on actual application scenarios.
[0140] S402: Input the logistics risk data, operational risk data and delivery party risk data into the waybill data decision tree to identify the risk parameters of the risk waybill.
[0141] In order to identify the risk parameters of risky waybills, logistics risk data, operational risk data and distributor risk data can be input into the waybill data decision tree.
[0142] See also Figure 7 , Figure 7 The following is a flow chart of identifying risk parameters of risky waybills according to an embodiment of the present invention. Specifically, the following steps are included:
[0143] S701. Input logistics risk data, operational risk data and distributor risk data into the waybill data decision tree to obtain leaf nodes of the waybill data decision tree.
[0144] The leaf nodes of the waybill data decision tree can represent risk parameters. Logistics risk data, operational risk data and distributor risk data can be input into the waybill data decision tree to obtain the leaf nodes of the waybill data decision tree.
[0145] S702: Identify risk parameters of risky waybills based on leaf nodes of the waybill data decision tree.
[0146] Once the leaf nodes of the waybill data decision tree are determined, the risk parameters of risky waybills can be identified. As an example, the risk parameter value of the waybill data is greater than the preset threshold, that is, the leaf nodes of the waybill data decision tree include high risk, and the risk parameter for identifying the risky waybill is 1. The risk parameter value is the specific parameter involved in the risky waybill. As an example, the risk parameter value includes one or more of the number of orders involved by the delivery party, the number of consignees involved in the waybill, and the number of resubmissions of the waybill. As another example, the risk parameter value of the waybill data is less than or equal to the preset threshold, that is, the leaf nodes of the waybill data decision tree include low risk, and the risk parameter for identifying the risky waybill is 0.
[0147] exist Figure 7 In an embodiment, risk parameters of risky waybills are identified based on leaf nodes of a waybill data decision tree.
[0148] In an embodiment of the present invention, logistics risk data, operational risk data and distributor risk data may be used to identify risk parameters of risky waybills, and waybill data processing instructions may be sent according to the risk parameters.
[0149] As an example, the risk parameter includes sending an indication at the waybill data to verify the risk waybill when the risk parameter value of the waybill data is greater than a preset threshold. For example, manually verifying whether it is a risky waybill. As another example, the risk parameter includes low risk, and sending an indication at the waybill data to indicate that there is no need to manually verify the risk waybill.
[0150] In one embodiment of the present invention, the risk parameter includes sending an indication at the waybill data to verify the risk waybill when the risk parameter value of the waybill data is greater than a preset threshold.
[0151] After verifying that the risk waybill is high risk, the logistics risk data, operational risk data and delivery party risk data in the verified risk waybill can be used to update the waybill data decision tree. As the number of updates increases, the waybill data decision tree identifies risk parameters with higher accuracy.
[0152] In the above embodiment, according to the delivery status of the waybill in the waybill data, the risky waybill is screened out from the waybill of the logistics business; the waybill risk data of the risky waybill is extracted, and the waybill risk data includes logistics risk data, operational risk data and distributor risk data; the risk parameters of the risky waybill are identified by using the logistics risk data, the operational risk data and the distributor risk data, and the waybill data processing instructions are sent according to the risk parameters. Since the waybill data processing instructions can be sent in time according to the risk parameters, the processing cycle of the waybill data can be shortened, and the timely processing of the waybill data can be guaranteed.
[0153] See also Figure 8 , Figure 8 is a schematic diagram of the main structure of the apparatus for processing waybill data according to an embodiment of the present invention. The apparatus for processing waybill data can implement a method for processing waybill data, such as Figure 8 As shown, the device for processing waybill data specifically includes:
[0154] The screening module 801 is used to screen out risky waybills from the waybills of the logistics business according to the waybill delivery status in the waybill data;
[0155] An extraction module 802 is used to extract the waybill risk data of the risk waybill, wherein the waybill risk data includes logistics risk data, operational risk data and delivery party risk data;
[0156] The identification module 803 is used to use the logistics risk data, the operational risk data and the delivery party risk data to identify the risk parameters of the risk waybill and send a waybill data processing instruction according to the risk parameters.
[0157] In one embodiment of the present invention, the extraction module 802 is specifically used to select the logistics risk data in the data warehouse based on the identification of the risk waybill, and identify the operational risk data;
[0158] The couriers of the risky waybills are aggregated to determine the couriers' risk data.
[0159] In one embodiment of the present invention, the identification module 803 is specifically used to establish a waybill data decision tree based on the information gain of logistics historical risk data, the information gain of operation historical risk data, and the information gain of delivery party historical risk data;
[0160] The logistics risk data, the operational risk data and the delivery party risk data are input into the waybill data decision tree to identify the risk parameters of the risk waybill.
[0161] In one embodiment of the present invention, the identification module 803 is specifically used to establish the root node of the waybill data decision tree based on the information gain of the operation history risk data;
[0162] On the basis of the root node, the internal nodes of the waybill data decision tree are established with the information gain of the logistics historical risk data and the information gain of the delivery party historical risk data.
[0163] In one embodiment of the present invention, the identification module 803 is specifically used to input the logistics risk data, the operational risk data and the delivery party risk data into the waybill data decision tree to obtain leaf nodes of the waybill data decision tree;
[0164] According to the leaf nodes of the waybill data decision tree, the risk parameters of the risk waybill are identified.
[0165] In one embodiment of the present invention, the screening module 801 is specifically used to adopt Hive SQL modeling to identify the waybill delivery status based on the waybill delivery operation and / or the number of unsuccessful waybill delivery in the waybill data;
[0166] According to the delivery status of the waybill, risky waybills are screened out from the waybills of the logistics business.
[0167] In one embodiment of the present invention, the identification module 803 is specifically configured to send an indication at the waybill data to verify the risk waybill when the risk parameter includes a value of the risk parameter of the waybill data greater than a preset threshold;
[0168] The waybill data decision tree is updated using the verified logistics risk data, operational risk data and delivery party risk data in the risk waybill.
[0169] Fig. 9 An exemplary system architecture 900 is shown to which the method or apparatus for processing waybill data according to an embodiment of the present invention may be applied.
[0170] like Fig. 9As shown, system architecture 900 may include terminal devices 901, 902, 903, network 904 and server 905. Network 904 is used to provide a medium for communication links between terminal devices 901, 902, 903 and server 905. Network 904 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.
[0171] Users can use terminal devices 901, 902, 903 to interact with server 905 through network 904 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 901, 902, 903, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social platform software, etc. (only examples).
[0172] The terminal devices 901 , 902 , and 903 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers, and desktop computers, etc.
[0173] The server 905 may be a server that provides various services, such as a backend management server (only an example) that provides support for shopping websites browsed by users using the terminal devices 901, 902, and 903. The backend management server may analyze and process the received data such as product information query requests, and feed back the processing results (such as target push information, product information - only an example) to the terminal device.
[0174] It should be noted that the method for processing waybill data provided in the embodiment of the present invention is generally executed by the server 905 , and accordingly, the device for processing waybill data is generally arranged in the server 905 .
[0175] It should be understood that Fig. 9 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.
[0176] Reference below Fig.10 , which shows a schematic diagram of the structure of a computer system 1000 of a terminal device suitable for implementing an embodiment of the present invention. Fig.10 The terminal device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.
[0177] like Fig.10As shown, the computer system 1000 includes a central processing unit (CPU) 1001, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1002 or a program loaded from a storage part 1008 into a random access memory (RAM) 1003. In the RAM 1003, various programs and data required for the operation of the system 1000 are also stored. The CPU 1001, the ROM 1002, and the RAM 1003 are connected to each other via a bus 1004. An input / output (I / O) interface 1005 is also connected to the bus 1004.
[0178] The following components are connected to the I / O interface 1005: an input section 1006 including a keyboard, a mouse, etc.; an output section 1007 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 1008 including a hard disk, etc.; and a communication section 1009 including a network interface card such as a LAN card, a modem, etc. The communication section 1009 performs communication processing via a network such as the Internet. A drive 1010 is also connected to the I / O interface 1005 as needed. A removable medium 1011, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 1010 as needed, so that a computer program read therefrom is installed into the storage section 1008 as needed.
[0179] In particular, according to the embodiments disclosed in the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present invention include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 1009, and / or installed from the removable medium 1011. When the computer program is executed by the central processing unit (CPU) 1001, the above-mentioned functions defined in the system of the present invention are executed.
[0180] It should be noted that the computer-readable medium shown in the present invention may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present invention, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.
[0181] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present invention. In this regard, each box in the flow chart or block diagram can represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flow chart, and the combination of the boxes in the block diagram or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.
[0182] The modules involved in the embodiments of the present invention may be implemented by software or hardware. The modules described may also be set in a processor. For example, they may be described as: a processor includes a screening module, an extraction module, and an identification module. The names of these modules do not, in some cases, constitute limitations on the modules themselves. For example, the screening module may also be described as "used to screen out risky waybills in the waybills of logistics business according to the waybill delivery status in the waybill data."
[0183] As another aspect, the present invention further provides a computer-readable medium, which may be included in the device described in the above embodiment; or may exist independently without being assembled into the device. The above computer-readable medium carries one or more programs, and when the above one or more programs are executed by a device, the device includes:
[0184] According to the delivery status of the waybill in the waybill data, filter out the risky waybill in the waybill of the logistics business;
[0185] Extracting the waybill risk data of the risk waybill, wherein the waybill risk data includes logistics risk data, operational risk data and delivery party risk data;
[0186] The logistics risk data, the operational risk data and the delivery party risk data are used to identify the risk parameters of the risk waybill, and a waybill data processing instruction is sent according to the risk parameters.
[0187] According to the technical solution of the embodiment of the present invention, according to the delivery status of the waybill in the waybill data, the risky waybill is screened out from the waybill of the logistics business; the waybill risk data of the risky waybill is extracted, and the waybill risk data includes logistics risk data, operational risk data and distributor risk data; the risk parameters of the risky waybill are identified by using the logistics risk data, the operational risk data and the distributor risk data, and the waybill data processing instructions are sent according to the risk parameters. Since the waybill data processing instructions can be sent in time according to the risk parameters, the processing cycle of the waybill data can be shortened, and the timely processing of the waybill data can be guaranteed.
[0188] The above specific implementation methods do not constitute limitations on the scope of protection of the present invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations and substitutions may occur depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of protection of the present invention. It should be noted that in the technical solution disclosed in this disclosure, the acquisition, storage and application of user personal information involved are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.
Claims
1. A method for processing waybill data, characterized in that: include: According to the delivery status of the waybill in the waybill data, filter out the risky waybill in the waybill of the logistics business; Extracting the waybill risk data of the risk waybill, wherein the waybill risk data includes logistics risk data, operational risk data and delivery party risk data; The logistics risk data, the operational risk data and the delivery party risk data are used to identify the risk parameters of the risk waybill, and a waybill data processing instruction is sent according to the risk parameters.
2. The method for processing waybill data according to claim 1, characterized in that: The extracting of the waybill risk data of the risk waybill, wherein the waybill risk data includes logistics risk data, operational risk data and delivery party risk data, includes: Selecting the logistics risk data in the data warehouse based on the identification of the risk waybill, and identifying the operational risk data; The couriers of the risky waybills are aggregated to determine the couriers' risk data.
3. The method for processing waybill data according to claim 1, characterized in that: The step of using the logistics risk data, the operational risk data and the delivery party risk data to identify the risk parameters of the risk waybill includes: A waybill data decision tree is established based on the information gain of logistics historical risk data, operation historical risk data, and delivery party historical risk data; The logistics risk data, the operational risk data and the delivery party risk data are input into the waybill data decision tree to identify the risk parameters of the risk waybill.
4. The method for processing waybill data according to claim 3, characterized in that: The method of establishing a waybill data decision tree based on the information gain of the logistics historical risk data, the information gain of the operation historical risk data and the information gain of the delivery party historical risk data includes: Establishing the root node of the waybill data decision tree based on the information gain of the operation history risk data; On the basis of the root node, the internal nodes of the waybill data decision tree are established with the information gain of the logistics historical risk data and the information gain of the delivery party historical risk data.
5. The method for processing waybill data according to claim 3, characterized in that: The step of inputting the logistics risk data, the operational risk data and the delivery party risk data into the waybill data decision tree to identify the risk parameters of the risk waybill includes: Inputting the logistics risk data, the operational risk data and the delivery party risk data into the waybill data decision tree to obtain leaf nodes of the waybill data decision tree; According to the leaf nodes of the waybill data decision tree, the risk parameters of the risk waybill are identified.
6. The method for processing waybill data according to claim 1, characterized in that: The method of screening out risky waybills from the waybills of the logistics business according to the waybill delivery status in the waybill data includes: Hive SQL modeling is used to identify the delivery status of the waybill based on the waybill delivery operation and / or the number of unsuccessful waybill deliveries in the waybill data; According to the delivery status of the waybill, risky waybills are screened out from the waybills of the logistics business.
7. The method for processing waybill data according to claim 3, characterized in that: The sending of the waybill data processing instruction according to the risk parameter includes: The risk parameter includes sending an indication at the waybill data to verify the risk waybill when the risk parameter value of the waybill data is greater than a preset threshold; The waybill data decision tree is updated using the verified logistics risk data, operational risk data and delivery party risk data in the risk waybill.
8. A device for processing waybill data, characterized in that: include: The screening module is used to screen out risky waybills from the waybills of the logistics business according to the waybill delivery status in the waybill data; An extraction module, used to extract the waybill risk data of the risk waybill, wherein the waybill risk data includes logistics risk data, operational risk data and delivery party risk data; An identification module is used to use the logistics risk data, the operational risk data and the delivery party risk data to identify the risk parameters of the risk waybill and send a waybill data processing instruction according to the risk parameters.
9. An electronic device for processing waybill data, characterized in that: include: one or more processors; a storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 7.
10. A computer readable medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.
